diff options
36 files changed, 7597 insertions, 771 deletions
diff --git a/docs/about/deprecated.rst b/docs/about/deprecated.rst index 5a3ed71..d50645a 100644 --- a/docs/about/deprecated.rst +++ b/docs/about/deprecated.rst @@ -352,6 +352,13 @@ they want to use and avoids confusion. Existing users of the ``spike`` machine must ensure that they're setting the ``spike`` machine in the command line (``-M spike``). +Arm ``highbank`` and ``midway`` machines (since 10.1) +''''''''''''''''''''''''''''''''''''''''''''''''''''' + +There are no known users left for these machines (if you still use it, +please write a mail to the qemu-devel mailing list). If you just want to +boot a Cortex-A15 or Cortex-A9 Linux, use the ``virt`` machine instead. + System emulator binaries ------------------------ diff --git a/docs/system/arm/emulation.rst b/docs/system/arm/emulation.rst index 78c2fd2..890dc6f 100644 --- a/docs/system/arm/emulation.rst +++ b/docs/system/arm/emulation.rst @@ -129,16 +129,22 @@ the following architecture extensions: - FEAT_SM3 (Advanced SIMD SM3 instructions) - FEAT_SM4 (Advanced SIMD SM4 instructions) - FEAT_SME (Scalable Matrix Extension) +- FEAT_SME2 (Scalable Matrix Extension version 2) +- FEAT_SME2p1 (Scalable Matrix Extension version 2.1) +- FEAT_SME_B16B16 (Non-widening BFloat16 arithmetic for SME2) - FEAT_SME_FA64 (Full A64 instruction set in Streaming SVE mode) +- FEAT_SME_F16F16 (Non-widening half-precision FP16 arithmetic for SME2) - FEAT_SME_F64F64 (Double-precision floating-point outer product instructions) - FEAT_SME_I16I64 (16-bit to 64-bit integer widening outer product instructions) - FEAT_SVE (Scalable Vector Extension) - FEAT_SVE_AES (Scalable Vector AES instructions) +- FEAT_SVE_B16B16 (Non-widening BFloat16 arithmetic for SVE2) - FEAT_SVE_BitPerm (Scalable Vector Bit Permutes instructions) - FEAT_SVE_PMULL128 (Scalable Vector PMULL instructions) - FEAT_SVE_SHA3 (Scalable Vector SHA3 instructions) - FEAT_SVE_SM4 (Scalable Vector SM4 instructions) - FEAT_SVE2 (Scalable Vector Extension version 2) +- FEAT_SVE2p1 (Scalable Vector Extension version 2.1) - FEAT_SPECRES (Speculation restriction instructions) - FEAT_SSBS (Speculative Store Bypass Safe) - FEAT_SSBS2 (MRS and MSR instructions for SSBS version 2) diff --git a/hw/arm/highbank.c b/hw/arm/highbank.c index 3ae26eb..165c0b7 100644 --- a/hw/arm/highbank.c +++ b/hw/arm/highbank.c @@ -357,6 +357,7 @@ static void highbank_class_init(ObjectClass *oc, const void *data) mc->max_cpus = 4; mc->ignore_memory_transaction_failures = true; mc->default_ram_id = "highbank.dram"; + mc->deprecation_reason = "no known users left for this machine"; } static const TypeInfo highbank_type = { @@ -381,6 +382,7 @@ static void midway_class_init(ObjectClass *oc, const void *data) mc->max_cpus = 4; mc->ignore_memory_transaction_failures = true; mc->default_ram_id = "highbank.dram"; + mc->deprecation_reason = "no known users left for this machine"; } static const TypeInfo midway_type = { diff --git a/linux-user/aarch64/signal.c b/linux-user/aarch64/signal.c index bc7a138..d50cab7 100644 --- a/linux-user/aarch64/signal.c +++ b/linux-user/aarch64/signal.c @@ -248,7 +248,7 @@ static void target_setup_za_record(struct target_za_context *za, for (i = 0; i < vl; ++i) { uint64_t *z = (void *)za + TARGET_ZA_SIG_ZAV_OFFSET(vq, i); for (j = 0; j < vq * 2; ++j) { - __put_user_e(env->zarray[i].d[j], z + j, le); + __put_user_e(env->za_state.za[i].d[j], z + j, le); } } } @@ -397,7 +397,7 @@ static bool target_restore_za_record(CPUARMState *env, for (i = 0; i < vl; ++i) { uint64_t *z = (void *)za + TARGET_ZA_SIG_ZAV_OFFSET(vq, i); for (j = 0; j < vq * 2; ++j) { - __get_user_e(env->zarray[i].d[j], z + j, le); + __get_user_e(env->za_state.za[i].d[j], z + j, le); } } return true; diff --git a/linux-user/elfload.c b/linux-user/elfload.c index 2add166..ea21410 100644 --- a/linux-user/elfload.c +++ b/linux-user/elfload.c @@ -915,6 +915,14 @@ uint64_t get_elf_hwcap2(void) GET_FEATURE_ID(aa64_sme_fa64, ARM_HWCAP2_A64_SME_FA64); GET_FEATURE_ID(aa64_hbc, ARM_HWCAP2_A64_HBC); GET_FEATURE_ID(aa64_mops, ARM_HWCAP2_A64_MOPS); + GET_FEATURE_ID(aa64_sve2p1, ARM_HWCAP2_A64_SVE2P1); + GET_FEATURE_ID(aa64_sme2, (ARM_HWCAP2_A64_SME2 | + ARM_HWCAP2_A64_SME_I16I32 | + ARM_HWCAP2_A64_SME_BI32I32)); + GET_FEATURE_ID(aa64_sme2p1, ARM_HWCAP2_A64_SME2P1); + GET_FEATURE_ID(aa64_sme_b16b16, ARM_HWCAP2_A64_SME_B16B16); + GET_FEATURE_ID(aa64_sme_f16f16, ARM_HWCAP2_A64_SME_F16F16); + GET_FEATURE_ID(aa64_sve_b16b16, ARM_HWCAP2_A64_SVE_B16B16); return hwcaps; } diff --git a/target/arm/cpu-features.h b/target/arm/cpu-features.h index 5d8adfb..5876162 100644 --- a/target/arm/cpu-features.h +++ b/target/arm/cpu-features.h @@ -604,6 +604,11 @@ static inline bool isar_feature_aa64_rpres(const ARMISARegisters *id) return FIELD_EX64_IDREG(id, ID_AA64ISAR2, RPRES); } +static inline bool isar_feature_aa64_lut(const ARMISARegisters *id) +{ + return FIELD_EX64_IDREG(id, ID_AA64ISAR2, LUT); +} + static inline bool isar_feature_aa64_fp_simd(const ARMISARegisters *id) { /* We always set the AdvSIMD and FP fields identically. */ @@ -932,6 +937,11 @@ static inline bool isar_feature_aa64_sve2(const ARMISARegisters *id) return FIELD_EX64_IDREG(id, ID_AA64ZFR0, SVEVER) != 0; } +static inline bool isar_feature_aa64_sve2p1(const ARMISARegisters *id) +{ + return FIELD_EX64_IDREG(id, ID_AA64ZFR0, SVEVER) >=2; +} + static inline bool isar_feature_aa64_sve2_aes(const ARMISARegisters *id) { return FIELD_EX64_IDREG(id, ID_AA64ZFR0, AES) != 0; @@ -977,6 +987,21 @@ static inline bool isar_feature_aa64_sve_f64mm(const ARMISARegisters *id) return FIELD_EX64_IDREG(id, ID_AA64ZFR0, F64MM) != 0; } +static inline bool isar_feature_aa64_sve_b16b16(const ARMISARegisters *id) +{ + return FIELD_EX64_IDREG(id, ID_AA64ZFR0, B16B16); +} + +static inline bool isar_feature_aa64_sme_b16b16(const ARMISARegisters *id) +{ + return FIELD_EX64_IDREG(id, ID_AA64SMFR0, B16B16); +} + +static inline bool isar_feature_aa64_sme_f16f16(const ARMISARegisters *id) +{ + return FIELD_EX64_IDREG(id, ID_AA64SMFR0, F16F16); +} + static inline bool isar_feature_aa64_sme_f64f64(const ARMISARegisters *id) { return FIELD_EX64_IDREG(id, ID_AA64SMFR0, F64F64); @@ -992,6 +1017,44 @@ static inline bool isar_feature_aa64_sme_fa64(const ARMISARegisters *id) return FIELD_EX64_IDREG(id, ID_AA64SMFR0, FA64); } +static inline bool isar_feature_aa64_sme2(const ARMISARegisters *id) +{ + return FIELD_EX64_IDREG(id, ID_AA64SMFR0, SMEVER) != 0; +} + +static inline bool isar_feature_aa64_sme2p1(const ARMISARegisters *id) +{ + return FIELD_EX64_IDREG(id, ID_AA64SMFR0, SMEVER) >= 2; +} + +/* + * Combinations of feature tests, for ease of use with TRANS_FEAT. + */ +static inline bool isar_feature_aa64_sme_or_sve2p1(const ARMISARegisters *id) +{ + return isar_feature_aa64_sme(id) || isar_feature_aa64_sve2p1(id); +} + +static inline bool isar_feature_aa64_sme2_or_sve2p1(const ARMISARegisters *id) +{ + return isar_feature_aa64_sme2(id) || isar_feature_aa64_sve2p1(id); +} + +static inline bool isar_feature_aa64_sme2p1_or_sve2p1(const ARMISARegisters *id) +{ + return isar_feature_aa64_sme2p1(id) || isar_feature_aa64_sve2p1(id); +} + +static inline bool isar_feature_aa64_sme2_i16i64(const ARMISARegisters *id) +{ + return isar_feature_aa64_sme2(id) && isar_feature_aa64_sme_i16i64(id); +} + +static inline bool isar_feature_aa64_sme2_f64f64(const ARMISARegisters *id) +{ + return isar_feature_aa64_sme2(id) && isar_feature_aa64_sme_f64f64(id); +} + /* * Feature tests for "does this exist in either 32-bit or 64-bit?" */ diff --git a/target/arm/cpu.c b/target/arm/cpu.c index ebac86f..08c43f6 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -554,11 +554,15 @@ static void arm_cpu_reset_hold(Object *obj, ResetType type) set_flush_inputs_to_zero(1, &env->vfp.fp_status[FPST_STD]); set_default_nan_mode(1, &env->vfp.fp_status[FPST_STD]); set_default_nan_mode(1, &env->vfp.fp_status[FPST_STD_F16]); + set_default_nan_mode(1, &env->vfp.fp_status[FPST_ZA]); + set_default_nan_mode(1, &env->vfp.fp_status[FPST_ZA_F16]); arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_A32]); arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_A64]); + arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_ZA]); arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_STD]); arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_A32_F16]); arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_A64_F16]); + arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_ZA_F16]); arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_STD_F16]); arm_set_ah_fp_behaviours(&env->vfp.fp_status[FPST_AH]); set_flush_to_zero(1, &env->vfp.fp_status[FPST_AH]); @@ -631,6 +635,9 @@ void arm_emulate_firmware_reset(CPUState *cpustate, int target_el) env->cp15.cptr_el[3] |= R_CPTR_EL3_ESM_MASK; env->cp15.scr_el3 |= SCR_ENTP2; env->vfp.smcr_el[3] = 0xf; + if (cpu_isar_feature(aa64_sme2, cpu)) { + env->vfp.smcr_el[3] |= R_SMCR_EZT0_MASK; + } } if (cpu_isar_feature(aa64_hcx, cpu)) { env->cp15.scr_el3 |= SCR_HXEN; @@ -1331,8 +1338,8 @@ static void aarch64_cpu_dump_state(CPUState *cs, FILE *f, int flags) qemu_fprintf(f, "ZA[%0*d]=", svl_lg10, i); for (j = zcr_len; j >= 0; --j) { qemu_fprintf(f, "%016" PRIx64 ":%016" PRIx64 "%c", - env->zarray[i].d[2 * j + 1], - env->zarray[i].d[2 * j], + env->za_state.za[i].d[2 * j + 1], + env->za_state.za[i].d[2 * j], j ? ':' : '\n'); } } diff --git a/target/arm/cpu.h b/target/arm/cpu.h index 0338153..c8cf0ab 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -207,6 +207,8 @@ typedef struct NVICState NVICState; * when FPCR.AH == 1 (bfloat16 conversions and multiplies, * and the reciprocal and square root estimate/step insns); * for half-precision + * ZA: the "streaming sve" fp status. + * ZA_F16: likewise for half-precision. * * Half-precision operations are governed by a separate * flush-to-zero control bit in FPSCR:FZ16. We pass a separate @@ -227,6 +229,12 @@ typedef struct NVICState NVICState; * they ignore FPCR.RMode. But they don't ignore FPCR.FZ16, * which means we need an FPST_AH_F16 as well. * + * The "ZA" float_status are for Streaming SVE operations which use + * default-NaN and do not generate fp exceptions, which means that they + * do not accumulate exception bits back into FPCR. + * See e.g. FPAdd vs FPAdd_ZA pseudocode functions, and the setting + * of fpcr.DN and fpexec parameters. + * * To avoid having to transfer exception bits around, we simply * say that the FPSCR cumulative exception flags are the logical * OR of the flags in the four fp statuses. This relies on the @@ -240,10 +248,12 @@ typedef enum ARMFPStatusFlavour { FPST_A64_F16, FPST_AH, FPST_AH_F16, + FPST_ZA, + FPST_ZA_F16, FPST_STD, FPST_STD_F16, } ARMFPStatusFlavour; -#define FPST_COUNT 8 +#define FPST_COUNT 10 typedef struct CPUArchState { /* Regs for current mode. */ @@ -669,9 +679,6 @@ typedef struct CPUArchState { uint32_t xregs[16]; - /* Scratch space for aa32 neon expansion. */ - uint32_t scratch[8]; - /* There are a number of distinct float control structures. */ float_status fp_status[FPST_COUNT]; @@ -708,27 +715,36 @@ typedef struct CPUArchState { uint64_t scxtnum_el[4]; - /* - * SME ZA storage -- 256 x 256 byte array, with bytes in host word order, - * as we do with vfp.zregs[]. This corresponds to the architectural ZA - * array, where ZA[N] is in the least-significant bytes of env->zarray[N]. - * When SVL is less than the architectural maximum, the accessible - * storage is restricted, such that if the SVL is X bytes the guest can - * see only the bottom X elements of zarray[], and only the least - * significant X bytes of each element of the array. (In other words, - * the observable part is always square.) - * - * The ZA storage can also be considered as a set of square tiles of - * elements of different sizes. The mapping from tiles to the ZA array - * is architecturally defined, such that for tiles of elements of esz - * bytes, the Nth row (or "horizontal slice") of tile T is in - * ZA[T + N * esz]. Note that this means that each tile is not contiguous - * in the ZA storage, because its rows are striped through the ZA array. - * - * Because this is so large, keep this toward the end of the reset area, - * to keep the offsets into the rest of the structure smaller. - */ - ARMVectorReg zarray[ARM_MAX_VQ * 16]; + struct { + /* SME2 ZT0 -- 512 bit array, with data ordered like ARMVectorReg. */ + uint64_t zt0[512 / 64] QEMU_ALIGNED(16); + + /* + * SME ZA storage -- 256 x 256 byte array, with bytes in host + * word order, as we do with vfp.zregs[]. This corresponds to + * the architectural ZA array, where ZA[N] is in the least + * significant bytes of env->za_state.za[N]. + * + * When SVL is less than the architectural maximum, the accessible + * storage is restricted, such that if the SVL is X bytes the guest + * can see only the bottom X elements of zarray[], and only the least + * significant X bytes of each element of the array. (In other words, + * the observable part is always square.) + * + * The ZA storage can also be considered as a set of square tiles of + * elements of different sizes. The mapping from tiles to the ZA array + * is architecturally defined, such that for tiles of elements of esz + * bytes, the Nth row (or "horizontal slice") of tile T is in + * ZA[T + N * esz]. Note that this means that each tile is not + * contiguous in the ZA storage, because its rows are striped through + * the ZA array. + * + * Because this is so large, keep this toward the end of the + * reset area, to keep the offsets into the rest of the structure + * smaller. + */ + ARMVectorReg za[ARM_MAX_VQ * 16]; + } za_state; struct CPUBreakpoint *cpu_breakpoint[16]; struct CPUWatchpoint *cpu_watchpoint[16]; @@ -1120,6 +1136,7 @@ struct ArchCPU { /* Used to set the maximum vector length the cpu will support. */ uint32_t sve_max_vq; + uint32_t sme_max_vq; #ifdef CONFIG_USER_ONLY /* Used to set the default vector length at process start. */ @@ -1497,6 +1514,7 @@ FIELD(SVCR, ZA, 1, 1) /* Fields for SMCR_ELx. */ FIELD(SMCR, LEN, 0, 4) +FIELD(SMCR, EZT0, 30, 1) FIELD(SMCR, FA64, 31, 1) /* Write a new value to v7m.exception, thus transitioning into or out @@ -2198,6 +2216,7 @@ FIELD(ID_AA64ISAR2, SYSINSTR_128, 36, 4) FIELD(ID_AA64ISAR2, PRFMSLC, 40, 4) FIELD(ID_AA64ISAR2, RPRFM, 48, 4) FIELD(ID_AA64ISAR2, CSSC, 52, 4) +FIELD(ID_AA64ISAR2, LUT, 56, 4) FIELD(ID_AA64ISAR2, ATS1A, 60, 4) FIELD(ID_AA64PFR0, EL0, 0, 4) @@ -3067,6 +3086,7 @@ FIELD(TBFLAG_A64, NV2_MEM_E20, 35, 1) FIELD(TBFLAG_A64, NV2_MEM_BE, 36, 1) FIELD(TBFLAG_A64, AH, 37, 1) /* FPCR.AH */ FIELD(TBFLAG_A64, NEP, 38, 1) /* FPCR.NEP */ +FIELD(TBFLAG_A64, ZT0EXC_EL, 39, 2) /* * Helpers for using the above. Note that only the A64 accessors use diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index 1f34067..bd33d6c 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -259,6 +259,13 @@ void arm_cpu_sve_finalize(ARMCPU *cpu, Error **errp) /* From now on sve_max_vq is the actual maximum supported length. */ cpu->sve_max_vq = max_vq; cpu->sve_vq.map = vq_map; + + /* FEAT_F64MM requires the existence of a 256-bit vector size. */ + if (max_vq < 2) { + uint64_t t = GET_IDREG(&cpu->isar, ID_AA64ZFR0); + t = FIELD_DP64(t, ID_AA64ZFR0, F64MM, 0); + SET_IDREG(&cpu->isar, ID_AA64ZFR0, t); + } } /* @@ -356,6 +363,7 @@ void arm_cpu_sme_finalize(ARMCPU *cpu, Error **errp) } cpu->sme_vq.map = vq_map; + cpu->sme_max_vq = 32 - clz32(vq_map); } static bool cpu_arm_get_sme(Object *obj, Error **errp) diff --git a/target/arm/helper.c b/target/arm/helper.c index c311d2d..b3f0d6f 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -6663,7 +6663,7 @@ void aarch64_set_svcr(CPUARMState *env, uint64_t new, uint64_t mask) * when disabled either. */ if (change & new & R_SVCR_ZA_MASK) { - memset(env->zarray, 0, sizeof(env->zarray)); + memset(&env->za_state, 0, sizeof(env->za_state)); } if (tcg_enabled()) { @@ -6682,10 +6682,14 @@ static void smcr_write(CPUARMState *env, const ARMCPRegInfo *ri, { int cur_el = arm_current_el(env); int old_len = sve_vqm1_for_el(env, cur_el); + uint64_t valid_mask = R_SMCR_LEN_MASK | R_SMCR_FA64_MASK; int new_len; QEMU_BUILD_BUG_ON(ARM_MAX_VQ > R_SMCR_LEN_MASK + 1); - value &= R_SMCR_LEN_MASK | R_SMCR_FA64_MASK; + if (cpu_isar_feature(aa64_sme2, env_archcpu(env))) { + valid_mask |= R_SMCR_EZT0_MASK; + } + value &= valid_mask; raw_write(env, ri, value); /* diff --git a/target/arm/machine.c b/target/arm/machine.c index e442d48..6986915 100644 --- a/target/arm/machine.c +++ b/target/arm/machine.c @@ -315,12 +315,31 @@ static const VMStateDescription vmstate_za = { .minimum_version_id = 1, .needed = za_needed, .fields = (const VMStateField[]) { - VMSTATE_STRUCT_ARRAY(env.zarray, ARMCPU, ARM_MAX_VQ * 16, 0, + VMSTATE_STRUCT_ARRAY(env.za_state.za, ARMCPU, ARM_MAX_VQ * 16, 0, vmstate_vreg, ARMVectorReg), VMSTATE_END_OF_LIST() } }; +static bool zt0_needed(void *opaque) +{ + ARMCPU *cpu = opaque; + + return za_needed(cpu) && cpu_isar_feature(aa64_sme2, cpu); +} + +static const VMStateDescription vmstate_zt0 = { + .name = "cpu/zt0", + .version_id = 1, + .minimum_version_id = 1, + .needed = zt0_needed, + .fields = (VMStateField[]) { + VMSTATE_UINT64_ARRAY(env.za_state.zt0, ARMCPU, + ARRAY_SIZE(((CPUARMState *)0)->za_state.zt0)), + VMSTATE_END_OF_LIST() + } +}; + static bool serror_needed(void *opaque) { ARMCPU *cpu = opaque; @@ -1096,6 +1115,7 @@ const VMStateDescription vmstate_arm_cpu = { &vmstate_m_security, &vmstate_sve, &vmstate_za, + &vmstate_zt0, &vmstate_serror, &vmstate_irq_line_state, &vmstate_wfxt_timer, diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h index 3244e07..c48d3b8 100644 --- a/target/arm/syndrome.h +++ b/target/arm/syndrome.h @@ -80,6 +80,7 @@ typedef enum { SME_ET_Streaming, SME_ET_NotStreaming, SME_ET_InactiveZA, + SME_ET_InaccessibleZT0, } SMEExceptionType; #define ARM_EL_EC_LENGTH 6 diff --git a/target/arm/tcg/cpu64.c b/target/arm/tcg/cpu64.c index 937f29e2..d0df50a 100644 --- a/target/arm/tcg/cpu64.c +++ b/target/arm/tcg/cpu64.c @@ -1201,7 +1201,7 @@ void aarch64_max_tcg_initfn(Object *obj) */ t = FIELD_DP64(t, ID_AA64PFR1, MTE, 3); /* FEAT_MTE3 */ t = FIELD_DP64(t, ID_AA64PFR1, RAS_FRAC, 0); /* FEAT_RASv1p1 + FEAT_DoubleFault */ - t = FIELD_DP64(t, ID_AA64PFR1, SME, 1); /* FEAT_SME */ + t = FIELD_DP64(t, ID_AA64PFR1, SME, 2); /* FEAT_SME2 */ t = FIELD_DP64(t, ID_AA64PFR1, CSV2_FRAC, 0); /* FEAT_CSV2_3 */ t = FIELD_DP64(t, ID_AA64PFR1, NMI, 1); /* FEAT_NMI */ SET_IDREG(isar, ID_AA64PFR1, t); @@ -1250,10 +1250,11 @@ void aarch64_max_tcg_initfn(Object *obj) FIELD_DP64_IDREG(isar, ID_AA64MMFR3, SPEC_FPACC, 1); /* FEAT_FPACC_SPEC */ t = GET_IDREG(isar, ID_AA64ZFR0); - t = FIELD_DP64(t, ID_AA64ZFR0, SVEVER, 1); + t = FIELD_DP64(t, ID_AA64ZFR0, SVEVER, 2); /* FEAT_SVE2p1 */ t = FIELD_DP64(t, ID_AA64ZFR0, AES, 2); /* FEAT_SVE_PMULL128 */ t = FIELD_DP64(t, ID_AA64ZFR0, BITPERM, 1); /* FEAT_SVE_BitPerm */ t = FIELD_DP64(t, ID_AA64ZFR0, BFLOAT16, 2); /* FEAT_BF16, FEAT_EBF16 */ + t = FIELD_DP64(t, ID_AA64ZFR0, B16B16, 1); /* FEAT_SVE_B16B16 */ t = FIELD_DP64(t, ID_AA64ZFR0, SHA3, 1); /* FEAT_SVE_SHA3 */ t = FIELD_DP64(t, ID_AA64ZFR0, SM4, 1); /* FEAT_SVE_SM4 */ t = FIELD_DP64(t, ID_AA64ZFR0, I8MM, 1); /* FEAT_I8MM */ @@ -1269,11 +1270,16 @@ void aarch64_max_tcg_initfn(Object *obj) t = GET_IDREG(isar, ID_AA64SMFR0); t = FIELD_DP64(t, ID_AA64SMFR0, F32F32, 1); /* FEAT_SME */ + t = FIELD_DP64(t, ID_AA64SMFR0, BI32I32, 1); /* FEAT_SME2 */ t = FIELD_DP64(t, ID_AA64SMFR0, B16F32, 1); /* FEAT_SME */ t = FIELD_DP64(t, ID_AA64SMFR0, F16F32, 1); /* FEAT_SME */ t = FIELD_DP64(t, ID_AA64SMFR0, I8I32, 0xf); /* FEAT_SME */ + t = FIELD_DP64(t, ID_AA64SMFR0, F16F16, 1); /* FEAT_SME_F16F16 */ + t = FIELD_DP64(t, ID_AA64SMFR0, B16B16, 1); /* FEAT_SME_B16B16 */ + t = FIELD_DP64(t, ID_AA64SMFR0, I16I32, 5); /* FEAT_SME2 */ t = FIELD_DP64(t, ID_AA64SMFR0, F64F64, 1); /* FEAT_SME_F64F64 */ t = FIELD_DP64(t, ID_AA64SMFR0, I16I64, 0xf); /* FEAT_SME_I16I64 */ + t = FIELD_DP64(t, ID_AA64SMFR0, SMEVER, 2); /* FEAT_SME2p1 */ t = FIELD_DP64(t, ID_AA64SMFR0, FA64, 1); /* FEAT_SME_FA64 */ SET_IDREG(isar, ID_AA64SMFR0, t); diff --git a/target/arm/tcg/gengvec64.c b/target/arm/tcg/gengvec64.c index 2617cde..2429cab 100644 --- a/target/arm/tcg/gengvec64.c +++ b/target/arm/tcg/gengvec64.c @@ -369,3 +369,14 @@ void gen_gvec_usqadd_qc(unsigned vece, uint32_t rd_ofs, tcg_gen_gvec_4(rd_ofs, offsetof(CPUARMState, vfp.qc), rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); } + +void gen_gvec_sve2_sqdmulh(unsigned vece, uint32_t rd_ofs, + uint32_t rn_ofs, uint32_t rm_ofs, + uint32_t opr_sz, uint32_t max_sz) +{ + static gen_helper_gvec_3 * const fns[4] = { + gen_helper_sve2_sqdmulh_b, gen_helper_sve2_sqdmulh_h, + gen_helper_sve2_sqdmulh_s, gen_helper_sve2_sqdmulh_d, + }; + tcg_gen_gvec_3_ool(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, 0, fns[vece]); +} diff --git a/target/arm/tcg/helper-a64.c b/target/arm/tcg/helper-a64.c index 4f618ae..c66d521 100644 --- a/target/arm/tcg/helper-a64.c +++ b/target/arm/tcg/helper-a64.c @@ -402,6 +402,8 @@ AH_MINMAX_HELPER(vfp_ah_mind, float64, float64, min) AH_MINMAX_HELPER(vfp_ah_maxh, dh_ctype_f16, float16, max) AH_MINMAX_HELPER(vfp_ah_maxs, float32, float32, max) AH_MINMAX_HELPER(vfp_ah_maxd, float64, float64, max) +AH_MINMAX_HELPER(sme2_ah_fmax_b16, bfloat16, bfloat16, max) +AH_MINMAX_HELPER(sme2_ah_fmin_b16, bfloat16, bfloat16, min) /* 64-bit versions of the CRC helpers. Note that although the operation * (and the prototypes of crc32c() and crc32() mean that only the bottom diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h index 858d691..1fc756b 100644 --- a/target/arm/tcg/helper-sme.h +++ b/target/arm/tcg/helper-sme.h @@ -33,6 +33,21 @@ DEF_HELPER_FLAGS_4(sme_mova_zc_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sme_mova_cz_q, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sme_mova_zc_q, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_mova_cz_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_mova_zc_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_mova_cz_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_mova_zc_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_mova_cz_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_mova_zc_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_mova_cz_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_mova_zc_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sme2p1_movaz_zc_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2p1_movaz_zc_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2p1_movaz_zc_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2p1_movaz_zc_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2p1_movaz_zc_q, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + DEF_HELPER_FLAGS_5(sme_ld1b_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_5(sme_ld1b_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_5(sme_ld1b_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) @@ -120,14 +135,45 @@ DEF_HELPER_FLAGS_5(sme_addva_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sme_addha_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sme_addva_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_7(sme_fmopa_h, TCG_CALL_NO_RWG, +DEF_HELPER_FLAGS_7(sme_fmopa_w_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_7(sme_fmopa_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_7(sme_fmopa_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_7(sme_fmopa_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_7(sme_bfmopa_w, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, env, i32) DEF_HELPER_FLAGS_7(sme_bfmopa, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, fpst, i32) + +DEF_HELPER_FLAGS_7(sme_fmops_w_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_7(sme_fmops_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_7(sme_fmops_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_7(sme_fmops_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_7(sme_bfmops_w, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_7(sme_bfmops, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, fpst, i32) + +DEF_HELPER_FLAGS_7(sme_ah_fmops_w_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_7(sme_ah_fmops_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_7(sme_ah_fmops_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_7(sme_ah_fmops_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_7(sme_ah_bfmops_w, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_7(sme_ah_bfmops, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, fpst, i32) + DEF_HELPER_FLAGS_6(sme_smopa_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_6(sme_umopa_s, TCG_CALL_NO_RWG, @@ -144,3 +190,168 @@ DEF_HELPER_FLAGS_6(sme_sumopa_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_6(sme_usmopa_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_6(sme2_bmopa_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sme2_smopa2_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sme2_umopa2_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(gvec_fmax_b16, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_fmin_b16, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_ah_fmax_b16, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_ah_fmin_b16, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_fmaxnum_b16, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_fminnum_b16, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, fpst, i32) + +DEF_HELPER_FLAGS_6(sme2_fdot_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_6(sme2_fdot_idx_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_6(sme2_fvdot_idx_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, env, i32) + +DEF_HELPER_FLAGS_4(sme2_svdot_idx_4b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme2_uvdot_idx_4b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme2_suvdot_idx_4b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme2_usvdot_idx_4b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sme2_svdot_idx_4h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme2_uvdot_idx_4h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sme2_svdot_idx_2h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme2_uvdot_idx_2h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sme2_smlall_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sme2_smlall_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sme2_smlsll_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sme2_smlsll_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sme2_umlall_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sme2_umlall_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sme2_umlsll_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sme2_umlsll_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sme2_usmlall_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sme2_smlall_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sme2_smlall_idx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sme2_smlsll_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sme2_smlsll_idx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sme2_umlall_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sme2_umlall_idx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sme2_umlsll_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sme2_umlsll_idx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sme2_usmlall_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sme2_sumlall_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sme2_bfcvt, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_4(sme2_bfcvtn, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_4(sme2_fcvt_n, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_4(sme2_fcvtn, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_4(sme2_fcvt_w, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_4(sme2_fcvtl, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_4(sme2_scvtf, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_4(sme2_ucvtf, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) + +DEF_HELPER_FLAGS_3(sme2_sqcvt_sb, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_uqcvt_sb, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_sqcvtu_sb, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_sqcvt_sh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_uqcvt_sh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_sqcvtu_sh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_sqcvt_dh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_uqcvt_dh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_sqcvtu_dh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sme2_sqcvtn_sb, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_uqcvtn_sb, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_sqcvtun_sb, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_sqcvtn_sh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_uqcvtn_sh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_sqcvtun_sh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_sqcvtn_dh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_uqcvtn_dh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_sqcvtun_dh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sme2_sunpk2_bh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_sunpk2_hs, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_sunpk2_sd, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_sunpk4_bh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_sunpk4_hs, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_sunpk4_sd, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_uunpk2_bh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_uunpk2_hs, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_uunpk2_sd, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_uunpk4_bh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_uunpk4_hs, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_uunpk4_sd, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sme2_zip2_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme2_zip2_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme2_zip2_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme2_zip2_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme2_zip2_q, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sme2_uzp2_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme2_uzp2_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme2_uzp2_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme2_uzp2_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme2_uzp2_q, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sme2_zip4_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_zip4_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_zip4_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_zip4_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_zip4_q, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sme2_uzp4_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_uzp4_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_uzp4_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_uzp4_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_uzp4_q, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sme2_sqrshr_sh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_uqrshr_sh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_sqrshru_sh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_sqrshr_sb, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_uqrshr_sb, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_sqrshru_sb, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_sqrshr_dh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_uqrshr_dh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_sqrshru_dh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(sme2_sqrshrn_sh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_uqrshrn_sh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_sqrshrun_sh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_sqrshrn_sb, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_uqrshrn_sb, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_sqrshrun_sb, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_sqrshrn_dh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_uqrshrn_dh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sme2_sqrshrun_dh, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sme2_sclamp_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme2_sclamp_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme2_sclamp_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme2_sclamp_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sme2_uclamp_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme2_uclamp_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme2_uclamp_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme2_uclamp_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sme2_fclamp_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(sme2_fclamp_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(sme2_fclamp_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(sme2_bfclamp, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) + +DEF_HELPER_FLAGS_5(sme2_sel_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32, i32) +DEF_HELPER_FLAGS_5(sme2_sel_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32, i32) +DEF_HELPER_FLAGS_5(sme2_sel_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32, i32) +DEF_HELPER_FLAGS_5(sme2_sel_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32, i32) diff --git a/target/arm/tcg/helper-sve.h b/target/arm/tcg/helper-sve.h index 0b1b588..c36090d 100644 --- a/target/arm/tcg/helper-sve.h +++ b/target/arm/tcg/helper-sve.h @@ -676,11 +676,21 @@ DEF_HELPER_FLAGS_5(sve2_tbl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve2_tbl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve2_tbl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_tblq_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_tblq_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_tblq_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_tblq_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(sve2_tbx_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve2_tbx_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve2_tbx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve2_tbx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_tbxq_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_tbxq_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_tbxq_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_tbxq_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_3(sve_sunpk_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sve_sunpk_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sve_sunpk_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) @@ -701,12 +711,22 @@ DEF_HELPER_FLAGS_4(sve_zip_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve_zip_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve2_zip_q, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_zipq_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_zipq_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_zipq_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_zipq_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(sve_uzp_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve_uzp_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve_uzp_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve_uzp_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve2_uzp_q, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_uzpq_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_uzpq_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_uzpq_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_uzpq_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(sve_trn_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve_trn_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve_trn_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) @@ -937,10 +957,17 @@ DEF_HELPER_FLAGS_4(sve_brkn, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve_brkns, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sve_cntp, TCG_CALL_NO_RWG, i64, ptr, ptr, i32) +DEF_HELPER_FLAGS_2(sve2p1_cntp_c, TCG_CALL_NO_RWG_SE, i64, i32, i32) DEF_HELPER_FLAGS_3(sve_whilel, TCG_CALL_NO_RWG, i32, ptr, i32, i32) DEF_HELPER_FLAGS_3(sve_whileg, TCG_CALL_NO_RWG, i32, ptr, i32, i32) +DEF_HELPER_FLAGS_3(sve_while2l, TCG_CALL_NO_RWG, i32, ptr, i32, i32) +DEF_HELPER_FLAGS_3(sve_while2g, TCG_CALL_NO_RWG, i32, ptr, i32, i32) + +DEF_HELPER_FLAGS_3(sve_whilecl, TCG_CALL_NO_RWG, i32, ptr, i32, i32) +DEF_HELPER_FLAGS_3(sve_whilecg, TCG_CALL_NO_RWG, i32, ptr, i32, i32) + DEF_HELPER_FLAGS_4(sve_subri_b, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) DEF_HELPER_FLAGS_4(sve_subri_h, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) DEF_HELPER_FLAGS_4(sve_subri_s, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) @@ -1071,6 +1098,55 @@ DEF_HELPER_FLAGS_4(sve_ah_fminv_s, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_4(sve_ah_fminv_d, TCG_CALL_NO_RWG, i64, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(sve2p1_faddqv_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(sve2p1_faddqv_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(sve2p1_faddqv_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, fpst, i32) + +DEF_HELPER_FLAGS_5(sve2p1_fmaxnmqv_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(sve2p1_fmaxnmqv_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(sve2p1_fmaxnmqv_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, fpst, i32) + +DEF_HELPER_FLAGS_5(sve2p1_fminnmqv_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(sve2p1_fminnmqv_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(sve2p1_fminnmqv_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, fpst, i32) + +DEF_HELPER_FLAGS_5(sve2p1_fmaxqv_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(sve2p1_fmaxqv_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(sve2p1_fmaxqv_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, fpst, i32) + +DEF_HELPER_FLAGS_5(sve2p1_fminqv_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(sve2p1_fminqv_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(sve2p1_fminqv_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, fpst, i32) + +DEF_HELPER_FLAGS_5(sve2p1_ah_fmaxqv_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(sve2p1_ah_fmaxqv_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(sve2p1_ah_fmaxqv_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, fpst, i32) + +DEF_HELPER_FLAGS_5(sve2p1_ah_fminqv_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(sve2p1_ah_fminqv_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(sve2p1_ah_fminqv_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, fpst, i32) + DEF_HELPER_FLAGS_5(sve_fadda_h, TCG_CALL_NO_RWG, i64, i64, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_fadda_s, TCG_CALL_NO_RWG, @@ -1582,6 +1658,14 @@ DEF_HELPER_FLAGS_4(sve_ld2dd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ld3dd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ld4dd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld2qq_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld3qq_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld4qq_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + +DEF_HELPER_FLAGS_4(sve_ld2qq_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld3qq_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld4qq_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + DEF_HELPER_FLAGS_4(sve_ld1bhu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ld1bsu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ld1bdu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) @@ -1602,9 +1686,15 @@ DEF_HELPER_FLAGS_4(sve_ld1hds_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ld1sdu_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ld1sds_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld1squ_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld1dqu_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + DEF_HELPER_FLAGS_4(sve_ld1sdu_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ld1sds_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld1squ_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld1dqu_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + DEF_HELPER_FLAGS_4(sve_ld1bb_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ld2bb_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ld3bb_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) @@ -1640,6 +1730,14 @@ DEF_HELPER_FLAGS_4(sve_ld2dd_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ld3dd_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ld4dd_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld2qq_le_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld3qq_le_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld4qq_le_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + +DEF_HELPER_FLAGS_4(sve_ld2qq_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld3qq_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld4qq_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + DEF_HELPER_FLAGS_4(sve_ld1bhu_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ld1bsu_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ld1bdu_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) @@ -1660,9 +1758,15 @@ DEF_HELPER_FLAGS_4(sve_ld1hds_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ld1sdu_le_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ld1sds_le_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld1squ_le_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld1dqu_le_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + DEF_HELPER_FLAGS_4(sve_ld1sdu_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ld1sds_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld1squ_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld1dqu_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + DEF_HELPER_FLAGS_4(sve_ldff1bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ldff1bhu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ldff1bsu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) @@ -1858,6 +1962,14 @@ DEF_HELPER_FLAGS_4(sve_st2dd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_st3dd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_st4dd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st2qq_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st3qq_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st4qq_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + +DEF_HELPER_FLAGS_4(sve_st2qq_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st3qq_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st4qq_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + DEF_HELPER_FLAGS_4(sve_st1bh_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_st1bs_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_st1bd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) @@ -1870,6 +1982,11 @@ DEF_HELPER_FLAGS_4(sve_st1hd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_st1sd_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_st1sd_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st1sq_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st1sq_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st1dq_le_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st1dq_be_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + DEF_HELPER_FLAGS_4(sve_st1bb_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_st2bb_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_st3bb_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) @@ -1905,6 +2022,14 @@ DEF_HELPER_FLAGS_4(sve_st2dd_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_st3dd_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_st4dd_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st2qq_le_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st3qq_le_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st4qq_le_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + +DEF_HELPER_FLAGS_4(sve_st2qq_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st3qq_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st4qq_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + DEF_HELPER_FLAGS_4(sve_st1bh_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_st1bs_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_st1bd_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) @@ -1917,6 +2042,11 @@ DEF_HELPER_FLAGS_4(sve_st1hd_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_st1sd_le_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_st1sd_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st1sq_le_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st1sq_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st1dq_le_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st1dq_be_r_mte, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + DEF_HELPER_FLAGS_6(sve_ldbsu_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_ldhsu_le_zsu, TCG_CALL_NO_WG, @@ -2025,6 +2155,10 @@ DEF_HELPER_FLAGS_6(sve_ldsds_le_zd, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_ldsds_be_zd, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldqq_le_zd, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldqq_be_zd, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_ldbsu_zsu_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) @@ -2134,6 +2268,10 @@ DEF_HELPER_FLAGS_6(sve_ldsds_le_zd_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_ldsds_be_zd_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldqq_le_zd_mte, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldqq_be_zd_mte, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_ldffbsu_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) @@ -2419,6 +2557,10 @@ DEF_HELPER_FLAGS_6(sve_stdd_le_zd, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_stdd_be_zd, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_stqq_le_zd, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_stqq_be_zd, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_stbs_zsu_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) @@ -2486,6 +2628,10 @@ DEF_HELPER_FLAGS_6(sve_stdd_le_zd_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_stdd_be_zd_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_stqq_le_zd_mte, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_stqq_be_zd_mte, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve2_sqdmull_zzz_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) @@ -2922,3 +3068,69 @@ DEF_HELPER_FLAGS_4(sve2_sqshlu_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve2_sqshlu_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve2_sqshlu_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve2_sqshlu_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2p1_addqv_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_addqv_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_addqv_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_addqv_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2p1_smaxqv_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_smaxqv_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_smaxqv_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_smaxqv_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2p1_sminqv_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_sminqv_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_sminqv_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_sminqv_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2p1_umaxqv_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_umaxqv_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_umaxqv_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_umaxqv_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2p1_uminqv_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_uminqv_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_uminqv_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_uminqv_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(pext, TCG_CALL_NO_RWG, void, ptr, i32, i32) + +DEF_HELPER_FLAGS_4(sve2p1_orqv_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_orqv_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_orqv_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_orqv_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2p1_eorqv_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_eorqv_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_eorqv_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_eorqv_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve2p1_andqv_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_andqv_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_andqv_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve2p1_andqv_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(pmov_pv_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(pmov_pv_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(pmov_pv_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(pmov_vp_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(pmov_vp_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(pmov_vp_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve2p1_ld1bb_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32) +DEF_HELPER_FLAGS_5(sve2p1_ld1hh_le_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32) +DEF_HELPER_FLAGS_5(sve2p1_ld1hh_be_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32) +DEF_HELPER_FLAGS_5(sve2p1_ld1ss_le_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32) +DEF_HELPER_FLAGS_5(sve2p1_ld1ss_be_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32) +DEF_HELPER_FLAGS_5(sve2p1_ld1dd_le_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32) +DEF_HELPER_FLAGS_5(sve2p1_ld1dd_be_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32) + +DEF_HELPER_FLAGS_5(sve2p1_st1bb_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32) +DEF_HELPER_FLAGS_5(sve2p1_st1hh_le_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32) +DEF_HELPER_FLAGS_5(sve2p1_st1hh_be_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32) +DEF_HELPER_FLAGS_5(sve2p1_st1ss_le_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32) +DEF_HELPER_FLAGS_5(sve2p1_st1ss_be_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32) +DEF_HELPER_FLAGS_5(sve2p1_st1dd_le_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32) +DEF_HELPER_FLAGS_5(sve2p1_st1dd_be_c, TCG_CALL_NO_WG, void, env, ptr, tl, i32, i32) diff --git a/target/arm/tcg/helper.h b/target/arm/tcg/helper.h index 80db7c2..d9565c8 100644 --- a/target/arm/tcg/helper.h +++ b/target/arm/tcg/helper.h @@ -353,6 +353,14 @@ DEF_HELPER_FLAGS_4(gvec_urshl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_urshl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_urshl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme2_srshl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme2_srshl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme2_srshl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sme2_urshl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme2_urshl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme2_urshl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_2(neon_add_u8, i32, i32, i32) DEF_HELPER_2(neon_add_u16, i32, i32, i32) DEF_HELPER_2(neon_sub_u8, i32, i32, i32) @@ -608,23 +616,31 @@ DEF_HELPER_FLAGS_5(sve2_sqrdmlah_d, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_5(sve2_sqrdmlsh_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_sdot_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_udot_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_sdot_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_udot_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_usdot_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_sdot_4b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_udot_4b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_sdot_4h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_udot_4h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_usdot_4b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(gvec_sdot_2h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_udot_2h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_sdot_idx_b, TCG_CALL_NO_RWG, +DEF_HELPER_FLAGS_5(gvec_sdot_idx_4b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_udot_idx_4b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_sdot_idx_4h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_udot_idx_b, TCG_CALL_NO_RWG, +DEF_HELPER_FLAGS_5(gvec_udot_idx_4h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_sdot_idx_h, TCG_CALL_NO_RWG, +DEF_HELPER_FLAGS_5(gvec_sudot_idx_4b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_udot_idx_h, TCG_CALL_NO_RWG, +DEF_HELPER_FLAGS_5(gvec_usdot_idx_4b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_sudot_idx_b, TCG_CALL_NO_RWG, + +DEF_HELPER_FLAGS_5(gvec_sdot_idx_2h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_usdot_idx_b, TCG_CALL_NO_RWG, +DEF_HELPER_FLAGS_5(gvec_udot_idx_2h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fcaddh, TCG_CALL_NO_RWG, @@ -715,10 +731,12 @@ DEF_HELPER_FLAGS_4(gvec_fclt0_d, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_fadd_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_fadd_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_fadd_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_bfadd, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_fsub_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_fsub_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_fsub_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_bfsub, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_fmul_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_fmul_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) @@ -774,23 +792,26 @@ DEF_HELPER_FLAGS_5(gvec_recps_nf_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, DEF_HELPER_FLAGS_5(gvec_rsqrts_nf_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_rsqrts_nf_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) -DEF_HELPER_FLAGS_5(gvec_fmla_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) -DEF_HELPER_FLAGS_5(gvec_fmla_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_fmla_nf_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_fmla_nf_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) -DEF_HELPER_FLAGS_5(gvec_fmls_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) -DEF_HELPER_FLAGS_5(gvec_fmls_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_fmls_nf_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_fmls_nf_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_vfma_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_vfma_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_vfma_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_bfmla, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_vfms_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_vfms_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_vfms_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_bfmls, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_ah_vfms_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_ah_vfms_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_ah_vfms_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_ah_bfmls, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_ftsmul_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) @@ -822,6 +843,8 @@ DEF_HELPER_FLAGS_6(gvec_fmla_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(gvec_fmla_idx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_6(gvec_bfmla_idx, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(gvec_fmls_idx_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, fpst, i32) @@ -829,6 +852,8 @@ DEF_HELPER_FLAGS_6(gvec_fmls_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(gvec_fmls_idx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_6(gvec_bfmls_idx, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(gvec_ah_fmls_idx_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, fpst, i32) @@ -836,6 +861,8 @@ DEF_HELPER_FLAGS_6(gvec_ah_fmls_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(gvec_ah_fmls_idx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_6(gvec_ah_bfmls_idx, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_uqadd_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) @@ -1081,14 +1108,24 @@ DEF_HELPER_FLAGS_6(gvec_bfdot, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, env, i32) DEF_HELPER_FLAGS_6(gvec_bfdot_idx, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_6(sme2_bfvdot_idx, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, env, i32) DEF_HELPER_FLAGS_6(gvec_bfmmla, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, env, i32) DEF_HELPER_FLAGS_6(gvec_bfmlal, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_6(gvec_bfmlsl, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_6(gvec_ah_bfmlsl, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(gvec_bfmlal_idx, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_6(gvec_bfmlsl_idx, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_6(gvec_ah_bfmlsl_idx, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_sclamp_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) @@ -1151,3 +1188,27 @@ DEF_HELPER_FLAGS_4(gvec_uminp_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_3(gvec_urecpe_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(gvec_ursqrte_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sme2_luti2_1b, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_4(sme2_luti2_1h, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_4(sme2_luti2_1s, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32) + +DEF_HELPER_FLAGS_4(sme2_luti2_2b, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_4(sme2_luti2_2h, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_4(sme2_luti2_2s, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32) + +DEF_HELPER_FLAGS_4(sme2_luti2_4b, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_4(sme2_luti2_4h, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_4(sme2_luti2_4s, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32) + +DEF_HELPER_FLAGS_4(sme2_luti4_1b, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_4(sme2_luti4_1h, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_4(sme2_luti4_1s, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32) + +DEF_HELPER_FLAGS_4(sme2_luti4_2b, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_4(sme2_luti4_2h, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_4(sme2_luti4_2s, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32) + +DEF_HELPER_FLAGS_4(sme2_luti4_4b, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_4(sme2_luti4_4h, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_4(sme2_luti4_4s, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32) diff --git a/target/arm/tcg/hflags.c b/target/arm/tcg/hflags.c index 1ccec63..59ab526 100644 --- a/target/arm/tcg/hflags.c +++ b/target/arm/tcg/hflags.c @@ -214,6 +214,31 @@ static CPUARMTBFlags rebuild_hflags_a32(CPUARMState *env, int fp_el, return rebuild_hflags_common_32(env, fp_el, mmu_idx, flags); } +/* + * Return the exception level to which exceptions should be taken for ZT0. + * C.f. the ARM pseudocode function CheckSMEZT0Enabled, after the ZA check. + */ +static int zt0_exception_el(CPUARMState *env, int el) +{ +#ifndef CONFIG_USER_ONLY + if (el <= 1 + && !el_is_in_host(env, el) + && !FIELD_EX64(env->vfp.smcr_el[1], SMCR, EZT0)) { + return 1; + } + if (el <= 2 + && arm_is_el2_enabled(env) + && !FIELD_EX64(env->vfp.smcr_el[2], SMCR, EZT0)) { + return 2; + } + if (arm_feature(env, ARM_FEATURE_EL3) + && !FIELD_EX64(env->vfp.smcr_el[3], SMCR, EZT0)) { + return 3; + } +#endif + return 0; +} + static CPUARMTBFlags rebuild_hflags_a64(CPUARMState *env, int el, int fp_el, ARMMMUIdx mmu_idx) { @@ -269,7 +294,14 @@ static CPUARMTBFlags rebuild_hflags_a64(CPUARMState *env, int el, int fp_el, DP_TBFLAG_A64(flags, PSTATE_SM, 1); DP_TBFLAG_A64(flags, SME_TRAP_NONSTREAMING, !sme_fa64(env, el)); } - DP_TBFLAG_A64(flags, PSTATE_ZA, FIELD_EX64(env->svcr, SVCR, ZA)); + + if (FIELD_EX64(env->svcr, SVCR, ZA)) { + DP_TBFLAG_A64(flags, PSTATE_ZA, 1); + if (cpu_isar_feature(aa64_sme2, env_archcpu(env))) { + int zt0_el = zt0_exception_el(env, el); + DP_TBFLAG_A64(flags, ZT0EXC_EL, zt0_el); + } + } } sctlr = regime_sctlr(env, stage1); diff --git a/target/arm/tcg/m_helper.c b/target/arm/tcg/m_helper.c index 6614719..28307b5 100644 --- a/target/arm/tcg/m_helper.c +++ b/target/arm/tcg/m_helper.c @@ -632,8 +632,11 @@ void HELPER(v7m_blxns)(CPUARMState *env, uint32_t dest) } /* Note that these stores can throw exceptions on MPU faults */ - cpu_stl_data_ra(env, sp, nextinst, GETPC()); - cpu_stl_data_ra(env, sp + 4, saved_psr, GETPC()); + ARMMMUIdx mmu_idx = arm_mmu_idx(env); + MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, + arm_to_core_mmu_idx(mmu_idx)); + cpu_stl_mmu(env, sp, nextinst, oi, GETPC()); + cpu_stl_mmu(env, sp + 4, saved_psr, oi, GETPC()); env->regs[13] = sp; env->regs[14] = 0xfeffffff; @@ -1048,6 +1051,9 @@ void HELPER(v7m_vlstm)(CPUARMState *env, uint32_t fptr) bool s = env->v7m.fpccr[M_REG_S] & R_V7M_FPCCR_S_MASK; bool lspact = env->v7m.fpccr[s] & R_V7M_FPCCR_LSPACT_MASK; uintptr_t ra = GETPC(); + ARMMMUIdx mmu_idx = arm_mmu_idx(env); + MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, + arm_to_core_mmu_idx(mmu_idx)); assert(env->v7m.secure); @@ -1073,7 +1079,7 @@ void HELPER(v7m_vlstm)(CPUARMState *env, uint32_t fptr) * Note that we do not use v7m_stack_write() here, because the * accesses should not set the FSR bits for stacking errors if they * fail. (In pseudocode terms, they are AccType_NORMAL, not AccType_STACK - * or AccType_LAZYFP). Faults in cpu_stl_data_ra() will throw exceptions + * or AccType_LAZYFP). Faults in cpu_stl_mmu() will throw exceptions * and longjmp out. */ if (!(env->v7m.fpccr[M_REG_S] & R_V7M_FPCCR_LSPEN_MASK)) { @@ -1089,12 +1095,12 @@ void HELPER(v7m_vlstm)(CPUARMState *env, uint32_t fptr) if (i >= 16) { faddr += 8; /* skip the slot for the FPSCR */ } - cpu_stl_data_ra(env, faddr, slo, ra); - cpu_stl_data_ra(env, faddr + 4, shi, ra); + cpu_stl_mmu(env, faddr, slo, oi, ra); + cpu_stl_mmu(env, faddr + 4, shi, oi, ra); } - cpu_stl_data_ra(env, fptr + 0x40, vfp_get_fpscr(env), ra); + cpu_stl_mmu(env, fptr + 0x40, vfp_get_fpscr(env), oi, ra); if (cpu_isar_feature(aa32_mve, cpu)) { - cpu_stl_data_ra(env, fptr + 0x44, env->v7m.vpr, ra); + cpu_stl_mmu(env, fptr + 0x44, env->v7m.vpr, oi, ra); } /* @@ -1121,6 +1127,9 @@ void HELPER(v7m_vlldm)(CPUARMState *env, uint32_t fptr) { ARMCPU *cpu = env_archcpu(env); uintptr_t ra = GETPC(); + ARMMMUIdx mmu_idx = arm_mmu_idx(env); + MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, + arm_to_core_mmu_idx(mmu_idx)); /* fptr is the value of Rn, the frame pointer we load the FP regs from */ assert(env->v7m.secure); @@ -1155,16 +1164,16 @@ void HELPER(v7m_vlldm)(CPUARMState *env, uint32_t fptr) faddr += 8; /* skip the slot for the FPSCR and VPR */ } - slo = cpu_ldl_data_ra(env, faddr, ra); - shi = cpu_ldl_data_ra(env, faddr + 4, ra); + slo = cpu_ldl_mmu(env, faddr, oi, ra); + shi = cpu_ldl_mmu(env, faddr + 4, oi, ra); dn = (uint64_t) shi << 32 | slo; *aa32_vfp_dreg(env, i / 2) = dn; } - fpscr = cpu_ldl_data_ra(env, fptr + 0x40, ra); + fpscr = cpu_ldl_mmu(env, fptr + 0x40, oi, ra); vfp_set_fpscr(env, fpscr); if (cpu_isar_feature(aa32_mve, cpu)) { - env->v7m.vpr = cpu_ldl_data_ra(env, fptr + 0x44, ra); + env->v7m.vpr = cpu_ldl_mmu(env, fptr + 0x44, oi, ra); } } @@ -1937,7 +1946,7 @@ static bool do_v7m_function_return(ARMCPU *cpu) * do them as secure, so work out what MMU index that is. */ mmu_idx = arm_v7m_mmu_idx_for_secstate(env, true); - oi = make_memop_idx(MO_LEUL, arm_to_core_mmu_idx(mmu_idx)); + oi = make_memop_idx(MO_LEUL | MO_ALIGN, arm_to_core_mmu_idx(mmu_idx)); newpc = cpu_ldl_mmu(env, frameptr, oi, 0); newpsr = cpu_ldl_mmu(env, frameptr + 4, oi, 0); diff --git a/target/arm/tcg/mve_helper.c b/target/arm/tcg/mve_helper.c index 506d1c3..63ddcf3 100644 --- a/target/arm/tcg/mve_helper.c +++ b/target/arm/tcg/mve_helper.c @@ -148,13 +148,15 @@ static void mve_advance_vpt(CPUARMState *env) } /* For loads, predicated lanes are zeroed instead of keeping their old values */ -#define DO_VLDR(OP, MSIZE, LDTYPE, ESIZE, TYPE) \ +#define DO_VLDR(OP, MFLAG, MSIZE, MTYPE, LDTYPE, ESIZE, TYPE) \ void HELPER(mve_##OP)(CPUARMState *env, void *vd, uint32_t addr) \ { \ TYPE *d = vd; \ uint16_t mask = mve_element_mask(env); \ uint16_t eci_mask = mve_eci_mask(env); \ unsigned b, e; \ + int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ + MemOpIdx oi = make_memop_idx(MFLAG | MO_ALIGN, mmu_idx); \ /* \ * R_SXTM allows the dest reg to become UNKNOWN for abandoned \ * beats so we don't care if we update part of the dest and \ @@ -163,46 +165,48 @@ static void mve_advance_vpt(CPUARMState *env) for (b = 0, e = 0; b < 16; b += ESIZE, e++) { \ if (eci_mask & (1 << b)) { \ d[H##ESIZE(e)] = (mask & (1 << b)) ? \ - cpu_##LDTYPE##_data_ra(env, addr, GETPC()) : 0; \ + (MTYPE)cpu_##LDTYPE##_mmu(env, addr, oi, GETPC()) : 0;\ } \ addr += MSIZE; \ } \ mve_advance_vpt(env); \ } -#define DO_VSTR(OP, MSIZE, STTYPE, ESIZE, TYPE) \ +#define DO_VSTR(OP, MFLAG, MSIZE, STTYPE, ESIZE, TYPE) \ void HELPER(mve_##OP)(CPUARMState *env, void *vd, uint32_t addr) \ { \ TYPE *d = vd; \ uint16_t mask = mve_element_mask(env); \ unsigned b, e; \ + int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ + MemOpIdx oi = make_memop_idx(MFLAG | MO_ALIGN, mmu_idx); \ for (b = 0, e = 0; b < 16; b += ESIZE, e++) { \ if (mask & (1 << b)) { \ - cpu_##STTYPE##_data_ra(env, addr, d[H##ESIZE(e)], GETPC()); \ + cpu_##STTYPE##_mmu(env, addr, d[H##ESIZE(e)], oi, GETPC()); \ } \ addr += MSIZE; \ } \ mve_advance_vpt(env); \ } -DO_VLDR(vldrb, 1, ldub, 1, uint8_t) -DO_VLDR(vldrh, 2, lduw, 2, uint16_t) -DO_VLDR(vldrw, 4, ldl, 4, uint32_t) +DO_VLDR(vldrb, MO_UB, 1, uint8_t, ldb, 1, uint8_t) +DO_VLDR(vldrh, MO_TEUW, 2, uint16_t, ldw, 2, uint16_t) +DO_VLDR(vldrw, MO_TEUL, 4, uint32_t, ldl, 4, uint32_t) -DO_VSTR(vstrb, 1, stb, 1, uint8_t) -DO_VSTR(vstrh, 2, stw, 2, uint16_t) -DO_VSTR(vstrw, 4, stl, 4, uint32_t) +DO_VSTR(vstrb, MO_UB, 1, stb, 1, uint8_t) +DO_VSTR(vstrh, MO_TEUW, 2, stw, 2, uint16_t) +DO_VSTR(vstrw, MO_TEUL, 4, stl, 4, uint32_t) -DO_VLDR(vldrb_sh, 1, ldsb, 2, int16_t) -DO_VLDR(vldrb_sw, 1, ldsb, 4, int32_t) -DO_VLDR(vldrb_uh, 1, ldub, 2, uint16_t) -DO_VLDR(vldrb_uw, 1, ldub, 4, uint32_t) -DO_VLDR(vldrh_sw, 2, ldsw, 4, int32_t) -DO_VLDR(vldrh_uw, 2, lduw, 4, uint32_t) +DO_VLDR(vldrb_sh, MO_SB, 1, int8_t, ldb, 2, int16_t) +DO_VLDR(vldrb_sw, MO_SB, 1, int8_t, ldb, 4, int32_t) +DO_VLDR(vldrb_uh, MO_UB, 1, uint8_t, ldb, 2, uint16_t) +DO_VLDR(vldrb_uw, MO_UB, 1, uint8_t, ldb, 4, uint32_t) +DO_VLDR(vldrh_sw, MO_TESW, 2, int16_t, ldw, 4, int32_t) +DO_VLDR(vldrh_uw, MO_TEUW, 2, uint16_t, ldw, 4, uint32_t) -DO_VSTR(vstrb_h, 1, stb, 2, int16_t) -DO_VSTR(vstrb_w, 1, stb, 4, int32_t) -DO_VSTR(vstrh_w, 2, stw, 4, int32_t) +DO_VSTR(vstrb_h, MO_UB, 1, stb, 2, int16_t) +DO_VSTR(vstrb_w, MO_UB, 1, stb, 4, int32_t) +DO_VSTR(vstrh_w, MO_TEUW, 2, stw, 4, int32_t) #undef DO_VLDR #undef DO_VSTR @@ -214,7 +218,7 @@ DO_VSTR(vstrh_w, 2, stw, 4, int32_t) * For loads, predicated lanes are zeroed instead of retaining * their previous values. */ -#define DO_VLDR_SG(OP, LDTYPE, ESIZE, TYPE, OFFTYPE, ADDRFN, WB) \ +#define DO_VLDR_SG(OP, MFLAG, MTYPE, LDTYPE, ESIZE, TYPE, OFFTYPE, ADDRFN, WB)\ void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm, \ uint32_t base) \ { \ @@ -224,13 +228,15 @@ DO_VSTR(vstrh_w, 2, stw, 4, int32_t) uint16_t eci_mask = mve_eci_mask(env); \ unsigned e; \ uint32_t addr; \ + int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ + MemOpIdx oi = make_memop_idx(MFLAG | MO_ALIGN, mmu_idx); \ for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE, eci_mask >>= ESIZE) { \ if (!(eci_mask & 1)) { \ continue; \ } \ addr = ADDRFN(base, m[H##ESIZE(e)]); \ d[H##ESIZE(e)] = (mask & 1) ? \ - cpu_##LDTYPE##_data_ra(env, addr, GETPC()) : 0; \ + (MTYPE)cpu_##LDTYPE##_mmu(env, addr, oi, GETPC()) : 0; \ if (WB) { \ m[H##ESIZE(e)] = addr; \ } \ @@ -239,7 +245,7 @@ DO_VSTR(vstrh_w, 2, stw, 4, int32_t) } /* We know here TYPE is unsigned so always the same as the offset type */ -#define DO_VSTR_SG(OP, STTYPE, ESIZE, TYPE, ADDRFN, WB) \ +#define DO_VSTR_SG(OP, MFLAG, STTYPE, ESIZE, TYPE, ADDRFN, WB) \ void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm, \ uint32_t base) \ { \ @@ -249,13 +255,15 @@ DO_VSTR(vstrh_w, 2, stw, 4, int32_t) uint16_t eci_mask = mve_eci_mask(env); \ unsigned e; \ uint32_t addr; \ + int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ + MemOpIdx oi = make_memop_idx(MFLAG | MO_ALIGN, mmu_idx); \ for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE, eci_mask >>= ESIZE) { \ if (!(eci_mask & 1)) { \ continue; \ } \ addr = ADDRFN(base, m[H##ESIZE(e)]); \ if (mask & 1) { \ - cpu_##STTYPE##_data_ra(env, addr, d[H##ESIZE(e)], GETPC()); \ + cpu_##STTYPE##_mmu(env, addr, d[H##ESIZE(e)], oi, GETPC()); \ } \ if (WB) { \ m[H##ESIZE(e)] = addr; \ @@ -282,13 +290,15 @@ DO_VSTR(vstrh_w, 2, stw, 4, int32_t) uint16_t eci_mask = mve_eci_mask(env); \ unsigned e; \ uint32_t addr; \ + int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ + MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ for (e = 0; e < 16 / 4; e++, mask >>= 4, eci_mask >>= 4) { \ if (!(eci_mask & 1)) { \ continue; \ } \ addr = ADDRFN(base, m[H4(e & ~1)]); \ addr += 4 * (e & 1); \ - d[H4(e)] = (mask & 1) ? cpu_ldl_data_ra(env, addr, GETPC()) : 0; \ + d[H4(e)] = (mask & 1) ? cpu_ldl_mmu(env, addr, oi, GETPC()) : 0; \ if (WB && (e & 1)) { \ m[H4(e & ~1)] = addr - 4; \ } \ @@ -306,6 +316,8 @@ DO_VSTR(vstrh_w, 2, stw, 4, int32_t) uint16_t eci_mask = mve_eci_mask(env); \ unsigned e; \ uint32_t addr; \ + int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ + MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ for (e = 0; e < 16 / 4; e++, mask >>= 4, eci_mask >>= 4) { \ if (!(eci_mask & 1)) { \ continue; \ @@ -313,7 +325,7 @@ DO_VSTR(vstrh_w, 2, stw, 4, int32_t) addr = ADDRFN(base, m[H4(e & ~1)]); \ addr += 4 * (e & 1); \ if (mask & 1) { \ - cpu_stl_data_ra(env, addr, d[H4(e)], GETPC()); \ + cpu_stl_mmu(env, addr, d[H4(e)], oi, GETPC()); \ } \ if (WB && (e & 1)) { \ m[H4(e & ~1)] = addr - 4; \ @@ -327,40 +339,44 @@ DO_VSTR(vstrh_w, 2, stw, 4, int32_t) #define ADDR_ADD_OSW(BASE, OFFSET) ((BASE) + ((OFFSET) << 2)) #define ADDR_ADD_OSD(BASE, OFFSET) ((BASE) + ((OFFSET) << 3)) -DO_VLDR_SG(vldrb_sg_sh, ldsb, 2, int16_t, uint16_t, ADDR_ADD, false) -DO_VLDR_SG(vldrb_sg_sw, ldsb, 4, int32_t, uint32_t, ADDR_ADD, false) -DO_VLDR_SG(vldrh_sg_sw, ldsw, 4, int32_t, uint32_t, ADDR_ADD, false) +DO_VLDR_SG(vldrb_sg_sh, MO_SB, int8_t, ldb, 2, int16_t, uint16_t, ADDR_ADD, false) +DO_VLDR_SG(vldrb_sg_sw, MO_SB, int8_t, ldb, 4, int32_t, uint32_t, ADDR_ADD, false) +DO_VLDR_SG(vldrh_sg_sw, MO_TESW, int16_t, ldw, 4, int32_t, uint32_t, ADDR_ADD, false) -DO_VLDR_SG(vldrb_sg_ub, ldub, 1, uint8_t, uint8_t, ADDR_ADD, false) -DO_VLDR_SG(vldrb_sg_uh, ldub, 2, uint16_t, uint16_t, ADDR_ADD, false) -DO_VLDR_SG(vldrb_sg_uw, ldub, 4, uint32_t, uint32_t, ADDR_ADD, false) -DO_VLDR_SG(vldrh_sg_uh, lduw, 2, uint16_t, uint16_t, ADDR_ADD, false) -DO_VLDR_SG(vldrh_sg_uw, lduw, 4, uint32_t, uint32_t, ADDR_ADD, false) -DO_VLDR_SG(vldrw_sg_uw, ldl, 4, uint32_t, uint32_t, ADDR_ADD, false) +DO_VLDR_SG(vldrb_sg_ub, MO_UB, uint8_t, ldb, 1, uint8_t, uint8_t, ADDR_ADD, false) +DO_VLDR_SG(vldrb_sg_uh, MO_UB, uint8_t, ldb, 2, uint16_t, uint16_t, ADDR_ADD, false) +DO_VLDR_SG(vldrb_sg_uw, MO_UB, uint8_t, ldb, 4, uint32_t, uint32_t, ADDR_ADD, false) +DO_VLDR_SG(vldrh_sg_uh, MO_TEUW, uint16_t, ldw, 2, uint16_t, uint16_t, ADDR_ADD, false) +DO_VLDR_SG(vldrh_sg_uw, MO_TEUW, uint16_t, ldw, 4, uint32_t, uint32_t, ADDR_ADD, false) +DO_VLDR_SG(vldrw_sg_uw, MO_TEUL, uint32_t, ldl, 4, uint32_t, uint32_t, ADDR_ADD, false) DO_VLDR64_SG(vldrd_sg_ud, ADDR_ADD, false) -DO_VLDR_SG(vldrh_sg_os_sw, ldsw, 4, int32_t, uint32_t, ADDR_ADD_OSH, false) -DO_VLDR_SG(vldrh_sg_os_uh, lduw, 2, uint16_t, uint16_t, ADDR_ADD_OSH, false) -DO_VLDR_SG(vldrh_sg_os_uw, lduw, 4, uint32_t, uint32_t, ADDR_ADD_OSH, false) -DO_VLDR_SG(vldrw_sg_os_uw, ldl, 4, uint32_t, uint32_t, ADDR_ADD_OSW, false) +DO_VLDR_SG(vldrh_sg_os_sw, MO_TESW, int16_t, ldw, 4, + int32_t, uint32_t, ADDR_ADD_OSH, false) +DO_VLDR_SG(vldrh_sg_os_uh, MO_TEUW, uint16_t, ldw, 2, + uint16_t, uint16_t, ADDR_ADD_OSH, false) +DO_VLDR_SG(vldrh_sg_os_uw, MO_TEUW, uint16_t, ldw, 4, + uint32_t, uint32_t, ADDR_ADD_OSH, false) +DO_VLDR_SG(vldrw_sg_os_uw, MO_TEUL, uint32_t, ldl, 4, + uint32_t, uint32_t, ADDR_ADD_OSW, false) DO_VLDR64_SG(vldrd_sg_os_ud, ADDR_ADD_OSD, false) -DO_VSTR_SG(vstrb_sg_ub, stb, 1, uint8_t, ADDR_ADD, false) -DO_VSTR_SG(vstrb_sg_uh, stb, 2, uint16_t, ADDR_ADD, false) -DO_VSTR_SG(vstrb_sg_uw, stb, 4, uint32_t, ADDR_ADD, false) -DO_VSTR_SG(vstrh_sg_uh, stw, 2, uint16_t, ADDR_ADD, false) -DO_VSTR_SG(vstrh_sg_uw, stw, 4, uint32_t, ADDR_ADD, false) -DO_VSTR_SG(vstrw_sg_uw, stl, 4, uint32_t, ADDR_ADD, false) +DO_VSTR_SG(vstrb_sg_ub, MO_UB, stb, 1, uint8_t, ADDR_ADD, false) +DO_VSTR_SG(vstrb_sg_uh, MO_UB, stb, 2, uint16_t, ADDR_ADD, false) +DO_VSTR_SG(vstrb_sg_uw, MO_UB, stb, 4, uint32_t, ADDR_ADD, false) +DO_VSTR_SG(vstrh_sg_uh, MO_TEUW, stw, 2, uint16_t, ADDR_ADD, false) +DO_VSTR_SG(vstrh_sg_uw, MO_TEUW, stw, 4, uint32_t, ADDR_ADD, false) +DO_VSTR_SG(vstrw_sg_uw, MO_TEUL, stl, 4, uint32_t, ADDR_ADD, false) DO_VSTR64_SG(vstrd_sg_ud, ADDR_ADD, false) -DO_VSTR_SG(vstrh_sg_os_uh, stw, 2, uint16_t, ADDR_ADD_OSH, false) -DO_VSTR_SG(vstrh_sg_os_uw, stw, 4, uint32_t, ADDR_ADD_OSH, false) -DO_VSTR_SG(vstrw_sg_os_uw, stl, 4, uint32_t, ADDR_ADD_OSW, false) +DO_VSTR_SG(vstrh_sg_os_uh, MO_TEUW, stw, 2, uint16_t, ADDR_ADD_OSH, false) +DO_VSTR_SG(vstrh_sg_os_uw, MO_TEUW, stw, 4, uint32_t, ADDR_ADD_OSH, false) +DO_VSTR_SG(vstrw_sg_os_uw, MO_TEUL, stl, 4, uint32_t, ADDR_ADD_OSW, false) DO_VSTR64_SG(vstrd_sg_os_ud, ADDR_ADD_OSD, false) -DO_VLDR_SG(vldrw_sg_wb_uw, ldl, 4, uint32_t, uint32_t, ADDR_ADD, true) +DO_VLDR_SG(vldrw_sg_wb_uw, MO_TEUL, uint32_t, ldl, 4, uint32_t, uint32_t, ADDR_ADD, true) DO_VLDR64_SG(vldrd_sg_wb_ud, ADDR_ADD, true) -DO_VSTR_SG(vstrw_sg_wb_uw, stl, 4, uint32_t, ADDR_ADD, true) +DO_VSTR_SG(vstrw_sg_wb_uw, MO_TEUL, stl, 4, uint32_t, ADDR_ADD, true) DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true) /* @@ -387,13 +403,15 @@ DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true) uint16_t mask = mve_eci_mask(env); \ static const uint8_t off[4] = { O1, O2, O3, O4 }; \ uint32_t addr, data; \ + int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ + MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ continue; \ } \ addr = base + off[beat] * 4; \ - data = cpu_ldl_le_data_ra(env, addr, GETPC()); \ + data = cpu_ldl_mmu(env, addr, oi, GETPC()); \ for (e = 0; e < 4; e++, data >>= 8) { \ uint8_t *qd = (uint8_t *)aa32_vfp_qreg(env, qnidx + e); \ qd[H1(off[beat])] = data; \ @@ -411,13 +429,15 @@ DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true) uint32_t addr, data; \ int y; /* y counts 0 2 0 2 */ \ uint16_t *qd; \ + int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ + MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ for (beat = 0, y = 0; beat < 4; beat++, mask >>= 4, y ^= 2) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ continue; \ } \ addr = base + off[beat] * 8 + (beat & 1) * 4; \ - data = cpu_ldl_le_data_ra(env, addr, GETPC()); \ + data = cpu_ldl_mmu(env, addr, oi, GETPC()); \ qd = (uint16_t *)aa32_vfp_qreg(env, qnidx + y); \ qd[H2(off[beat])] = data; \ data >>= 16; \ @@ -436,13 +456,15 @@ DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true) uint32_t addr, data; \ uint32_t *qd; \ int y; \ + int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ + MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ continue; \ } \ addr = base + off[beat] * 4; \ - data = cpu_ldl_le_data_ra(env, addr, GETPC()); \ + data = cpu_ldl_mmu(env, addr, oi, GETPC()); \ y = (beat + (O1 & 2)) & 3; \ qd = (uint32_t *)aa32_vfp_qreg(env, qnidx + y); \ qd[H4(off[beat] >> 2)] = data; \ @@ -473,13 +495,15 @@ DO_VLD4W(vld43w, 6, 7, 8, 9) static const uint8_t off[4] = { O1, O2, O3, O4 }; \ uint32_t addr, data; \ uint8_t *qd; \ + int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ + MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ continue; \ } \ addr = base + off[beat] * 2; \ - data = cpu_ldl_le_data_ra(env, addr, GETPC()); \ + data = cpu_ldl_mmu(env, addr, oi, GETPC()); \ for (e = 0; e < 4; e++, data >>= 8) { \ qd = (uint8_t *)aa32_vfp_qreg(env, qnidx + (e & 1)); \ qd[H1(off[beat] + (e >> 1))] = data; \ @@ -497,13 +521,15 @@ DO_VLD4W(vld43w, 6, 7, 8, 9) uint32_t addr, data; \ int e; \ uint16_t *qd; \ + int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ + MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ continue; \ } \ addr = base + off[beat] * 4; \ - data = cpu_ldl_le_data_ra(env, addr, GETPC()); \ + data = cpu_ldl_mmu(env, addr, oi, GETPC()); \ for (e = 0; e < 2; e++, data >>= 16) { \ qd = (uint16_t *)aa32_vfp_qreg(env, qnidx + e); \ qd[H2(off[beat])] = data; \ @@ -520,13 +546,15 @@ DO_VLD4W(vld43w, 6, 7, 8, 9) static const uint8_t off[4] = { O1, O2, O3, O4 }; \ uint32_t addr, data; \ uint32_t *qd; \ + int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ + MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ continue; \ } \ addr = base + off[beat]; \ - data = cpu_ldl_le_data_ra(env, addr, GETPC()); \ + data = cpu_ldl_mmu(env, addr, oi, GETPC()); \ qd = (uint32_t *)aa32_vfp_qreg(env, qnidx + (beat & 1)); \ qd[H4(off[beat] >> 3)] = data; \ } \ @@ -549,6 +577,8 @@ DO_VLD2W(vld21w, 8, 12, 16, 20) uint16_t mask = mve_eci_mask(env); \ static const uint8_t off[4] = { O1, O2, O3, O4 }; \ uint32_t addr, data; \ + int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ + MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ @@ -560,7 +590,7 @@ DO_VLD2W(vld21w, 8, 12, 16, 20) uint8_t *qd = (uint8_t *)aa32_vfp_qreg(env, qnidx + e); \ data = (data << 8) | qd[H1(off[beat])]; \ } \ - cpu_stl_le_data_ra(env, addr, data, GETPC()); \ + cpu_stl_mmu(env, addr, data, oi, GETPC()); \ } \ } @@ -574,6 +604,8 @@ DO_VLD2W(vld21w, 8, 12, 16, 20) uint32_t addr, data; \ int y; /* y counts 0 2 0 2 */ \ uint16_t *qd; \ + int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ + MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ for (beat = 0, y = 0; beat < 4; beat++, mask >>= 4, y ^= 2) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ @@ -584,7 +616,7 @@ DO_VLD2W(vld21w, 8, 12, 16, 20) data = qd[H2(off[beat])]; \ qd = (uint16_t *)aa32_vfp_qreg(env, qnidx + y + 1); \ data |= qd[H2(off[beat])] << 16; \ - cpu_stl_le_data_ra(env, addr, data, GETPC()); \ + cpu_stl_mmu(env, addr, data, oi, GETPC()); \ } \ } @@ -598,6 +630,8 @@ DO_VLD2W(vld21w, 8, 12, 16, 20) uint32_t addr, data; \ uint32_t *qd; \ int y; \ + int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ + MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ @@ -607,7 +641,7 @@ DO_VLD2W(vld21w, 8, 12, 16, 20) y = (beat + (O1 & 2)) & 3; \ qd = (uint32_t *)aa32_vfp_qreg(env, qnidx + y); \ data = qd[H4(off[beat] >> 2)]; \ - cpu_stl_le_data_ra(env, addr, data, GETPC()); \ + cpu_stl_mmu(env, addr, data, oi, GETPC()); \ } \ } @@ -635,6 +669,8 @@ DO_VST4W(vst43w, 6, 7, 8, 9) static const uint8_t off[4] = { O1, O2, O3, O4 }; \ uint32_t addr, data; \ uint8_t *qd; \ + int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ + MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ @@ -646,7 +682,7 @@ DO_VST4W(vst43w, 6, 7, 8, 9) qd = (uint8_t *)aa32_vfp_qreg(env, qnidx + (e & 1)); \ data = (data << 8) | qd[H1(off[beat] + (e >> 1))]; \ } \ - cpu_stl_le_data_ra(env, addr, data, GETPC()); \ + cpu_stl_mmu(env, addr, data, oi, GETPC()); \ } \ } @@ -660,6 +696,8 @@ DO_VST4W(vst43w, 6, 7, 8, 9) uint32_t addr, data; \ int e; \ uint16_t *qd; \ + int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ + MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ @@ -671,7 +709,7 @@ DO_VST4W(vst43w, 6, 7, 8, 9) qd = (uint16_t *)aa32_vfp_qreg(env, qnidx + e); \ data = (data << 16) | qd[H2(off[beat])]; \ } \ - cpu_stl_le_data_ra(env, addr, data, GETPC()); \ + cpu_stl_mmu(env, addr, data, oi, GETPC()); \ } \ } @@ -684,6 +722,8 @@ DO_VST4W(vst43w, 6, 7, 8, 9) static const uint8_t off[4] = { O1, O2, O3, O4 }; \ uint32_t addr, data; \ uint32_t *qd; \ + int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ + MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ @@ -692,7 +732,7 @@ DO_VST4W(vst43w, 6, 7, 8, 9) addr = base + off[beat]; \ qd = (uint32_t *)aa32_vfp_qreg(env, qnidx + (beat & 1)); \ data = qd[H4(off[beat] >> 3)]; \ - cpu_stl_le_data_ra(env, addr, data, GETPC()); \ + cpu_stl_mmu(env, addr, data, oi, GETPC()); \ } \ } @@ -2164,27 +2204,6 @@ DO_VSHLL_ALL(vshllt, true) DO_VSHRN(OP##tb, true, 1, uint8_t, 2, uint16_t, FN) \ DO_VSHRN(OP##th, true, 2, uint16_t, 4, uint32_t, FN) -static inline uint64_t do_urshr(uint64_t x, unsigned sh) -{ - if (likely(sh < 64)) { - return (x >> sh) + ((x >> (sh - 1)) & 1); - } else if (sh == 64) { - return x >> 63; - } else { - return 0; - } -} - -static inline int64_t do_srshr(int64_t x, unsigned sh) -{ - if (likely(sh < 64)) { - return (x >> sh) + ((x >> (sh - 1)) & 1); - } else { - /* Rounding the sign bit always produces 0. */ - return 0; - } -} - DO_VSHRN_ALL(vshrn, DO_SHR) DO_VSHRN_ALL(vrshrn, do_urshr) diff --git a/target/arm/tcg/neon_helper.c b/target/arm/tcg/neon_helper.c index 2cc8241..8d288f3 100644 --- a/target/arm/tcg/neon_helper.c +++ b/target/arm/tcg/neon_helper.c @@ -229,15 +229,30 @@ NEON_GVEC_VOP2(gvec_srshl_h, int16_t) #undef NEON_FN #define NEON_FN(dest, src1, src2) \ + (dest = do_sqrshl_bhs(src1, src2, 16, true, NULL)) +NEON_GVEC_VOP2(sme2_srshl_h, int16_t) +#undef NEON_FN + +#define NEON_FN(dest, src1, src2) \ (dest = do_sqrshl_bhs(src1, (int8_t)src2, 32, true, NULL)) NEON_GVEC_VOP2(gvec_srshl_s, int32_t) #undef NEON_FN #define NEON_FN(dest, src1, src2) \ + (dest = do_sqrshl_bhs(src1, src2, 32, true, NULL)) +NEON_GVEC_VOP2(sme2_srshl_s, int32_t) +#undef NEON_FN + +#define NEON_FN(dest, src1, src2) \ (dest = do_sqrshl_d(src1, (int8_t)src2, true, NULL)) NEON_GVEC_VOP2(gvec_srshl_d, int64_t) #undef NEON_FN +#define NEON_FN(dest, src1, src2) \ + (dest = do_sqrshl_d(src1, src2, true, NULL)) +NEON_GVEC_VOP2(sme2_srshl_d, int64_t) +#undef NEON_FN + uint32_t HELPER(neon_rshl_s32)(uint32_t val, uint32_t shift) { return do_sqrshl_bhs(val, (int8_t)shift, 32, true, NULL); @@ -261,15 +276,30 @@ NEON_GVEC_VOP2(gvec_urshl_h, uint16_t) #undef NEON_FN #define NEON_FN(dest, src1, src2) \ + (dest = do_uqrshl_bhs(src1, (int16_t)src2, 16, true, NULL)) +NEON_GVEC_VOP2(sme2_urshl_h, uint16_t) +#undef NEON_FN + +#define NEON_FN(dest, src1, src2) \ (dest = do_uqrshl_bhs(src1, (int8_t)src2, 32, true, NULL)) NEON_GVEC_VOP2(gvec_urshl_s, int32_t) #undef NEON_FN #define NEON_FN(dest, src1, src2) \ + (dest = do_uqrshl_bhs(src1, src2, 32, true, NULL)) +NEON_GVEC_VOP2(sme2_urshl_s, int32_t) +#undef NEON_FN + +#define NEON_FN(dest, src1, src2) \ (dest = do_uqrshl_d(src1, (int8_t)src2, true, NULL)) NEON_GVEC_VOP2(gvec_urshl_d, int64_t) #undef NEON_FN +#define NEON_FN(dest, src1, src2) \ + (dest = do_uqrshl_d(src1, src2, true, NULL)) +NEON_GVEC_VOP2(sme2_urshl_d, int64_t) +#undef NEON_FN + uint32_t HELPER(neon_rshl_u32)(uint32_t val, uint32_t shift) { return do_uqrshl_bhs(val, (int8_t)shift, 32, true, NULL); diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode index 628804e..6bb9aa2 100644 --- a/target/arm/tcg/sme.decode +++ b/target/arm/tcg/sme.decode @@ -22,30 +22,139 @@ ### SME Misc ZERO 11000000 00 001 00000000000 imm:8 +ZERO_zt0 11000000 01 001 00000000000 00000001 ### SME Move into/from Array %mova_rs 13:2 !function=plus_12 -&mova esz rs pg zr za_imm v:bool to_vec:bool +%mova_rv 13:2 !function=plus_8 +&mova_a rv zr off +&mova_p esz rs pg zr za off v:bool +&mova_t esz rs zr za off v:bool -MOVA 11000000 esz:2 00000 0 v:1 .. pg:3 zr:5 0 za_imm:4 \ - &mova to_vec=0 rs=%mova_rs -MOVA 11000000 11 00000 1 v:1 .. pg:3 zr:5 0 za_imm:4 \ - &mova to_vec=0 rs=%mova_rs esz=4 +MOVA_tz 11000000 00 00000 0 v:1 .. pg:3 zr:5 0 off:4 \ + &mova_p rs=%mova_rs esz=0 za=0 +MOVA_tz 11000000 01 00000 0 v:1 .. pg:3 zr:5 0 za:1 off:3 \ + &mova_p rs=%mova_rs esz=1 +MOVA_tz 11000000 10 00000 0 v:1 .. pg:3 zr:5 0 za:2 off:2 \ + &mova_p rs=%mova_rs esz=2 +MOVA_tz 11000000 11 00000 0 v:1 .. pg:3 zr:5 0 za:3 off:1 \ + &mova_p rs=%mova_rs esz=3 +MOVA_tz 11000000 11 00000 1 v:1 .. pg:3 zr:5 0 za:4 \ + &mova_p rs=%mova_rs esz=4 off=0 -MOVA 11000000 esz:2 00001 0 v:1 .. pg:3 0 za_imm:4 zr:5 \ - &mova to_vec=1 rs=%mova_rs -MOVA 11000000 11 00001 1 v:1 .. pg:3 0 za_imm:4 zr:5 \ - &mova to_vec=1 rs=%mova_rs esz=4 +MOVA_zt 11000000 00 00001 0 v:1 .. pg:3 0 off:4 zr:5 \ + &mova_p rs=%mova_rs esz=0 za=0 +MOVA_zt 11000000 01 00001 0 v:1 .. pg:3 0 za:1 off:3 zr:5 \ + &mova_p rs=%mova_rs esz=1 +MOVA_zt 11000000 10 00001 0 v:1 .. pg:3 0 za:2 off:2 zr:5 \ + &mova_p rs=%mova_rs esz=2 +MOVA_zt 11000000 11 00001 0 v:1 .. pg:3 0 za:3 off:1 zr:5 \ + &mova_p rs=%mova_rs esz=3 +MOVA_zt 11000000 11 00001 1 v:1 .. pg:3 0 za:4 zr:5 \ + &mova_p rs=%mova_rs esz=4 off=0 + +MOVA_tz2 11000000 00 00010 0 v:1 .. 000 zr:4 0 00 off:3 \ + &mova_t rs=%mova_rs esz=0 za=0 +MOVA_tz2 11000000 01 00010 0 v:1 .. 000 zr:4 0 00 za:1 off:2 \ + &mova_t rs=%mova_rs esz=1 +MOVA_tz2 11000000 10 00010 0 v:1 .. 000 zr:4 0 00 za:2 off:1 \ + &mova_t rs=%mova_rs esz=2 +MOVA_tz2 11000000 11 00010 0 v:1 .. 000 zr:4 0 00 za:3 \ + &mova_t rs=%mova_rs esz=3 off=0 + +MOVA_zt2 11000000 00 00011 0 v:1 .. 000 00 off:3 zr:4 0 \ + &mova_t rs=%mova_rs esz=0 za=0 +MOVA_zt2 11000000 01 00011 0 v:1 .. 000 00 za:1 off:2 zr:4 0 \ + &mova_t rs=%mova_rs esz=1 +MOVA_zt2 11000000 10 00011 0 v:1 .. 000 00 za:2 off:1 zr:4 0 \ + &mova_t rs=%mova_rs esz=2 +MOVA_zt2 11000000 11 00011 0 v:1 .. 000 00 za:3 zr:4 0 \ + &mova_t rs=%mova_rs esz=3 off=0 + +MOVA_tz4 11000000 00 00010 0 v:1 .. 001 zr:3 00 000 off:2 \ + &mova_t rs=%mova_rs esz=0 za=0 +MOVA_tz4 11000000 01 00010 0 v:1 .. 001 zr:3 00 000 za:1 off:1 \ + &mova_t rs=%mova_rs esz=1 +MOVA_tz4 11000000 10 00010 0 v:1 .. 001 zr:3 00 000 za:2 \ + &mova_t rs=%mova_rs esz=2 off=0 +MOVA_tz4 11000000 11 00010 0 v:1 .. 001 zr:3 00 00 za:3 \ + &mova_t rs=%mova_rs esz=3 off=0 + +MOVA_zt4 11000000 00 00011 0 v:1 .. 001 000 off:2 zr:3 00 \ + &mova_t rs=%mova_rs esz=0 za=0 +MOVA_zt4 11000000 01 00011 0 v:1 .. 001 000 za:1 off:1 zr:3 00 \ + &mova_t rs=%mova_rs esz=1 +MOVA_zt4 11000000 10 00011 0 v:1 .. 001 000 za:2 zr:3 00 \ + &mova_t rs=%mova_rs esz=2 off=0 +MOVA_zt4 11000000 11 00011 0 v:1 .. 001 00 za:3 zr:3 00 \ + &mova_t rs=%mova_rs esz=3 off=0 + +MOVA_az2 11000000 00 00010 00 .. 010 zr:4 000 off:3 \ + &mova_a rv=%mova_rv +MOVA_az4 11000000 00 00010 00 .. 011 zr:3 0000 off:3 \ + &mova_a rv=%mova_rv + +MOVA_za2 11000000 00 00011 00 .. 010 00 off:3 zr:4 0 \ + &mova_a rv=%mova_rv +MOVA_za4 11000000 00 00011 00 .. 011 00 off:3 zr:3 00 \ + &mova_a rv=%mova_rv + +### SME Move and Zero + +MOVAZ_za2 11000000 00000110 0 .. 01010 off:3 zr:4 0 \ + &mova_a rv=%mova_rv +MOVAZ_za4 11000000 00000110 0 .. 01110 off:3 zr:3 00 \ + &mova_a rv=%mova_rv + +MOVAZ_zt 11000000 00 00001 0 v:1 .. 0001 off:4 zr:5 \ + &mova_t rs=%mova_rs esz=0 za=0 +MOVAZ_zt 11000000 01 00001 0 v:1 .. 0001 za:1 off:3 zr:5 \ + &mova_t rs=%mova_rs esz=1 +MOVAZ_zt 11000000 10 00001 0 v:1 .. 0001 za:2 off:2 zr:5 \ + &mova_t rs=%mova_rs esz=2 +MOVAZ_zt 11000000 11 00001 0 v:1 .. 0001 za:3 off:1 zr:5 \ + &mova_t rs=%mova_rs esz=3 +MOVAZ_zt 11000000 11 00001 1 v:1 .. 0001 za:4 zr:5 \ + &mova_t rs=%mova_rs esz=4 off=0 + +MOVAZ_zt2 11000000 00 00011 0 v:1 .. 00010 off:3 zr:4 0 \ + &mova_t rs=%mova_rs esz=0 za=0 +MOVAZ_zt2 11000000 01 00011 0 v:1 .. 00010 za:1 off:2 zr:4 0 \ + &mova_t rs=%mova_rs esz=1 +MOVAZ_zt2 11000000 10 00011 0 v:1 .. 00010 za:2 off:1 zr:4 0 \ + &mova_t rs=%mova_rs esz=2 +MOVAZ_zt2 11000000 11 00011 0 v:1 .. 00010 za:3 zr:4 0 \ + &mova_t rs=%mova_rs esz=3 off=0 + +MOVAZ_zt4 11000000 00 00011 0 v:1 .. 001100 off:2 zr:3 00 \ + &mova_t rs=%mova_rs esz=0 za=0 +MOVAZ_zt4 11000000 01 00011 0 v:1 .. 001100 za:1 off:1 zr:3 00 \ + &mova_t rs=%mova_rs esz=1 +MOVAZ_zt4 11000000 10 00011 0 v:1 .. 001100 za:2 zr:3 00 \ + &mova_t rs=%mova_rs esz=2 off=0 +MOVAZ_zt4 11000000 11 00011 0 v:1 .. 00110 za:3 zr:3 00 \ + &mova_t rs=%mova_rs esz=3 off=0 + +### SME Move into/from ZT0 + +MOVT_rzt 1100 0000 0100 1100 0 off:3 00 11111 rt:5 +MOVT_ztr 1100 0000 0100 1110 0 off:3 00 11111 rt:5 ### SME Memory -&ldst esz rs pg rn rm za_imm v:bool st:bool +&ldst esz rs pg rn rm za off v:bool st:bool -LDST1 1110000 0 esz:2 st:1 rm:5 v:1 .. pg:3 rn:5 0 za_imm:4 \ - &ldst rs=%mova_rs -LDST1 1110000 111 st:1 rm:5 v:1 .. pg:3 rn:5 0 za_imm:4 \ - &ldst esz=4 rs=%mova_rs +LDST1 1110000 0 00 st:1 rm:5 v:1 .. pg:3 rn:5 0 off:4 \ + &ldst rs=%mova_rs esz=0 za=0 +LDST1 1110000 0 01 st:1 rm:5 v:1 .. pg:3 rn:5 0 za:1 off:3 \ + &ldst rs=%mova_rs esz=1 +LDST1 1110000 0 10 st:1 rm:5 v:1 .. pg:3 rn:5 0 za:2 off:2 \ + &ldst rs=%mova_rs esz=2 +LDST1 1110000 0 11 st:1 rm:5 v:1 .. pg:3 rn:5 0 za:3 off:1 \ + &ldst rs=%mova_rs esz=3 +LDST1 1110000 1 11 st:1 rm:5 v:1 .. pg:3 rn:5 0 za:4 \ + &ldst rs=%mova_rs esz=4 off=0 &ldstr rv rn imm @ldstr ....... ... . ...... .. ... rn:5 . imm:4 \ @@ -54,6 +163,12 @@ LDST1 1110000 111 st:1 rm:5 v:1 .. pg:3 rn:5 0 za_imm:4 \ LDR 1110000 100 0 000000 .. 000 ..... 0 .... @ldstr STR 1110000 100 1 000000 .. 000 ..... 0 .... @ldstr +&ldstzt0 rn +@ldstzt0 ....... ... . ...... .. ... rn:5 ..... &ldstzt0 + +LDR_zt0 1110000 100 0 111111 00 000 ..... 00000 @ldstzt0 +STR_zt0 1110000 100 1 111111 00 000 ..... 00000 @ldstzt0 + ### SME Add Vector to Array &adda zad zn pm pn @@ -68,14 +183,18 @@ ADDVA_d 11000000 11 01000 1 ... ... ..... 00 ... @adda_64 ### SME Outer Product &op zad zn zm pm pn sub:bool +@op_16 ........ ... zm:5 pm:3 pn:3 zn:5 sub:1 ... zad:1 &op @op_32 ........ ... zm:5 pm:3 pn:3 zn:5 sub:1 .. zad:2 &op @op_64 ........ ... zm:5 pm:3 pn:3 zn:5 sub:1 . zad:3 &op +FMOPA_h 10000001 100 ..... ... ... ..... . 100 . @op_16 FMOPA_s 10000000 100 ..... ... ... ..... . 00 .. @op_32 FMOPA_d 10000000 110 ..... ... ... ..... . 0 ... @op_64 -BFMOPA 10000001 100 ..... ... ... ..... . 00 .. @op_32 -FMOPA_h 10000001 101 ..... ... ... ..... . 00 .. @op_32 +BFMOPA 10000001 101 ..... ... ... ..... . 100 . @op_16 + +BFMOPA_w 10000001 100 ..... ... ... ..... . 00 .. @op_32 +FMOPA_w_h 10000001 101 ..... ... ... ..... . 00 .. @op_32 SMOPA_s 1010000 0 10 0 ..... ... ... ..... . 00 .. @op_32 SUMOPA_s 1010000 0 10 1 ..... ... ... ..... . 00 .. @op_32 @@ -86,3 +205,789 @@ SMOPA_d 1010000 0 11 0 ..... ... ... ..... . 0 ... @op_64 SUMOPA_d 1010000 0 11 1 ..... ... ... ..... . 0 ... @op_64 USMOPA_d 1010000 1 11 0 ..... ... ... ..... . 0 ... @op_64 UMOPA_d 1010000 1 11 1 ..... ... ... ..... . 0 ... @op_64 + +BMOPA 1000000 0 10 0 ..... ... ... ..... . 10 .. @op_32 +SMOPA2_s 1010000 0 10 0 ..... ... ... ..... . 10 .. @op_32 +UMOPA2_s 1010000 1 10 0 ..... ... ... ..... . 10 .. @op_32 + +### SME2 Multi-vector Multiple and Single SVE Destructive + +%zd_ax2 1:4 !function=times_2 +%zd_ax4 2:3 !function=times_4 + +&z2z_en zdn zm esz n +@z2z_2x1 ....... . esz:2 .. zm:4 ....0. ..... .... . \ + &z2z_en n=2 zdn=%zd_ax2 +@z2z_4x1 ....... . esz:2 .. zm:4 ....1. ..... ...0 . \ + &z2z_en n=4 zdn=%zd_ax4 + +SMAX_n1 1100000 1 .. 10 .... 1010.0 00000 .... 0 @z2z_2x1 +SMAX_n1 1100000 1 .. 10 .... 1010.0 00000 .... 0 @z2z_4x1 +UMAX_n1 1100000 1 .. 10 .... 1010.0 00000 .... 1 @z2z_2x1 +UMAX_n1 1100000 1 .. 10 .... 1010.0 00000 .... 1 @z2z_4x1 +SMIN_n1 1100000 1 .. 10 .... 1010.0 00001 .... 0 @z2z_2x1 +SMIN_n1 1100000 1 .. 10 .... 1010.0 00001 .... 0 @z2z_4x1 +UMIN_n1 1100000 1 .. 10 .... 1010.0 00001 .... 1 @z2z_2x1 +UMIN_n1 1100000 1 .. 10 .... 1010.0 00001 .... 1 @z2z_4x1 + +FMAX_n1 1100000 1 .. 10 .... 1010.0 01000 .... 0 @z2z_2x1 +FMAX_n1 1100000 1 .. 10 .... 1010.0 01000 .... 0 @z2z_4x1 +FMIN_n1 1100000 1 .. 10 .... 1010.0 01000 .... 1 @z2z_2x1 +FMIN_n1 1100000 1 .. 10 .... 1010.0 01000 .... 1 @z2z_4x1 +FMAXNM_n1 1100000 1 .. 10 .... 1010.0 01001 .... 0 @z2z_2x1 +FMAXNM_n1 1100000 1 .. 10 .... 1010.0 01001 .... 0 @z2z_4x1 +FMINNM_n1 1100000 1 .. 10 .... 1010.0 01001 .... 1 @z2z_2x1 +FMINNM_n1 1100000 1 .. 10 .... 1010.0 01001 .... 1 @z2z_4x1 + +SRSHL_n1 1100000 1 .. 10 .... 1010.0 10001 .... 0 @z2z_2x1 +SRSHL_n1 1100000 1 .. 10 .... 1010.0 10001 .... 0 @z2z_4x1 +URSHL_n1 1100000 1 .. 10 .... 1010.0 10001 .... 1 @z2z_2x1 +URSHL_n1 1100000 1 .. 10 .... 1010.0 10001 .... 1 @z2z_4x1 + +ADD_n1 1100000 1 .. 10 .... 1010.0 11000 .... 0 @z2z_2x1 +ADD_n1 1100000 1 .. 10 .... 1010.0 11000 .... 0 @z2z_4x1 + +SQDMULH_n1 1100000 1 .. 10 .... 1010.1 00000 .... 0 @z2z_2x1 +SQDMULH_n1 1100000 1 .. 10 .... 1010.1 00000 .... 0 @z2z_4x1 + +### SME2 Multi-vector Multiple Vectors SVE Destructive + +%zm_ax2 17:4 !function=times_2 +%zm_ax4 18:3 !function=times_4 + +@z2z_2x2 ....... . esz:2 . ....0 ....0. ..... .... . \ + &z2z_en n=2 zdn=%zd_ax2 zm=%zm_ax2 +@z2z_4x4 ....... . esz:2 . ...00 ....1. ..... ...0 . \ + &z2z_en n=4 zdn=%zd_ax4 zm=%zm_ax4 + +SMAX_nn 1100000 1 .. 1 ..... 1011.0 00000 .... 0 @z2z_2x2 +SMAX_nn 1100000 1 .. 1 ..... 1011.0 00000 .... 0 @z2z_4x4 +UMAX_nn 1100000 1 .. 1 ..... 1011.0 00000 .... 1 @z2z_2x2 +UMAX_nn 1100000 1 .. 1 ..... 1011.0 00000 .... 1 @z2z_4x4 +SMIN_nn 1100000 1 .. 1 ..... 1011.0 00001 .... 0 @z2z_2x2 +SMIN_nn 1100000 1 .. 1 ..... 1011.0 00001 .... 0 @z2z_4x4 +UMIN_nn 1100000 1 .. 1 ..... 1011.0 00001 .... 1 @z2z_2x2 +UMIN_nn 1100000 1 .. 1 ..... 1011.0 00001 .... 1 @z2z_4x4 + +FMAX_nn 1100000 1 .. 1 ..... 1011.0 01000 .... 0 @z2z_2x2 +FMAX_nn 1100000 1 .. 1 ..... 1011.0 01000 .... 0 @z2z_4x4 +FMIN_nn 1100000 1 .. 1 ..... 1011.0 01000 .... 1 @z2z_2x2 +FMIN_nn 1100000 1 .. 1 ..... 1011.0 01000 .... 1 @z2z_4x4 +FMAXNM_nn 1100000 1 .. 1 ..... 1011.0 01001 .... 0 @z2z_2x2 +FMAXNM_nn 1100000 1 .. 1 ..... 1011.0 01001 .... 0 @z2z_4x4 +FMINNM_nn 1100000 1 .. 1 ..... 1011.0 01001 .... 1 @z2z_2x2 +FMINNM_nn 1100000 1 .. 1 ..... 1011.0 01001 .... 1 @z2z_4x4 + +SRSHL_nn 1100000 1 .. 1 ..... 1011.0 10001 .... 0 @z2z_2x2 +SRSHL_nn 1100000 1 .. 1 ..... 1011.0 10001 .... 0 @z2z_4x4 +URSHL_nn 1100000 1 .. 1 ..... 1011.0 10001 .... 1 @z2z_2x2 +URSHL_nn 1100000 1 .. 1 ..... 1011.0 10001 .... 1 @z2z_4x4 + +SQDMULH_nn 1100000 1 .. 1 ..... 1011.1 00000 .... 0 @z2z_2x2 +SQDMULH_nn 1100000 1 .. 1 ..... 1011.1 00000 .... 0 @z2z_4x4 + +### SME2 Multi-vector Multiple and Single Array Vectors + +&azz_n n off rv zn zm +@azz_nx1_o3 ........ .... zm:4 ...... zn:5 .. off:3 &azz_n rv=%mova_rv + +ADD_azz_n1_s 11000001 0010 .... 0 .. 110 ..... 10 ... @azz_nx1_o3 n=2 +ADD_azz_n1_s 11000001 0011 .... 0 .. 110 ..... 10 ... @azz_nx1_o3 n=4 +ADD_azz_n1_d 11000001 0110 .... 0 .. 110 ..... 10 ... @azz_nx1_o3 n=2 +ADD_azz_n1_d 11000001 0111 .... 0 .. 110 ..... 10 ... @azz_nx1_o3 n=4 + +SUB_azz_n1_s 11000001 0010 .... 0 .. 110 ..... 11 ... @azz_nx1_o3 n=2 +SUB_azz_n1_s 11000001 0011 .... 0 .. 110 ..... 11 ... @azz_nx1_o3 n=4 +SUB_azz_n1_d 11000001 0110 .... 0 .. 110 ..... 11 ... @azz_nx1_o3 n=2 +SUB_azz_n1_d 11000001 0111 .... 0 .. 110 ..... 11 ... @azz_nx1_o3 n=4 + +%off3_x2 0:3 !function=times_2 +%off2_x2 0:2 !function=times_2 + +@azz_nx1_o3x2 ........ ... . zm:4 . .. ... zn:5 .. ... \ + &azz_n off=%off3_x2 rv=%mova_rv +@azz_nx1_o2x2 ........ ... . zm:4 . .. ... zn:5 ... .. \ + &azz_n off=%off2_x2 rv=%mova_rv + +FMLAL_n1 11000001 001 0 .... 0 .. 011 ..... 00 ... @azz_nx1_o3x2 n=1 +FMLAL_n1 11000001 001 0 .... 0 .. 010 ..... 000 .. @azz_nx1_o2x2 n=2 +FMLAL_n1 11000001 001 1 .... 0 .. 010 ..... 000 .. @azz_nx1_o2x2 n=4 + +FMLSL_n1 11000001 001 0 .... 0 .. 011 ..... 01 ... @azz_nx1_o3x2 n=1 +FMLSL_n1 11000001 001 0 .... 0 .. 010 ..... 010 .. @azz_nx1_o2x2 n=2 +FMLSL_n1 11000001 001 1 .... 0 .. 010 ..... 010 .. @azz_nx1_o2x2 n=4 + +BFMLAL_n1 11000001 001 0 .... 0 .. 011 ..... 10 ... @azz_nx1_o3x2 n=1 +BFMLAL_n1 11000001 001 0 .... 0 .. 010 ..... 100 .. @azz_nx1_o2x2 n=2 +BFMLAL_n1 11000001 001 1 .... 0 .. 010 ..... 100 .. @azz_nx1_o2x2 n=4 + +BFMLSL_n1 11000001 001 0 .... 0 .. 011 ..... 11 ... @azz_nx1_o3x2 n=1 +BFMLSL_n1 11000001 001 0 .... 0 .. 010 ..... 110 .. @azz_nx1_o2x2 n=2 +BFMLSL_n1 11000001 001 1 .... 0 .. 010 ..... 110 .. @azz_nx1_o2x2 n=4 + +FDOT_n1 11000001 001 0 .... 0 .. 100 ..... 00 ... @azz_nx1_o3 n=2 +FDOT_n1 11000001 001 1 .... 0 .. 100 ..... 00 ... @azz_nx1_o3 n=4 + +BFDOT_n1 11000001 001 0 .... 0 .. 100 ..... 10 ... @azz_nx1_o3 n=2 +BFDOT_n1 11000001 001 1 .... 0 .. 100 ..... 10 ... @azz_nx1_o3 n=4 + +USDOT_n1 11000001 001 0 .... 0 .. 101 ..... 01 ... @azz_nx1_o3 n=2 +USDOT_n1 11000001 001 1 .... 0 .. 101 ..... 01 ... @azz_nx1_o3 n=4 + +SUDOT_n1 11000001 001 0 .... 0 .. 101 ..... 11 ... @azz_nx1_o3 n=2 +SUDOT_n1 11000001 001 1 .... 0 .. 101 ..... 11 ... @azz_nx1_o3 n=4 + +SDOT_n1_4b 11000001 001 0 .... 0 .. 101 ..... 00 ... @azz_nx1_o3 n=2 +SDOT_n1_4b 11000001 001 1 .... 0 .. 101 ..... 00 ... @azz_nx1_o3 n=4 +SDOT_n1_4h 11000001 011 0 .... 0 .. 101 ..... 00 ... @azz_nx1_o3 n=2 +SDOT_n1_4h 11000001 011 1 .... 0 .. 101 ..... 00 ... @azz_nx1_o3 n=4 +SDOT_n1_2h 11000001 011 0 .... 0 .. 101 ..... 01 ... @azz_nx1_o3 n=2 +SDOT_n1_2h 11000001 011 1 .... 0 .. 101 ..... 01 ... @azz_nx1_o3 n=4 + +UDOT_n1_4b 11000001 001 0 .... 0 .. 101 ..... 10 ... @azz_nx1_o3 n=2 +UDOT_n1_4b 11000001 001 1 .... 0 .. 101 ..... 10 ... @azz_nx1_o3 n=4 +UDOT_n1_4h 11000001 011 0 .... 0 .. 101 ..... 10 ... @azz_nx1_o3 n=2 +UDOT_n1_4h 11000001 011 1 .... 0 .. 101 ..... 10 ... @azz_nx1_o3 n=4 +UDOT_n1_2h 11000001 011 0 .... 0 .. 101 ..... 11 ... @azz_nx1_o3 n=2 +UDOT_n1_2h 11000001 011 1 .... 0 .. 101 ..... 11 ... @azz_nx1_o3 n=4 + +SMLAL_n1 11000001 011 0 .... 0 .. 011 ..... 00 ... @azz_nx1_o3x2 n=1 +SMLAL_n1 11000001 011 0 .... 0 .. 010 ..... 000 .. @azz_nx1_o2x2 n=2 +SMLAL_n1 11000001 011 1 .... 0 .. 010 ..... 000 .. @azz_nx1_o2x2 n=4 + +SMLSL_n1 11000001 011 0 .... 0 .. 011 ..... 01 ... @azz_nx1_o3x2 n=1 +SMLSL_n1 11000001 011 0 .... 0 .. 010 ..... 010 .. @azz_nx1_o2x2 n=2 +SMLSL_n1 11000001 011 1 .... 0 .. 010 ..... 010 .. @azz_nx1_o2x2 n=4 + +UMLAL_n1 11000001 011 0 .... 0 .. 011 ..... 10 ... @azz_nx1_o3x2 n=1 +UMLAL_n1 11000001 011 0 .... 0 .. 010 ..... 100 .. @azz_nx1_o2x2 n=2 +UMLAL_n1 11000001 011 1 .... 0 .. 010 ..... 100 .. @azz_nx1_o2x2 n=4 + +UMLSL_n1 11000001 011 0 .... 0 .. 011 ..... 11 ... @azz_nx1_o3x2 n=1 +UMLSL_n1 11000001 011 0 .... 0 .. 010 ..... 110 .. @azz_nx1_o2x2 n=2 +UMLSL_n1 11000001 011 1 .... 0 .. 010 ..... 110 .. @azz_nx1_o2x2 n=4 + +%off2_x4 0:2 !function=times_4 +%off1_x4 0:1 !function=times_4 + +@azz_nx1_o2x4 ........ ... . zm:4 . .. ... zn:5 ... .. \ + &azz_n off=%off2_x4 rv=%mova_rv +@azz_nx1_o1x4 ........ ... . zm:4 . .. ... zn:5 .... . \ + &azz_n off=%off1_x4 rv=%mova_rv + +SMLALL_n1_s 11000001 001 0 .... 0 .. 001 ..... 000 .. @azz_nx1_o2x4 n=1 +SMLALL_n1_d 11000001 011 0 .... 0 .. 001 ..... 000 .. @azz_nx1_o2x4 n=1 +SMLALL_n1_s 11000001 001 0 .... 0 .. 000 ..... 0000 . @azz_nx1_o1x4 n=2 +SMLALL_n1_d 11000001 011 0 .... 0 .. 000 ..... 0000 . @azz_nx1_o1x4 n=2 +SMLALL_n1_s 11000001 001 1 .... 0 .. 000 ..... 0000 . @azz_nx1_o1x4 n=4 +SMLALL_n1_d 11000001 011 1 .... 0 .. 000 ..... 0000 . @azz_nx1_o1x4 n=4 + +SMLSLL_n1_s 11000001 001 0 .... 0 .. 001 ..... 010 .. @azz_nx1_o2x4 n=1 +SMLSLL_n1_d 11000001 011 0 .... 0 .. 001 ..... 010 .. @azz_nx1_o2x4 n=1 +SMLSLL_n1_s 11000001 001 0 .... 0 .. 000 ..... 0100 . @azz_nx1_o1x4 n=2 +SMLSLL_n1_d 11000001 011 0 .... 0 .. 000 ..... 0100 . @azz_nx1_o1x4 n=2 +SMLSLL_n1_s 11000001 001 1 .... 0 .. 000 ..... 0100 . @azz_nx1_o1x4 n=4 +SMLSLL_n1_d 11000001 011 1 .... 0 .. 000 ..... 0100 . @azz_nx1_o1x4 n=4 + +UMLALL_n1_s 11000001 001 0 .... 0 .. 001 ..... 100 .. @azz_nx1_o2x4 n=1 +UMLALL_n1_d 11000001 011 0 .... 0 .. 001 ..... 100 .. @azz_nx1_o2x4 n=1 +UMLALL_n1_s 11000001 001 0 .... 0 .. 000 ..... 1000 . @azz_nx1_o1x4 n=2 +UMLALL_n1_d 11000001 011 0 .... 0 .. 000 ..... 1000 . @azz_nx1_o1x4 n=2 +UMLALL_n1_s 11000001 001 1 .... 0 .. 000 ..... 1000 . @azz_nx1_o1x4 n=4 +UMLALL_n1_d 11000001 011 1 .... 0 .. 000 ..... 1000 . @azz_nx1_o1x4 n=4 + +UMLSLL_n1_s 11000001 001 0 .... 0 .. 001 ..... 110 .. @azz_nx1_o2x4 n=1 +UMLSLL_n1_d 11000001 011 0 .... 0 .. 001 ..... 110 .. @azz_nx1_o2x4 n=1 +UMLSLL_n1_s 11000001 001 0 .... 0 .. 000 ..... 1100 . @azz_nx1_o1x4 n=2 +UMLSLL_n1_d 11000001 011 0 .... 0 .. 000 ..... 1100 . @azz_nx1_o1x4 n=2 +UMLSLL_n1_s 11000001 001 1 .... 0 .. 000 ..... 1100 . @azz_nx1_o1x4 n=4 +UMLSLL_n1_d 11000001 011 1 .... 0 .. 000 ..... 1100 . @azz_nx1_o1x4 n=4 + +USMLALL_n1_s 11000001 001 0 .... 0 .. 001 ..... 001 .. @azz_nx1_o2x4 n=1 +USMLALL_n1_s 11000001 001 0 .... 0 .. 000 ..... 0010 . @azz_nx1_o1x4 n=2 +USMLALL_n1_s 11000001 001 1 .... 0 .. 000 ..... 0010 . @azz_nx1_o1x4 n=4 + +SUMLALL_n1_s 11000001 001 0 .... 0 .. 000 ..... 1010 . @azz_nx1_o1x4 n=2 +SUMLALL_n1_s 11000001 001 1 .... 0 .. 000 ..... 1010 . @azz_nx1_o1x4 n=4 + +BFMLA_n1 11000001 011 0 .... 0 .. 111 ..... 00 ... @azz_nx1_o3 n=2 +FMLA_n1_h 11000001 001 0 .... 0 .. 111 ..... 00 ... @azz_nx1_o3 n=2 +FMLA_n1_s 11000001 001 0 .... 0 .. 110 ..... 00 ... @azz_nx1_o3 n=2 +FMLA_n1_d 11000001 011 0 .... 0 .. 110 ..... 00 ... @azz_nx1_o3 n=2 + +BFMLA_n1 11000001 011 1 .... 0 .. 111 ..... 00 ... @azz_nx1_o3 n=4 +FMLA_n1_h 11000001 001 1 .... 0 .. 111 ..... 00 ... @azz_nx1_o3 n=4 +FMLA_n1_s 11000001 001 1 .... 0 .. 110 ..... 00 ... @azz_nx1_o3 n=4 +FMLA_n1_d 11000001 011 1 .... 0 .. 110 ..... 00 ... @azz_nx1_o3 n=4 + +BFMLS_n1 11000001 011 0 .... 0 .. 111 ..... 01 ... @azz_nx1_o3 n=2 +FMLS_n1_h 11000001 001 0 .... 0 .. 111 ..... 01 ... @azz_nx1_o3 n=2 +FMLS_n1_s 11000001 001 0 .... 0 .. 110 ..... 01 ... @azz_nx1_o3 n=2 +FMLS_n1_d 11000001 011 0 .... 0 .. 110 ..... 01 ... @azz_nx1_o3 n=2 + +BFMLS_n1 11000001 011 1 .... 0 .. 111 ..... 01 ... @azz_nx1_o3 n=4 +FMLS_n1_h 11000001 001 1 .... 0 .. 111 ..... 01 ... @azz_nx1_o3 n=4 +FMLS_n1_s 11000001 001 1 .... 0 .. 110 ..... 01 ... @azz_nx1_o3 n=4 +FMLS_n1_d 11000001 011 1 .... 0 .. 110 ..... 01 ... @azz_nx1_o3 n=4 + +### SME2 Multi-vector Multiple Array Vectors + +%zn_ax2 6:4 !function=times_2 +%zn_ax4 7:3 !function=times_4 + +@azz_2x2_o3 ........ ... ..... . .. ... ..... .. off:3 \ + &azz_n n=2 rv=%mova_rv zn=%zn_ax2 zm=%zm_ax2 +@azz_4x4_o3 ........ ... ..... . .. ... ..... .. off:3 \ + &azz_n n=4 rv=%mova_rv zn=%zn_ax4 zm=%zm_ax4 + +ADD_azz_nn_s 11000001 101 ....0 0 .. 110 ....0 10 ... @azz_2x2_o3 +ADD_azz_nn_s 11000001 101 ...01 0 .. 110 ...00 10 ... @azz_4x4_o3 +ADD_azz_nn_d 11000001 111 ....0 0 .. 110 ....0 10 ... @azz_2x2_o3 +ADD_azz_nn_d 11000001 111 ...01 0 .. 110 ...00 10 ... @azz_4x4_o3 + +SUB_azz_nn_s 11000001 101 ....0 0 .. 110 ....0 11 ... @azz_2x2_o3 +SUB_azz_nn_s 11000001 101 ...01 0 .. 110 ...00 11 ... @azz_4x4_o3 +SUB_azz_nn_d 11000001 111 ....0 0 .. 110 ....0 11 ... @azz_2x2_o3 +SUB_azz_nn_d 11000001 111 ...01 0 .. 110 ...00 11 ... @azz_4x4_o3 + +@azz_2x2_o2x2 ........ ... ..... . .. ... ..... ... .. \ + &azz_n n=2 rv=%mova_rv zn=%zn_ax2 zm=%zm_ax2 off=%off2_x2 +@azz_4x4_o2x2 ........ ... ..... . .. ... ..... ... .. \ + &azz_n n=4 rv=%mova_rv zn=%zn_ax4 zm=%zm_ax4 off=%off2_x2 + +FMLAL_nn 11000001 101 ....0 0 .. 010 ....0 000 .. @azz_2x2_o2x2 +FMLAL_nn 11000001 101 ...01 0 .. 010 ...00 000 .. @azz_4x4_o2x2 + +FMLSL_nn 11000001 101 ....0 0 .. 010 ....0 010 .. @azz_2x2_o2x2 +FMLSL_nn 11000001 101 ...01 0 .. 010 ...00 010 .. @azz_4x4_o2x2 + +BFMLAL_nn 11000001 101 ....0 0 .. 010 ....0 100 .. @azz_2x2_o2x2 +BFMLAL_nn 11000001 101 ...01 0 .. 010 ...00 100 .. @azz_4x4_o2x2 + +BFMLSL_nn 11000001 101 ....0 0 .. 010 ....0 110 .. @azz_2x2_o2x2 +BFMLSL_nn 11000001 101 ...01 0 .. 010 ...00 110 .. @azz_4x4_o2x2 + +FDOT_nn 11000001 101 ....0 0 .. 100 ....0 00 ... @azz_2x2_o3 +FDOT_nn 11000001 101 ...01 0 .. 100 ...00 00 ... @azz_4x4_o3 + +BFDOT_nn 11000001 101 ....0 0 .. 100 ....0 10 ... @azz_2x2_o3 +BFDOT_nn 11000001 101 ...01 0 .. 100 ...00 10 ... @azz_4x4_o3 + +USDOT_nn 11000001 101 ....0 0 .. 101 ....0 01 ... @azz_2x2_o3 +USDOT_nn 11000001 101 ...01 0 .. 101 ...00 01 ... @azz_4x4_o3 + +SDOT_nn_4b 11000001 101 ....0 0 .. 101 ....0 00 ... @azz_2x2_o3 +SDOT_nn_4b 11000001 101 ...01 0 .. 101 ...00 00 ... @azz_4x4_o3 +SDOT_nn_4h 11000001 111 ....0 0 .. 101 ....0 00 ... @azz_2x2_o3 +SDOT_nn_4h 11000001 111 ...01 0 .. 101 ...00 00 ... @azz_4x4_o3 +SDOT_nn_2h 11000001 111 ....0 0 .. 101 ....0 01 ... @azz_2x2_o3 +SDOT_nn_2h 11000001 111 ...01 0 .. 101 ...00 01 ... @azz_4x4_o3 + +UDOT_nn_4b 11000001 101 ....0 0 .. 101 ....0 10 ... @azz_2x2_o3 +UDOT_nn_4b 11000001 101 ...01 0 .. 101 ...00 10 ... @azz_4x4_o3 +UDOT_nn_4h 11000001 111 ....0 0 .. 101 ....0 10 ... @azz_2x2_o3 +UDOT_nn_4h 11000001 111 ...01 0 .. 101 ...00 10 ... @azz_4x4_o3 +UDOT_nn_2h 11000001 111 ....0 0 .. 101 ....0 11 ... @azz_2x2_o3 +UDOT_nn_2h 11000001 111 ...01 0 .. 101 ...00 11 ... @azz_4x4_o3 + +SMLAL_nn 11000001 111 ....0 0 .. 010 ....0 000 .. @azz_2x2_o2x2 +SMLAL_nn 11000001 111 ...01 0 .. 010 ...00 000 .. @azz_4x4_o2x2 + +SMLSL_nn 11000001 111 ....0 0 .. 010 ....0 010 .. @azz_2x2_o2x2 +SMLSL_nn 11000001 111 ...01 0 .. 010 ...00 010 .. @azz_4x4_o2x2 + +UMLAL_nn 11000001 111 ....0 0 .. 010 ....0 100 .. @azz_2x2_o2x2 +UMLAL_nn 11000001 111 ...01 0 .. 010 ...00 100 .. @azz_4x4_o2x2 + +UMLSL_nn 11000001 111 ....0 0 .. 010 ....0 110 .. @azz_2x2_o2x2 +UMLSL_nn 11000001 111 ...01 0 .. 010 ...00 110 .. @azz_4x4_o2x2 + +@azz_2x2_o1x4 ........ ... ..... . .. ... ..... ... .. \ + &azz_n n=2 rv=%mova_rv zn=%zn_ax2 zm=%zm_ax2 off=%off1_x4 +@azz_4x4_o1x4 ........ ... ..... . .. ... ..... ... .. \ + &azz_n n=4 rv=%mova_rv zn=%zn_ax4 zm=%zm_ax4 off=%off1_x4 + +SMLALL_nn_s 11000001 101 ....0 0 .. 000 ....0 0000 . @azz_2x2_o1x4 +SMLALL_nn_d 11000001 111 ....0 0 .. 000 ....0 0000 . @azz_2x2_o1x4 +SMLALL_nn_s 11000001 101 ...01 0 .. 000 ...00 0000 . @azz_4x4_o1x4 +SMLALL_nn_d 11000001 111 ...01 0 .. 000 ...00 0000 . @azz_4x4_o1x4 + +SMLSLL_nn_s 11000001 101 ....0 0 .. 000 ....0 0100 . @azz_2x2_o1x4 +SMLSLL_nn_d 11000001 111 ....0 0 .. 000 ....0 0100 . @azz_2x2_o1x4 +SMLSLL_nn_s 11000001 101 ...01 0 .. 000 ...00 0100 . @azz_4x4_o1x4 +SMLSLL_nn_d 11000001 111 ...01 0 .. 000 ...00 0100 . @azz_4x4_o1x4 + +UMLALL_nn_s 11000001 101 ....0 0 .. 000 ....0 1000 . @azz_2x2_o1x4 +UMLALL_nn_d 11000001 111 ....0 0 .. 000 ....0 1000 . @azz_2x2_o1x4 +UMLALL_nn_s 11000001 101 ...01 0 .. 000 ...00 1000 . @azz_4x4_o1x4 +UMLALL_nn_d 11000001 111 ...01 0 .. 000 ...00 1000 . @azz_4x4_o1x4 + +UMLSLL_nn_s 11000001 101 ....0 0 .. 000 ....0 1100 . @azz_2x2_o1x4 +UMLSLL_nn_d 11000001 111 ....0 0 .. 000 ....0 1100 . @azz_2x2_o1x4 +UMLSLL_nn_s 11000001 101 ...01 0 .. 000 ...00 1100 . @azz_4x4_o1x4 +UMLSLL_nn_d 11000001 111 ...01 0 .. 000 ...00 1100 . @azz_4x4_o1x4 + +USMLALL_nn_s 11000001 101 ....0 0 .. 000 ....0 0010 . @azz_2x2_o1x4 +USMLALL_nn_s 11000001 101 ...01 0 .. 000 ...00 0010 . @azz_4x4_o1x4 + +BFMLA_nn 11000001 111 ....0 0 .. 100 ....0 01 ... @azz_2x2_o3 +FMLA_nn_h 11000001 101 ....0 0 .. 100 ....0 01 ... @azz_2x2_o3 +FMLA_nn_s 11000001 101 ....0 0 .. 110 ....0 00 ... @azz_2x2_o3 +FMLA_nn_d 11000001 111 ....0 0 .. 110 ....0 00 ... @azz_2x2_o3 + +BFMLA_nn 11000001 111 ...01 0 .. 100 ...00 01 ... @azz_4x4_o3 +FMLA_nn_h 11000001 101 ...01 0 .. 100 ...00 01 ... @azz_4x4_o3 +FMLA_nn_s 11000001 101 ...01 0 .. 110 ...00 00 ... @azz_4x4_o3 +FMLA_nn_d 11000001 111 ...01 0 .. 110 ...00 00 ... @azz_4x4_o3 + +BFMLS_nn 11000001 111 ....0 0 .. 100 ....0 11 ... @azz_2x2_o3 +FMLS_nn_h 11000001 101 ....0 0 .. 100 ....0 11 ... @azz_2x2_o3 +FMLS_nn_s 11000001 101 ....0 0 .. 110 ....0 01 ... @azz_2x2_o3 +FMLS_nn_d 11000001 111 ....0 0 .. 110 ....0 01 ... @azz_2x2_o3 + +BFMLS_nn 11000001 111 ...01 0 .. 100 ...00 11 ... @azz_4x4_o3 +FMLS_nn_h 11000001 101 ...01 0 .. 100 ...00 11 ... @azz_4x4_o3 +FMLS_nn_s 11000001 101 ...01 0 .. 110 ...00 01 ... @azz_4x4_o3 +FMLS_nn_d 11000001 111 ...01 0 .. 110 ...00 01 ... @azz_4x4_o3 + +&az_n n off rv zm +@az_2x2_o3 ........ ... ..... . .. ... ..... .. off:3 \ + &az_n n=2 rv=%mova_rv zm=%zn_ax2 +@az_4x4_o3 ........ ... ..... . .. ... ..... .. off:3 \ + &az_n n=4 rv=%mova_rv zm=%zn_ax4 + +FADD_nn_h 11000001 101 00100 0 .. 111 ....0 00 ... @az_2x2_o3 +FADD_nn_s 11000001 101 00000 0 .. 111 ....0 00 ... @az_2x2_o3 +FADD_nn_d 11000001 111 00000 0 .. 111 ....0 00 ... @az_2x2_o3 +FADD_nn_h 11000001 101 00101 0 .. 111 ...00 00 ... @az_4x4_o3 +FADD_nn_s 11000001 101 00001 0 .. 111 ...00 00 ... @az_4x4_o3 +FADD_nn_d 11000001 111 00001 0 .. 111 ...00 00 ... @az_4x4_o3 + +FSUB_nn_h 11000001 101 00100 0 .. 111 ....0 01 ... @az_2x2_o3 +FSUB_nn_s 11000001 101 00000 0 .. 111 ....0 01 ... @az_2x2_o3 +FSUB_nn_d 11000001 111 00000 0 .. 111 ....0 01 ... @az_2x2_o3 +FSUB_nn_h 11000001 101 00101 0 .. 111 ...00 01 ... @az_4x4_o3 +FSUB_nn_s 11000001 101 00001 0 .. 111 ...00 01 ... @az_4x4_o3 +FSUB_nn_d 11000001 111 00001 0 .. 111 ...00 01 ... @az_4x4_o3 + +BFADD_nn 11000001 111 00100 0 .. 111 ....0 00 ... @az_2x2_o3 +BFADD_nn 11000001 111 00101 0 .. 111 ...00 00 ... @az_4x4_o3 +BFSUB_nn 11000001 111 00100 0 .. 111 ....0 01 ... @az_2x2_o3 +BFSUB_nn 11000001 111 00101 0 .. 111 ...00 01 ... @az_4x4_o3 + +### SME2 Multi-vector Indexed + +&azx_n n off rv zn zm idx + +%idx3_15_10 15:1 10:2 +%idx2_10_2 10:2 2:1 + +@azx_1x1_o3x2 ........ .... zm:4 . .. . .. zn:5 .. ... \ + &azx_n n=1 rv=%mova_rv off=%off3_x2 idx=%idx3_15_10 +@azx_2x1_o2x2 ........ .... zm:4 . .. . .. ..... .. ... \ + &azx_n n=2 rv=%mova_rv off=%off2_x2 zn=%zn_ax2 idx=%idx2_10_2 +@azx_4x1_o2x2 ........ .... zm:4 . .. . .. ..... .. ... \ + &azx_n n=4 rv=%mova_rv off=%off2_x2 zn=%zn_ax4 idx=%idx2_10_2 + +FMLAL_nx 11000001 1000 .... . .. 1 .. ..... 00 ... @azx_1x1_o3x2 +FMLAL_nx 11000001 1001 .... 0 .. 1 .. ....0 00 ... @azx_2x1_o2x2 +FMLAL_nx 11000001 1001 .... 1 .. 1 .. ...00 00 ... @azx_4x1_o2x2 + +FMLSL_nx 11000001 1000 .... . .. 1 .. ..... 01 ... @azx_1x1_o3x2 +FMLSL_nx 11000001 1001 .... 0 .. 1 .. ....0 01 ... @azx_2x1_o2x2 +FMLSL_nx 11000001 1001 .... 1 .. 1 .. ...00 01 ... @azx_4x1_o2x2 + +BFMLAL_nx 11000001 1000 .... . .. 1 .. ..... 10 ... @azx_1x1_o3x2 +BFMLAL_nx 11000001 1001 .... 0 .. 1 .. ....0 10 ... @azx_2x1_o2x2 +BFMLAL_nx 11000001 1001 .... 1 .. 1 .. ...00 10 ... @azx_4x1_o2x2 + +BFMLSL_nx 11000001 1000 .... . .. 1 .. ..... 11 ... @azx_1x1_o3x2 +BFMLSL_nx 11000001 1001 .... 0 .. 1 .. ....0 11 ... @azx_2x1_o2x2 +BFMLSL_nx 11000001 1001 .... 1 .. 1 .. ...00 11 ... @azx_4x1_o2x2 + +@azx_2x1_i2_o3 ........ .... zm:4 . .. . idx:2 .... ... off:3 \ + &azx_n n=2 rv=%mova_rv zn=%zn_ax2 +@azx_4x1_i2_o3 ........ .... zm:4 . .. . idx:2 .... ... off:3 \ + &azx_n n=4 rv=%mova_rv zn=%zn_ax4 +@azx_2x1_i1_o3 ........ .... zm:4 . .. .. idx:1 .... ... off:3 \ + &azx_n n=2 rv=%mova_rv zn=%zn_ax2 +@azx_4x1_i1_o3 ........ .... zm:4 . .. .. idx:1 .... ... off:3 \ + &azx_n n=4 rv=%mova_rv zn=%zn_ax4 + +FDOT_nx 11000001 0101 .... 0 .. 1 .. ....0 01 ... @azx_2x1_i2_o3 +FDOT_nx 11000001 0101 .... 1 .. 1 .. ...00 01 ... @azx_4x1_i2_o3 + +BFDOT_nx 11000001 0101 .... 0 .. 1 .. ....0 11 ... @azx_2x1_i2_o3 +BFDOT_nx 11000001 0101 .... 1 .. 1 .. ...00 11 ... @azx_4x1_i2_o3 + +FVDOT 11000001 0101 .... 0 .. 0 .. ....0 01 ... @azx_2x1_i2_o3 +BFVDOT 11000001 0101 .... 0 .. 0 .. ....0 11 ... @azx_2x1_i2_o3 + +SDOT_nx_2h 11000001 0101 .... 0 .. 1 .. ....0 00 ... @azx_2x1_i2_o3 +SDOT_nx_2h 11000001 0101 .... 1 .. 1 .. ...00 00 ... @azx_4x1_i2_o3 +SDOT_nx_4b 11000001 0101 .... 0 .. 1 .. ....1 00 ... @azx_2x1_i2_o3 +SDOT_nx_4b 11000001 0101 .... 1 .. 1 .. ...01 00 ... @azx_4x1_i2_o3 +SDOT_nx_4h 11000001 1101 .... 0 .. 00 . ....0 01 ... @azx_2x1_i1_o3 +SDOT_nx_4h 11000001 1101 .... 1 .. 00 . ...00 01 ... @azx_4x1_i1_o3 + +UDOT_nx_2h 11000001 0101 .... 0 .. 1 .. ....0 10 ... @azx_2x1_i2_o3 +UDOT_nx_2h 11000001 0101 .... 1 .. 1 .. ...00 10 ... @azx_4x1_i2_o3 +UDOT_nx_4b 11000001 0101 .... 0 .. 1 .. ....1 10 ... @azx_2x1_i2_o3 +UDOT_nx_4b 11000001 0101 .... 1 .. 1 .. ...01 10 ... @azx_4x1_i2_o3 +UDOT_nx_4h 11000001 1101 .... 0 .. 00 . ....0 11 ... @azx_2x1_i1_o3 +UDOT_nx_4h 11000001 1101 .... 1 .. 00 . ...00 11 ... @azx_4x1_i1_o3 + +USDOT_nx 11000001 0101 .... 0 .. 1 .. ....1 01 ... @azx_2x1_i2_o3 +USDOT_nx 11000001 0101 .... 1 .. 1 .. ...01 01 ... @azx_4x1_i2_o3 + +SUDOT_nx 11000001 0101 .... 0 .. 1 .. ....1 11 ... @azx_2x1_i2_o3 +SUDOT_nx 11000001 0101 .... 1 .. 1 .. ...01 11 ... @azx_4x1_i2_o3 + +SVDOT_nx_2h 11000001 0101 .... 0 .. 0 .. ....1 00 ... @azx_2x1_i2_o3 +SVDOT_nx_4b 11000001 0101 .... 1 .. 0 .. ...01 00 ... @azx_4x1_i2_o3 +SVDOT_nx_4h 11000001 1101 .... 1 .. 01 . ...00 01 ... @azx_4x1_i1_o3 + +UVDOT_nx_2h 11000001 0101 .... 0 .. 0 .. ....1 10 ... @azx_2x1_i2_o3 +UVDOT_nx_4b 11000001 0101 .... 1 .. 0 .. ...01 10 ... @azx_4x1_i2_o3 +UVDOT_nx_4h 11000001 1101 .... 1 .. 01 . ...00 11 ... @azx_4x1_i1_o3 + +SUVDOT_nx_4b 11000001 0101 .... 1 .. 0 .. ...01 11 ... @azx_4x1_i2_o3 +USVDOT_nx_4b 11000001 0101 .... 1 .. 0 .. ...01 01 ... @azx_4x1_i2_o3 + +SMLAL_nx 11000001 1100 .... . .. 1 .. ..... 00 ... @azx_1x1_o3x2 +SMLAL_nx 11000001 1101 .... 0 .. 1 .. ....0 00 ... @azx_2x1_o2x2 +SMLAL_nx 11000001 1101 .... 1 .. 1 .. ...00 00 ... @azx_4x1_o2x2 + +SMLSL_nx 11000001 1100 .... . .. 1 .. ..... 01 ... @azx_1x1_o3x2 +SMLSL_nx 11000001 1101 .... 0 .. 1 .. ....0 01 ... @azx_2x1_o2x2 +SMLSL_nx 11000001 1101 .... 1 .. 1 .. ...00 01 ... @azx_4x1_o2x2 + +UMLAL_nx 11000001 1100 .... . .. 1 .. ..... 10 ... @azx_1x1_o3x2 +UMLAL_nx 11000001 1101 .... 0 .. 1 .. ....0 10 ... @azx_2x1_o2x2 +UMLAL_nx 11000001 1101 .... 1 .. 1 .. ...00 10 ... @azx_4x1_o2x2 + +UMLSL_nx 11000001 1100 .... . .. 1 .. ..... 11 ... @azx_1x1_o3x2 +UMLSL_nx 11000001 1101 .... 0 .. 1 .. ....0 11 ... @azx_2x1_o2x2 +UMLSL_nx 11000001 1101 .... 1 .. 1 .. ...00 11 ... @azx_4x1_o2x2 + +%idx4_15_10 15:1 10:3 +%idx4_10_1 10:2 1:2 +%idx3_10_1 10:1 1:2 + +@azx_1x1_i4_o2 ........ .... zm:4 . .. ... zn:5 ... .. \ + &azx_n n=1 rv=%mova_rv off=%off2_x4 idx=%idx4_15_10 +@azx_1x1_i3_o2 ........ .... zm:4 . .. ... zn:5 ... .. \ + &azx_n n=1 rv=%mova_rv off=%off2_x4 idx=%idx3_15_10 +@azx_2x1_i4_o1 ........ .... zm:4 . .. ... ..... ... .. \ + &azx_n n=2 rv=%mova_rv off=%off1_x4 zn=%zn_ax2 idx=%idx4_10_1 +@azx_2x1_i3_o1 ........ .... zm:4 . .. ... ..... ... .. \ + &azx_n n=2 rv=%mova_rv off=%off1_x4 zn=%zn_ax2 idx=%idx3_10_1 +@azx_4x1_i4_o1 ........ .... zm:4 . .. ... ..... ... .. \ + &azx_n n=4 rv=%mova_rv off=%off1_x4 zn=%zn_ax4 idx=%idx4_10_1 +@azx_4x1_i3_o1 ........ .... zm:4 . .. ... ..... ... .. \ + &azx_n n=4 rv=%mova_rv off=%off1_x4 zn=%zn_ax4 idx=%idx3_10_1 + +SMLALL_nx_s 11000001 0000 .... . .. ... ..... 000 .. @azx_1x1_i4_o2 +SMLALL_nx_d 11000001 1000 .... . .. 0.. ..... 000 .. @azx_1x1_i3_o2 +SMLALL_nx_s 11000001 0001 .... 0 .. 0.. ....0 00 ... @azx_2x1_i4_o1 +SMLALL_nx_d 11000001 1001 .... 0 .. 00. ....0 00 ... @azx_2x1_i3_o1 +SMLALL_nx_s 11000001 0001 .... 1 .. 0.. ...00 00 ... @azx_4x1_i4_o1 +SMLALL_nx_d 11000001 1001 .... 1 .. 00. ...00 00 ... @azx_4x1_i3_o1 + +SMLSLL_nx_s 11000001 0000 .... . .. ... ..... 010 .. @azx_1x1_i4_o2 +SMLSLL_nx_d 11000001 1000 .... . .. 0.. ..... 010 .. @azx_1x1_i3_o2 +SMLSLL_nx_s 11000001 0001 .... 0 .. 0.. ....0 01 ... @azx_2x1_i4_o1 +SMLSLL_nx_d 11000001 1001 .... 0 .. 00. ....0 01 ... @azx_2x1_i3_o1 +SMLSLL_nx_s 11000001 0001 .... 1 .. 0.. ...00 01 ... @azx_4x1_i4_o1 +SMLSLL_nx_d 11000001 1001 .... 1 .. 00. ...00 01 ... @azx_4x1_i3_o1 + +UMLALL_nx_s 11000001 0000 .... . .. ... ..... 100 .. @azx_1x1_i4_o2 +UMLALL_nx_d 11000001 1000 .... . .. 0.. ..... 100 .. @azx_1x1_i3_o2 +UMLALL_nx_s 11000001 0001 .... 0 .. 0.. ....0 10 ... @azx_2x1_i4_o1 +UMLALL_nx_d 11000001 1001 .... 0 .. 00. ....0 10 ... @azx_2x1_i3_o1 +UMLALL_nx_s 11000001 0001 .... 1 .. 0.. ...00 10 ... @azx_4x1_i4_o1 +UMLALL_nx_d 11000001 1001 .... 1 .. 00. ...00 10 ... @azx_4x1_i3_o1 + +UMLSLL_nx_s 11000001 0000 .... . .. ... ..... 110 .. @azx_1x1_i4_o2 +UMLSLL_nx_d 11000001 1000 .... . .. 0.. ..... 110 .. @azx_1x1_i3_o2 +UMLSLL_nx_s 11000001 0001 .... 0 .. 0.. ....0 11 ... @azx_2x1_i4_o1 +UMLSLL_nx_d 11000001 1001 .... 0 .. 00. ....0 11 ... @azx_2x1_i3_o1 +UMLSLL_nx_s 11000001 0001 .... 1 .. 0.. ...00 11 ... @azx_4x1_i4_o1 +UMLSLL_nx_d 11000001 1001 .... 1 .. 00. ...00 11 ... @azx_4x1_i3_o1 + +USMLALL_nx_s 11000001 0000 .... . .. ... ..... 001 .. @azx_1x1_i4_o2 +USMLALL_nx_s 11000001 0001 .... 0 .. 0.. ....1 00 ... @azx_2x1_i4_o1 +USMLALL_nx_s 11000001 0001 .... 1 .. 0.. ...01 00 ... @azx_4x1_i4_o1 + +SUMLALL_nx_s 11000001 0000 .... . .. ... ..... 101 .. @azx_1x1_i4_o2 +SUMLALL_nx_s 11000001 0001 .... 0 .. 0.. ....1 10 ... @azx_2x1_i4_o1 +SUMLALL_nx_s 11000001 0001 .... 1 .. 0.. ...01 10 ... @azx_4x1_i4_o1 + +%idx3_10_3 10:2 3:1 +@azx_2x1_i3_o3 ........ .... zm:4 . .. ... ..... .. off:3 \ + &azx_n n=2 rv=%mova_rv zn=%zn_ax2 idx=%idx3_10_3 +@azx_4x1_i3_o3 ........ .... zm:4 . .. ... ..... .. off:3 \ + &azx_n n=4 rv=%mova_rv zn=%zn_ax4 idx=%idx3_10_3 + +BFMLA_nx 11000001 0001 .... 0 .. 1.. ....1 0 .... @azx_2x1_i3_o3 +FMLA_nx_h 11000001 0001 .... 0 .. 1.. ....0 0 .... @azx_2x1_i3_o3 +FMLA_nx_s 11000001 0101 .... 0 .. 0.. ....0 00 ... @azx_2x1_i2_o3 +FMLA_nx_d 11000001 1101 .... 0 .. 00. ....0 00 ... @azx_2x1_i1_o3 + +BFMLA_nx 11000001 0001 .... 1 .. 1.. ...01 0 .... @azx_4x1_i3_o3 +FMLA_nx_h 11000001 0001 .... 1 .. 1.. ...00 0 .... @azx_4x1_i3_o3 +FMLA_nx_s 11000001 0101 .... 1 .. 0.. ...00 00 ... @azx_4x1_i2_o3 +FMLA_nx_d 11000001 1101 .... 1 .. 00. ...00 00 ... @azx_4x1_i1_o3 + +BFMLS_nx 11000001 0001 .... 0 .. 1.. ....1 1 .... @azx_2x1_i3_o3 +FMLS_nx_h 11000001 0001 .... 0 .. 1.. ....0 1 .... @azx_2x1_i3_o3 +FMLS_nx_s 11000001 0101 .... 0 .. 0.. ....0 10 ... @azx_2x1_i2_o3 +FMLS_nx_d 11000001 1101 .... 0 .. 00. ....0 10 ... @azx_2x1_i1_o3 + +BFMLS_nx 11000001 0001 .... 1 .. 1.. ...01 1 .... @azx_4x1_i3_o3 +FMLS_nx_h 11000001 0001 .... 1 .. 1.. ...00 1 .... @azx_4x1_i3_o3 +FMLS_nx_s 11000001 0101 .... 1 .. 0.. ...00 10 ... @azx_4x1_i2_o3 +FMLS_nx_d 11000001 1101 .... 1 .. 00. ...00 10 ... @azx_4x1_i1_o3 + +### SME2 Add / Sub array accumulators + +ADD_aaz_s 11000001 101 000000 .. 111 ....0 10 ... @az_2x2_o3 +ADD_aaz_s 11000001 101 000010 .. 111 ...00 10 ... @az_4x4_o3 +ADD_aaz_d 11000001 111 000000 .. 111 ....0 10 ... @az_2x2_o3 +ADD_aaz_d 11000001 111 000010 .. 111 ...00 10 ... @az_4x4_o3 + +SUB_aaz_s 11000001 101 000000 .. 111 ....0 11 ... @az_2x2_o3 +SUB_aaz_s 11000001 101 000010 .. 111 ...00 11 ... @az_4x4_o3 +SUB_aaz_d 11000001 111 000000 .. 111 ....0 11 ... @az_2x2_o3 +SUB_aaz_d 11000001 111 000010 .. 111 ...00 11 ... @az_4x4_o3 + +### SME2 Multi-vector SVE Constructive Unary + +&zz_e zd zn esz +&zz_n zd zn n +@zz_1x2 ........ ... ..... ...... ..... zd:5 \ + &zz_n n=1 zn=%zn_ax2 +@zz_1x4 ........ ... ..... ...... ..... zd:5 \ + &zz_n n=1 zn=%zn_ax4 +@zz_2x1 ........ ... ..... ...... zn:5 ..... \ + &zz_n n=1 zd=%zd_ax2 +@zz_2x2 ........ ... ..... ...... .... . ..... \ + &zz_n n=2 zd=%zd_ax2 zn=%zn_ax2 +@zz_4x4 ........ ... ..... ...... .... . ..... \ + &zz_n n=4 zd=%zd_ax4 zn=%zn_ax4 +@zz_4x2_n1 ........ ... ..... ...... .... . ..... \ + &zz_n n=1 zd=%zd_ax4 zn=%zn_ax2 + +BFCVT 11000001 011 00000 111000 ....0 ..... @zz_1x2 +BFCVTN 11000001 011 00000 111000 ....1 ..... @zz_1x2 + +FCVT_n 11000001 001 00000 111000 ....0 ..... @zz_1x2 +FCVTN 11000001 001 00000 111000 ....1 ..... @zz_1x2 + +FCVT_w 11000001 101 00000 111000 ..... ....0 @zz_2x1 +FCVTL 11000001 101 00000 111000 ..... ....1 @zz_2x1 + +FCVTZS 11000001 001 00001 111000 ....0 ....0 @zz_2x2 +FCVTZS 11000001 001 10001 111000 ...00 ...00 @zz_4x4 +FCVTZU 11000001 001 00001 111000 ....1 ....0 @zz_2x2 +FCVTZU 11000001 001 10001 111000 ...01 ...00 @zz_4x4 + +SCVTF 11000001 001 00010 111000 ....0 ....0 @zz_2x2 +SCVTF 11000001 001 10010 111000 ...00 ...00 @zz_4x4 +UCVTF 11000001 001 00010 111000 ....1 ....0 @zz_2x2 +UCVTF 11000001 001 10010 111000 ...01 ...00 @zz_4x4 + +FRINTN 11000001 101 01000 111000 ....0 ....0 @zz_2x2 +FRINTN 11000001 101 11000 111000 ...00 ...00 @zz_4x4 +FRINTP 11000001 101 01001 111000 ....0 ....0 @zz_2x2 +FRINTP 11000001 101 11001 111000 ...00 ...00 @zz_4x4 +FRINTM 11000001 101 01010 111000 ....0 ....0 @zz_2x2 +FRINTM 11000001 101 11010 111000 ...00 ...00 @zz_4x4 +FRINTA 11000001 101 01100 111000 ....0 ....0 @zz_2x2 +FRINTA 11000001 101 11100 111000 ...00 ...00 @zz_4x4 + +SQCVT_sh 11000001 001 00011 111000 ....0 ..... @zz_1x2 +UQCVT_sh 11000001 001 00011 111000 ....1 ..... @zz_1x2 +SQCVTU_sh 11000001 011 00011 111000 ....0 ..... @zz_1x2 + +SQCVT_sb 11000001 001 10011 111000 ...00 ..... @zz_1x4 +UQCVT_sb 11000001 001 10011 111000 ...01 ..... @zz_1x4 +SQCVTU_sb 11000001 011 10011 111000 ...00 ..... @zz_1x4 + +SQCVT_dh 11000001 101 10011 111000 ...00 ..... @zz_1x4 +UQCVT_dh 11000001 101 10011 111000 ...01 ..... @zz_1x4 +SQCVTU_dh 11000001 111 10011 111000 ...00 ..... @zz_1x4 + +SQCVTN_sb 11000001 001 10011 111000 ...10 ..... @zz_1x4 +UQCVTN_sb 11000001 001 10011 111000 ...11 ..... @zz_1x4 +SQCVTUN_sb 11000001 011 10011 111000 ...10 ..... @zz_1x4 + +SQCVTN_dh 11000001 101 10011 111000 ...10 ..... @zz_1x4 +UQCVTN_dh 11000001 101 10011 111000 ...11 ..... @zz_1x4 +SQCVTUN_dh 11000001 111 10011 111000 ...10 ..... @zz_1x4 + +SUNPK_2bh 11000001 011 00101 111000 ..... ....0 @zz_2x1 +SUNPK_2hs 11000001 101 00101 111000 ..... ....0 @zz_2x1 +SUNPK_2sd 11000001 111 00101 111000 ..... ....0 @zz_2x1 + +UUNPK_2bh 11000001 011 00101 111000 ..... ....1 @zz_2x1 +UUNPK_2hs 11000001 101 00101 111000 ..... ....1 @zz_2x1 +UUNPK_2sd 11000001 111 00101 111000 ..... ....1 @zz_2x1 + +SUNPK_4bh 11000001 011 10101 111000 ....0 ...00 @zz_4x2_n1 +SUNPK_4hs 11000001 101 10101 111000 ....0 ...00 @zz_4x2_n1 +SUNPK_4sd 11000001 111 10101 111000 ....0 ...00 @zz_4x2_n1 + +UUNPK_4bh 11000001 011 10101 111000 ....0 ...01 @zz_4x2_n1 +UUNPK_4hs 11000001 101 10101 111000 ....0 ...01 @zz_4x2_n1 +UUNPK_4sd 11000001 111 10101 111000 ....0 ...01 @zz_4x2_n1 + +ZIP_4 11000001 esz:2 1 10110 111000 ...00 ... 00 \ + &zz_e zd=%zd_ax4 zn=%zn_ax4 +ZIP_4 11000001 001 10111 111000 ...00 ... 00 \ + &zz_e esz=4 zd=%zd_ax4 zn=%zn_ax4 + +UZP_4 11000001 esz:2 1 10110 111000 ...00 ... 10 \ + &zz_e zd=%zd_ax4 zn=%zn_ax4 +UZP_4 11000001 001 10111 111000 ...00 ... 10 \ + &zz_e esz=4 zd=%zd_ax4 zn=%zn_ax4 + +### SME2 Multi-vector SVE Constructive Binary + +&rshr zd zn shift + +%rshr_sh_shift 16:4 !function=rsub_16 +%rshr_sb_shift 16:5 !function=rsub_32 +%rshr_dh_shift 22:1 16:5 !function=rsub_64 + +@rshr_sh ........ .... .... ...... ..... zd:5 \ + &rshr zn=%zn_ax2 shift=%rshr_sh_shift +@rshr_sb ........ ... ..... ...... ..... zd:5 \ + &rshr zn=%zn_ax4 shift=%rshr_sb_shift +@rshr_dh ........ ... ..... ...... ..... zd:5 \ + &rshr zn=%zn_ax4 shift=%rshr_dh_shift + +SQRSHR_sh 11000001 1110 .... 110101 ....0 ..... @rshr_sh +UQRSHR_sh 11000001 1110 .... 110101 ....1 ..... @rshr_sh +SQRSHRU_sh 11000001 1111 .... 110101 ....0 ..... @rshr_sh + +SQRSHR_sb 11000001 011 ..... 110110 ...00 ..... @rshr_sb +SQRSHR_dh 11000001 1.1 ..... 110110 ...00 ..... @rshr_dh +UQRSHR_sb 11000001 011 ..... 110110 ...01 ..... @rshr_sb +UQRSHR_dh 11000001 1.1 ..... 110110 ...01 ..... @rshr_dh +SQRSHRU_sb 11000001 011 ..... 110110 ...10 ..... @rshr_sb +SQRSHRU_dh 11000001 1.1 ..... 110110 ...10 ..... @rshr_dh + +SQRSHRN_sh 01000101 1011 .... 001010 ....0 ..... @rshr_sh +UQRSHRN_sh 01000101 1011 .... 001110 ....0 ..... @rshr_sh +SQRSHRUN_sh 01000101 1011 .... 000010 ....0 ..... @rshr_sh + +SQRSHRN_sb 11000001 011 ..... 110111 ...00 ..... @rshr_sb +SQRSHRN_dh 11000001 1.1 ..... 110111 ...00 ..... @rshr_dh +UQRSHRN_sb 11000001 011 ..... 110111 ...01 ..... @rshr_sb +UQRSHRN_dh 11000001 1.1 ..... 110111 ...01 ..... @rshr_dh +SQRSHRUN_sb 11000001 011 ..... 110111 ...10 ..... @rshr_sb +SQRSHRUN_dh 11000001 1.1 ..... 110111 ...10 ..... @rshr_dh + +&zzz_e zd zn zm esz + +ZIP_2 11000001 esz:2 1 zm:5 110100 zn:5 .... 0 \ + &zzz_e zd=%zd_ax2 +ZIP_2 11000001 00 1 zm:5 110101 zn:5 .... 0 \ + &zzz_e zd=%zd_ax2 esz=4 + +UZP_2 11000001 esz:2 1 zm:5 110100 zn:5 .... 1 \ + &zzz_e zd=%zd_ax2 +UZP_2 11000001 00 1 zm:5 110101 zn:5 .... 1 \ + &zzz_e zd=%zd_ax2 esz=4 + +&zzz_en zd zn zm esz n + +FCLAMP 11000001 esz:2 1 zm:5 110000 zn:5 .... 0 \ + &zzz_en zd=%zd_ax2 n=2 +FCLAMP 11000001 esz:2 1 zm:5 110010 zn:5 ...0 0 \ + &zzz_en zd=%zd_ax4 n=4 + +SCLAMP 11000001 esz:2 1 zm:5 110001 zn:5 .... 0 \ + &zzz_en zd=%zd_ax2 n=2 +SCLAMP 11000001 esz:2 1 zm:5 110011 zn:5 ...0 0 \ + &zzz_en zd=%zd_ax4 n=4 + +UCLAMP 11000001 esz:2 1 zm:5 110001 zn:5 .... 1 \ + &zzz_en zd=%zd_ax2 n=2 +UCLAMP 11000001 esz:2 1 zm:5 110011 zn:5 ...0 1 \ + &zzz_en zd=%zd_ax4 n=4 + +### SME2 Multi-vector SVE Select + +%sel_pg 10:3 !function=plus_8 + +SEL 11000001 esz:2 1 ....0 100 ... ....0 ....0 \ + n=2 zd=%zd_ax2 zn=%zn_ax2 zm=%zm_ax2 pg=%sel_pg +SEL 11000001 esz:2 1 ...01 100 ... ...00 ...00 \ + n=4 zd=%zd_ax4 zn=%zn_ax4 zm=%zm_ax4 pg=%sel_pg + +### SME Multiple Zero + +&zero_za rv off ngrp nvec + +ZERO_za 11000000 000011 000 .. 0000000000 off:3 \ + &zero_za ngrp=2 nvec=1 rv=%mova_rv +ZERO_za 11000000 000011 100 .. 0000000000 off:3 \ + &zero_za ngrp=4 nvec=1 rv=%mova_rv + +ZERO_za 11000000 000011 001 .. 0000000000 ... \ + &zero_za ngrp=1 nvec=2 rv=%mova_rv off=%off3_x2 +ZERO_za 11000000 000011 010 .. 0000000000 0.. \ + &zero_za ngrp=2 nvec=2 rv=%mova_rv off=%off2_x2 +ZERO_za 11000000 000011 011 .. 0000000000 0.. \ + &zero_za ngrp=4 nvec=2 rv=%mova_rv off=%off2_x2 + +ZERO_za 11000000 000011 101 .. 0000000000 0.. \ + &zero_za ngrp=1 nvec=4 rv=%mova_rv off=%off2_x4 +ZERO_za 11000000 000011 110 .. 0000000000 00. \ + &zero_za ngrp=2 nvec=4 rv=%mova_rv off=%off1_x4 +ZERO_za 11000000 000011 111 .. 0000000000 00. \ + &zero_za ngrp=4 nvec=4 rv=%mova_rv off=%off1_x4 + +### SME Lookup Table Read + +&lut zd zn idx + +# LUTI2, consecutive +LUTI2_c_1b 1100 0000 1100 11 idx:4 00 00 zn:5 zd:5 &lut +LUTI2_c_1h 1100 0000 1100 11 idx:4 01 00 zn:5 zd:5 &lut +LUTI2_c_1s 1100 0000 1100 11 idx:4 10 00 zn:5 zd:5 &lut + +LUTI2_c_2b 1100 0000 1000 11 idx:3 1 00 00 zn:5 .... 0 &lut zd=%zd_ax2 +LUTI2_c_2h 1100 0000 1000 11 idx:3 1 01 00 zn:5 .... 0 &lut zd=%zd_ax2 +LUTI2_c_2s 1100 0000 1000 11 idx:3 1 10 00 zn:5 .... 0 &lut zd=%zd_ax2 + +LUTI2_c_4b 1100 0000 1000 11 idx:2 10 00 00 zn:5 ... 00 &lut zd=%zd_ax4 +LUTI2_c_4h 1100 0000 1000 11 idx:2 10 01 00 zn:5 ... 00 &lut zd=%zd_ax4 +LUTI2_c_4s 1100 0000 1000 11 idx:2 10 10 00 zn:5 ... 00 &lut zd=%zd_ax4 + +# LUTI2, strided (must check zd alignment) +LUTI2_s_2b 1100 0000 1001 11 idx:3 1 00 00 zn:5 zd:5 &lut +LUTI2_s_2h 1100 0000 1001 11 idx:3 1 01 00 zn:5 zd:5 &lut + +LUTI2_s_4b 1100 0000 1001 11 idx:2 10 00 00 zn:5 zd:5 &lut +LUTI2_s_4h 1100 0000 1001 11 idx:2 10 01 00 zn:5 zd:5 &lut + +# LUTI4, consecutive +LUTI4_c_1b 1100 0000 1100 101 idx:3 00 00 zn:5 zd:5 &lut +LUTI4_c_1h 1100 0000 1100 101 idx:3 01 00 zn:5 zd:5 &lut +LUTI4_c_1s 1100 0000 1100 101 idx:3 10 00 zn:5 zd:5 &lut + +LUTI4_c_2b 1100 0000 1000 101 idx:2 1 00 00 zn:5 .... 0 &lut zd=%zd_ax2 +LUTI4_c_2h 1100 0000 1000 101 idx:2 1 01 00 zn:5 .... 0 &lut zd=%zd_ax2 +LUTI4_c_2s 1100 0000 1000 101 idx:2 1 10 00 zn:5 .... 0 &lut zd=%zd_ax2 + +LUTI4_c_4h 1100 0000 1000 101 idx:1 10 01 00 zn:5 ... 00 &lut zd=%zd_ax4 +LUTI4_c_4s 1100 0000 1000 101 idx:1 10 10 00 zn:5 ... 00 &lut zd=%zd_ax4 + +# LUTI4, strided (must check zd alignment) +LUTI4_s_2b 1100 0000 1001 101 idx:2 1 00 00 zn:5 zd:5 &lut +LUTI4_s_2h 1100 0000 1001 101 idx:2 1 01 00 zn:5 zd:5 &lut + +LUTI4_s_4h 1100 0000 1001 101 idx:1 10 01 00 zn:5 zd:5 &lut diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c index de0c6e5..bb8ed1e 100644 --- a/target/arm/tcg/sme_helper.c +++ b/target/arm/tcg/sme_helper.c @@ -29,6 +29,13 @@ #include "vec_internal.h" #include "sve_ldst_internal.h" + +static bool vectors_overlap(ARMVectorReg *x, unsigned nx, + ARMVectorReg *y, unsigned ny) +{ + return !(x + nx <= y || y + ny <= x); +} + void helper_set_svcr(CPUARMState *env, uint32_t val, uint32_t mask) { aarch64_set_svcr(env, val, mask); @@ -39,12 +46,12 @@ void helper_sme_zero(CPUARMState *env, uint32_t imm, uint32_t svl) uint32_t i; /* - * Special case clearing the entire ZA space. + * Special case clearing the entire ZArray. * This falls into the CONSTRAINED UNPREDICTABLE zeroing of any * parts of the ZA storage outside of SVL. */ if (imm == 0xff) { - memset(env->zarray, 0, sizeof(env->zarray)); + memset(env->za_state.za, 0, sizeof(env->za_state.za)); return; } @@ -54,7 +61,7 @@ void helper_sme_zero(CPUARMState *env, uint32_t imm, uint32_t svl) */ for (i = 0; i < svl; i++) { if (imm & (1 << (i % 8))) { - memset(&env->zarray[i], 0, svl); + memset(&env->za_state.za[i], 0, svl); } } } @@ -206,6 +213,110 @@ void HELPER(sme_mova_zc_q)(void *vd, void *za, void *vg, uint32_t desc) #undef DO_MOVA_Z +void HELPER(sme2_mova_zc_b)(void *vdst, void *vsrc, uint32_t desc) +{ + const uint8_t *src = vsrc; + uint8_t *dst = vdst; + size_t i, n = simd_oprsz(desc); + + for (i = 0; i < n; ++i) { + dst[i] = src[tile_vslice_index(i)]; + } +} + +void HELPER(sme2_mova_zc_h)(void *vdst, void *vsrc, uint32_t desc) +{ + const uint16_t *src = vsrc; + uint16_t *dst = vdst; + size_t i, n = simd_oprsz(desc) / 2; + + for (i = 0; i < n; ++i) { + dst[i] = src[tile_vslice_index(i)]; + } +} + +void HELPER(sme2_mova_zc_s)(void *vdst, void *vsrc, uint32_t desc) +{ + const uint32_t *src = vsrc; + uint32_t *dst = vdst; + size_t i, n = simd_oprsz(desc) / 4; + + for (i = 0; i < n; ++i) { + dst[i] = src[tile_vslice_index(i)]; + } +} + +void HELPER(sme2_mova_zc_d)(void *vdst, void *vsrc, uint32_t desc) +{ + const uint64_t *src = vsrc; + uint64_t *dst = vdst; + size_t i, n = simd_oprsz(desc) / 8; + + for (i = 0; i < n; ++i) { + dst[i] = src[tile_vslice_index(i)]; + } +} + +void HELPER(sme2p1_movaz_zc_b)(void *vdst, void *vsrc, uint32_t desc) +{ + uint8_t *src = vsrc; + uint8_t *dst = vdst; + size_t i, n = simd_oprsz(desc); + + for (i = 0; i < n; ++i) { + dst[i] = src[tile_vslice_index(i)]; + src[tile_vslice_index(i)] = 0; + } +} + +void HELPER(sme2p1_movaz_zc_h)(void *vdst, void *vsrc, uint32_t desc) +{ + uint16_t *src = vsrc; + uint16_t *dst = vdst; + size_t i, n = simd_oprsz(desc) / 2; + + for (i = 0; i < n; ++i) { + dst[i] = src[tile_vslice_index(i)]; + src[tile_vslice_index(i)] = 0; + } +} + +void HELPER(sme2p1_movaz_zc_s)(void *vdst, void *vsrc, uint32_t desc) +{ + uint32_t *src = vsrc; + uint32_t *dst = vdst; + size_t i, n = simd_oprsz(desc) / 4; + + for (i = 0; i < n; ++i) { + dst[i] = src[tile_vslice_index(i)]; + src[tile_vslice_index(i)] = 0; + } +} + +void HELPER(sme2p1_movaz_zc_d)(void *vdst, void *vsrc, uint32_t desc) +{ + uint64_t *src = vsrc; + uint64_t *dst = vdst; + size_t i, n = simd_oprsz(desc) / 8; + + for (i = 0; i < n; ++i) { + dst[i] = src[tile_vslice_index(i)]; + src[tile_vslice_index(i)] = 0; + } +} + +void HELPER(sme2p1_movaz_zc_q)(void *vdst, void *vsrc, uint32_t desc) +{ + Int128 *src = vsrc; + Int128 *dst = vdst; + size_t i, n = simd_oprsz(desc) / 16; + + for (i = 0; i < n; ++i) { + dst[i] = src[tile_vslice_index(i)]; + memset(&src[tile_vslice_index(i)], 0, 16); + } +} + /* * Clear elements in a tile slice comprising len bytes. */ @@ -314,6 +425,26 @@ static void copy_vertical_q(void *vdst, const void *vsrc, size_t len) } } +void HELPER(sme2_mova_cz_b)(void *vdst, void *vsrc, uint32_t desc) +{ + copy_vertical_b(vdst, vsrc, simd_oprsz(desc)); +} + +void HELPER(sme2_mova_cz_h)(void *vdst, void *vsrc, uint32_t desc) +{ + copy_vertical_h(vdst, vsrc, simd_oprsz(desc)); +} + +void HELPER(sme2_mova_cz_s)(void *vdst, void *vsrc, uint32_t desc) +{ + copy_vertical_s(vdst, vsrc, simd_oprsz(desc)); +} + +void HELPER(sme2_mova_cz_d)(void *vdst, void *vsrc, uint32_t desc) +{ + copy_vertical_d(vdst, vsrc, simd_oprsz(desc)); +} + /* * Host and TLB primitives for vertical tile slice addressing. */ @@ -344,54 +475,22 @@ static inline void sme_##NAME##_v_tlb(CPUARMState *env, void *za, \ TLB(env, useronly_clean_ptr(addr), val, ra); \ } -/* - * The ARMVectorReg elements are stored in host-endian 64-bit units. - * For 128-bit quantities, the sequence defined by the Elem[] pseudocode - * corresponds to storing the two 64-bit pieces in little-endian order. - */ -#define DO_LDQ(HNAME, VNAME, BE, HOST, TLB) \ -static inline void HNAME##_host(void *za, intptr_t off, void *host) \ -{ \ - uint64_t val0 = HOST(host), val1 = HOST(host + 8); \ - uint64_t *ptr = za + off; \ - ptr[0] = BE ? val1 : val0, ptr[1] = BE ? val0 : val1; \ -} \ +#define DO_LDQ(HNAME, VNAME) \ static inline void VNAME##_v_host(void *za, intptr_t off, void *host) \ { \ HNAME##_host(za, tile_vslice_offset(off), host); \ } \ -static inline void HNAME##_tlb(CPUARMState *env, void *za, intptr_t off, \ - target_ulong addr, uintptr_t ra) \ -{ \ - uint64_t val0 = TLB(env, useronly_clean_ptr(addr), ra); \ - uint64_t val1 = TLB(env, useronly_clean_ptr(addr + 8), ra); \ - uint64_t *ptr = za + off; \ - ptr[0] = BE ? val1 : val0, ptr[1] = BE ? val0 : val1; \ -} \ static inline void VNAME##_v_tlb(CPUARMState *env, void *za, intptr_t off, \ target_ulong addr, uintptr_t ra) \ { \ HNAME##_tlb(env, za, tile_vslice_offset(off), addr, ra); \ } -#define DO_STQ(HNAME, VNAME, BE, HOST, TLB) \ -static inline void HNAME##_host(void *za, intptr_t off, void *host) \ -{ \ - uint64_t *ptr = za + off; \ - HOST(host, ptr[BE]); \ - HOST(host + 8, ptr[!BE]); \ -} \ +#define DO_STQ(HNAME, VNAME) \ static inline void VNAME##_v_host(void *za, intptr_t off, void *host) \ { \ HNAME##_host(za, tile_vslice_offset(off), host); \ } \ -static inline void HNAME##_tlb(CPUARMState *env, void *za, intptr_t off, \ - target_ulong addr, uintptr_t ra) \ -{ \ - uint64_t *ptr = za + off; \ - TLB(env, useronly_clean_ptr(addr), ptr[BE], ra); \ - TLB(env, useronly_clean_ptr(addr + 8), ptr[!BE], ra); \ -} \ static inline void VNAME##_v_tlb(CPUARMState *env, void *za, intptr_t off, \ target_ulong addr, uintptr_t ra) \ { \ @@ -406,8 +505,8 @@ DO_LD(ld1s_le, uint32_t, ldl_le_p, cpu_ldl_le_data_ra) DO_LD(ld1d_be, uint64_t, ldq_be_p, cpu_ldq_be_data_ra) DO_LD(ld1d_le, uint64_t, ldq_le_p, cpu_ldq_le_data_ra) -DO_LDQ(sve_ld1qq_be, sme_ld1q_be, 1, ldq_be_p, cpu_ldq_be_data_ra) -DO_LDQ(sve_ld1qq_le, sme_ld1q_le, 0, ldq_le_p, cpu_ldq_le_data_ra) +DO_LDQ(sve_ld1qq_be, sme_ld1q_be) +DO_LDQ(sve_ld1qq_le, sme_ld1q_le) DO_ST(st1b, uint8_t, stb_p, cpu_stb_data_ra) DO_ST(st1h_be, uint16_t, stw_be_p, cpu_stw_be_data_ra) @@ -417,8 +516,8 @@ DO_ST(st1s_le, uint32_t, stl_le_p, cpu_stl_le_data_ra) DO_ST(st1d_be, uint64_t, stq_be_p, cpu_stq_be_data_ra) DO_ST(st1d_le, uint64_t, stq_le_p, cpu_stq_le_data_ra) -DO_STQ(sve_st1qq_be, sme_st1q_be, 1, stq_be_p, cpu_stq_be_data_ra) -DO_STQ(sve_st1qq_le, sme_st1q_le, 0, stq_le_p, cpu_stq_le_data_ra) +DO_STQ(sve_st1qq_be, sme_st1q_be) +DO_STQ(sve_st1qq_le, sme_st1q_le) #undef DO_LD #undef DO_ST @@ -903,28 +1002,69 @@ void HELPER(sme_addva_d)(void *vzda, void *vzn, void *vpn, } } -void HELPER(sme_fmopa_s)(void *vza, void *vzn, void *vzm, void *vpn, - void *vpm, float_status *fpst_in, uint32_t desc) +static void do_fmopa_h(void *vza, void *vzn, void *vzm, uint16_t *pn, + uint16_t *pm, float_status *fpst, uint32_t desc, + uint16_t negx, int negf) { intptr_t row, col, oprsz = simd_maxsz(desc); - uint32_t neg = simd_data(desc) << 31; - uint16_t *pn = vpn, *pm = vpm; - float_status fpst; - /* - * Make a copy of float_status because this operation does not - * update the cumulative fp exception status. It also produces - * default nans. - */ - fpst = *fpst_in; - set_default_nan_mode(true, &fpst); + for (row = 0; row < oprsz; ) { + uint16_t pa = pn[H2(row >> 4)]; + do { + if (pa & 1) { + void *vza_row = vza + tile_vslice_offset(row); + uint16_t n = *(uint32_t *)(vzn + H1_2(row)) ^ negx; + + for (col = 0; col < oprsz; ) { + uint16_t pb = pm[H2(col >> 4)]; + do { + if (pb & 1) { + uint16_t *a = vza_row + H1_2(col); + uint16_t *m = vzm + H1_2(col); + *a = float16_muladd(n, *m, *a, negf, fpst); + } + col += 2; + pb >>= 2; + } while (col & 15); + } + } + row += 2; + pa >>= 2; + } while (row & 15); + } +} + +void HELPER(sme_fmopa_h)(void *vza, void *vzn, void *vzm, void *vpn, + void *vpm, float_status *fpst, uint32_t desc) +{ + do_fmopa_h(vza, vzn, vzm, vpn, vpm, fpst, desc, 0, 0); +} + +void HELPER(sme_fmops_h)(void *vza, void *vzn, void *vzm, void *vpn, + void *vpm, float_status *fpst, uint32_t desc) +{ + do_fmopa_h(vza, vzn, vzm, vpn, vpm, fpst, desc, 1u << 15, 0); +} + +void HELPER(sme_ah_fmops_h)(void *vza, void *vzn, void *vzm, void *vpn, + void *vpm, float_status *fpst, uint32_t desc) +{ + do_fmopa_h(vza, vzn, vzm, vpn, vpm, fpst, desc, 0, + float_muladd_negate_product); +} + +static void do_fmopa_s(void *vza, void *vzn, void *vzm, uint16_t *pn, + uint16_t *pm, float_status *fpst, uint32_t desc, + uint32_t negx, int negf) +{ + intptr_t row, col, oprsz = simd_maxsz(desc); for (row = 0; row < oprsz; ) { uint16_t pa = pn[H2(row >> 4)]; do { if (pa & 1) { void *vza_row = vza + tile_vslice_offset(row); - uint32_t n = *(uint32_t *)(vzn + H1_4(row)) ^ neg; + uint32_t n = *(uint32_t *)(vzn + H1_4(row)) ^ negx; for (col = 0; col < oprsz; ) { uint16_t pb = pm[H2(col >> 4)]; @@ -932,7 +1072,7 @@ void HELPER(sme_fmopa_s)(void *vza, void *vzn, void *vzm, void *vpn, if (pb & 1) { uint32_t *a = vza_row + H1_4(col); uint32_t *m = vzm + H1_4(col); - *a = float32_muladd(n, *m, *a, 0, &fpst); + *a = float32_muladd(n, *m, *a, negf, fpst); } col += 4; pb >>= 4; @@ -945,32 +1085,116 @@ void HELPER(sme_fmopa_s)(void *vza, void *vzn, void *vzm, void *vpn, } } -void HELPER(sme_fmopa_d)(void *vza, void *vzn, void *vzm, void *vpn, - void *vpm, float_status *fpst_in, uint32_t desc) +void HELPER(sme_fmopa_s)(void *vza, void *vzn, void *vzm, void *vpn, + void *vpm, float_status *fpst, uint32_t desc) { - intptr_t row, col, oprsz = simd_oprsz(desc) / 8; - uint64_t neg = (uint64_t)simd_data(desc) << 63; - uint64_t *za = vza, *zn = vzn, *zm = vzm; - uint8_t *pn = vpn, *pm = vpm; - float_status fpst = *fpst_in; + do_fmopa_s(vza, vzn, vzm, vpn, vpm, fpst, desc, 0, 0); +} - set_default_nan_mode(true, &fpst); +void HELPER(sme_fmops_s)(void *vza, void *vzn, void *vzm, void *vpn, + void *vpm, float_status *fpst, uint32_t desc) +{ + do_fmopa_s(vza, vzn, vzm, vpn, vpm, fpst, desc, 1u << 31, 0); +} + +void HELPER(sme_ah_fmops_s)(void *vza, void *vzn, void *vzm, void *vpn, + void *vpm, float_status *fpst, uint32_t desc) +{ + do_fmopa_s(vza, vzn, vzm, vpn, vpm, fpst, desc, 0, + float_muladd_negate_product); +} + +static void do_fmopa_d(uint64_t *za, uint64_t *zn, uint64_t *zm, uint8_t *pn, + uint8_t *pm, float_status *fpst, uint32_t desc, + uint64_t negx, int negf) +{ + intptr_t row, col, oprsz = simd_oprsz(desc) / 8; for (row = 0; row < oprsz; ++row) { if (pn[H1(row)] & 1) { uint64_t *za_row = &za[tile_vslice_index(row)]; - uint64_t n = zn[row] ^ neg; + uint64_t n = zn[row] ^ negx; for (col = 0; col < oprsz; ++col) { if (pm[H1(col)] & 1) { uint64_t *a = &za_row[col]; - *a = float64_muladd(n, zm[col], *a, 0, &fpst); + *a = float64_muladd(n, zm[col], *a, negf, fpst); } } } } } +void HELPER(sme_fmopa_d)(void *vza, void *vzn, void *vzm, void *vpn, + void *vpm, float_status *fpst, uint32_t desc) +{ + do_fmopa_d(vza, vzn, vzm, vpn, vpm, fpst, desc, 0, 0); +} + +void HELPER(sme_fmops_d)(void *vza, void *vzn, void *vzm, void *vpn, + void *vpm, float_status *fpst, uint32_t desc) +{ + do_fmopa_d(vza, vzn, vzm, vpn, vpm, fpst, desc, 1ull << 63, 0); +} + +void HELPER(sme_ah_fmops_d)(void *vza, void *vzn, void *vzm, void *vpn, + void *vpm, float_status *fpst, uint32_t desc) +{ + do_fmopa_d(vza, vzn, vzm, vpn, vpm, fpst, desc, 0, + float_muladd_negate_product); +} + +static void do_bfmopa(void *vza, void *vzn, void *vzm, uint16_t *pn, + uint16_t *pm, float_status *fpst, uint32_t desc, + uint16_t negx, int negf) +{ + intptr_t row, col, oprsz = simd_maxsz(desc); + + for (row = 0; row < oprsz; ) { + uint16_t pa = pn[H2(row >> 4)]; + do { + if (pa & 1) { + void *vza_row = vza + tile_vslice_offset(row); + uint16_t n = *(uint32_t *)(vzn + H1_2(row)) ^ negx; + + for (col = 0; col < oprsz; ) { + uint16_t pb = pm[H2(col >> 4)]; + do { + if (pb & 1) { + uint16_t *a = vza_row + H1_2(col); + uint16_t *m = vzm + H1_2(col); + *a = bfloat16_muladd(n, *m, *a, negf, fpst); + } + col += 2; + pb >>= 2; + } while (col & 15); + } + } + row += 2; + pa >>= 2; + } while (row & 15); + } +} + +void HELPER(sme_bfmopa)(void *vza, void *vzn, void *vzm, void *vpn, + void *vpm, float_status *fpst, uint32_t desc) +{ + do_bfmopa(vza, vzn, vzm, vpn, vpm, fpst, desc, 0, 0); +} + +void HELPER(sme_bfmops)(void *vza, void *vzn, void *vzm, void *vpn, + void *vpm, float_status *fpst, uint32_t desc) +{ + do_bfmopa(vza, vzn, vzm, vpn, vpm, fpst, desc, 1u << 15, 0); +} + +void HELPER(sme_ah_bfmops)(void *vza, void *vzn, void *vzm, void *vpn, + void *vpm, float_status *fpst, uint32_t desc) +{ + do_bfmopa(vza, vzn, vzm, vpn, vpm, fpst, desc, 0, + float_muladd_negate_product); +} + /* * Alter PAIR as needed for controlling predicates being false, * and for NEG on an enabled row element. @@ -991,6 +1215,20 @@ static inline uint32_t f16mop_adj_pair(uint32_t pair, uint32_t pg, uint32_t neg) return pair; } +static inline uint32_t f16mop_ah_neg_adj_pair(uint32_t pair, uint32_t pg) +{ + uint32_t l = pg & 1 ? float16_ah_chs(pair) : 0; + uint32_t h = pg & 4 ? float16_ah_chs(pair >> 16) : 0; + return l | (h << 16); +} + +static inline uint32_t bf16mop_ah_neg_adj_pair(uint32_t pair, uint32_t pg) +{ + uint32_t l = pg & 1 ? bfloat16_ah_chs(pair) : 0; + uint32_t h = pg & 4 ? bfloat16_ah_chs(pair >> 16) : 0; + return l | (h << 16); +} + static float32 f16_dotadd(float32 sum, uint32_t e1, uint32_t e2, float_status *s_f16, float_status *s_std, float_status *s_odd) @@ -1005,49 +1243,67 @@ static float32 f16_dotadd(float32 sum, uint32_t e1, uint32_t e2, * - we have pre-set-up copy of s_std which is set to round-to-odd, * for the multiply (see below) */ - float64 e1r = float16_to_float64(e1 & 0xffff, true, s_f16); - float64 e1c = float16_to_float64(e1 >> 16, true, s_f16); - float64 e2r = float16_to_float64(e2 & 0xffff, true, s_f16); - float64 e2c = float16_to_float64(e2 >> 16, true, s_f16); - float64 t64; + float16 h1r = e1 & 0xffff; + float16 h1c = e1 >> 16; + float16 h2r = e2 & 0xffff; + float16 h2c = e2 >> 16; float32 t32; - /* - * The ARM pseudocode function FPDot performs both multiplies - * and the add with a single rounding operation. Emulate this - * by performing the first multiply in round-to-odd, then doing - * the second multiply as fused multiply-add, and rounding to - * float32 all in one step. - */ - t64 = float64_mul(e1r, e2r, s_odd); - t64 = float64r32_muladd(e1c, e2c, t64, 0, s_std); + /* C.f. FPProcessNaNs4 */ + if (float16_is_any_nan(h1r) || float16_is_any_nan(h1c) || + float16_is_any_nan(h2r) || float16_is_any_nan(h2c)) { + float16 t16; + + if (float16_is_signaling_nan(h1r, s_f16)) { + t16 = h1r; + } else if (float16_is_signaling_nan(h1c, s_f16)) { + t16 = h1c; + } else if (float16_is_signaling_nan(h2r, s_f16)) { + t16 = h2r; + } else if (float16_is_signaling_nan(h2c, s_f16)) { + t16 = h2c; + } else if (float16_is_any_nan(h1r)) { + t16 = h1r; + } else if (float16_is_any_nan(h1c)) { + t16 = h1c; + } else if (float16_is_any_nan(h2r)) { + t16 = h2r; + } else { + t16 = h2c; + } + t32 = float16_to_float32(t16, true, s_f16); + } else { + float64 e1r = float16_to_float64(h1r, true, s_f16); + float64 e1c = float16_to_float64(h1c, true, s_f16); + float64 e2r = float16_to_float64(h2r, true, s_f16); + float64 e2c = float16_to_float64(h2c, true, s_f16); + float64 t64; + + /* + * The ARM pseudocode function FPDot performs both multiplies + * and the add with a single rounding operation. Emulate this + * by performing the first multiply in round-to-odd, then doing + * the second multiply as fused multiply-add, and rounding to + * float32 all in one step. + */ + t64 = float64_mul(e1r, e2r, s_odd); + t64 = float64r32_muladd(e1c, e2c, t64, 0, s_std); - /* This conversion is exact, because we've already rounded. */ - t32 = float64_to_float32(t64, s_std); + /* This conversion is exact, because we've already rounded. */ + t32 = float64_to_float32(t64, s_std); + } /* The final accumulation step is not fused. */ return float32_add(sum, t32, s_std); } -void HELPER(sme_fmopa_h)(void *vza, void *vzn, void *vzm, void *vpn, - void *vpm, CPUARMState *env, uint32_t desc) +static void do_fmopa_w_h(void *vza, void *vzn, void *vzm, uint16_t *pn, + uint16_t *pm, CPUARMState *env, uint32_t desc, + uint32_t negx, bool ah_neg) { intptr_t row, col, oprsz = simd_maxsz(desc); - uint32_t neg = simd_data(desc) * 0x80008000u; - uint16_t *pn = vpn, *pm = vpm; - float_status fpst_odd, fpst_std, fpst_f16; + float_status fpst_odd = env->vfp.fp_status[FPST_ZA]; - /* - * Make copies of the fp status fields we use, because this operation - * does not update the cumulative fp exception status. It also - * produces default NaNs. We also need a second copy of fp_status with - * round-to-odd -- see above. - */ - fpst_f16 = env->vfp.fp_status[FPST_A64_F16]; - fpst_std = env->vfp.fp_status[FPST_A64]; - set_default_nan_mode(true, &fpst_std); - set_default_nan_mode(true, &fpst_f16); - fpst_odd = fpst_std; set_float_rounding_mode(float_round_to_odd, &fpst_odd); for (row = 0; row < oprsz; ) { @@ -1056,7 +1312,11 @@ void HELPER(sme_fmopa_h)(void *vza, void *vzn, void *vzm, void *vpn, void *vza_row = vza + tile_vslice_offset(row); uint32_t n = *(uint32_t *)(vzn + H1_4(row)); - n = f16mop_adj_pair(n, prow, neg); + if (ah_neg) { + n = f16mop_ah_neg_adj_pair(n, prow); + } else { + n = f16mop_adj_pair(n, prow, negx); + } for (col = 0; col < oprsz; ) { uint16_t pcol = pm[H2(col >> 4)]; @@ -1067,7 +1327,9 @@ void HELPER(sme_fmopa_h)(void *vza, void *vzn, void *vzm, void *vpn, m = f16mop_adj_pair(m, pcol, 0); *a = f16_dotadd(*a, n, m, - &fpst_f16, &fpst_std, &fpst_odd); + &env->vfp.fp_status[FPST_ZA_F16], + &env->vfp.fp_status[FPST_ZA], + &fpst_odd); } col += 4; pcol >>= 4; @@ -1079,12 +1341,103 @@ void HELPER(sme_fmopa_h)(void *vza, void *vzn, void *vzm, void *vpn, } } -void HELPER(sme_bfmopa)(void *vza, void *vzn, void *vzm, - void *vpn, void *vpm, CPUARMState *env, uint32_t desc) +void HELPER(sme_fmopa_w_h)(void *vza, void *vzn, void *vzm, void *vpn, + void *vpm, CPUARMState *env, uint32_t desc) +{ + do_fmopa_w_h(vza, vzn, vzm, vpn, vpm, env, desc, 0, false); +} + +void HELPER(sme_fmops_w_h)(void *vza, void *vzn, void *vzm, void *vpn, + void *vpm, CPUARMState *env, uint32_t desc) +{ + do_fmopa_w_h(vza, vzn, vzm, vpn, vpm, env, desc, 0x80008000u, false); +} + +void HELPER(sme_ah_fmops_w_h)(void *vza, void *vzn, void *vzm, void *vpn, + void *vpm, CPUARMState *env, uint32_t desc) +{ + do_fmopa_w_h(vza, vzn, vzm, vpn, vpm, env, desc, 0, true); +} + +void HELPER(sme2_fdot_h)(void *vd, void *vn, void *vm, void *va, + CPUARMState *env, uint32_t desc) +{ + intptr_t i, oprsz = simd_maxsz(desc); + bool za = extract32(desc, SIMD_DATA_SHIFT, 1); + float_status *fpst_std = &env->vfp.fp_status[za ? FPST_ZA : FPST_A64]; + float_status *fpst_f16 = &env->vfp.fp_status[za ? FPST_ZA_F16 : FPST_A64_F16]; + float_status fpst_odd = *fpst_std; + float32 *d = vd, *a = va; + uint32_t *n = vn, *m = vm; + + set_float_rounding_mode(float_round_to_odd, &fpst_odd); + + for (i = 0; i < oprsz / sizeof(float32); ++i) { + d[H4(i)] = f16_dotadd(a[H4(i)], n[H4(i)], m[H4(i)], + fpst_f16, fpst_std, &fpst_odd); + } +} + +void HELPER(sme2_fdot_idx_h)(void *vd, void *vn, void *vm, void *va, + CPUARMState *env, uint32_t desc) +{ + intptr_t i, j, oprsz = simd_maxsz(desc); + intptr_t elements = oprsz / sizeof(float32); + intptr_t eltspersegment = MIN(4, elements); + int idx = extract32(desc, SIMD_DATA_SHIFT, 2); + bool za = extract32(desc, SIMD_DATA_SHIFT + 2, 1); + float_status *fpst_std = &env->vfp.fp_status[za ? FPST_ZA : FPST_A64]; + float_status *fpst_f16 = &env->vfp.fp_status[za ? FPST_ZA_F16 : FPST_A64_F16]; + float_status fpst_odd = *fpst_std; + float32 *d = vd, *a = va; + uint32_t *n = vn, *m = (uint32_t *)vm + H4(idx); + + set_float_rounding_mode(float_round_to_odd, &fpst_odd); + + for (i = 0; i < elements; i += eltspersegment) { + uint32_t mm = m[i]; + for (j = 0; j < eltspersegment; ++j) { + d[H4(i + j)] = f16_dotadd(a[H4(i + j)], n[H4(i + j)], mm, + fpst_f16, fpst_std, &fpst_odd); + } + } +} + +void HELPER(sme2_fvdot_idx_h)(void *vd, void *vn, void *vm, void *va, + CPUARMState *env, uint32_t desc) +{ + intptr_t i, j, oprsz = simd_maxsz(desc); + intptr_t elements = oprsz / sizeof(float32); + intptr_t eltspersegment = MIN(4, elements); + int idx = extract32(desc, SIMD_DATA_SHIFT, 2); + int sel = extract32(desc, SIMD_DATA_SHIFT + 2, 1); + float_status fpst_odd, *fpst_std, *fpst_f16; + float32 *d = vd, *a = va; + uint16_t *n0 = vn; + uint16_t *n1 = vn + sizeof(ARMVectorReg); + uint32_t *m = (uint32_t *)vm + H4(idx); + + fpst_std = &env->vfp.fp_status[FPST_ZA]; + fpst_f16 = &env->vfp.fp_status[FPST_ZA_F16]; + fpst_odd = *fpst_std; + set_float_rounding_mode(float_round_to_odd, &fpst_odd); + + for (i = 0; i < elements; i += eltspersegment) { + uint32_t mm = m[i]; + for (j = 0; j < eltspersegment; ++j) { + uint32_t nn = (n0[H2(2 * (i + j) + sel)]) + | (n1[H2(2 * (i + j) + sel)] << 16); + d[i + H4(j)] = f16_dotadd(a[i + H4(j)], nn, mm, + fpst_f16, fpst_std, &fpst_odd); + } + } +} + +static void do_bfmopa_w(void *vza, void *vzn, void *vzm, + uint16_t *pn, uint16_t *pm, CPUARMState *env, + uint32_t desc, uint32_t negx, bool ah_neg) { intptr_t row, col, oprsz = simd_maxsz(desc); - uint32_t neg = simd_data(desc) * 0x80008000u; - uint16_t *pn = vpn, *pm = vpm; float_status fpst, fpst_odd; if (is_ebf(env, &fpst, &fpst_odd)) { @@ -1094,7 +1447,11 @@ void HELPER(sme_bfmopa)(void *vza, void *vzn, void *vzm, void *vza_row = vza + tile_vslice_offset(row); uint32_t n = *(uint32_t *)(vzn + H1_4(row)); - n = f16mop_adj_pair(n, prow, neg); + if (ah_neg) { + n = bf16mop_ah_neg_adj_pair(n, prow); + } else { + n = f16mop_adj_pair(n, prow, negx); + } for (col = 0; col < oprsz; ) { uint16_t pcol = pm[H2(col >> 4)]; @@ -1121,7 +1478,11 @@ void HELPER(sme_bfmopa)(void *vza, void *vzn, void *vzm, void *vza_row = vza + tile_vslice_offset(row); uint32_t n = *(uint32_t *)(vzn + H1_4(row)); - n = f16mop_adj_pair(n, prow, neg); + if (ah_neg) { + n = bf16mop_ah_neg_adj_pair(n, prow); + } else { + n = f16mop_adj_pair(n, prow, negx); + } for (col = 0; col < oprsz; ) { uint16_t pcol = pm[H2(col >> 4)]; @@ -1144,6 +1505,24 @@ void HELPER(sme_bfmopa)(void *vza, void *vzn, void *vzm, } } +void HELPER(sme_bfmopa_w)(void *vza, void *vzn, void *vzm, void *vpn, + void *vpm, CPUARMState *env, uint32_t desc) +{ + do_bfmopa_w(vza, vzn, vzm, vpn, vpm, env, desc, 0, false); +} + +void HELPER(sme_bfmops_w)(void *vza, void *vzn, void *vzm, void *vpn, + void *vpm, CPUARMState *env, uint32_t desc) +{ + do_bfmopa_w(vza, vzn, vzm, vpn, vpm, env, desc, 0x80008000u, false); +} + +void HELPER(sme_ah_bfmops_w)(void *vza, void *vzn, void *vzm, void *vpn, + void *vpm, CPUARMState *env, uint32_t desc) +{ + do_bfmopa_w(vza, vzn, vzm, vpn, vpm, env, desc, 0, true); +} + typedef uint32_t IMOPFn32(uint32_t, uint32_t, uint32_t, uint8_t, bool); static inline void do_imopa_s(uint32_t *za, uint32_t *zn, uint32_t *zm, uint8_t *pn, uint8_t *pm, @@ -1188,7 +1567,7 @@ static inline void do_imopa_d(uint64_t *za, uint64_t *zn, uint64_t *zm, } } -#define DEF_IMOP_32(NAME, NTYPE, MTYPE) \ +#define DEF_IMOP_8x4_32(NAME, NTYPE, MTYPE) \ static uint32_t NAME(uint32_t n, uint32_t m, uint32_t a, uint8_t p, bool neg) \ { \ uint32_t sum = 0; \ @@ -1201,7 +1580,7 @@ static uint32_t NAME(uint32_t n, uint32_t m, uint32_t a, uint8_t p, bool neg) \ return neg ? a - sum : a + sum; \ } -#define DEF_IMOP_64(NAME, NTYPE, MTYPE) \ +#define DEF_IMOP_16x4_64(NAME, NTYPE, MTYPE) \ static uint64_t NAME(uint64_t n, uint64_t m, uint64_t a, uint8_t p, bool neg) \ { \ uint64_t sum = 0; \ @@ -1214,27 +1593,1070 @@ static uint64_t NAME(uint64_t n, uint64_t m, uint64_t a, uint8_t p, bool neg) \ return neg ? a - sum : a + sum; \ } -DEF_IMOP_32(smopa_s, int8_t, int8_t) -DEF_IMOP_32(umopa_s, uint8_t, uint8_t) -DEF_IMOP_32(sumopa_s, int8_t, uint8_t) -DEF_IMOP_32(usmopa_s, uint8_t, int8_t) +DEF_IMOP_8x4_32(smopa_s, int8_t, int8_t) +DEF_IMOP_8x4_32(umopa_s, uint8_t, uint8_t) +DEF_IMOP_8x4_32(sumopa_s, int8_t, uint8_t) +DEF_IMOP_8x4_32(usmopa_s, uint8_t, int8_t) -DEF_IMOP_64(smopa_d, int16_t, int16_t) -DEF_IMOP_64(umopa_d, uint16_t, uint16_t) -DEF_IMOP_64(sumopa_d, int16_t, uint16_t) -DEF_IMOP_64(usmopa_d, uint16_t, int16_t) +DEF_IMOP_16x4_64(smopa_d, int16_t, int16_t) +DEF_IMOP_16x4_64(umopa_d, uint16_t, uint16_t) +DEF_IMOP_16x4_64(sumopa_d, int16_t, uint16_t) +DEF_IMOP_16x4_64(usmopa_d, uint16_t, int16_t) -#define DEF_IMOPH(NAME, S) \ - void HELPER(sme_##NAME##_##S)(void *vza, void *vzn, void *vzm, \ +#define DEF_IMOPH(P, NAME, S) \ + void HELPER(P##_##NAME##_##S)(void *vza, void *vzn, void *vzm, \ void *vpn, void *vpm, uint32_t desc) \ { do_imopa_##S(vza, vzn, vzm, vpn, vpm, desc, NAME##_##S); } -DEF_IMOPH(smopa, s) -DEF_IMOPH(umopa, s) -DEF_IMOPH(sumopa, s) -DEF_IMOPH(usmopa, s) +DEF_IMOPH(sme, smopa, s) +DEF_IMOPH(sme, umopa, s) +DEF_IMOPH(sme, sumopa, s) +DEF_IMOPH(sme, usmopa, s) + +DEF_IMOPH(sme, smopa, d) +DEF_IMOPH(sme, umopa, d) +DEF_IMOPH(sme, sumopa, d) +DEF_IMOPH(sme, usmopa, d) + +static uint32_t bmopa_s(uint32_t n, uint32_t m, uint32_t a, uint8_t p, bool neg) +{ + uint32_t sum = ctpop32(~(n ^ m)); + if (neg) { + sum = -sum; + } + if (!(p & 1)) { + sum = 0; + } + return a + sum; +} + +DEF_IMOPH(sme2, bmopa, s) + +#define DEF_IMOP_16x2_32(NAME, NTYPE, MTYPE) \ +static uint32_t NAME(uint32_t n, uint32_t m, uint32_t a, uint8_t p, bool neg) \ +{ \ + uint32_t sum = 0; \ + /* Apply P to N as a mask, making the inactive elements 0. */ \ + n &= expand_pred_h(p); \ + sum += (NTYPE)(n >> 0) * (MTYPE)(m >> 0); \ + sum += (NTYPE)(n >> 16) * (MTYPE)(m >> 16); \ + return neg ? a - sum : a + sum; \ +} + +DEF_IMOP_16x2_32(smopa2_s, int16_t, int16_t) +DEF_IMOP_16x2_32(umopa2_s, uint16_t, uint16_t) + +DEF_IMOPH(sme2, smopa2, s) +DEF_IMOPH(sme2, umopa2, s) + +#define DO_VDOT_IDX(NAME, TYPED, TYPEN, TYPEM, HD, HN) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ +{ \ + intptr_t svl = simd_oprsz(desc); \ + intptr_t elements = svl / sizeof(TYPED); \ + intptr_t eltperseg = 16 / sizeof(TYPED); \ + intptr_t nreg = sizeof(TYPED) / sizeof(TYPEN); \ + intptr_t vstride = (svl / nreg) * sizeof(ARMVectorReg); \ + intptr_t zstride = sizeof(ARMVectorReg) / sizeof(TYPEN); \ + intptr_t idx = extract32(desc, SIMD_DATA_SHIFT, 2); \ + TYPEN *n = vn; \ + TYPEM *m = vm; \ + for (intptr_t r = 0; r < nreg; r++) { \ + TYPED *d = vd + r * vstride; \ + for (intptr_t seg = 0; seg < elements; seg += eltperseg) { \ + intptr_t s = seg + idx; \ + for (intptr_t e = seg; e < seg + eltperseg; e++) { \ + TYPED sum = d[HD(e)]; \ + for (intptr_t i = 0; i < nreg; i++) { \ + TYPED nn = n[i * zstride + HN(nreg * e + r)]; \ + TYPED mm = m[HN(nreg * s + i)]; \ + sum += nn * mm; \ + } \ + d[HD(e)] = sum; \ + } \ + } \ + } \ +} + +DO_VDOT_IDX(sme2_svdot_idx_4b, int32_t, int8_t, int8_t, H4, H1) +DO_VDOT_IDX(sme2_uvdot_idx_4b, uint32_t, uint8_t, uint8_t, H4, H1) +DO_VDOT_IDX(sme2_suvdot_idx_4b, int32_t, int8_t, uint8_t, H4, H1) +DO_VDOT_IDX(sme2_usvdot_idx_4b, int32_t, uint8_t, int8_t, H4, H1) + +DO_VDOT_IDX(sme2_svdot_idx_4h, int64_t, int16_t, int16_t, H8, H2) +DO_VDOT_IDX(sme2_uvdot_idx_4h, uint64_t, uint16_t, uint16_t, H8, H2) + +DO_VDOT_IDX(sme2_svdot_idx_2h, int32_t, int16_t, int16_t, H4, H2) +DO_VDOT_IDX(sme2_uvdot_idx_2h, uint32_t, uint16_t, uint16_t, H4, H2) + +#undef DO_VDOT_IDX + +#define DO_MLALL(NAME, TYPEW, TYPEN, TYPEM, HW, HN, OP) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \ +{ \ + intptr_t elements = simd_oprsz(desc) / sizeof(TYPEW); \ + intptr_t sel = extract32(desc, SIMD_DATA_SHIFT, 2); \ + TYPEW *d = vd, *a = va; TYPEN *n = vn; TYPEM *m = vm; \ + for (intptr_t i = 0; i < elements; ++i) { \ + TYPEW nn = n[HN(i * 4 + sel)]; \ + TYPEM mm = m[HN(i * 4 + sel)]; \ + d[HW(i)] = a[HW(i)] OP (nn * mm); \ + } \ +} + +DO_MLALL(sme2_smlall_s, int32_t, int8_t, int8_t, H4, H1, +) +DO_MLALL(sme2_smlall_d, int64_t, int16_t, int16_t, H8, H2, +) +DO_MLALL(sme2_smlsll_s, int32_t, int8_t, int8_t, H4, H1, -) +DO_MLALL(sme2_smlsll_d, int64_t, int16_t, int16_t, H8, H2, -) + +DO_MLALL(sme2_umlall_s, uint32_t, uint8_t, uint8_t, H4, H1, +) +DO_MLALL(sme2_umlall_d, uint64_t, uint16_t, uint16_t, H8, H2, +) +DO_MLALL(sme2_umlsll_s, uint32_t, uint8_t, uint8_t, H4, H1, -) +DO_MLALL(sme2_umlsll_d, uint64_t, uint16_t, uint16_t, H8, H2, -) + +DO_MLALL(sme2_usmlall_s, uint32_t, uint8_t, int8_t, H4, H1, +) + +#undef DO_MLALL + +#define DO_MLALL_IDX(NAME, TYPEW, TYPEN, TYPEM, HW, HN, OP) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \ +{ \ + intptr_t elements = simd_oprsz(desc) / sizeof(TYPEW); \ + intptr_t eltspersegment = 16 / sizeof(TYPEW); \ + intptr_t sel = extract32(desc, SIMD_DATA_SHIFT, 2); \ + intptr_t idx = extract32(desc, SIMD_DATA_SHIFT + 2, 4); \ + TYPEW *d = vd, *a = va; TYPEN *n = vn; TYPEM *m = vm; \ + for (intptr_t i = 0; i < elements; i += eltspersegment) { \ + TYPEW mm = m[HN(i * 4 + idx)]; \ + for (intptr_t j = 0; j < eltspersegment; ++j) { \ + TYPEN nn = n[HN((i + j) * 4 + sel)]; \ + d[HW(i + j)] = a[HW(i + j)] OP (nn * mm); \ + } \ + } \ +} + +DO_MLALL_IDX(sme2_smlall_idx_s, int32_t, int8_t, int8_t, H4, H1, +) +DO_MLALL_IDX(sme2_smlall_idx_d, int64_t, int16_t, int16_t, H8, H2, +) +DO_MLALL_IDX(sme2_smlsll_idx_s, int32_t, int8_t, int8_t, H4, H1, -) +DO_MLALL_IDX(sme2_smlsll_idx_d, int64_t, int16_t, int16_t, H8, H2, -) + +DO_MLALL_IDX(sme2_umlall_idx_s, uint32_t, uint8_t, uint8_t, H4, H1, +) +DO_MLALL_IDX(sme2_umlall_idx_d, uint64_t, uint16_t, uint16_t, H8, H2, +) +DO_MLALL_IDX(sme2_umlsll_idx_s, uint32_t, uint8_t, uint8_t, H4, H1, -) +DO_MLALL_IDX(sme2_umlsll_idx_d, uint64_t, uint16_t, uint16_t, H8, H2, -) + +DO_MLALL_IDX(sme2_usmlall_idx_s, uint32_t, uint8_t, int8_t, H4, H1, +) +DO_MLALL_IDX(sme2_sumlall_idx_s, uint32_t, int8_t, uint8_t, H4, H1, +) + +#undef DO_MLALL_IDX + +/* Convert and compress */ +void HELPER(sme2_bfcvt)(void *vd, void *vs, float_status *fpst, uint32_t desc) +{ + ARMVectorReg scratch; + size_t oprsz = simd_oprsz(desc); + size_t i, n = oprsz / 4; + float32 *s0 = vs; + float32 *s1 = vs + sizeof(ARMVectorReg); + bfloat16 *d = vd; + + if (vd == s1) { + s1 = memcpy(&scratch, s1, oprsz); + } + + for (i = 0; i < n; ++i) { + d[H2(i)] = float32_to_bfloat16(s0[H4(i)], fpst); + } + for (i = 0; i < n; ++i) { + d[H2(i) + n] = float32_to_bfloat16(s1[H4(i)], fpst); + } +} + +void HELPER(sme2_fcvt_n)(void *vd, void *vs, float_status *fpst, uint32_t desc) +{ + ARMVectorReg scratch; + size_t oprsz = simd_oprsz(desc); + size_t i, n = oprsz / 4; + float32 *s0 = vs; + float32 *s1 = vs + sizeof(ARMVectorReg); + float16 *d = vd; + + if (vd == s1) { + s1 = memcpy(&scratch, s1, oprsz); + } + + for (i = 0; i < n; ++i) { + d[H2(i)] = sve_f32_to_f16(s0[H4(i)], fpst); + } + for (i = 0; i < n; ++i) { + d[H2(i) + n] = sve_f32_to_f16(s1[H4(i)], fpst); + } +} + +#define SQCVT2(NAME, TW, TN, HW, HN, SAT) \ +void HELPER(NAME)(void *vd, void *vs, uint32_t desc) \ +{ \ + ARMVectorReg scratch; \ + size_t oprsz = simd_oprsz(desc), n = oprsz / sizeof(TW); \ + TW *s0 = vs, *s1 = vs + sizeof(ARMVectorReg); \ + TN *d = vd; \ + if (vectors_overlap(vd, 1, vs, 2)) { \ + d = (TN *)&scratch; \ + } \ + for (size_t i = 0; i < n; ++i) { \ + d[HN(i)] = SAT(s0[HW(i)]); \ + d[HN(i + n)] = SAT(s1[HW(i)]); \ + } \ + if (d != vd) { \ + memcpy(vd, d, oprsz); \ + } \ +} + +SQCVT2(sme2_sqcvt_sh, int32_t, int16_t, H4, H2, do_ssat_h) +SQCVT2(sme2_uqcvt_sh, uint32_t, uint16_t, H4, H2, do_usat_h) +SQCVT2(sme2_sqcvtu_sh, int32_t, uint16_t, H4, H2, do_usat_h) + +#undef SQCVT2 + +#define SQCVT4(NAME, TW, TN, HW, HN, SAT) \ +void HELPER(NAME)(void *vd, void *vs, uint32_t desc) \ +{ \ + ARMVectorReg scratch; \ + size_t oprsz = simd_oprsz(desc), n = oprsz / sizeof(TW); \ + TW *s0 = vs, *s1 = vs + sizeof(ARMVectorReg); \ + TW *s2 = vs + 2 * sizeof(ARMVectorReg); \ + TW *s3 = vs + 3 * sizeof(ARMVectorReg); \ + TN *d = vd; \ + if (vectors_overlap(vd, 1, vs, 4)) { \ + d = (TN *)&scratch; \ + } \ + for (size_t i = 0; i < n; ++i) { \ + d[HN(i)] = SAT(s0[HW(i)]); \ + d[HN(i + n)] = SAT(s1[HW(i)]); \ + d[HN(i + 2 * n)] = SAT(s2[HW(i)]); \ + d[HN(i + 3 * n)] = SAT(s3[HW(i)]); \ + } \ + if (d != vd) { \ + memcpy(vd, d, oprsz); \ + } \ +} + +SQCVT4(sme2_sqcvt_sb, int32_t, int8_t, H4, H2, do_ssat_b) +SQCVT4(sme2_uqcvt_sb, uint32_t, uint8_t, H4, H2, do_usat_b) +SQCVT4(sme2_sqcvtu_sb, int32_t, uint8_t, H4, H2, do_usat_b) + +SQCVT4(sme2_sqcvt_dh, int64_t, int16_t, H8, H2, do_ssat_h) +SQCVT4(sme2_uqcvt_dh, uint64_t, uint16_t, H8, H2, do_usat_h) +SQCVT4(sme2_sqcvtu_dh, int64_t, uint16_t, H8, H2, do_usat_h) + +#undef SQCVT4 + +#define SQRSHR2(NAME, TW, TN, HW, HN, RSHR, SAT) \ +void HELPER(NAME)(void *vd, void *vs, uint32_t desc) \ +{ \ + ARMVectorReg scratch; \ + size_t oprsz = simd_oprsz(desc), n = oprsz / sizeof(TW); \ + int shift = simd_data(desc); \ + TW *s0 = vs, *s1 = vs + sizeof(ARMVectorReg); \ + TN *d = vd; \ + if (vectors_overlap(vd, 1, vs, 2)) { \ + d = (TN *)&scratch; \ + } \ + for (size_t i = 0; i < n; ++i) { \ + d[HN(i)] = SAT(RSHR(s0[HW(i)], shift)); \ + d[HN(i + n)] = SAT(RSHR(s1[HW(i)], shift)); \ + } \ + if (d != vd) { \ + memcpy(vd, d, oprsz); \ + } \ +} + +SQRSHR2(sme2_sqrshr_sh, int32_t, int16_t, H4, H2, do_srshr, do_ssat_h) +SQRSHR2(sme2_uqrshr_sh, uint32_t, uint16_t, H4, H2, do_urshr, do_usat_h) +SQRSHR2(sme2_sqrshru_sh, int32_t, uint16_t, H4, H2, do_srshr, do_usat_h) + +#undef SQRSHR2 + +#define SQRSHR4(NAME, TW, TN, HW, HN, RSHR, SAT) \ +void HELPER(NAME)(void *vd, void *vs, uint32_t desc) \ +{ \ + ARMVectorReg scratch; \ + size_t oprsz = simd_oprsz(desc), n = oprsz / sizeof(TW); \ + int shift = simd_data(desc); \ + TW *s0 = vs, *s1 = vs + sizeof(ARMVectorReg); \ + TW *s2 = vs + 2 * sizeof(ARMVectorReg); \ + TW *s3 = vs + 3 * sizeof(ARMVectorReg); \ + TN *d = vd; \ + if (vectors_overlap(vd, 1, vs, 4)) { \ + d = (TN *)&scratch; \ + } \ + for (size_t i = 0; i < n; ++i) { \ + d[HN(i)] = SAT(RSHR(s0[HW(i)], shift)); \ + d[HN(i + n)] = SAT(RSHR(s1[HW(i)], shift)); \ + d[HN(i + 2 * n)] = SAT(RSHR(s2[HW(i)], shift)); \ + d[HN(i + 3 * n)] = SAT(RSHR(s3[HW(i)], shift)); \ + } \ + if (d != vd) { \ + memcpy(vd, d, oprsz); \ + } \ +} + +SQRSHR4(sme2_sqrshr_sb, int32_t, int8_t, H4, H2, do_srshr, do_ssat_b) +SQRSHR4(sme2_uqrshr_sb, uint32_t, uint8_t, H4, H2, do_urshr, do_usat_b) +SQRSHR4(sme2_sqrshru_sb, int32_t, uint8_t, H4, H2, do_srshr, do_usat_b) + +SQRSHR4(sme2_sqrshr_dh, int64_t, int16_t, H8, H2, do_srshr, do_ssat_h) +SQRSHR4(sme2_uqrshr_dh, uint64_t, uint16_t, H8, H2, do_urshr, do_usat_h) +SQRSHR4(sme2_sqrshru_dh, int64_t, uint16_t, H8, H2, do_srshr, do_usat_h) + +#undef SQRSHR4 + +/* Convert and interleave */ +void HELPER(sme2_bfcvtn)(void *vd, void *vs, float_status *fpst, uint32_t desc) +{ + size_t i, n = simd_oprsz(desc) / 4; + float32 *s0 = vs; + float32 *s1 = vs + sizeof(ARMVectorReg); + bfloat16 *d = vd; + + for (i = 0; i < n; ++i) { + bfloat16 d0 = float32_to_bfloat16(s0[H4(i)], fpst); + bfloat16 d1 = float32_to_bfloat16(s1[H4(i)], fpst); + d[H2(i * 2 + 0)] = d0; + d[H2(i * 2 + 1)] = d1; + } +} + +void HELPER(sme2_fcvtn)(void *vd, void *vs, float_status *fpst, uint32_t desc) +{ + size_t i, n = simd_oprsz(desc) / 4; + float32 *s0 = vs; + float32 *s1 = vs + sizeof(ARMVectorReg); + bfloat16 *d = vd; + + for (i = 0; i < n; ++i) { + bfloat16 d0 = sve_f32_to_f16(s0[H4(i)], fpst); + bfloat16 d1 = sve_f32_to_f16(s1[H4(i)], fpst); + d[H2(i * 2 + 0)] = d0; + d[H2(i * 2 + 1)] = d1; + } +} + +#define SQCVTN2(NAME, TW, TN, HW, HN, SAT) \ +void HELPER(NAME)(void *vd, void *vs, uint32_t desc) \ +{ \ + ARMVectorReg scratch; \ + size_t oprsz = simd_oprsz(desc), n = oprsz / sizeof(TW); \ + TW *s0 = vs, *s1 = vs + sizeof(ARMVectorReg); \ + TN *d = vd; \ + if (vectors_overlap(vd, 1, vs, 2)) { \ + d = (TN *)&scratch; \ + } \ + for (size_t i = 0; i < n; ++i) { \ + d[HN(2 * i + 0)] = SAT(s0[HW(i)]); \ + d[HN(2 * i + 1)] = SAT(s1[HW(i)]); \ + } \ + if (d != vd) { \ + memcpy(vd, d, oprsz); \ + } \ +} + +SQCVTN2(sme2_sqcvtn_sh, int32_t, int16_t, H4, H2, do_ssat_h) +SQCVTN2(sme2_uqcvtn_sh, uint32_t, uint16_t, H4, H2, do_usat_h) +SQCVTN2(sme2_sqcvtun_sh, int32_t, uint16_t, H4, H2, do_usat_h) + +#undef SQCVTN2 + +#define SQCVTN4(NAME, TW, TN, HW, HN, SAT) \ +void HELPER(NAME)(void *vd, void *vs, uint32_t desc) \ +{ \ + ARMVectorReg scratch; \ + size_t oprsz = simd_oprsz(desc), n = oprsz / sizeof(TW); \ + TW *s0 = vs, *s1 = vs + sizeof(ARMVectorReg); \ + TW *s2 = vs + 2 * sizeof(ARMVectorReg); \ + TW *s3 = vs + 3 * sizeof(ARMVectorReg); \ + TN *d = vd; \ + if (vectors_overlap(vd, 1, vs, 4)) { \ + d = (TN *)&scratch; \ + } \ + for (size_t i = 0; i < n; ++i) { \ + d[HN(4 * i + 0)] = SAT(s0[HW(i)]); \ + d[HN(4 * i + 1)] = SAT(s1[HW(i)]); \ + d[HN(4 * i + 2)] = SAT(s2[HW(i)]); \ + d[HN(4 * i + 3)] = SAT(s3[HW(i)]); \ + } \ + if (d != vd) { \ + memcpy(vd, d, oprsz); \ + } \ +} + +SQCVTN4(sme2_sqcvtn_sb, int32_t, int8_t, H4, H1, do_ssat_b) +SQCVTN4(sme2_uqcvtn_sb, uint32_t, uint8_t, H4, H1, do_usat_b) +SQCVTN4(sme2_sqcvtun_sb, int32_t, uint8_t, H4, H1, do_usat_b) + +SQCVTN4(sme2_sqcvtn_dh, int64_t, int16_t, H8, H2, do_ssat_h) +SQCVTN4(sme2_uqcvtn_dh, uint64_t, uint16_t, H8, H2, do_usat_h) +SQCVTN4(sme2_sqcvtun_dh, int64_t, uint16_t, H8, H2, do_usat_h) + +#undef SQCVTN4 + +#define SQRSHRN2(NAME, TW, TN, HW, HN, RSHR, SAT) \ +void HELPER(NAME)(void *vd, void *vs, uint32_t desc) \ +{ \ + ARMVectorReg scratch; \ + size_t oprsz = simd_oprsz(desc), n = oprsz / sizeof(TW); \ + int shift = simd_data(desc); \ + TW *s0 = vs, *s1 = vs + sizeof(ARMVectorReg); \ + TN *d = vd; \ + if (vectors_overlap(vd, 1, vs, 2)) { \ + d = (TN *)&scratch; \ + } \ + for (size_t i = 0; i < n; ++i) { \ + d[HN(2 * i + 0)] = SAT(RSHR(s0[HW(i)], shift)); \ + d[HN(2 * i + 1)] = SAT(RSHR(s1[HW(i)], shift)); \ + } \ + if (d != vd) { \ + memcpy(vd, d, oprsz); \ + } \ +} + +SQRSHRN2(sme2_sqrshrn_sh, int32_t, int16_t, H4, H2, do_srshr, do_ssat_h) +SQRSHRN2(sme2_uqrshrn_sh, uint32_t, uint16_t, H4, H2, do_urshr, do_usat_h) +SQRSHRN2(sme2_sqrshrun_sh, int32_t, uint16_t, H4, H2, do_srshr, do_usat_h) + +#undef SQRSHRN2 + +#define SQRSHRN4(NAME, TW, TN, HW, HN, RSHR, SAT) \ +void HELPER(NAME)(void *vd, void *vs, uint32_t desc) \ +{ \ + ARMVectorReg scratch; \ + size_t oprsz = simd_oprsz(desc), n = oprsz / sizeof(TW); \ + int shift = simd_data(desc); \ + TW *s0 = vs, *s1 = vs + sizeof(ARMVectorReg); \ + TW *s2 = vs + 2 * sizeof(ARMVectorReg); \ + TW *s3 = vs + 3 * sizeof(ARMVectorReg); \ + TN *d = vd; \ + if (vectors_overlap(vd, 1, vs, 4)) { \ + d = (TN *)&scratch; \ + } \ + for (size_t i = 0; i < n; ++i) { \ + d[HN(4 * i + 0)] = SAT(RSHR(s0[HW(i)], shift)); \ + d[HN(4 * i + 1)] = SAT(RSHR(s1[HW(i)], shift)); \ + d[HN(4 * i + 2)] = SAT(RSHR(s2[HW(i)], shift)); \ + d[HN(4 * i + 3)] = SAT(RSHR(s3[HW(i)], shift)); \ + } \ + if (d != vd) { \ + memcpy(vd, d, oprsz); \ + } \ +} + +SQRSHRN4(sme2_sqrshrn_sb, int32_t, int8_t, H4, H1, do_srshr, do_ssat_b) +SQRSHRN4(sme2_uqrshrn_sb, uint32_t, uint8_t, H4, H1, do_urshr, do_usat_b) +SQRSHRN4(sme2_sqrshrun_sb, int32_t, uint8_t, H4, H1, do_srshr, do_usat_b) + +SQRSHRN4(sme2_sqrshrn_dh, int64_t, int16_t, H8, H2, do_srshr, do_ssat_h) +SQRSHRN4(sme2_uqrshrn_dh, uint64_t, uint16_t, H8, H2, do_urshr, do_usat_h) +SQRSHRN4(sme2_sqrshrun_dh, int64_t, uint16_t, H8, H2, do_srshr, do_usat_h) + +#undef SQRSHRN4 + +/* Expand and convert */ +void HELPER(sme2_fcvt_w)(void *vd, void *vs, float_status *fpst, uint32_t desc) +{ + ARMVectorReg scratch; + size_t oprsz = simd_oprsz(desc); + size_t i, n = oprsz / 4; + float16 *s = vs; + float32 *d0 = vd; + float32 *d1 = vd + sizeof(ARMVectorReg); + + if (vectors_overlap(vd, 1, vs, 2)) { + s = memcpy(&scratch, s, oprsz); + } + + for (i = 0; i < n; ++i) { + d0[H4(i)] = sve_f16_to_f32(s[H2(i)], fpst); + } + for (i = 0; i < n; ++i) { + d1[H4(i)] = sve_f16_to_f32(s[H2(n + i)], fpst); + } +} + +#define UNPK(NAME, SREG, TW, TN, HW, HN) \ +void HELPER(NAME)(void *vd, void *vs, uint32_t desc) \ +{ \ + ARMVectorReg scratch[SREG]; \ + size_t oprsz = simd_oprsz(desc); \ + size_t n = oprsz / sizeof(TW); \ + if (vectors_overlap(vd, 2 * SREG, vs, SREG)) { \ + vs = memcpy(scratch, vs, sizeof(scratch)); \ + } \ + for (size_t r = 0; r < SREG; ++r) { \ + TN *s = vs + r * sizeof(ARMVectorReg); \ + for (size_t i = 0; i < 2; ++i) { \ + TW *d = vd + (2 * r + i) * sizeof(ARMVectorReg); \ + for (size_t e = 0; e < n; ++e) { \ + d[HW(e)] = s[HN(i * n + e)]; \ + } \ + } \ + } \ +} + +UNPK(sme2_sunpk2_bh, 1, int16_t, int8_t, H2, H1) +UNPK(sme2_sunpk2_hs, 1, int32_t, int16_t, H4, H2) +UNPK(sme2_sunpk2_sd, 1, int64_t, int32_t, H8, H4) + +UNPK(sme2_sunpk4_bh, 2, int16_t, int8_t, H2, H1) +UNPK(sme2_sunpk4_hs, 2, int32_t, int16_t, H4, H2) +UNPK(sme2_sunpk4_sd, 2, int64_t, int32_t, H8, H4) + +UNPK(sme2_uunpk2_bh, 1, uint16_t, uint8_t, H2, H1) +UNPK(sme2_uunpk2_hs, 1, uint32_t, uint16_t, H4, H2) +UNPK(sme2_uunpk2_sd, 1, uint64_t, uint32_t, H8, H4) + +UNPK(sme2_uunpk4_bh, 2, uint16_t, uint8_t, H2, H1) +UNPK(sme2_uunpk4_hs, 2, uint32_t, uint16_t, H4, H2) +UNPK(sme2_uunpk4_sd, 2, uint64_t, uint32_t, H8, H4) + +#undef UNPK + +/* Deinterleave and convert. */ +void HELPER(sme2_fcvtl)(void *vd, void *vs, float_status *fpst, uint32_t desc) +{ + size_t i, n = simd_oprsz(desc) / 4; + float16 *s = vs; + float32 *d0 = vd; + float32 *d1 = vd + sizeof(ARMVectorReg); + + for (i = 0; i < n; ++i) { + float32 v0 = sve_f16_to_f32(s[H2(i * 2 + 0)], fpst); + float32 v1 = sve_f16_to_f32(s[H2(i * 2 + 1)], fpst); + d0[H4(i)] = v0; + d1[H4(i)] = v1; + } +} + +void HELPER(sme2_scvtf)(void *vd, void *vs, float_status *fpst, uint32_t desc) +{ + size_t i, n = simd_oprsz(desc) / 4; + int32_t *d = vd; + float32 *s = vs; + + for (i = 0; i < n; ++i) { + d[i] = int32_to_float32(s[i], fpst); + } +} + +void HELPER(sme2_ucvtf)(void *vd, void *vs, float_status *fpst, uint32_t desc) +{ + size_t i, n = simd_oprsz(desc) / 4; + uint32_t *d = vd; + float32 *s = vs; + + for (i = 0; i < n; ++i) { + d[i] = uint32_to_float32(s[i], fpst); + } +} + +#define ZIP2(NAME, TYPE, H) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ +{ \ + ARMVectorReg scratch[2]; \ + size_t oprsz = simd_oprsz(desc); \ + size_t pairs = oprsz / (sizeof(TYPE) * 2); \ + TYPE *n = vn, *m = vm; \ + if (vectors_overlap(vd, 2, vn, 1)) { \ + n = memcpy(&scratch[0], vn, oprsz); \ + } \ + if (vectors_overlap(vd, 2, vm, 1)) { \ + m = memcpy(&scratch[1], vm, oprsz); \ + } \ + for (size_t r = 0; r < 2; ++r) { \ + TYPE *d = vd + r * sizeof(ARMVectorReg); \ + size_t base = r * pairs; \ + for (size_t p = 0; p < pairs; ++p) { \ + d[H(2 * p + 0)] = n[base + H(p)]; \ + d[H(2 * p + 1)] = m[base + H(p)]; \ + } \ + } \ +} + +ZIP2(sme2_zip2_b, uint8_t, H1) +ZIP2(sme2_zip2_h, uint16_t, H2) +ZIP2(sme2_zip2_s, uint32_t, H4) +ZIP2(sme2_zip2_d, uint64_t, ) +ZIP2(sme2_zip2_q, Int128, ) + +#undef ZIP2 + +#define ZIP4(NAME, TYPE, H) \ +void HELPER(NAME)(void *vd, void *vs, uint32_t desc) \ +{ \ + ARMVectorReg scratch[4]; \ + size_t oprsz = simd_oprsz(desc); \ + size_t quads = oprsz / (sizeof(TYPE) * 4); \ + TYPE *s0, *s1, *s2, *s3; \ + if (vs == vd) { \ + vs = memcpy(scratch, vs, sizeof(scratch)); \ + } \ + s0 = vs; \ + s1 = vs + sizeof(ARMVectorReg); \ + s2 = vs + 2 * sizeof(ARMVectorReg); \ + s3 = vs + 3 * sizeof(ARMVectorReg); \ + for (size_t r = 0; r < 4; ++r) { \ + TYPE *d = vd + r * sizeof(ARMVectorReg); \ + size_t base = r * quads; \ + for (size_t q = 0; q < quads; ++q) { \ + d[H(4 * q + 0)] = s0[base + H(q)]; \ + d[H(4 * q + 1)] = s1[base + H(q)]; \ + d[H(4 * q + 2)] = s2[base + H(q)]; \ + d[H(4 * q + 3)] = s3[base + H(q)]; \ + } \ + } \ +} + +ZIP4(sme2_zip4_b, uint8_t, H1) +ZIP4(sme2_zip4_h, uint16_t, H2) +ZIP4(sme2_zip4_s, uint32_t, H4) +ZIP4(sme2_zip4_d, uint64_t, ) +ZIP4(sme2_zip4_q, Int128, ) + +#undef ZIP4 + +#define UZP2(NAME, TYPE, H) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ +{ \ + ARMVectorReg scratch[2]; \ + size_t oprsz = simd_oprsz(desc); \ + size_t pairs = oprsz / (sizeof(TYPE) * 2); \ + TYPE *d0 = vd, *d1 = vd + sizeof(ARMVectorReg); \ + if (vectors_overlap(vd, 2, vn, 1)) { \ + vn = memcpy(&scratch[0], vn, oprsz); \ + } \ + if (vectors_overlap(vd, 2, vm, 1)) { \ + vm = memcpy(&scratch[1], vm, oprsz); \ + } \ + for (size_t r = 0; r < 2; ++r) { \ + TYPE *s = r ? vm : vn; \ + size_t base = r * pairs; \ + for (size_t p = 0; p < pairs; ++p) { \ + d0[base + H(p)] = s[H(2 * p + 0)]; \ + d1[base + H(p)] = s[H(2 * p + 1)]; \ + } \ + } \ +} + +UZP2(sme2_uzp2_b, uint8_t, H1) +UZP2(sme2_uzp2_h, uint16_t, H2) +UZP2(sme2_uzp2_s, uint32_t, H4) +UZP2(sme2_uzp2_d, uint64_t, ) +UZP2(sme2_uzp2_q, Int128, ) + +#undef UZP2 + +#define UZP4(NAME, TYPE, H) \ +void HELPER(NAME)(void *vd, void *vs, uint32_t desc) \ +{ \ + ARMVectorReg scratch[4]; \ + size_t oprsz = simd_oprsz(desc); \ + size_t quads = oprsz / (sizeof(TYPE) * 4); \ + TYPE *d0, *d1, *d2, *d3; \ + if (vs == vd) { \ + vs = memcpy(scratch, vs, sizeof(scratch)); \ + } \ + d0 = vd; \ + d1 = vd + sizeof(ARMVectorReg); \ + d2 = vd + 2 * sizeof(ARMVectorReg); \ + d3 = vd + 3 * sizeof(ARMVectorReg); \ + for (size_t r = 0; r < 4; ++r) { \ + TYPE *s = vs + r * sizeof(ARMVectorReg); \ + size_t base = r * quads; \ + for (size_t q = 0; q < quads; ++q) { \ + d0[base + H(q)] = s[H(4 * q + 0)]; \ + d1[base + H(q)] = s[H(4 * q + 1)]; \ + d2[base + H(q)] = s[H(4 * q + 2)]; \ + d3[base + H(q)] = s[H(4 * q + 3)]; \ + } \ + } \ +} + +UZP4(sme2_uzp4_b, uint8_t, H1) +UZP4(sme2_uzp4_h, uint16_t, H2) +UZP4(sme2_uzp4_s, uint32_t, H4) +UZP4(sme2_uzp4_d, uint64_t, ) +UZP4(sme2_uzp4_q, Int128, ) + +#undef UZP4 + +#define ICLAMP(NAME, TYPE, H) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ +{ \ + size_t stride = sizeof(ARMVectorReg) / sizeof(TYPE); \ + size_t elements = simd_oprsz(desc) / sizeof(TYPE); \ + size_t nreg = simd_data(desc); \ + TYPE *d = vd, *n = vn, *m = vm; \ + for (size_t e = 0; e < elements; e++) { \ + TYPE nn = n[H(e)], mm = m[H(e)]; \ + for (size_t r = 0; r < nreg; r++) { \ + TYPE *dd = &d[r * stride + H(e)]; \ + *dd = MIN(MAX(*dd, nn), mm); \ + } \ + } \ +} + +ICLAMP(sme2_sclamp_b, int8_t, H1) +ICLAMP(sme2_sclamp_h, int16_t, H2) +ICLAMP(sme2_sclamp_s, int32_t, H4) +ICLAMP(sme2_sclamp_d, int64_t, H8) + +ICLAMP(sme2_uclamp_b, uint8_t, H1) +ICLAMP(sme2_uclamp_h, uint16_t, H2) +ICLAMP(sme2_uclamp_s, uint32_t, H4) +ICLAMP(sme2_uclamp_d, uint64_t, H8) + +#undef ICLAMP + +/* + * Note the argument ordering to minnum and maxnum must match + * the ARM pseudocode so that NaNs are propagated properly. + */ +#define FCLAMP(NAME, TYPE, H) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, \ + float_status *fpst, uint32_t desc) \ +{ \ + size_t stride = sizeof(ARMVectorReg) / sizeof(TYPE); \ + size_t elements = simd_oprsz(desc) / sizeof(TYPE); \ + size_t nreg = simd_data(desc); \ + TYPE *d = vd, *n = vn, *m = vm; \ + for (size_t e = 0; e < elements; e++) { \ + TYPE nn = n[H(e)], mm = m[H(e)]; \ + for (size_t r = 0; r < nreg; r++) { \ + TYPE *dd = &d[r * stride + H(e)]; \ + *dd = TYPE##_minnum(TYPE##_maxnum(nn, *dd, fpst), mm, fpst); \ + } \ + } \ +} + +FCLAMP(sme2_fclamp_h, float16, H2) +FCLAMP(sme2_fclamp_s, float32, H4) +FCLAMP(sme2_fclamp_d, float64, H8) +FCLAMP(sme2_bfclamp, bfloat16, H2) + +#undef FCLAMP + +void HELPER(sme2_sel_b)(void *vd, void *vn, void *vm, + uint32_t png, uint32_t desc) +{ + int vl = simd_oprsz(desc); + int nreg = simd_data(desc); + int elements = vl / sizeof(uint8_t); + DecodeCounter p = decode_counter(png, vl, MO_8); + + if (p.lg2_stride == 0) { + if (p.invert) { + for (int r = 0; r < nreg; r++) { + uint8_t *d = vd + r * sizeof(ARMVectorReg); + uint8_t *n = vn + r * sizeof(ARMVectorReg); + uint8_t *m = vm + r * sizeof(ARMVectorReg); + int split = p.count - r * elements; + + if (split <= 0) { + memcpy(d, n, vl); /* all true */ + } else if (elements <= split) { + memcpy(d, m, vl); /* all false */ + } else { + for (int e = 0; e < split; e++) { + d[H1(e)] = m[H1(e)]; + } + for (int e = split; e < elements; e++) { + d[H1(e)] = n[H1(e)]; + } + } + } + } else { + for (int r = 0; r < nreg; r++) { + uint8_t *d = vd + r * sizeof(ARMVectorReg); + uint8_t *n = vn + r * sizeof(ARMVectorReg); + uint8_t *m = vm + r * sizeof(ARMVectorReg); + int split = p.count - r * elements; + + if (split <= 0) { + memcpy(d, m, vl); /* all false */ + } else if (elements <= split) { + memcpy(d, n, vl); /* all true */ + } else { + for (int e = 0; e < split; e++) { + d[H1(e)] = n[H1(e)]; + } + for (int e = split; e < elements; e++) { + d[H1(e)] = m[H1(e)]; + } + } + } + } + } else { + int estride = 1 << p.lg2_stride; + if (p.invert) { + for (int r = 0; r < nreg; r++) { + uint8_t *d = vd + r * sizeof(ARMVectorReg); + uint8_t *n = vn + r * sizeof(ARMVectorReg); + uint8_t *m = vm + r * sizeof(ARMVectorReg); + int split = p.count - r * elements; + int e = 0; + + for (; e < MIN(split, elements); e++) { + d[H1(e)] = m[H1(e)]; + } + for (; e < elements; e += estride) { + d[H1(e)] = n[H1(e)]; + for (int i = 1; i < estride; i++) { + d[H1(e + i)] = m[H1(e + i)]; + } + } + } + } else { + for (int r = 0; r < nreg; r++) { + uint8_t *d = vd + r * sizeof(ARMVectorReg); + uint8_t *n = vn + r * sizeof(ARMVectorReg); + uint8_t *m = vm + r * sizeof(ARMVectorReg); + int split = p.count - r * elements; + int e = 0; + + for (; e < MIN(split, elements); e += estride) { + d[H1(e)] = n[H1(e)]; + for (int i = 1; i < estride; i++) { + d[H1(e + i)] = m[H1(e + i)]; + } + } + for (; e < elements; e++) { + d[H1(e)] = m[H1(e)]; + } + } + } + } +} + +void HELPER(sme2_sel_h)(void *vd, void *vn, void *vm, + uint32_t png, uint32_t desc) +{ + int vl = simd_oprsz(desc); + int nreg = simd_data(desc); + int elements = vl / sizeof(uint16_t); + DecodeCounter p = decode_counter(png, vl, MO_16); + + if (p.lg2_stride == 0) { + if (p.invert) { + for (int r = 0; r < nreg; r++) { + uint16_t *d = vd + r * sizeof(ARMVectorReg); + uint16_t *n = vn + r * sizeof(ARMVectorReg); + uint16_t *m = vm + r * sizeof(ARMVectorReg); + int split = p.count - r * elements; + + if (split <= 0) { + memcpy(d, n, vl); /* all true */ + } else if (elements <= split) { + memcpy(d, m, vl); /* all false */ + } else { + for (int e = 0; e < split; e++) { + d[H2(e)] = m[H2(e)]; + } + for (int e = split; e < elements; e++) { + d[H2(e)] = n[H2(e)]; + } + } + } + } else { + for (int r = 0; r < nreg; r++) { + uint16_t *d = vd + r * sizeof(ARMVectorReg); + uint16_t *n = vn + r * sizeof(ARMVectorReg); + uint16_t *m = vm + r * sizeof(ARMVectorReg); + int split = p.count - r * elements; + + if (split <= 0) { + memcpy(d, m, vl); /* all false */ + } else if (elements <= split) { + memcpy(d, n, vl); /* all true */ + } else { + for (int e = 0; e < split; e++) { + d[H2(e)] = n[H2(e)]; + } + for (int e = split; e < elements; e++) { + d[H2(e)] = m[H2(e)]; + } + } + } + } + } else { + int estride = 1 << p.lg2_stride; + if (p.invert) { + for (int r = 0; r < nreg; r++) { + uint16_t *d = vd + r * sizeof(ARMVectorReg); + uint16_t *n = vn + r * sizeof(ARMVectorReg); + uint16_t *m = vm + r * sizeof(ARMVectorReg); + int split = p.count - r * elements; + int e = 0; + + for (; e < MIN(split, elements); e++) { + d[H2(e)] = m[H2(e)]; + } + for (; e < elements; e += estride) { + d[H2(e)] = n[H2(e)]; + for (int i = 1; i < estride; i++) { + d[H2(e + i)] = m[H2(e + i)]; + } + } + } + } else { + for (int r = 0; r < nreg; r++) { + uint16_t *d = vd + r * sizeof(ARMVectorReg); + uint16_t *n = vn + r * sizeof(ARMVectorReg); + uint16_t *m = vm + r * sizeof(ARMVectorReg); + int split = p.count - r * elements; + int e = 0; + + for (; e < MIN(split, elements); e += estride) { + d[H2(e)] = n[H2(e)]; + for (int i = 1; i < estride; i++) { + d[H2(e + i)] = m[H2(e + i)]; + } + } + for (; e < elements; e++) { + d[H2(e)] = m[H2(e)]; + } + } + } + } +} -DEF_IMOPH(smopa, d) -DEF_IMOPH(umopa, d) -DEF_IMOPH(sumopa, d) -DEF_IMOPH(usmopa, d) +void HELPER(sme2_sel_s)(void *vd, void *vn, void *vm, + uint32_t png, uint32_t desc) +{ + int vl = simd_oprsz(desc); + int nreg = simd_data(desc); + int elements = vl / sizeof(uint32_t); + DecodeCounter p = decode_counter(png, vl, MO_32); + + if (p.lg2_stride == 0) { + if (p.invert) { + for (int r = 0; r < nreg; r++) { + uint32_t *d = vd + r * sizeof(ARMVectorReg); + uint32_t *n = vn + r * sizeof(ARMVectorReg); + uint32_t *m = vm + r * sizeof(ARMVectorReg); + int split = p.count - r * elements; + + if (split <= 0) { + memcpy(d, n, vl); /* all true */ + } else if (elements <= split) { + memcpy(d, m, vl); /* all false */ + } else { + for (int e = 0; e < split; e++) { + d[H4(e)] = m[H4(e)]; + } + for (int e = split; e < elements; e++) { + d[H4(e)] = n[H4(e)]; + } + } + } + } else { + for (int r = 0; r < nreg; r++) { + uint32_t *d = vd + r * sizeof(ARMVectorReg); + uint32_t *n = vn + r * sizeof(ARMVectorReg); + uint32_t *m = vm + r * sizeof(ARMVectorReg); + int split = p.count - r * elements; + + if (split <= 0) { + memcpy(d, m, vl); /* all false */ + } else if (elements <= split) { + memcpy(d, n, vl); /* all true */ + } else { + for (int e = 0; e < split; e++) { + d[H4(e)] = n[H4(e)]; + } + for (int e = split; e < elements; e++) { + d[H4(e)] = m[H4(e)]; + } + } + } + } + } else { + /* p.esz must be MO_64, so stride must be 2. */ + if (p.invert) { + for (int r = 0; r < nreg; r++) { + uint32_t *d = vd + r * sizeof(ARMVectorReg); + uint32_t *n = vn + r * sizeof(ARMVectorReg); + uint32_t *m = vm + r * sizeof(ARMVectorReg); + int split = p.count - r * elements; + int e = 0; + + for (; e < MIN(split, elements); e++) { + d[H4(e)] = m[H4(e)]; + } + for (; e < elements; e += 2) { + d[H4(e)] = n[H4(e)]; + d[H4(e + 1)] = m[H4(e + 1)]; + } + } + } else { + for (int r = 0; r < nreg; r++) { + uint32_t *d = vd + r * sizeof(ARMVectorReg); + uint32_t *n = vn + r * sizeof(ARMVectorReg); + uint32_t *m = vm + r * sizeof(ARMVectorReg); + int split = p.count - r * elements; + int e = 0; + + for (; e < MIN(split, elements); e += 2) { + d[H4(e)] = n[H4(e)]; + d[H4(e + 1)] = m[H4(e + 1)]; + } + for (; e < elements; e++) { + d[H4(e)] = m[H4(e)]; + } + } + } + } +} + +void HELPER(sme2_sel_d)(void *vd, void *vn, void *vm, + uint32_t png, uint32_t desc) +{ + int vl = simd_oprsz(desc); + int nreg = simd_data(desc); + int elements = vl / sizeof(uint64_t); + DecodeCounter p = decode_counter(png, vl, MO_64); + + if (p.invert) { + for (int r = 0; r < nreg; r++) { + uint64_t *d = vd + r * sizeof(ARMVectorReg); + uint64_t *n = vn + r * sizeof(ARMVectorReg); + uint64_t *m = vm + r * sizeof(ARMVectorReg); + int split = p.count - r * elements; + + if (split <= 0) { + memcpy(d, n, vl); /* all true */ + } else if (elements <= split) { + memcpy(d, m, vl); /* all false */ + } else { + memcpy(d, m, split * sizeof(uint64_t)); + memcpy(d + split, n + split, + (elements - split) * sizeof(uint64_t)); + } + } + } else { + for (int r = 0; r < nreg; r++) { + uint64_t *d = vd + r * sizeof(ARMVectorReg); + uint64_t *n = vn + r * sizeof(ARMVectorReg); + uint64_t *m = vm + r * sizeof(ARMVectorReg); + int split = p.count - r * elements; + + if (split <= 0) { + memcpy(d, m, vl); /* all false */ + } else if (elements <= split) { + memcpy(d, n, vl); /* all true */ + } else { + memcpy(d, n, split * sizeof(uint64_t)); + memcpy(d + split, m + split, + (elements - split) * sizeof(uint64_t)); + } + } + } +} diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode index 04b6fcc..2efd5f5 100644 --- a/target/arm/tcg/sve.decode +++ b/target/arm/tcg/sve.decode @@ -30,6 +30,7 @@ %size_23 23:2 %dtype_23_13 23:2 13:2 %index3_22_19 22:1 19:2 +%index3_22_17 22:1 17:2 %index3_19_11 19:2 11:1 %index2_20_11 20:1 11:1 @@ -57,6 +58,11 @@ # as propagated via the MOVPRFX instruction. %reg_movprfx 0:5 +%rn_ax2 6:4 !function=times_2 + +%pnd 0:3 !function=plus_8 +%pnn 5:3 !function=plus_8 + ########################################################################### # Named attribute sets. These are used to make nice(er) names # when creating helpers common to those for the individual @@ -102,6 +108,7 @@ # Two operand @pd_pn ........ esz:2 .. .... ....... rn:4 . rd:4 &rr_esz @rd_rn ........ esz:2 ...... ...... rn:5 rd:5 &rr_esz +@rd_rnx2 ........ ... ..... ...... ..... rd:5 &rr_esz rn=%rn_ax2 # Two operand with governing predicate, flags setting @pd_pg_pn_s ........ . s:1 ...... .. pg:4 . rn:4 . rd:4 &rpr_s @@ -131,11 +138,11 @@ @rda_rn_rm ........ esz:2 . rm:5 ... ... rn:5 rd:5 \ &rrrr_esz ra=%reg_movprfx -# Four operand with unused vector element size -@rda_rn_rm_e0 ........ ... rm:5 ... ... rn:5 rd:5 \ - &rrrr_esz esz=0 ra=%reg_movprfx -@rdn_ra_rm_e0 ........ ... rm:5 ... ... ra:5 rd:5 \ - &rrrr_esz esz=0 rn=%reg_movprfx +# Four operand with explicit vector element size +@rda_rn_rm_ex ........ ... rm:5 ... ... rn:5 rd:5 \ + &rrrr_esz ra=%reg_movprfx +@rdn_ra_rm_ex ........ ... rm:5 ... ... ra:5 rd:5 \ + &rrrr_esz rn=%reg_movprfx # Three operand with "memory" size, aka immediate left shift @rd_rn_msz_rm ........ ... rm:5 .... imm:2 rn:5 rd:5 &rrri @@ -222,6 +229,9 @@ @rprr_load_dt ....... dtype:4 rm:5 ... pg:3 rn:5 rd:5 &rprr_load @rpri_load_dt ....... dtype:4 . imm:s4 ... pg:3 rn:5 rd:5 &rpri_load +@rprr_load ....... .... rm:5 ... pg:3 rn:5 rd:5 &rprr_load +@rpri_load ....... .... . imm:s4 ... pg:3 rn:5 rd:5 &rpri_load + @rprr_load_msz ....... .... rm:5 ... pg:3 rn:5 rd:5 \ &rprr_load dtype=%msz_dtype @rpri_load_msz ....... .... . imm:s4 ... pg:3 rn:5 rd:5 \ @@ -245,7 +255,7 @@ # Stores; user must fill in ESZ, MSZ, NREG as needed. @rprr_store ....... .. .. rm:5 ... pg:3 rn:5 rd:5 &rprr_store -@rpri_store_msz ....... msz:2 .. . imm:s4 ... pg:3 rn:5 rd:5 &rpri_store +@rpri_store ....... .. .. . imm:s4 ... pg:3 rn:5 rd:5 &rpri_store @rprr_store_esz_n0 ....... .. esz:2 rm:5 ... pg:3 rn:5 rd:5 \ &rprr_store nreg=0 @rprr_scatter_store ....... msz:2 .. rm:5 ... pg:3 rn:5 rd:5 \ @@ -320,6 +330,11 @@ ORV 00000100 .. 011 000 001 ... ..... ..... @rd_pg_rn EORV 00000100 .. 011 001 001 ... ..... ..... @rd_pg_rn ANDV 00000100 .. 011 010 001 ... ..... ..... @rd_pg_rn +# SVE2.1 bitwise logical reduction (quadwords) +ORQV 00000100 .. 011 100 001 ... ..... ..... @rd_pg_rn +EORQV 00000100 .. 011 101 001 ... ..... ..... @rd_pg_rn +ANDQV 00000100 .. 011 110 001 ... ..... ..... @rd_pg_rn + # SVE constructive prefix (predicated) MOVPRFX_z 00000100 .. 010 000 001 ... ..... ..... @rd_pg_rn MOVPRFX_m 00000100 .. 010 001 001 ... ..... ..... @rd_pg_rn @@ -335,6 +350,13 @@ UMAXV 00000100 .. 001 001 001 ... ..... ..... @rd_pg_rn SMINV 00000100 .. 001 010 001 ... ..... ..... @rd_pg_rn UMINV 00000100 .. 001 011 001 ... ..... ..... @rd_pg_rn +# SVE2.1 segment reduction +ADDQV 00000100 .. 000 101 001 ... ..... ..... @rd_pg_rn +SMAXQV 00000100 .. 001 100 001 ... ..... ..... @rd_pg_rn +SMINQV 00000100 .. 001 110 001 ... ..... ..... @rd_pg_rn +UMAXQV 00000100 .. 001 101 001 ... ..... ..... @rd_pg_rn +UMINQV 00000100 .. 001 111 001 ... ..... ..... @rd_pg_rn + ### SVE Shift by Immediate - Predicated Group # SVE bitwise shift by immediate (predicated) @@ -428,12 +450,12 @@ XAR 00000100 .. 1 ..... 001 101 rm:5 rd:5 &rrri_esz \ rn=%reg_movprfx esz=%tszimm16_esz imm=%tszimm16_shr # SVE2 bitwise ternary operations -EOR3 00000100 00 1 ..... 001 110 ..... ..... @rdn_ra_rm_e0 -BSL 00000100 00 1 ..... 001 111 ..... ..... @rdn_ra_rm_e0 -BCAX 00000100 01 1 ..... 001 110 ..... ..... @rdn_ra_rm_e0 -BSL1N 00000100 01 1 ..... 001 111 ..... ..... @rdn_ra_rm_e0 -BSL2N 00000100 10 1 ..... 001 111 ..... ..... @rdn_ra_rm_e0 -NBSL 00000100 11 1 ..... 001 111 ..... ..... @rdn_ra_rm_e0 +EOR3 00000100 00 1 ..... 001 110 ..... ..... @rdn_ra_rm_ex esz=0 +BSL 00000100 00 1 ..... 001 111 ..... ..... @rdn_ra_rm_ex esz=0 +BCAX 00000100 01 1 ..... 001 110 ..... ..... @rdn_ra_rm_ex esz=0 +BSL1N 00000100 01 1 ..... 001 111 ..... ..... @rdn_ra_rm_ex esz=0 +BSL2N 00000100 10 1 ..... 001 111 ..... ..... @rdn_ra_rm_ex esz=0 +NBSL 00000100 11 1 ..... 001 111 ..... ..... @rdn_ra_rm_ex esz=0 ### SVE Index Generation Group @@ -559,6 +581,14 @@ DUP_s 00000101 .. 1 00000 001110 ..... ..... @rd_rn DUP_x 00000101 .. 1 ..... 001000 rn:5 rd:5 \ &rri imm=%imm7_22_16 +# SVE Permute Vector - one source quadwords +DUPQ 00000101 001 imm:4 1 001001 rn:5 rd:5 &rri_esz esz=0 +DUPQ 00000101 001 imm:3 10 001001 rn:5 rd:5 &rri_esz esz=1 +DUPQ 00000101 001 imm:2 100 001001 rn:5 rd:5 &rri_esz esz=2 +DUPQ 00000101 001 imm:1 1000 001001 rn:5 rd:5 &rri_esz esz=3 + +EXTQ 00000101 0110 imm:4 001001 rn:5 rd:5 &rri + # SVE insert SIMD&FP scalar register INSR_f 00000101 .. 1 10100 001110 ..... ..... @rdn_rm @@ -568,6 +598,22 @@ INSR_r 00000101 .. 1 00100 001110 ..... ..... @rdn_rm # SVE reverse vector elements REV_v 00000101 .. 1 11000 001110 ..... ..... @rd_rn +# SVE move predicate to/from vector + +PMOV_pv 00000101 00 101 01 0001110 rn:5 0 rd:4 \ + &rri_esz esz=0 imm=0 +PMOV_pv 00000101 00 101 1 imm:1 0001110 rn:5 0 rd:4 &rri_esz esz=1 +PMOV_pv 00000101 01 101 imm:2 0001110 rn:5 0 rd:4 &rri_esz esz=2 +PMOV_pv 00000101 1. 101 .. 0001110 rn:5 0 rd:4 \ + &rri_esz esz=3 imm=%index3_22_17 + +PMOV_vp 00000101 00 101 01 1001110 0 rn:4 rd:5 \ + &rri_esz esz=0 imm=0 +PMOV_vp 00000101 00 101 1 imm:1 1001110 0 rn:4 rd:5 &rri_esz esz=1 +PMOV_vp 00000101 01 101 imm:2 1001110 0 rn:4 rd:5 &rri_esz esz=2 +PMOV_vp 00000101 1. 101 .. 1001110 0 rn:4 rd:5 \ + &rri_esz esz=3 imm=%index3_22_17 + # SVE vector table lookup TBL 00000101 .. 1 ..... 001100 ..... ..... @rd_rn_rm @@ -614,6 +660,15 @@ UZP2_q 00000101 10 1 ..... 000 011 ..... ..... @rd_rn_rm_e0 TRN1_q 00000101 10 1 ..... 000 110 ..... ..... @rd_rn_rm_e0 TRN2_q 00000101 10 1 ..... 000 111 ..... ..... @rd_rn_rm_e0 +# SVE2.1 permute vector elements (quadwords) +ZIPQ1 01000100 .. 0 ..... 111 000 ..... ..... @rd_rn_rm +ZIPQ2 01000100 .. 0 ..... 111 001 ..... ..... @rd_rn_rm +UZPQ1 01000100 .. 0 ..... 111 010 ..... ..... @rd_rn_rm +UZPQ2 01000100 .. 0 ..... 111 011 ..... ..... @rd_rn_rm + +TBLQ 01000100 .. 0 ..... 111 110 ..... ..... @rd_rn_rm +TBXQ 00000101 .. 1 ..... 001 101 ..... ..... @rd_rn_rm + ### SVE Permute - Predicated Group # SVE compress active elements @@ -725,6 +780,7 @@ PTEST 00100101 01 010000 11 pg:4 0 rn:4 0 0000 # SVE predicate initialize PTRUE 00100101 esz:2 01100 s:1 111000 pat:5 0 rd:4 +PTRUE_cnt 00100101 esz:2 1000000111100000010 ... rd=%pnd # SVE initialize FFR SETFFR 00100101 0010 1100 1001 0000 0000 0000 @@ -765,7 +821,8 @@ BRKN 00100101 0. 01100001 .... 0 .... 0 .... @pd_pg_pn_s ### SVE Predicate Count Group # SVE predicate count -CNTP 00100101 .. 100 000 10 .... 0 .... ..... @rd_pg4_pn +CNTP 00100101 .. 100 000 10 .... 0 .... ..... @rd_pg4_pn +CNTP_c 00100101 esz:2 100 000 10 000 vl:1 1 rn:4 rd:5 # SVE inc/dec register by predicate count INCDECP_r 00100101 .. 10110 d:1 10001 00 .... ..... @incdec_pred u=1 @@ -786,11 +843,35 @@ SINCDECP_z 00100101 .. 1010 d:1 u:1 10000 00 .... ..... @incdec2_pred CTERM 00100101 1 sf:1 1 rm:5 001000 rn:5 ne:1 0000 # SVE integer compare scalar count and limit -WHILE 00100101 esz:2 1 rm:5 000 sf:1 u:1 lt:1 rn:5 eq:1 rd:4 +&while esz rd rn rm sf u eq +WHILE_lt 00100101 esz:2 1 rm:5 000 sf:1 u:1 1 rn:5 eq:1 rd:4 &while +WHILE_gt 00100101 esz:2 1 rm:5 000 sf:1 u:1 0 rn:5 eq:1 rd:4 &while # SVE2 pointer conflict compare WHILE_ptr 00100101 esz:2 1 rm:5 001 100 rn:5 rw:1 rd:4 +# SVE2.1 predicate pair +%pd_pair 1:3 !function=times_2 +@while_pair ........ esz:2 . rm:5 .... u:1 . rn:5 . ... eq:1 \ + &while rd=%pd_pair sf=1 + +WHILE_lt_pair 00100101 .. 1 ..... 0101 . 1 ..... 1 ... . @while_pair +WHILE_gt_pair 00100101 .. 1 ..... 0101 . 0 ..... 1 ... . @while_pair + +# SVE2.1 predicate as count +@while_cnt ........ esz:2 . rm:5 .... u:1 . rn:5 . eq:1 ... \ + &while rd=%pnd sf=1 + +WHILE_lt_cnt2 00100101 .. 1 ..... 0100 . 1 ..... 1 . ... @while_cnt +WHILE_lt_cnt4 00100101 .. 1 ..... 0110 . 1 ..... 1 . ... @while_cnt +WHILE_gt_cnt2 00100101 .. 1 ..... 0100 . 0 ..... 1 . ... @while_cnt +WHILE_gt_cnt4 00100101 .. 1 ..... 0110 . 0 ..... 1 . ... @while_cnt + +# SVE2.1 extract mask predicate from predicate-as-counter +&pext rd rn esz imm +PEXT_1 00100101 esz:2 1 00000 0111 00 imm:2 ... 1 rd:4 &pext rn=%pnn +PEXT_2 00100101 esz:2 1 00000 0111 010 imm:1 ... 1 rd:4 &pext rn=%pnn + ### SVE Integer Wide Immediate - Unpredicated Group # SVE broadcast floating-point immediate (unpredicated) @@ -851,10 +932,13 @@ CDOT_zzzz 01000100 esz:2 0 rm:5 0001 rot:2 rn:5 rd:5 ra=%reg_movprfx #### SVE Multiply - Indexed # SVE integer dot product (indexed) -SDOT_zzxw_s 01000100 10 1 ..... 000000 ..... ..... @rrxr_2 esz=2 -SDOT_zzxw_d 01000100 11 1 ..... 000000 ..... ..... @rrxr_1 esz=3 -UDOT_zzxw_s 01000100 10 1 ..... 000001 ..... ..... @rrxr_2 esz=2 -UDOT_zzxw_d 01000100 11 1 ..... 000001 ..... ..... @rrxr_1 esz=3 +SDOT_zzxw_4s 01000100 10 1 ..... 000000 ..... ..... @rrxr_2 esz=2 +SDOT_zzxw_4d 01000100 11 1 ..... 000000 ..... ..... @rrxr_1 esz=3 +UDOT_zzxw_4s 01000100 10 1 ..... 000001 ..... ..... @rrxr_2 esz=2 +UDOT_zzxw_4d 01000100 11 1 ..... 000001 ..... ..... @rrxr_1 esz=3 + +SDOT_zzxw_2s 01000100 10 0 ..... 110010 ..... ..... @rrxr_2 esz=2 +UDOT_zzxw_2s 01000100 10 0 ..... 110011 ..... ..... @rrxr_2 esz=2 # SVE2 integer multiply-add (indexed) MLA_zzxz_h 01000100 0. 1 ..... 000010 ..... ..... @rrxr_3 esz=1 @@ -873,8 +957,8 @@ SQRDMLSH_zzxz_s 01000100 10 1 ..... 000101 ..... ..... @rrxr_2 esz=2 SQRDMLSH_zzxz_d 01000100 11 1 ..... 000101 ..... ..... @rrxr_1 esz=3 # SVE mixed sign dot product (indexed) -USDOT_zzxw_s 01000100 10 1 ..... 000110 ..... ..... @rrxr_2 esz=2 -SUDOT_zzxw_s 01000100 10 1 ..... 000111 ..... ..... @rrxr_2 esz=2 +USDOT_zzxw_4s 01000100 10 1 ..... 000110 ..... ..... @rrxr_2 esz=2 +SUDOT_zzxw_4s 01000100 10 1 ..... 000111 ..... ..... @rrxr_2 esz=2 # SVE2 saturating multiply-add (indexed) SQDMLALB_zzxw_s 01000100 10 1 ..... 0010.0 ..... ..... @rrxr_3a esz=2 @@ -990,6 +1074,14 @@ FMINNMV 01100101 .. 000 101 001 ... ..... ..... @rd_pg_rn FMAXV 01100101 .. 000 110 001 ... ..... ..... @rd_pg_rn FMINV 01100101 .. 000 111 001 ... ..... ..... @rd_pg_rn +### SVE FP recursive reduction (quadwords) + +FADDQV 01100100 .. 010 000 101 ... ..... ..... @rd_pg_rn +FMAXNMQV 01100100 .. 010 100 101 ... ..... ..... @rd_pg_rn +FMINNMQV 01100100 .. 010 101 101 ... ..... ..... @rd_pg_rn +FMAXQV 01100100 .. 010 110 101 ... ..... ..... @rd_pg_rn +FMINQV 01100100 .. 010 111 101 ... ..... ..... @rd_pg_rn + ## SVE Floating Point Unary Operations - Unpredicated Group FRECPE 01100101 .. 001 110 001100 ..... ..... @rd_rn @@ -1151,12 +1243,24 @@ LD1_zpiz 1000010 .. 01 ..... 1.. ... ..... ..... \ # SVE contiguous load (scalar plus scalar) LD_zprr 1010010 .... ..... 010 ... ..... ..... @rprr_load_dt nreg=0 +# LD1W (128-bit element) +LD_zprr 1010010 1000 rm:5 100 pg:3 rn:5 rd:5 \ + &rprr_load dtype=16 nreg=0 +# LD1D (128-bit element) +LD_zprr 1010010 1100 rm:5 100 pg:3 rn:5 rd:5 \ + &rprr_load dtype=17 nreg=0 # SVE contiguous first-fault load (scalar plus scalar) LDFF1_zprr 1010010 .... ..... 011 ... ..... ..... @rprr_load_dt nreg=0 # SVE contiguous load (scalar plus immediate) LD_zpri 1010010 .... 0.... 101 ... ..... ..... @rpri_load_dt nreg=0 +# LD1W (128-bit element) +LD_zpri 1010010 1000 1 imm:s4 001 pg:3 rn:5 rd:5 \ + &rpri_load dtype=16 nreg=0 +# LD1D (128-bit element) +LD_zpri 1010010 1100 1 imm:s4 001 pg:3 rn:5 rd:5 \ + &rpri_load dtype=17 nreg=0 # SVE contiguous non-fault load (scalar plus immediate) LDNF1_zpri 1010010 .... 1.... 101 ... ..... ..... @rpri_load_dt nreg=0 @@ -1166,12 +1270,26 @@ LDNF1_zpri 1010010 .... 1.... 101 ... ..... ..... @rpri_load_dt nreg=0 # SVE load multiple structures (scalar plus scalar) # LD2B, LD2H, LD2W, LD2D; etc. LD_zprr 1010010 .. nreg:2 ..... 110 ... ..... ..... @rprr_load_msz +# LD[234]Q +LD_zprr 1010010 01 01 ..... 100 ... ..... ..... \ + @rprr_load dtype=18 nreg=1 +LD_zprr 1010010 10 01 ..... 100 ... ..... ..... \ + @rprr_load dtype=18 nreg=2 +LD_zprr 1010010 11 01 ..... 100 ... ..... ..... \ + @rprr_load dtype=18 nreg=3 # SVE contiguous non-temporal load (scalar plus immediate) # LDNT1B, LDNT1H, LDNT1W, LDNT1D # SVE load multiple structures (scalar plus immediate) # LD2B, LD2H, LD2W, LD2D; etc. LD_zpri 1010010 .. nreg:2 0.... 111 ... ..... ..... @rpri_load_msz +# LD[234]Q +LD_zpri 1010010 01 001 .... 111 ... ..... ..... \ + @rpri_load dtype=18 nreg=1 +LD_zpri 1010010 10 001 .... 111 ... ..... ..... \ + @rpri_load dtype=18 nreg=2 +LD_zpri 1010010 11 001 .... 111 ... ..... ..... \ + @rpri_load dtype=18 nreg=3 # SVE load and broadcast quadword (scalar plus scalar) LD1RQ_zprr 1010010 .. 00 ..... 000 ... ..... ..... \ @@ -1222,6 +1340,10 @@ LD1_zprz 1100010 10 1. ..... 1.. ... ..... ..... \ LD1_zprz 1100010 11 1. ..... 11. ... ..... ..... \ @rprr_g_load_sc esz=3 msz=3 u=1 +# LD1Q +LD1_zprz 1100 0100 000 rm:5 101 pg:3 rn:5 rd:5 \ + &rprr_gather_load u=0 ff=0 xs=2 esz=4 msz=4 scale=0 + # SVE 64-bit gather load (vector plus immediate) LD1_zpiz 1100010 .. 01 ..... 1.. ... ..... ..... \ @rpri_g_load esz=3 @@ -1245,8 +1367,20 @@ STR_zri 1110010 11 0. ..... 010 ... ..... ..... @rd_rn_i9 # SVE contiguous store (scalar plus immediate) # ST1B, ST1H, ST1W, ST1D; require msz <= esz -ST_zpri 1110010 .. esz:2 0.... 111 ... ..... ..... \ - @rpri_store_msz nreg=0 +ST_zpri 1110010 00 esz:2 0.... 111 ... ..... ..... \ + @rpri_store msz=0 nreg=0 +ST_zpri 1110010 01 esz:2 0.... 111 ... ..... ..... \ + @rpri_store msz=1 nreg=0 +ST_zpri 1110010 10 10 0.... 111 ... ..... ..... \ + @rpri_store msz=2 esz=2 nreg=0 +ST_zpri 1110010 10 11 0.... 111 ... ..... ..... \ + @rpri_store msz=2 esz=3 nreg=0 +ST_zpri 1110010 11 11 0.... 111 ... ..... ..... \ + @rpri_store msz=3 esz=3 nreg=0 +ST_zpri 1110010 10 00 0.... 111 ... ..... ..... \ + @rpri_store msz=2 esz=4 nreg=0 +ST_zpri 1110010 11 10 0.... 111 ... ..... ..... \ + @rpri_store msz=3 esz=4 nreg=0 # SVE contiguous store (scalar plus scalar) # ST1B, ST1H, ST1W, ST1D; require msz <= esz @@ -1255,20 +1389,40 @@ ST_zprr 1110010 00 .. ..... 010 ... ..... ..... \ @rprr_store_esz_n0 msz=0 ST_zprr 1110010 01 .. ..... 010 ... ..... ..... \ @rprr_store_esz_n0 msz=1 -ST_zprr 1110010 10 .. ..... 010 ... ..... ..... \ - @rprr_store_esz_n0 msz=2 +ST_zprr 1110010 10 10 ..... 010 ... ..... ..... \ + @rprr_store msz=2 esz=2 nreg=0 +ST_zprr 1110010 10 11 ..... 010 ... ..... ..... \ + @rprr_store msz=2 esz=3 nreg=0 ST_zprr 1110010 11 11 ..... 010 ... ..... ..... \ @rprr_store msz=3 esz=3 nreg=0 +ST_zprr 1110010 10 00 ..... 010 ... ..... ..... \ + @rprr_store msz=2 esz=4 nreg=0 +ST_zprr 1110010 11 10 ..... 010 ... ..... ..... \ + @rprr_store msz=3 esz=4 nreg=0 # SVE contiguous non-temporal store (scalar plus immediate) (nreg == 0) # SVE store multiple structures (scalar plus immediate) (nreg != 0) ST_zpri 1110010 .. nreg:2 1.... 111 ... ..... ..... \ - @rpri_store_msz esz=%size_23 + @rpri_store msz=%size_23 esz=%size_23 +# ST[234]Q +ST_zpri 11100100 01 00 .... 000 ... ..... ..... \ + @rpri_store msz=4 esz=4 nreg=1 +ST_zpri 11100100 10 00 .... 000 ... ..... ..... \ + @rpri_store msz=4 esz=4 nreg=2 +ST_zpri 11100100 11 00 .... 000 ... ..... ..... \ + @rpri_store msz=4 esz=4 nreg=3 # SVE contiguous non-temporal store (scalar plus scalar) (nreg == 0) # SVE store multiple structures (scalar plus scalar) (nreg != 0) -ST_zprr 1110010 msz:2 nreg:2 ..... 011 ... ..... ..... \ - @rprr_store esz=%size_23 +ST_zprr 1110010 .. nreg:2 ..... 011 ... ..... ..... \ + @rprr_store msz=%size_23 esz=%size_23 +# ST[234]Q +ST_zprr 11100100 01 1 ..... 000 ... ..... ..... \ + @rprr_store msz=4 esz=4 nreg=1 +ST_zprr 11100100 10 1 ..... 000 ... ..... ..... \ + @rprr_store msz=4 esz=4 nreg=2 +ST_zprr 11100100 11 1 ..... 000 ... ..... ..... \ + @rprr_store msz=4 esz=4 nreg=3 # SVE 32-bit scatter store (scalar plus 32-bit scaled offsets) # Require msz > 0 && msz <= esz. @@ -1293,6 +1447,10 @@ ST1_zprz 1110010 .. 01 ..... 101 ... ..... ..... \ ST1_zprz 1110010 .. 00 ..... 101 ... ..... ..... \ @rprr_scatter_store xs=2 esz=3 scale=0 +# ST1Q +ST1_zprz 1110 0100 001 rm:5 001 pg:3 rn:5 rd:5 \ + &rprr_scatter_store xs=2 msz=4 esz=4 scale=0 + # SVE 64-bit scatter store (vector plus immediate) ST1_zpiz 1110010 .. 10 ..... 101 ... ..... ..... \ @rpri_scatter_store esz=3 @@ -1450,9 +1608,9 @@ EORTB 01000101 .. 0 ..... 10010 1 ..... ..... @rd_rn_rm ## SVE integer matrix multiply accumulate -SMMLA 01000101 00 0 ..... 10011 0 ..... ..... @rda_rn_rm_e0 -USMMLA 01000101 10 0 ..... 10011 0 ..... ..... @rda_rn_rm_e0 -UMMLA 01000101 11 0 ..... 10011 0 ..... ..... @rda_rn_rm_e0 +SMMLA 01000101 00 0 ..... 10011 0 ..... ..... @rda_rn_rm_ex esz=2 +USMMLA 01000101 10 0 ..... 10011 0 ..... ..... @rda_rn_rm_ex esz=2 +UMMLA 01000101 11 0 ..... 10011 0 ..... ..... @rda_rn_rm_ex esz=2 ## SVE2 bitwise permute @@ -1504,13 +1662,22 @@ UABA 01000101 .. 0 ..... 11111 1 ..... ..... @rd_rn_rm #### SVE2 Narrowing ## SVE2 saturating extract narrow - # Bits 23, 18-16 are zero, limited in the translator via esz < 3 & imm == 0. -SQXTNB 01000101 .. 1 ..... 010 000 ..... ..... @rd_rn_tszimm_shl + +{ + SQCVTN_sh 01000101 00 1 10001 010 000 ....0 ..... @rd_rnx2 esz=1 + SQXTNB 01000101 .. 1 ..... 010 000 ..... ..... @rd_rn_tszimm_shl +} SQXTNT 01000101 .. 1 ..... 010 001 ..... ..... @rd_rn_tszimm_shl -UQXTNB 01000101 .. 1 ..... 010 010 ..... ..... @rd_rn_tszimm_shl +{ + UQCVTN_sh 01000101 00 1 10001 010 010 ....0 ..... @rd_rnx2 esz=1 + UQXTNB 01000101 .. 1 ..... 010 010 ..... ..... @rd_rn_tszimm_shl +} UQXTNT 01000101 .. 1 ..... 010 011 ..... ..... @rd_rn_tszimm_shl -SQXTUNB 01000101 .. 1 ..... 010 100 ..... ..... @rd_rn_tszimm_shl +{ + SQCVTUN_sh 01000101 00 1 10001 010 100 ....0 ..... @rd_rnx2 esz=1 + SQXTUNB 01000101 .. 1 ..... 010 100 ..... ..... @rd_rn_tszimm_shl +} SQXTUNT 01000101 .. 1 ..... 010 101 ..... ..... @rd_rn_tszimm_shl ## SVE2 bitwise shift right narrow @@ -1597,14 +1764,17 @@ UMLSLT_zzzw 01000100 .. 0 ..... 010 111 ..... ..... @rda_rn_rm CMLA_zzzz 01000100 esz:2 0 rm:5 0010 rot:2 rn:5 rd:5 ra=%reg_movprfx SQRDCMLAH_zzzz 01000100 esz:2 0 rm:5 0011 rot:2 rn:5 rd:5 ra=%reg_movprfx -## SVE mixed sign dot product +## SVE dot product + +SDOT_zzzz_2s 01000100 00 0 ..... 110 010 ..... ..... @rda_rn_rm_ex esz=2 +UDOT_zzzz_2s 01000100 00 0 ..... 110 011 ..... ..... @rda_rn_rm_ex esz=2 -USDOT_zzzz 01000100 .. 0 ..... 011 110 ..... ..... @rda_rn_rm +USDOT_zzzz_4s 01000100 10 0 ..... 011 110 ..... ..... @rda_rn_rm_ex esz=2 ### SVE2 floating point matrix multiply accumulate -BFMMLA 01100100 01 1 ..... 111 001 ..... ..... @rda_rn_rm_e0 -FMMLA_s 01100100 10 1 ..... 111 001 ..... ..... @rda_rn_rm_e0 -FMMLA_d 01100100 11 1 ..... 111 001 ..... ..... @rda_rn_rm_e0 +BFMMLA 01100100 01 1 ..... 111 001 ..... ..... @rda_rn_rm_ex esz=1 +FMMLA_s 01100100 10 1 ..... 111 001 ..... ..... @rda_rn_rm_ex esz=2 +FMMLA_d 01100100 11 1 ..... 111 001 ..... ..... @rda_rn_rm_ex esz=3 ### SVE2 Memory Gather Load Group @@ -1654,26 +1824,35 @@ FCVTLT_sd 01100100 11 0010 11 101 ... ..... ..... @rd_pg_rn_e0 FLOGB 01100101 00 011 esz:2 0101 pg:3 rn:5 rd:5 &rpr_esz ### SVE2 floating-point multiply-add long (vectors) -FMLALB_zzzw 01100100 10 1 ..... 10 0 00 0 ..... ..... @rda_rn_rm_e0 -FMLALT_zzzw 01100100 10 1 ..... 10 0 00 1 ..... ..... @rda_rn_rm_e0 -FMLSLB_zzzw 01100100 10 1 ..... 10 1 00 0 ..... ..... @rda_rn_rm_e0 -FMLSLT_zzzw 01100100 10 1 ..... 10 1 00 1 ..... ..... @rda_rn_rm_e0 +FMLALB_zzzw 01100100 10 1 ..... 10 0 00 0 ..... ..... @rda_rn_rm_ex esz=2 +FMLALT_zzzw 01100100 10 1 ..... 10 0 00 1 ..... ..... @rda_rn_rm_ex esz=2 +FMLSLB_zzzw 01100100 10 1 ..... 10 1 00 0 ..... ..... @rda_rn_rm_ex esz=2 +FMLSLT_zzzw 01100100 10 1 ..... 10 1 00 1 ..... ..... @rda_rn_rm_ex esz=2 -BFMLALB_zzzw 01100100 11 1 ..... 10 0 00 0 ..... ..... @rda_rn_rm_e0 -BFMLALT_zzzw 01100100 11 1 ..... 10 0 00 1 ..... ..... @rda_rn_rm_e0 +BFMLALB_zzzw 01100100 11 1 ..... 10 0 00 0 ..... ..... @rda_rn_rm_ex esz=2 +BFMLALT_zzzw 01100100 11 1 ..... 10 0 00 1 ..... ..... @rda_rn_rm_ex esz=2 +BFMLSLB_zzzw 01100100 11 1 ..... 10 1 00 0 ..... ..... @rda_rn_rm_ex esz=2 +BFMLSLT_zzzw 01100100 11 1 ..... 10 1 00 1 ..... ..... @rda_rn_rm_ex esz=2 -### SVE2 floating-point bfloat16 dot-product -BFDOT_zzzz 01100100 01 1 ..... 10 0 00 0 ..... ..... @rda_rn_rm_e0 +### SVE2 floating-point dot-product +FDOT_zzzz 01100100 00 1 ..... 10 0 00 0 ..... ..... @rda_rn_rm_ex esz=2 +BFDOT_zzzz 01100100 01 1 ..... 10 0 00 0 ..... ..... @rda_rn_rm_ex esz=2 ### SVE2 floating-point multiply-add long (indexed) + FMLALB_zzxw 01100100 10 1 ..... 0100.0 ..... ..... @rrxr_3a esz=2 FMLALT_zzxw 01100100 10 1 ..... 0100.1 ..... ..... @rrxr_3a esz=2 FMLSLB_zzxw 01100100 10 1 ..... 0110.0 ..... ..... @rrxr_3a esz=2 FMLSLT_zzxw 01100100 10 1 ..... 0110.1 ..... ..... @rrxr_3a esz=2 + BFMLALB_zzxw 01100100 11 1 ..... 0100.0 ..... ..... @rrxr_3a esz=2 BFMLALT_zzxw 01100100 11 1 ..... 0100.1 ..... ..... @rrxr_3a esz=2 +BFMLSLB_zzxw 01100100 11 1 ..... 0110.0 ..... ..... @rrxr_3a esz=2 +BFMLSLT_zzxw 01100100 11 1 ..... 0110.1 ..... ..... @rrxr_3a esz=2 -### SVE2 floating-point bfloat16 dot-product (indexed) +### SVE2 floating-point dot-product (indexed) + +FDOT_zzxz 01100100 00 1 ..... 010000 ..... ..... @rrxr_2 esz=2 BFDOT_zzxz 01100100 01 1 ..... 010000 ..... ..... @rrxr_2 esz=2 ### SVE broadcast predicate element @@ -1700,3 +1879,55 @@ PSEL 00100101 .1 1 000 .. 01 .... 0 .... 0 .... \ SCLAMP 01000100 .. 0 ..... 110000 ..... ..... @rda_rn_rm UCLAMP 01000100 .. 0 ..... 110001 ..... ..... @rda_rn_rm + +FCLAMP 01100100 .. 1 ..... 001001 ..... ..... @rda_rn_rm + +### SVE2p1 multi-vec contiguous load + +&zcrr_ldst rd png rn rm esz nreg +&zcri_ldst rd png rn imm esz nreg +%png 10:3 !function=plus_8 +%zd_ax2 1:4 !function=times_2 +%zd_ax4 2:3 !function=times_4 + +LD1_zcrr 10100000000 rm:5 0 esz:2 ... rn:5 .... - \ + &zcrr_ldst %png rd=%zd_ax2 nreg=2 +LD1_zcrr 10100000000 rm:5 1 esz:2 ... rn:5 ... 0- \ + &zcrr_ldst %png rd=%zd_ax4 nreg=4 + +ST1_zcrr 10100000001 rm:5 0 esz:2 ... rn:5 .... - \ + &zcrr_ldst %png rd=%zd_ax2 nreg=2 +ST1_zcrr 10100000001 rm:5 1 esz:2 ... rn:5 ... 0- \ + &zcrr_ldst %png rd=%zd_ax4 nreg=4 + +LD1_zcri 101000000100 imm:s4 0 esz:2 ... rn:5 .... - \ + &zcri_ldst %png rd=%zd_ax2 nreg=2 +LD1_zcri 101000000100 imm:s4 1 esz:2 ... rn:5 ... 0- \ + &zcri_ldst %png rd=%zd_ax4 nreg=4 + +ST1_zcri 101000000110 imm:s4 0 esz:2 ... rn:5 .... - \ + &zcri_ldst %png rd=%zd_ax2 nreg=2 +ST1_zcri 101000000110 imm:s4 1 esz:2 ... rn:5 ... 0- \ + &zcri_ldst %png rd=%zd_ax4 nreg=4 + +# Note: N bit and 0 bit (for nreg4) still mashed in rd. +# This is handled within gen_ldst_c(). +LD1_zcrr_stride 10100001000 rm:5 0 esz:2 ... rn:5 rd:5 \ + &zcrr_ldst %png nreg=2 +LD1_zcrr_stride 10100001000 rm:5 1 esz:2 ... rn:5 rd:5 \ + &zcrr_ldst %png nreg=4 + +ST1_zcrr_stride 10100001001 rm:5 0 esz:2 ... rn:5 rd:5 \ + &zcrr_ldst %png nreg=2 +ST1_zcrr_stride 10100001001 rm:5 1 esz:2 ... rn:5 rd:5 \ + &zcrr_ldst %png nreg=4 + +LD1_zcri_stride 101000010100 imm:s4 0 esz:2 ... rn:5 rd:5 \ + &zcri_ldst %png nreg=2 +LD1_zcri_stride 101000010100 imm:s4 1 esz:2 ... rn:5 rd:5 \ + &zcri_ldst %png nreg=4 + +ST1_zcri_stride 101000010110 imm:s4 0 esz:2 ... rn:5 rd:5 \ + &zcri_ldst %png nreg=2 +ST1_zcri_stride 101000010110 imm:s4 1 esz:2 ... rn:5 rd:5 \ + &zcri_ldst %png nreg=4 diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c index a2c363a..43b872c 100644 --- a/target/arm/tcg/sve_helper.c +++ b/target/arm/tcg/sve_helper.c @@ -123,6 +123,11 @@ static inline uint64_t expand_pred_s(uint8_t byte) return word[byte & 0x11]; } +static inline uint64_t expand_pred_d(uint8_t byte) +{ + return -(uint64_t)(byte & 1); +} + #define LOGICAL_PPPP(NAME, FUNC) \ void HELPER(NAME)(void *vd, void *vn, void *vm, void *vg, uint32_t desc) \ { \ @@ -206,6 +211,7 @@ void HELPER(NAME)(void *vd, void *vn, void *vm, void *vg, uint32_t desc) \ #define DO_EOR(N, M) (N ^ M) #define DO_ORR(N, M) (N | M) #define DO_BIC(N, M) (N & ~M) +#define DO_ORC(N, M) (N | ~M) #define DO_ADD(N, M) (N + M) #define DO_SUB(N, M) (N - M) #define DO_MAX(N, M) ((N) >= (M) ? (N) : (M)) @@ -527,14 +533,9 @@ DO_ZPZZ(sve2_uhsub_zpzz_h, uint16_t, H1_2, DO_HSUB_BHS) DO_ZPZZ(sve2_uhsub_zpzz_s, uint32_t, H1_4, DO_HSUB_BHS) DO_ZPZZ_D(sve2_uhsub_zpzz_d, uint64_t, DO_HSUB_D) -static inline int32_t do_sat_bhs(int64_t val, int64_t min, int64_t max) -{ - return val >= max ? max : val <= min ? min : val; -} - -#define DO_SQADD_B(n, m) do_sat_bhs((int64_t)n + m, INT8_MIN, INT8_MAX) -#define DO_SQADD_H(n, m) do_sat_bhs((int64_t)n + m, INT16_MIN, INT16_MAX) -#define DO_SQADD_S(n, m) do_sat_bhs((int64_t)n + m, INT32_MIN, INT32_MAX) +#define DO_SQADD_B(n, m) do_ssat_b((int64_t)n + m) +#define DO_SQADD_H(n, m) do_ssat_h((int64_t)n + m) +#define DO_SQADD_S(n, m) do_ssat_s((int64_t)n + m) static inline int64_t do_sqadd_d(int64_t n, int64_t m) { @@ -551,9 +552,9 @@ DO_ZPZZ(sve2_sqadd_zpzz_h, int16_t, H1_2, DO_SQADD_H) DO_ZPZZ(sve2_sqadd_zpzz_s, int32_t, H1_4, DO_SQADD_S) DO_ZPZZ_D(sve2_sqadd_zpzz_d, int64_t, do_sqadd_d) -#define DO_UQADD_B(n, m) do_sat_bhs((int64_t)n + m, 0, UINT8_MAX) -#define DO_UQADD_H(n, m) do_sat_bhs((int64_t)n + m, 0, UINT16_MAX) -#define DO_UQADD_S(n, m) do_sat_bhs((int64_t)n + m, 0, UINT32_MAX) +#define DO_UQADD_B(n, m) do_usat_b((int64_t)n + m) +#define DO_UQADD_H(n, m) do_usat_h((int64_t)n + m) +#define DO_UQADD_S(n, m) do_usat_s((int64_t)n + m) static inline uint64_t do_uqadd_d(uint64_t n, uint64_t m) { @@ -566,9 +567,9 @@ DO_ZPZZ(sve2_uqadd_zpzz_h, uint16_t, H1_2, DO_UQADD_H) DO_ZPZZ(sve2_uqadd_zpzz_s, uint32_t, H1_4, DO_UQADD_S) DO_ZPZZ_D(sve2_uqadd_zpzz_d, uint64_t, do_uqadd_d) -#define DO_SQSUB_B(n, m) do_sat_bhs((int64_t)n - m, INT8_MIN, INT8_MAX) -#define DO_SQSUB_H(n, m) do_sat_bhs((int64_t)n - m, INT16_MIN, INT16_MAX) -#define DO_SQSUB_S(n, m) do_sat_bhs((int64_t)n - m, INT32_MIN, INT32_MAX) +#define DO_SQSUB_B(n, m) do_ssat_b((int64_t)n - m) +#define DO_SQSUB_H(n, m) do_ssat_h((int64_t)n - m) +#define DO_SQSUB_S(n, m) do_ssat_s((int64_t)n - m) static inline int64_t do_sqsub_d(int64_t n, int64_t m) { @@ -585,9 +586,9 @@ DO_ZPZZ(sve2_sqsub_zpzz_h, int16_t, H1_2, DO_SQSUB_H) DO_ZPZZ(sve2_sqsub_zpzz_s, int32_t, H1_4, DO_SQSUB_S) DO_ZPZZ_D(sve2_sqsub_zpzz_d, int64_t, do_sqsub_d) -#define DO_UQSUB_B(n, m) do_sat_bhs((int64_t)n - m, 0, UINT8_MAX) -#define DO_UQSUB_H(n, m) do_sat_bhs((int64_t)n - m, 0, UINT16_MAX) -#define DO_UQSUB_S(n, m) do_sat_bhs((int64_t)n - m, 0, UINT32_MAX) +#define DO_UQSUB_B(n, m) do_usat_b((int64_t)n - m) +#define DO_UQSUB_H(n, m) do_usat_h((int64_t)n - m) +#define DO_UQSUB_S(n, m) do_usat_s((int64_t)n - m) static inline uint64_t do_uqsub_d(uint64_t n, uint64_t m) { @@ -599,12 +600,9 @@ DO_ZPZZ(sve2_uqsub_zpzz_h, uint16_t, H1_2, DO_UQSUB_H) DO_ZPZZ(sve2_uqsub_zpzz_s, uint32_t, H1_4, DO_UQSUB_S) DO_ZPZZ_D(sve2_uqsub_zpzz_d, uint64_t, do_uqsub_d) -#define DO_SUQADD_B(n, m) \ - do_sat_bhs((int64_t)(int8_t)n + m, INT8_MIN, INT8_MAX) -#define DO_SUQADD_H(n, m) \ - do_sat_bhs((int64_t)(int16_t)n + m, INT16_MIN, INT16_MAX) -#define DO_SUQADD_S(n, m) \ - do_sat_bhs((int64_t)(int32_t)n + m, INT32_MIN, INT32_MAX) +#define DO_SUQADD_B(n, m) do_ssat_b((int64_t)(int8_t)n + m) +#define DO_SUQADD_H(n, m) do_ssat_h((int64_t)(int16_t)n + m) +#define DO_SUQADD_S(n, m) do_ssat_s((int64_t)(int32_t)n + m) static inline int64_t do_suqadd_d(int64_t n, uint64_t m) { @@ -634,12 +632,9 @@ DO_ZPZZ(sve2_suqadd_zpzz_h, uint16_t, H1_2, DO_SUQADD_H) DO_ZPZZ(sve2_suqadd_zpzz_s, uint32_t, H1_4, DO_SUQADD_S) DO_ZPZZ_D(sve2_suqadd_zpzz_d, uint64_t, do_suqadd_d) -#define DO_USQADD_B(n, m) \ - do_sat_bhs((int64_t)n + (int8_t)m, 0, UINT8_MAX) -#define DO_USQADD_H(n, m) \ - do_sat_bhs((int64_t)n + (int16_t)m, 0, UINT16_MAX) -#define DO_USQADD_S(n, m) \ - do_sat_bhs((int64_t)n + (int32_t)m, 0, UINT32_MAX) +#define DO_USQADD_B(n, m) do_usat_b((int64_t)n + (int8_t)m) +#define DO_USQADD_H(n, m) do_usat_h((int64_t)n + (int16_t)m) +#define DO_USQADD_S(n, m) do_usat_s((int64_t)n + (int32_t)m) static inline uint64_t do_usqadd_d(uint64_t n, int64_t m) { @@ -1226,37 +1221,29 @@ void HELPER(NAME)(void *vd, void *vn, uint32_t desc) \ } \ } -#define DO_SQXTN_H(n) do_sat_bhs(n, INT8_MIN, INT8_MAX) -#define DO_SQXTN_S(n) do_sat_bhs(n, INT16_MIN, INT16_MAX) -#define DO_SQXTN_D(n) do_sat_bhs(n, INT32_MIN, INT32_MAX) - -DO_XTNB(sve2_sqxtnb_h, int16_t, DO_SQXTN_H) -DO_XTNB(sve2_sqxtnb_s, int32_t, DO_SQXTN_S) -DO_XTNB(sve2_sqxtnb_d, int64_t, DO_SQXTN_D) +DO_XTNB(sve2_sqxtnb_h, int16_t, do_ssat_b) +DO_XTNB(sve2_sqxtnb_s, int32_t, do_ssat_h) +DO_XTNB(sve2_sqxtnb_d, int64_t, do_ssat_s) -DO_XTNT(sve2_sqxtnt_h, int16_t, int8_t, H1, DO_SQXTN_H) -DO_XTNT(sve2_sqxtnt_s, int32_t, int16_t, H1_2, DO_SQXTN_S) -DO_XTNT(sve2_sqxtnt_d, int64_t, int32_t, H1_4, DO_SQXTN_D) +DO_XTNT(sve2_sqxtnt_h, int16_t, int8_t, H1, do_ssat_b) +DO_XTNT(sve2_sqxtnt_s, int32_t, int16_t, H1_2, do_ssat_h) +DO_XTNT(sve2_sqxtnt_d, int64_t, int32_t, H1_4, do_ssat_s) -#define DO_UQXTN_H(n) do_sat_bhs(n, 0, UINT8_MAX) -#define DO_UQXTN_S(n) do_sat_bhs(n, 0, UINT16_MAX) -#define DO_UQXTN_D(n) do_sat_bhs(n, 0, UINT32_MAX) +DO_XTNB(sve2_uqxtnb_h, uint16_t, do_usat_b) +DO_XTNB(sve2_uqxtnb_s, uint32_t, do_usat_h) +DO_XTNB(sve2_uqxtnb_d, uint64_t, do_usat_s) -DO_XTNB(sve2_uqxtnb_h, uint16_t, DO_UQXTN_H) -DO_XTNB(sve2_uqxtnb_s, uint32_t, DO_UQXTN_S) -DO_XTNB(sve2_uqxtnb_d, uint64_t, DO_UQXTN_D) +DO_XTNT(sve2_uqxtnt_h, uint16_t, uint8_t, H1, do_usat_b) +DO_XTNT(sve2_uqxtnt_s, uint32_t, uint16_t, H1_2, do_usat_h) +DO_XTNT(sve2_uqxtnt_d, uint64_t, uint32_t, H1_4, do_usat_s) -DO_XTNT(sve2_uqxtnt_h, uint16_t, uint8_t, H1, DO_UQXTN_H) -DO_XTNT(sve2_uqxtnt_s, uint32_t, uint16_t, H1_2, DO_UQXTN_S) -DO_XTNT(sve2_uqxtnt_d, uint64_t, uint32_t, H1_4, DO_UQXTN_D) +DO_XTNB(sve2_sqxtunb_h, int16_t, do_usat_b) +DO_XTNB(sve2_sqxtunb_s, int32_t, do_usat_h) +DO_XTNB(sve2_sqxtunb_d, int64_t, do_usat_s) -DO_XTNB(sve2_sqxtunb_h, int16_t, DO_UQXTN_H) -DO_XTNB(sve2_sqxtunb_s, int32_t, DO_UQXTN_S) -DO_XTNB(sve2_sqxtunb_d, int64_t, DO_UQXTN_D) - -DO_XTNT(sve2_sqxtunt_h, int16_t, int8_t, H1, DO_UQXTN_H) -DO_XTNT(sve2_sqxtunt_s, int32_t, int16_t, H1_2, DO_UQXTN_S) -DO_XTNT(sve2_sqxtunt_d, int64_t, int32_t, H1_4, DO_UQXTN_D) +DO_XTNT(sve2_sqxtunt_h, int16_t, int8_t, H1, do_usat_b) +DO_XTNT(sve2_sqxtunt_s, int32_t, int16_t, H1_2, do_usat_h) +DO_XTNT(sve2_sqxtunt_d, int64_t, int32_t, H1_4, do_usat_s) #undef DO_XTNB #undef DO_XTNT @@ -1833,6 +1820,52 @@ DO_VPZ_D(sve_uminv_d, uint64_t, uint64_t, -1, DO_MIN) #undef DO_VPZ #undef DO_VPZ_D +#define DO_VPQ(NAME, TYPE, H, INIT, OP) \ +void HELPER(NAME)(void *vd, void *vn, void *vg, uint32_t desc) \ +{ \ + TYPE tmp[16 / sizeof(TYPE)] = { [0 ... 16 / sizeof(TYPE) - 1] = INIT }; \ + TYPE *n = vn; uint16_t *g = vg; \ + uintptr_t oprsz = simd_oprsz(desc); \ + uintptr_t nseg = oprsz / 16, nsegelt = 16 / sizeof(TYPE); \ + for (uintptr_t s = 0; s < nseg; s++) { \ + uint16_t pg = g[H2(s)]; \ + for (uintptr_t e = 0; e < nsegelt; e++, pg >>= sizeof(TYPE)) { \ + if (pg & 1) { \ + tmp[e] = OP(tmp[H(e)], n[s * nsegelt + H(e)]); \ + } \ + } \ + } \ + memcpy(vd, tmp, 16); \ + clear_tail(vd, 16, simd_maxsz(desc)); \ +} + +DO_VPQ(sve2p1_addqv_b, uint8_t, H1, 0, DO_ADD) +DO_VPQ(sve2p1_addqv_h, uint16_t, H2, 0, DO_ADD) +DO_VPQ(sve2p1_addqv_s, uint32_t, H4, 0, DO_ADD) +DO_VPQ(sve2p1_addqv_d, uint64_t, H8, 0, DO_ADD) + +DO_VPQ(sve2p1_smaxqv_b, int8_t, H1, INT8_MIN, DO_MAX) +DO_VPQ(sve2p1_smaxqv_h, int16_t, H2, INT16_MIN, DO_MAX) +DO_VPQ(sve2p1_smaxqv_s, int32_t, H4, INT32_MIN, DO_MAX) +DO_VPQ(sve2p1_smaxqv_d, int64_t, H8, INT64_MIN, DO_MAX) + +DO_VPQ(sve2p1_sminqv_b, int8_t, H1, INT8_MAX, DO_MIN) +DO_VPQ(sve2p1_sminqv_h, int16_t, H2, INT16_MAX, DO_MIN) +DO_VPQ(sve2p1_sminqv_s, int32_t, H4, INT32_MAX, DO_MIN) +DO_VPQ(sve2p1_sminqv_d, int64_t, H8, INT64_MAX, DO_MIN) + +DO_VPQ(sve2p1_umaxqv_b, uint8_t, H1, 0, DO_MAX) +DO_VPQ(sve2p1_umaxqv_h, uint16_t, H2, 0, DO_MAX) +DO_VPQ(sve2p1_umaxqv_s, uint32_t, H4, 0, DO_MAX) +DO_VPQ(sve2p1_umaxqv_d, uint64_t, H8, 0, DO_MAX) + +DO_VPQ(sve2p1_uminqv_b, uint8_t, H1, -1, DO_MIN) +DO_VPQ(sve2p1_uminqv_h, uint16_t, H2, -1, DO_MIN) +DO_VPQ(sve2p1_uminqv_s, uint32_t, H4, -1, DO_MIN) +DO_VPQ(sve2p1_uminqv_d, uint64_t, H8, -1, DO_MIN) + +#undef DO_VPQ + /* Two vector operand, one scalar operand, unpredicated. */ #define DO_ZZI(NAME, TYPE, OP) \ void HELPER(NAME)(void *vd, void *vn, uint64_t s64, uint32_t desc) \ @@ -1873,10 +1906,46 @@ DO_ZZI(sve_umini_d, uint64_t, DO_MIN) #undef DO_ZZI +#define DO_LOGIC_QV(NAME, SUFF, INIT, VOP, POP) \ +void HELPER(NAME ## _ ## SUFF)(void *vd, void *vn, void *vg, uint32_t desc) \ +{ \ + unsigned seg = simd_oprsz(desc) / 16; \ + uint64_t r0 = INIT, r1 = INIT; \ + for (unsigned s = 0; s < seg; s++) { \ + uint64_t p0 = expand_pred_##SUFF(*(uint8_t *)(vg + H1(s * 2))); \ + uint64_t p1 = expand_pred_##SUFF(*(uint8_t *)(vg + H1(s * 2 + 1))); \ + uint64_t v0 = *(uint64_t *)(vn + s * 16); \ + uint64_t v1 = *(uint64_t *)(vn + s * 16 + 8); \ + v0 = POP(v0, p0), v1 = POP(v1, p1); \ + r0 = VOP(r0, v0), r1 = VOP(r1, v1); \ + } \ + *(uint64_t *)(vd + 0) = r0; \ + *(uint64_t *)(vd + 8) = r1; \ + clear_tail(vd, 16, simd_maxsz(desc)); \ +} + +DO_LOGIC_QV(sve2p1_orqv, b, 0, DO_ORR, DO_AND) +DO_LOGIC_QV(sve2p1_orqv, h, 0, DO_ORR, DO_AND) +DO_LOGIC_QV(sve2p1_orqv, s, 0, DO_ORR, DO_AND) +DO_LOGIC_QV(sve2p1_orqv, d, 0, DO_ORR, DO_AND) + +DO_LOGIC_QV(sve2p1_eorqv, b, 0, DO_EOR, DO_AND) +DO_LOGIC_QV(sve2p1_eorqv, h, 0, DO_EOR, DO_AND) +DO_LOGIC_QV(sve2p1_eorqv, s, 0, DO_EOR, DO_AND) +DO_LOGIC_QV(sve2p1_eorqv, d, 0, DO_EOR, DO_AND) + +DO_LOGIC_QV(sve2p1_andqv, b, -1, DO_AND, DO_ORC) +DO_LOGIC_QV(sve2p1_andqv, h, -1, DO_AND, DO_ORC) +DO_LOGIC_QV(sve2p1_andqv, s, -1, DO_AND, DO_ORC) +DO_LOGIC_QV(sve2p1_andqv, d, -1, DO_AND, DO_ORC) + +#undef DO_LOGIC_QV + #undef DO_AND #undef DO_ORR #undef DO_EOR #undef DO_BIC +#undef DO_ORC #undef DO_ADD #undef DO_SUB #undef DO_MAX @@ -2069,27 +2138,6 @@ void HELPER(NAME)(void *vd, void *vn, void *vg, uint32_t desc) \ when N is negative, add 2**M-1. */ #define DO_ASRD(N, M) ((N + (N < 0 ? ((__typeof(N))1 << M) - 1 : 0)) >> M) -static inline uint64_t do_urshr(uint64_t x, unsigned sh) -{ - if (likely(sh < 64)) { - return (x >> sh) + ((x >> (sh - 1)) & 1); - } else if (sh == 64) { - return x >> 63; - } else { - return 0; - } -} - -static inline int64_t do_srshr(int64_t x, unsigned sh) -{ - if (likely(sh < 64)) { - return (x >> sh) + ((x >> (sh - 1)) & 1); - } else { - /* Rounding the sign bit always produces 0. */ - return 0; - } -} - DO_ZPZI(sve_asr_zpzi_b, int8_t, H1, DO_SHR) DO_ZPZI(sve_asr_zpzi_h, int16_t, H1_2, DO_SHR) DO_ZPZI(sve_asr_zpzi_s, int32_t, H1_4, DO_SHR) @@ -2187,10 +2235,9 @@ DO_SHRNT(sve2_rshrnt_h, uint16_t, uint8_t, H1_2, H1, do_urshr) DO_SHRNT(sve2_rshrnt_s, uint32_t, uint16_t, H1_4, H1_2, do_urshr) DO_SHRNT(sve2_rshrnt_d, uint64_t, uint32_t, H1_8, H1_4, do_urshr) -#define DO_SQSHRUN_H(x, sh) do_sat_bhs((int64_t)(x) >> sh, 0, UINT8_MAX) -#define DO_SQSHRUN_S(x, sh) do_sat_bhs((int64_t)(x) >> sh, 0, UINT16_MAX) -#define DO_SQSHRUN_D(x, sh) \ - do_sat_bhs((int64_t)(x) >> (sh < 64 ? sh : 63), 0, UINT32_MAX) +#define DO_SQSHRUN_H(x, sh) do_usat_b((int64_t)(x) >> sh) +#define DO_SQSHRUN_S(x, sh) do_usat_h((int64_t)(x) >> sh) +#define DO_SQSHRUN_D(x, sh) do_usat_s((int64_t)(x) >> (sh < 64 ? sh : 63)) DO_SHRNB(sve2_sqshrunb_h, int16_t, uint8_t, DO_SQSHRUN_H) DO_SHRNB(sve2_sqshrunb_s, int32_t, uint16_t, DO_SQSHRUN_S) @@ -2200,9 +2247,9 @@ DO_SHRNT(sve2_sqshrunt_h, int16_t, uint8_t, H1_2, H1, DO_SQSHRUN_H) DO_SHRNT(sve2_sqshrunt_s, int32_t, uint16_t, H1_4, H1_2, DO_SQSHRUN_S) DO_SHRNT(sve2_sqshrunt_d, int64_t, uint32_t, H1_8, H1_4, DO_SQSHRUN_D) -#define DO_SQRSHRUN_H(x, sh) do_sat_bhs(do_srshr(x, sh), 0, UINT8_MAX) -#define DO_SQRSHRUN_S(x, sh) do_sat_bhs(do_srshr(x, sh), 0, UINT16_MAX) -#define DO_SQRSHRUN_D(x, sh) do_sat_bhs(do_srshr(x, sh), 0, UINT32_MAX) +#define DO_SQRSHRUN_H(x, sh) do_usat_b(do_srshr(x, sh)) +#define DO_SQRSHRUN_S(x, sh) do_usat_h(do_srshr(x, sh)) +#define DO_SQRSHRUN_D(x, sh) do_usat_s(do_srshr(x, sh)) DO_SHRNB(sve2_sqrshrunb_h, int16_t, uint8_t, DO_SQRSHRUN_H) DO_SHRNB(sve2_sqrshrunb_s, int32_t, uint16_t, DO_SQRSHRUN_S) @@ -2212,9 +2259,9 @@ DO_SHRNT(sve2_sqrshrunt_h, int16_t, uint8_t, H1_2, H1, DO_SQRSHRUN_H) DO_SHRNT(sve2_sqrshrunt_s, int32_t, uint16_t, H1_4, H1_2, DO_SQRSHRUN_S) DO_SHRNT(sve2_sqrshrunt_d, int64_t, uint32_t, H1_8, H1_4, DO_SQRSHRUN_D) -#define DO_SQSHRN_H(x, sh) do_sat_bhs(x >> sh, INT8_MIN, INT8_MAX) -#define DO_SQSHRN_S(x, sh) do_sat_bhs(x >> sh, INT16_MIN, INT16_MAX) -#define DO_SQSHRN_D(x, sh) do_sat_bhs(x >> sh, INT32_MIN, INT32_MAX) +#define DO_SQSHRN_H(x, sh) do_ssat_b(x >> sh) +#define DO_SQSHRN_S(x, sh) do_ssat_h(x >> sh) +#define DO_SQSHRN_D(x, sh) do_ssat_s(x >> sh) DO_SHRNB(sve2_sqshrnb_h, int16_t, uint8_t, DO_SQSHRN_H) DO_SHRNB(sve2_sqshrnb_s, int32_t, uint16_t, DO_SQSHRN_S) @@ -2224,9 +2271,9 @@ DO_SHRNT(sve2_sqshrnt_h, int16_t, uint8_t, H1_2, H1, DO_SQSHRN_H) DO_SHRNT(sve2_sqshrnt_s, int32_t, uint16_t, H1_4, H1_2, DO_SQSHRN_S) DO_SHRNT(sve2_sqshrnt_d, int64_t, uint32_t, H1_8, H1_4, DO_SQSHRN_D) -#define DO_SQRSHRN_H(x, sh) do_sat_bhs(do_srshr(x, sh), INT8_MIN, INT8_MAX) -#define DO_SQRSHRN_S(x, sh) do_sat_bhs(do_srshr(x, sh), INT16_MIN, INT16_MAX) -#define DO_SQRSHRN_D(x, sh) do_sat_bhs(do_srshr(x, sh), INT32_MIN, INT32_MAX) +#define DO_SQRSHRN_H(x, sh) do_ssat_b(do_srshr(x, sh)) +#define DO_SQRSHRN_S(x, sh) do_ssat_h(do_srshr(x, sh)) +#define DO_SQRSHRN_D(x, sh) do_ssat_s(do_srshr(x, sh)) DO_SHRNB(sve2_sqrshrnb_h, int16_t, uint8_t, DO_SQRSHRN_H) DO_SHRNB(sve2_sqrshrnb_s, int32_t, uint16_t, DO_SQRSHRN_S) @@ -2988,6 +3035,56 @@ void HELPER(sve_rev_d)(void *vd, void *vn, uint32_t desc) } } +/* + * TODO: This could use half_shuffle64 and similar bit tricks to + * expand blocks of bits at once. + */ +#define DO_PMOV_PV(NAME, ESIZE) \ +void HELPER(NAME)(void *vd, void *vs, uint32_t desc) \ +{ \ + unsigned vl = simd_oprsz(desc); \ + unsigned idx = simd_data(desc); \ + unsigned elements = vl / ESIZE; \ + ARMPredicateReg *d = vd; \ + ARMVectorReg *s = vs; \ + memset(d, 0, sizeof(*d)); \ + for (unsigned e = 0; e < elements; ++e) { \ + depositn(d->p, e * ESIZE, 1, extractn(s->d, elements * idx + e, 1)); \ + } \ +} + +DO_PMOV_PV(pmov_pv_h, 2) +DO_PMOV_PV(pmov_pv_s, 4) +DO_PMOV_PV(pmov_pv_d, 8) + +#undef DO_PMOV_PV + +/* + * TODO: This could use half_unshuffle64 and similar bit tricks to + * compress blocks of bits at once. + */ +#define DO_PMOV_VP(NAME, ESIZE) \ +void HELPER(NAME)(void *vd, void *vs, uint32_t desc) \ +{ \ + unsigned vl = simd_oprsz(desc); \ + unsigned idx = simd_data(desc); \ + unsigned elements = vl / ESIZE; \ + ARMVectorReg *d = vd; \ + ARMPredicateReg *s = vs; \ + if (idx == 0) { \ + memset(d, 0, vl); \ + } \ + for (unsigned e = 0; e < elements; ++e) { \ + depositn(d->d, elements * idx + e, 1, extractn(s->p, e * ESIZE, 1)); \ + } \ +} + +DO_PMOV_VP(pmov_vp_h, 2) +DO_PMOV_VP(pmov_vp_s, 4) +DO_PMOV_VP(pmov_vp_d, 8) + +#undef DO_PMOV_VP + typedef void tb_impl_fn(void *, void *, void *, void *, uintptr_t, bool); static inline void do_tbl1(void *vd, void *vn, void *vm, uint32_t desc, @@ -3453,6 +3550,45 @@ DO_UZP(sve_uzp_s, uint32_t, H1_4) DO_UZP(sve_uzp_d, uint64_t, H1_8) DO_UZP(sve2_uzp_q, Int128, ) +typedef void perseg_zzz_fn(void *vd, void *vn, void *vm, uint32_t desc); + +static void do_perseg_zzz(void *vd, void *vn, void *vm, + uint32_t desc, perseg_zzz_fn *fn) +{ + intptr_t oprsz = simd_oprsz(desc); + + desc = simd_desc(16, 16, simd_data(desc)); + for (intptr_t i = 0; i < oprsz; i += 16) { + fn(vd + i, vn + i, vm + i, desc); + } +} + +#define DO_PERSEG_ZZZ(NAME, FUNC) \ + void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ + { do_perseg_zzz(vd, vn, vm, desc, FUNC); } + +DO_PERSEG_ZZZ(sve2p1_uzpq_b, helper_sve_uzp_b) +DO_PERSEG_ZZZ(sve2p1_uzpq_h, helper_sve_uzp_h) +DO_PERSEG_ZZZ(sve2p1_uzpq_s, helper_sve_uzp_s) +DO_PERSEG_ZZZ(sve2p1_uzpq_d, helper_sve_uzp_d) + +DO_PERSEG_ZZZ(sve2p1_zipq_b, helper_sve_zip_b) +DO_PERSEG_ZZZ(sve2p1_zipq_h, helper_sve_zip_h) +DO_PERSEG_ZZZ(sve2p1_zipq_s, helper_sve_zip_s) +DO_PERSEG_ZZZ(sve2p1_zipq_d, helper_sve_zip_d) + +DO_PERSEG_ZZZ(sve2p1_tblq_b, helper_sve_tbl_b) +DO_PERSEG_ZZZ(sve2p1_tblq_h, helper_sve_tbl_h) +DO_PERSEG_ZZZ(sve2p1_tblq_s, helper_sve_tbl_s) +DO_PERSEG_ZZZ(sve2p1_tblq_d, helper_sve_tbl_d) + +DO_PERSEG_ZZZ(sve2p1_tbxq_b, helper_sve2_tbx_b) +DO_PERSEG_ZZZ(sve2p1_tbxq_h, helper_sve2_tbx_h) +DO_PERSEG_ZZZ(sve2p1_tbxq_s, helper_sve2_tbx_s) +DO_PERSEG_ZZZ(sve2p1_tbxq_d, helper_sve2_tbx_d) + +#undef DO_PERSEG_ZZZ + #define DO_TRN(NAME, TYPE, H) \ void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ { \ @@ -3993,15 +4129,6 @@ static uint32_t compute_brks_m(uint64_t *d, uint64_t *n, uint64_t *g, return flags; } -static uint32_t do_zero(ARMPredicateReg *d, intptr_t oprsz) -{ - /* It is quicker to zero the whole predicate than loop on OPRSZ. - * The compiler should turn this into 4 64-bit integer stores. - */ - memset(d, 0, sizeof(ARMPredicateReg)); - return PREDTEST_INIT; -} - void HELPER(sve_brkpa)(void *vd, void *vn, void *vm, void *vg, uint32_t pred_desc) { @@ -4009,7 +4136,7 @@ void HELPER(sve_brkpa)(void *vd, void *vn, void *vm, void *vg, if (last_active_pred(vn, vg, oprsz)) { compute_brk_z(vd, vm, vg, oprsz, true); } else { - do_zero(vd, oprsz); + memset(vd, 0, sizeof(ARMPredicateReg)); } } @@ -4020,7 +4147,8 @@ uint32_t HELPER(sve_brkpas)(void *vd, void *vn, void *vm, void *vg, if (last_active_pred(vn, vg, oprsz)) { return compute_brks_z(vd, vm, vg, oprsz, true); } else { - return do_zero(vd, oprsz); + memset(vd, 0, sizeof(ARMPredicateReg)); + return PREDTEST_INIT; } } @@ -4031,7 +4159,7 @@ void HELPER(sve_brkpb)(void *vd, void *vn, void *vm, void *vg, if (last_active_pred(vn, vg, oprsz)) { compute_brk_z(vd, vm, vg, oprsz, false); } else { - do_zero(vd, oprsz); + memset(vd, 0, sizeof(ARMPredicateReg)); } } @@ -4042,7 +4170,8 @@ uint32_t HELPER(sve_brkpbs)(void *vd, void *vn, void *vm, void *vg, if (last_active_pred(vn, vg, oprsz)) { return compute_brks_z(vd, vm, vg, oprsz, false); } else { - return do_zero(vd, oprsz); + memset(vd, 0, sizeof(ARMPredicateReg)); + return PREDTEST_INIT; } } @@ -4098,35 +4227,30 @@ void HELPER(sve_brkn)(void *vd, void *vn, void *vg, uint32_t pred_desc) { intptr_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ); if (!last_active_pred(vn, vg, oprsz)) { - do_zero(vd, oprsz); - } -} - -/* As if PredTest(Ones(PL), D, esz). */ -static uint32_t predtest_ones(ARMPredicateReg *d, intptr_t oprsz, - uint64_t esz_mask) -{ - uint32_t flags = PREDTEST_INIT; - intptr_t i; - - for (i = 0; i < oprsz / 8; i++) { - flags = iter_predtest_fwd(d->p[i], esz_mask, flags); - } - if (oprsz & 7) { - uint64_t mask = ~(-1ULL << (8 * (oprsz & 7))); - flags = iter_predtest_fwd(d->p[i], esz_mask & mask, flags); + memset(vd, 0, sizeof(ARMPredicateReg)); } - return flags; } uint32_t HELPER(sve_brkns)(void *vd, void *vn, void *vg, uint32_t pred_desc) { intptr_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ); if (last_active_pred(vn, vg, oprsz)) { - return predtest_ones(vd, oprsz, -1); - } else { - return do_zero(vd, oprsz); + ARMPredicateReg *d = vd; + uint32_t flags = PREDTEST_INIT; + intptr_t i; + + /* As if PredTest(Ones(PL), D, MO_8). */ + for (i = 0; i < oprsz / 8; i++) { + flags = iter_predtest_fwd(d->p[i], -1, flags); + } + if (oprsz & 7) { + uint64_t mask = ~(-1ULL << (8 * (oprsz & 7))); + flags = iter_predtest_fwd(d->p[i], mask, flags); + } + return flags; } + memset(vd, 0, sizeof(ARMPredicateReg)); + return PREDTEST_INIT; } uint64_t HELPER(sve_cntp)(void *vn, void *vg, uint32_t pred_desc) @@ -4143,66 +4267,200 @@ uint64_t HELPER(sve_cntp)(void *vn, void *vg, uint32_t pred_desc) return sum; } -uint32_t HELPER(sve_whilel)(void *vd, uint32_t count, uint32_t pred_desc) +uint64_t HELPER(sve2p1_cntp_c)(uint32_t png, uint32_t desc) { - intptr_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ); - intptr_t esz = FIELD_EX32(pred_desc, PREDDESC, ESZ); - uint64_t esz_mask = pred_esz_masks[esz]; - ARMPredicateReg *d = vd; - uint32_t flags; - intptr_t i; + int pl = FIELD_EX32(desc, PREDDESC, OPRSZ); + int vl = pl * 8; + unsigned v_esz = FIELD_EX32(desc, PREDDESC, ESZ); + int lg2_width = FIELD_EX32(desc, PREDDESC, DATA) + 1; + DecodeCounter p = decode_counter(png, vl, v_esz); + unsigned maxelem = (vl << lg2_width) >> v_esz; + unsigned count = p.count; + + if (p.invert) { + if (count >= maxelem) { + return 0; + } + count = maxelem - count; + } else { + count = MIN(count, maxelem); + } + return count >> p.lg2_stride; +} + +/* C.f. Arm pseudocode EncodePredCount */ +static uint64_t encode_pred_count(uint32_t elements, uint32_t count, + uint32_t esz, bool invert) +{ + uint32_t pred; - /* Begin with a zero predicate register. */ - flags = do_zero(d, oprsz); if (count == 0) { - return flags; + return 0; + } + if (invert) { + count = elements - count; + } else if (count == elements) { + count = 0; + invert = true; } - /* Set all of the requested bits. */ - for (i = 0; i < count / 64; ++i) { - d->p[i] = esz_mask; + pred = (count << 1) | 1; + pred <<= esz; + pred |= invert << 15; + + return pred; +} + +/* C.f. Arm pseudocode PredCountTest */ +static uint32_t pred_count_test(uint32_t elements, uint32_t count, bool invert) +{ + uint32_t flags; + + if (count == 0) { + flags = 1; /* !N, Z, C */ + } else if (!invert) { + flags = (1u << 31) | 2; /* N, !Z */ + flags |= count != elements; /* C */ + } else { + flags = 2; /* !Z, !C */ + flags |= (count == elements) << 31; /* N */ } - if (count & 63) { - d->p[i] = MAKE_64BIT_MASK(0, count & 63) & esz_mask; + return flags; +} + +/* D must be cleared on entry. */ +static void do_whilel(ARMPredicateReg *d, uint64_t esz_mask, + uint32_t count, uint32_t oprbits) +{ + tcg_debug_assert(count <= oprbits); + if (count) { + uint32_t i; + + /* Set all of the requested bits. */ + for (i = 0; i < count / 64; ++i) { + d->p[i] = esz_mask; + } + if (count & 63) { + d->p[i] = MAKE_64BIT_MASK(0, count & 63) & esz_mask; + } } +} - return predtest_ones(d, oprsz, esz_mask); +uint32_t HELPER(sve_whilel)(void *vd, uint32_t count, uint32_t pred_desc) +{ + uint32_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ); + uint32_t esz = FIELD_EX32(pred_desc, PREDDESC, ESZ); + uint32_t oprbits = oprsz * 8; + uint64_t esz_mask = pred_esz_masks[esz]; + ARMPredicateReg *d = vd; + + count <<= esz; + memset(d, 0, sizeof(*d)); + do_whilel(d, esz_mask, count, oprbits); + return pred_count_test(oprbits, count, false); } -uint32_t HELPER(sve_whileg)(void *vd, uint32_t count, uint32_t pred_desc) +uint32_t HELPER(sve_while2l)(void *vd, uint32_t count, uint32_t pred_desc) { - intptr_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ); - intptr_t esz = FIELD_EX32(pred_desc, PREDDESC, ESZ); + uint32_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ); + uint32_t esz = FIELD_EX32(pred_desc, PREDDESC, ESZ); + uint32_t oprbits = oprsz * 8; uint64_t esz_mask = pred_esz_masks[esz]; ARMPredicateReg *d = vd; - intptr_t i, invcount, oprbits; - uint64_t bits; - if (count == 0) { - return do_zero(d, oprsz); + count <<= esz; + memset(d, 0, 2 * sizeof(*d)); + if (count <= oprbits) { + do_whilel(&d[0], esz_mask, count, oprbits); + } else { + do_whilel(&d[0], esz_mask, oprbits, oprbits); + do_whilel(&d[1], esz_mask, count - oprbits, oprbits); } - oprbits = oprsz * 8; + return pred_count_test(2 * oprbits, count, false); +} + +uint32_t HELPER(sve_whilecl)(void *vd, uint32_t count, uint32_t pred_desc) +{ + uint32_t pl = FIELD_EX32(pred_desc, PREDDESC, OPRSZ); + uint32_t esz = FIELD_EX32(pred_desc, PREDDESC, ESZ); + uint32_t scale = FIELD_EX32(pred_desc, PREDDESC, DATA); + uint32_t vl = pl * 8; + uint32_t elements = (vl >> esz) << scale; + ARMPredicateReg *d = vd; + + *d = (ARMPredicateReg) { + .p[0] = encode_pred_count(elements, count, esz, false) + }; + return pred_count_test(elements, count, false); +} + +/* D must be cleared on entry. */ +static void do_whileg(ARMPredicateReg *d, uint64_t esz_mask, + uint32_t count, uint32_t oprbits) +{ tcg_debug_assert(count <= oprbits); + if (count) { + uint32_t i, invcount = oprbits - count; + uint64_t bits = esz_mask & MAKE_64BIT_MASK(invcount & 63, 64); - bits = esz_mask; - if (oprbits & 63) { - bits &= MAKE_64BIT_MASK(0, oprbits & 63); + for (i = invcount / 64; i < oprbits / 64; ++i) { + d->p[i] = bits; + bits = esz_mask; + } + if (oprbits & 63) { + d->p[i] = bits & MAKE_64BIT_MASK(0, oprbits & 63); + } } +} - invcount = oprbits - count; - for (i = (oprsz - 1) / 8; i > invcount / 64; --i) { - d->p[i] = bits; - bits = esz_mask; - } +uint32_t HELPER(sve_whileg)(void *vd, uint32_t count, uint32_t pred_desc) +{ + uint32_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ); + uint32_t esz = FIELD_EX32(pred_desc, PREDDESC, ESZ); + uint32_t oprbits = oprsz * 8; + uint64_t esz_mask = pred_esz_masks[esz]; + ARMPredicateReg *d = vd; - d->p[i] = bits & MAKE_64BIT_MASK(invcount & 63, 64); + count <<= esz; + memset(d, 0, sizeof(*d)); + do_whileg(d, esz_mask, count, oprbits); + return pred_count_test(oprbits, count, true); +} + +uint32_t HELPER(sve_while2g)(void *vd, uint32_t count, uint32_t pred_desc) +{ + uint32_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ); + uint32_t esz = FIELD_EX32(pred_desc, PREDDESC, ESZ); + uint32_t oprbits = oprsz * 8; + uint64_t esz_mask = pred_esz_masks[esz]; + ARMPredicateReg *d = vd; - while (--i >= 0) { - d->p[i] = 0; + count <<= esz; + memset(d, 0, 2 * sizeof(*d)); + if (count <= oprbits) { + do_whileg(&d[1], esz_mask, count, oprbits); + } else { + do_whilel(&d[1], esz_mask, oprbits, oprbits); + do_whileg(&d[0], esz_mask, count - oprbits, oprbits); } - return predtest_ones(d, oprsz, esz_mask); + return pred_count_test(2 * oprbits, count, true); +} + +uint32_t HELPER(sve_whilecg)(void *vd, uint32_t count, uint32_t pred_desc) +{ + uint32_t pl = FIELD_EX32(pred_desc, PREDDESC, OPRSZ); + uint32_t esz = FIELD_EX32(pred_desc, PREDDESC, ESZ); + uint32_t scale = FIELD_EX32(pred_desc, PREDDESC, DATA); + uint32_t vl = pl * 8; + uint32_t elements = (vl >> esz) << scale; + ARMPredicateReg *d = vd; + + *d = (ARMPredicateReg) { + .p[0] = encode_pred_count(elements, count, esz, true) + }; + return pred_count_test(elements, count, true); } /* Recursive reduction on a function; @@ -4213,19 +4471,20 @@ uint32_t HELPER(sve_whileg)(void *vd, uint32_t count, uint32_t pred_desc) * The recursion is bounded to depth 7 (128 fp16 elements), so there's * little to gain with a more complex non-recursive form. */ -#define DO_REDUCE(NAME, TYPE, H, FUNC, IDENT) \ -static TYPE NAME##_reduce(TYPE *data, float_status *status, uintptr_t n) \ +#define DO_REDUCE(NAME, SUF, TYPE, H, FUNC, IDENT) \ +static TYPE FUNC##_reduce(TYPE *data, float_status *status, uintptr_t n) \ { \ if (n == 1) { \ return *data; \ } else { \ uintptr_t half = n / 2; \ - TYPE lo = NAME##_reduce(data, status, half); \ - TYPE hi = NAME##_reduce(data + half, status, half); \ + TYPE lo = FUNC##_reduce(data, status, half); \ + TYPE hi = FUNC##_reduce(data + half, status, half); \ return FUNC(lo, hi, status); \ } \ } \ -uint64_t HELPER(NAME)(void *vn, void *vg, float_status *s, uint32_t desc) \ +uint64_t helper_sve_##NAME##v_##SUF(void *vn, void *vg, \ + float_status *s, uint32_t desc) \ { \ uintptr_t i, oprsz = simd_oprsz(desc), maxsz = simd_data(desc); \ TYPE data[sizeof(ARMVectorReg) / sizeof(TYPE)]; \ @@ -4240,39 +4499,54 @@ uint64_t HELPER(NAME)(void *vn, void *vg, float_status *s, uint32_t desc) \ for (; i < maxsz; i += sizeof(TYPE)) { \ *(TYPE *)((void *)data + i) = IDENT; \ } \ - return NAME##_reduce(data, s, maxsz / sizeof(TYPE)); \ + return FUNC##_reduce(data, s, maxsz / sizeof(TYPE)); \ +} \ +void helper_sve2p1_##NAME##qv_##SUF(void *vd, void *vn, void *vg, \ + float_status *status, uint32_t desc) \ +{ \ + unsigned oprsz = simd_oprsz(desc), segments = oprsz / 16; \ + for (unsigned e = 0; e < 16; e += sizeof(TYPE)) { \ + TYPE data[ARM_MAX_VQ]; \ + for (unsigned s = 0; s < segments; s++) { \ + uint16_t pg = *(uint16_t *)(vg + H1_2(s * 2)); \ + TYPE nn = *(TYPE *)(vn + H(s * 16 + H(e))); \ + data[s] = (pg >> e) & 1 ? nn : IDENT; \ + } \ + *(TYPE *)(vd + H(e)) = FUNC##_reduce(data, status, segments); \ + } \ + clear_tail(vd, 16, simd_maxsz(desc)); \ } -DO_REDUCE(sve_faddv_h, float16, H1_2, float16_add, float16_zero) -DO_REDUCE(sve_faddv_s, float32, H1_4, float32_add, float32_zero) -DO_REDUCE(sve_faddv_d, float64, H1_8, float64_add, float64_zero) +DO_REDUCE(fadd,h, float16, H1_2, float16_add, float16_zero) +DO_REDUCE(fadd,s, float32, H1_4, float32_add, float32_zero) +DO_REDUCE(fadd,d, float64, H1_8, float64_add, float64_zero) /* Identity is floatN_default_nan, without the function call. */ -DO_REDUCE(sve_fminnmv_h, float16, H1_2, float16_minnum, 0x7E00) -DO_REDUCE(sve_fminnmv_s, float32, H1_4, float32_minnum, 0x7FC00000) -DO_REDUCE(sve_fminnmv_d, float64, H1_8, float64_minnum, 0x7FF8000000000000ULL) +DO_REDUCE(fminnm,h, float16, H1_2, float16_minnum, 0x7E00) +DO_REDUCE(fminnm,s, float32, H1_4, float32_minnum, 0x7FC00000) +DO_REDUCE(fminnm,d, float64, H1_8, float64_minnum, 0x7FF8000000000000ULL) -DO_REDUCE(sve_fmaxnmv_h, float16, H1_2, float16_maxnum, 0x7E00) -DO_REDUCE(sve_fmaxnmv_s, float32, H1_4, float32_maxnum, 0x7FC00000) -DO_REDUCE(sve_fmaxnmv_d, float64, H1_8, float64_maxnum, 0x7FF8000000000000ULL) +DO_REDUCE(fmaxnm,h, float16, H1_2, float16_maxnum, 0x7E00) +DO_REDUCE(fmaxnm,s, float32, H1_4, float32_maxnum, 0x7FC00000) +DO_REDUCE(fmaxnm,d, float64, H1_8, float64_maxnum, 0x7FF8000000000000ULL) -DO_REDUCE(sve_fminv_h, float16, H1_2, float16_min, float16_infinity) -DO_REDUCE(sve_fminv_s, float32, H1_4, float32_min, float32_infinity) -DO_REDUCE(sve_fminv_d, float64, H1_8, float64_min, float64_infinity) +DO_REDUCE(fmin,h, float16, H1_2, float16_min, float16_infinity) +DO_REDUCE(fmin,s, float32, H1_4, float32_min, float32_infinity) +DO_REDUCE(fmin,d, float64, H1_8, float64_min, float64_infinity) -DO_REDUCE(sve_fmaxv_h, float16, H1_2, float16_max, float16_chs(float16_infinity)) -DO_REDUCE(sve_fmaxv_s, float32, H1_4, float32_max, float32_chs(float32_infinity)) -DO_REDUCE(sve_fmaxv_d, float64, H1_8, float64_max, float64_chs(float64_infinity)) +DO_REDUCE(fmax,h, float16, H1_2, float16_max, float16_chs(float16_infinity)) +DO_REDUCE(fmax,s, float32, H1_4, float32_max, float32_chs(float32_infinity)) +DO_REDUCE(fmax,d, float64, H1_8, float64_max, float64_chs(float64_infinity)) -DO_REDUCE(sve_ah_fminv_h, float16, H1_2, helper_vfp_ah_minh, float16_infinity) -DO_REDUCE(sve_ah_fminv_s, float32, H1_4, helper_vfp_ah_mins, float32_infinity) -DO_REDUCE(sve_ah_fminv_d, float64, H1_8, helper_vfp_ah_mind, float64_infinity) +DO_REDUCE(ah_fmin,h, float16, H1_2, helper_vfp_ah_minh, float16_infinity) +DO_REDUCE(ah_fmin,s, float32, H1_4, helper_vfp_ah_mins, float32_infinity) +DO_REDUCE(ah_fmin,d, float64, H1_8, helper_vfp_ah_mind, float64_infinity) -DO_REDUCE(sve_ah_fmaxv_h, float16, H1_2, helper_vfp_ah_maxh, +DO_REDUCE(ah_fmax,h, float16, H1_2, helper_vfp_ah_maxh, float16_chs(float16_infinity)) -DO_REDUCE(sve_ah_fmaxv_s, float32, H1_4, helper_vfp_ah_maxs, +DO_REDUCE(ah_fmax,s, float32, H1_4, helper_vfp_ah_maxs, float32_chs(float32_infinity)) -DO_REDUCE(sve_ah_fmaxv_d, float64, H1_8, helper_vfp_ah_maxd, +DO_REDUCE(ah_fmax,d, float64, H1_8, helper_vfp_ah_maxd, float64_chs(float64_infinity)) #undef DO_REDUCE @@ -4554,7 +4828,7 @@ void HELPER(NAME)(void *vd, void *vn, void *vg, \ * FZ16. When converting from fp16, this affects flushing input denormals; * when converting to fp16, this affects flushing output denormals. */ -static inline float32 sve_f16_to_f32(float16 f, float_status *fpst) +float32 sve_f16_to_f32(float16 f, float_status *fpst) { bool save = get_flush_inputs_to_zero(fpst); float32 ret; @@ -4576,7 +4850,7 @@ static inline float64 sve_f16_to_f64(float16 f, float_status *fpst) return ret; } -static inline float16 sve_f32_to_f16(float32 f, float_status *fpst) +float16 sve_f32_to_f16(float32 f, float_status *fpst) { bool save = get_flush_to_zero(fpst); float16 ret; @@ -6085,6 +6359,9 @@ DO_LD1_2(ld1sds, MO_64, MO_32) DO_LD1_2(ld1dd, MO_64, MO_64) +DO_LD1_2(ld1squ, MO_32, MO_128) +DO_LD1_2(ld1dqu, MO_64, MO_128) + #undef DO_LD1_1 #undef DO_LD1_2 @@ -6144,6 +6421,10 @@ DO_LDN_2(2, dd, MO_64) DO_LDN_2(3, dd, MO_64) DO_LDN_2(4, dd, MO_64) +DO_LDN_2(2, qq, MO_128) +DO_LDN_2(3, qq, MO_128) +DO_LDN_2(4, qq, MO_128) + #undef DO_LDN_1 #undef DO_LDN_2 @@ -6707,6 +6988,13 @@ DO_STN_2(2, dd, MO_64, MO_64) DO_STN_2(3, dd, MO_64, MO_64) DO_STN_2(4, dd, MO_64, MO_64) +DO_STN_2(1, sq, MO_128, MO_32) +DO_STN_2(1, dq, MO_128, MO_64) + +DO_STN_2(2, qq, MO_128, MO_128) +DO_STN_2(3, qq, MO_128, MO_128) +DO_STN_2(4, qq, MO_128, MO_128) + #undef DO_STN_1 #undef DO_STN_2 @@ -6923,6 +7211,9 @@ DO_LD1_ZPZ_D(dd_be, zsu, MO_64) DO_LD1_ZPZ_D(dd_be, zss, MO_64) DO_LD1_ZPZ_D(dd_be, zd, MO_64) +DO_LD1_ZPZ_D(qq_le, zd, MO_128) +DO_LD1_ZPZ_D(qq_be, zd, MO_128) + #undef DO_LD1_ZPZ_S #undef DO_LD1_ZPZ_D @@ -7309,9 +7600,505 @@ DO_ST1_ZPZ_D(sd_be, zd, MO_32) DO_ST1_ZPZ_D(dd_le, zd, MO_64) DO_ST1_ZPZ_D(dd_be, zd, MO_64) +DO_ST1_ZPZ_D(qq_le, zd, MO_128) +DO_ST1_ZPZ_D(qq_be, zd, MO_128) + #undef DO_ST1_ZPZ_S #undef DO_ST1_ZPZ_D +/* + * SVE2.1 consecutive register load/store + */ + +static unsigned sve2p1_cont_ldst_elements(SVEContLdSt *info, vaddr addr, + uint32_t png, intptr_t reg_max, + int N, int v_esz) +{ + const int esize = 1 << v_esz; + intptr_t reg_off_first = -1, reg_off_last = -1, reg_off_split; + DecodeCounter p = decode_counter(png, reg_max, v_esz); + unsigned b_count = p.count << v_esz; + unsigned b_stride = 1 << (v_esz + p.lg2_stride); + intptr_t page_split; + + /* Set all of the element indices to -1, and the TLB data to 0. */ + memset(info, -1, offsetof(SVEContLdSt, page)); + memset(info->page, 0, sizeof(info->page)); + + if (p.invert) { + if (b_count >= reg_max * N) { + return 0; + } + reg_off_first = b_count; + reg_off_last = reg_max * N - b_stride; + } else { + if (b_count == 0) { + return 0; + } + reg_off_first = 0; + reg_off_last = MIN(b_count - esize, reg_max * N - b_stride); + } + + info->reg_off_first[0] = reg_off_first; + info->mem_off_first[0] = reg_off_first; + + page_split = -(addr | TARGET_PAGE_MASK); + if (reg_off_last + esize <= page_split || reg_off_first >= page_split) { + /* The entire operation fits within a single page. */ + info->reg_off_last[0] = reg_off_last; + return b_stride; + } + + info->page_split = page_split; + reg_off_split = ROUND_DOWN(page_split, esize); + + /* + * This is the last full element on the first page, but it is not + * necessarily active. If there is no full element, i.e. the first + * active element is the one that's split, this value remains -1. + * It is useful as iteration bounds. + */ + if (reg_off_split != 0) { + info->reg_off_last[0] = ROUND_DOWN(reg_off_split - esize, b_stride); + } + + /* Determine if an unaligned element spans the pages. */ + if (page_split & (esize - 1)) { + /* It is helpful to know if the split element is active. */ + if ((reg_off_split & (b_stride - 1)) == 0) { + info->reg_off_split = reg_off_split; + info->mem_off_split = reg_off_split; + } + reg_off_split += esize; + } + + /* + * We do want the first active element on the second page, because + * this may affect the address reported in an exception. + */ + reg_off_split = ROUND_UP(reg_off_split, b_stride); + if (reg_off_split <= reg_off_last) { + info->reg_off_first[1] = reg_off_split; + info->mem_off_first[1] = reg_off_split; + info->reg_off_last[1] = reg_off_last; + } + return b_stride; +} + +static void sve2p1_cont_ldst_watchpoints(SVEContLdSt *info, CPUARMState *env, + target_ulong addr, unsigned estride, + int esize, int wp_access, uintptr_t ra) +{ +#ifndef CONFIG_USER_ONLY + intptr_t count_off, count_last; + int flags0 = info->page[0].flags; + int flags1 = info->page[1].flags; + + if (likely(!((flags0 | flags1) & TLB_WATCHPOINT))) { + return; + } + + /* Indicate that watchpoints are handled. */ + info->page[0].flags = flags0 & ~TLB_WATCHPOINT; + info->page[1].flags = flags1 & ~TLB_WATCHPOINT; + + if (flags0 & TLB_WATCHPOINT) { + count_off = info->reg_off_first[0]; + count_last = info->reg_off_split; + if (count_last < 0) { + count_last = info->reg_off_last[0]; + } + do { + cpu_check_watchpoint(env_cpu(env), addr + count_off, + esize, info->page[0].attrs, wp_access, ra); + count_off += estride; + } while (count_off <= count_last); + } + + count_off = info->reg_off_first[1]; + if ((flags1 & TLB_WATCHPOINT) && count_off >= 0) { + count_last = info->reg_off_last[1]; + do { + cpu_check_watchpoint(env_cpu(env), addr + count_off, + esize, info->page[1].attrs, + wp_access, ra); + count_off += estride; + } while (count_off <= count_last); + } +#endif +} + +static void sve2p1_cont_ldst_mte_check(SVEContLdSt *info, CPUARMState *env, + target_ulong addr, unsigned estride, + int esize, uint32_t mtedesc, + uintptr_t ra) +{ + intptr_t count_off, count_last; + + /* + * TODO: estride is always a small power of two, <= 8. + * Manipulate the stride within the loops such that + * - first iteration hits addr + off, as required, + * - second iteration hits ALIGN_UP(addr, 16), + * - other iterations advance addr by 16. + * This will minimize the probing to once per MTE granule. + */ + + /* Process the page only if MemAttr == Tagged. */ + if (info->page[0].tagged) { + count_off = info->reg_off_first[0]; + count_last = info->reg_off_split; + if (count_last < 0) { + count_last = info->reg_off_last[0]; + } + + do { + mte_check(env, mtedesc, addr + count_off, ra); + count_off += estride; + } while (count_off <= count_last); + } + + count_off = info->reg_off_first[1]; + if (count_off >= 0 && info->page[1].tagged) { + count_last = info->reg_off_last[1]; + do { + mte_check(env, mtedesc, addr + count_off, ra); + count_off += estride; + } while (count_off <= count_last); + } +} + +static inline QEMU_ALWAYS_INLINE +void sve2p1_ld1_c(CPUARMState *env, ARMVectorReg *zd, const vaddr addr, + uint32_t png, uint32_t desc, + const uintptr_t ra, const MemOp esz, + sve_ldst1_host_fn *host_fn, + sve_ldst1_tlb_fn *tlb_fn) +{ + const unsigned N = (desc >> SIMD_DATA_SHIFT) & 1 ? 4 : 2; + const unsigned rstride = 1 << ((desc >> (SIMD_DATA_SHIFT + 1)) % 4); + uint32_t mtedesc = desc >> (SIMD_DATA_SHIFT + SVE_MTEDESC_SHIFT); + const intptr_t reg_max = simd_oprsz(desc); + const unsigned esize = 1 << esz; + intptr_t count_off, count_last; + intptr_t reg_off, reg_last, reg_n; + SVEContLdSt info; + unsigned estride, flags; + void *host; + + estride = sve2p1_cont_ldst_elements(&info, addr, png, reg_max, N, esz); + if (estride == 0) { + /* The entire predicate was false; no load occurs. */ + for (unsigned n = 0; n < N; n++) { + memset(zd + n * rstride, 0, reg_max); + } + return; + } + + /* Probe the page(s). Exit with exception for any invalid page. */ + sve_cont_ldst_pages(&info, FAULT_ALL, env, addr, MMU_DATA_LOAD, ra); + + /* Handle watchpoints for all active elements. */ + sve2p1_cont_ldst_watchpoints(&info, env, addr, estride, + esize, BP_MEM_READ, ra); + + /* + * Handle mte checks for all active elements. + * Since TBI must be set for MTE, !mtedesc => !mte_active. + */ + if (mtedesc) { + sve2p1_cont_ldst_mte_check(&info, env, estride, addr, + esize, mtedesc, ra); + } + + flags = info.page[0].flags | info.page[1].flags; + if (unlikely(flags != 0)) { + /* + * At least one page includes MMIO. + * Any bus operation can fail with cpu_transaction_failed, + * which for ARM will raise SyncExternal. Perform the load + * into scratch memory to preserve register state until the end. + */ + ARMVectorReg scratch[4] = { }; + + count_off = info.reg_off_first[0]; + count_last = info.reg_off_last[1]; + if (count_last < 0) { + count_last = info.reg_off_split; + if (count_last < 0) { + count_last = info.reg_off_last[0]; + } + } + reg_off = count_off % reg_max; + reg_n = count_off / reg_max; + + do { + reg_last = MIN(count_last - count_off, reg_max - esize); + do { + tlb_fn(env, &scratch[reg_n], reg_off, addr + count_off, ra); + reg_off += estride; + count_off += estride; + } while (reg_off <= reg_last); + reg_off = 0; + reg_n++; + } while (count_off <= count_last); + + for (unsigned n = 0; n < N; ++n) { + memcpy(&zd[n * rstride], &scratch[n], reg_max); + } + return; + } + + /* The entire operation is in RAM, on valid pages. */ + + for (unsigned n = 0; n < N; ++n) { + memset(&zd[n * rstride], 0, reg_max); + } + + count_off = info.reg_off_first[0]; + count_last = info.reg_off_last[0]; + reg_off = count_off % reg_max; + reg_n = count_off / reg_max; + host = info.page[0].host; + + set_helper_retaddr(ra); + + do { + reg_last = MIN(count_last - reg_n * reg_max, reg_max - esize); + do { + host_fn(&zd[reg_n * rstride], reg_off, host + count_off); + reg_off += estride; + count_off += estride; + } while (reg_off <= reg_last); + reg_off = 0; + reg_n++; + } while (count_off <= count_last); + + clear_helper_retaddr(); + + /* + * Use the slow path to manage the cross-page misalignment. + * But we know this is RAM and cannot trap. + */ + count_off = info.reg_off_split; + if (unlikely(count_off >= 0)) { + reg_off = count_off % reg_max; + reg_n = count_off / reg_max; + tlb_fn(env, &zd[reg_n * rstride], reg_off, addr + count_off, ra); + } + + count_off = info.reg_off_first[1]; + if (unlikely(count_off >= 0)) { + count_last = info.reg_off_last[1]; + reg_off = count_off % reg_max; + reg_n = count_off / reg_max; + host = info.page[1].host; + + set_helper_retaddr(ra); + + do { + reg_last = MIN(count_last - reg_n * reg_max, reg_max - esize); + do { + host_fn(&zd[reg_n * rstride], reg_off, host + count_off); + reg_off += estride; + count_off += estride; + } while (reg_off <= reg_last); + reg_off = 0; + reg_n++; + } while (count_off <= count_last); + + clear_helper_retaddr(); + } +} + +void HELPER(sve2p1_ld1bb_c)(CPUARMState *env, void *vd, target_ulong addr, + uint32_t png, uint32_t desc) +{ + sve2p1_ld1_c(env, vd, addr, png, desc, GETPC(), MO_8, + sve_ld1bb_host, sve_ld1bb_tlb); +} + +#define DO_LD1_2(NAME, ESZ) \ +void HELPER(sve2p1_##NAME##_le_c)(CPUARMState *env, void *vd, \ + target_ulong addr, uint32_t png, \ + uint32_t desc) \ +{ \ + sve2p1_ld1_c(env, vd, addr, png, desc, GETPC(), ESZ, \ + sve_##NAME##_le_host, sve_##NAME##_le_tlb); \ +} \ +void HELPER(sve2p1_##NAME##_be_c)(CPUARMState *env, void *vd, \ + target_ulong addr, uint32_t png, \ + uint32_t desc) \ +{ \ + sve2p1_ld1_c(env, vd, addr, png, desc, GETPC(), ESZ, \ + sve_##NAME##_be_host, sve_##NAME##_be_tlb); \ +} + +DO_LD1_2(ld1hh, MO_16) +DO_LD1_2(ld1ss, MO_32) +DO_LD1_2(ld1dd, MO_64) + +#undef DO_LD1_2 + +static inline QEMU_ALWAYS_INLINE +void sve2p1_st1_c(CPUARMState *env, ARMVectorReg *zd, const vaddr addr, + uint32_t png, uint32_t desc, + const uintptr_t ra, const int esz, + sve_ldst1_host_fn *host_fn, + sve_ldst1_tlb_fn *tlb_fn) +{ + const unsigned N = (desc >> SIMD_DATA_SHIFT) & 1 ? 4 : 2; + const unsigned rstride = 1 << ((desc >> (SIMD_DATA_SHIFT + 1)) % 4); + uint32_t mtedesc = desc >> (SIMD_DATA_SHIFT + SVE_MTEDESC_SHIFT); + const intptr_t reg_max = simd_oprsz(desc); + const unsigned esize = 1 << esz; + intptr_t count_off, count_last; + intptr_t reg_off, reg_last, reg_n; + SVEContLdSt info; + unsigned estride, flags; + void *host; + + estride = sve2p1_cont_ldst_elements(&info, addr, png, reg_max, N, esz); + if (estride == 0) { + /* The entire predicate was false; no store occurs. */ + return; + } + + /* Probe the page(s). Exit with exception for any invalid page. */ + sve_cont_ldst_pages(&info, FAULT_ALL, env, addr, MMU_DATA_STORE, ra); + + /* Handle watchpoints for all active elements. */ + sve2p1_cont_ldst_watchpoints(&info, env, addr, estride, + esize, BP_MEM_WRITE, ra); + + /* + * Handle mte checks for all active elements. + * Since TBI must be set for MTE, !mtedesc => !mte_active. + */ + if (mtedesc) { + sve2p1_cont_ldst_mte_check(&info, env, estride, addr, + esize, mtedesc, ra); + } + + flags = info.page[0].flags | info.page[1].flags; + if (unlikely(flags != 0)) { + /* + * At least one page includes MMIO. + * Any bus operation can fail with cpu_transaction_failed, + * which for ARM will raise SyncExternal. Perform the load + * into scratch memory to preserve register state until the end. + */ + count_off = info.reg_off_first[0]; + count_last = info.reg_off_last[1]; + if (count_last < 0) { + count_last = info.reg_off_split; + if (count_last < 0) { + count_last = info.reg_off_last[0]; + } + } + reg_off = count_off % reg_max; + reg_n = count_off / reg_max; + + do { + reg_last = MIN(count_last - count_off, reg_max - esize); + do { + tlb_fn(env, &zd[reg_n * rstride], reg_off, addr + count_off, ra); + reg_off += estride; + count_off += estride; + } while (reg_off <= reg_last); + reg_off = 0; + reg_n++; + } while (count_off <= count_last); + return; + } + + /* The entire operation is in RAM, on valid pages. */ + + count_off = info.reg_off_first[0]; + count_last = info.reg_off_last[0]; + reg_off = count_off % reg_max; + reg_n = count_off / reg_max; + host = info.page[0].host; + + set_helper_retaddr(ra); + + do { + reg_last = MIN(count_last - reg_n * reg_max, reg_max - esize); + do { + host_fn(&zd[reg_n * rstride], reg_off, host + count_off); + reg_off += estride; + count_off += estride; + } while (reg_off <= reg_last); + reg_off = 0; + reg_n++; + } while (count_off <= count_last); + + clear_helper_retaddr(); + + /* + * Use the slow path to manage the cross-page misalignment. + * But we know this is RAM and cannot trap. + */ + count_off = info.reg_off_split; + if (unlikely(count_off >= 0)) { + reg_off = count_off % reg_max; + reg_n = count_off / reg_max; + tlb_fn(env, &zd[reg_n * rstride], reg_off, addr + count_off, ra); + } + + count_off = info.reg_off_first[1]; + if (unlikely(count_off >= 0)) { + count_last = info.reg_off_last[1]; + reg_off = count_off % reg_max; + reg_n = count_off / reg_max; + host = info.page[1].host; + + set_helper_retaddr(ra); + + do { + reg_last = MIN(count_last - reg_n * reg_max, reg_max - esize); + do { + host_fn(&zd[reg_n * rstride], reg_off, host + count_off); + reg_off += estride; + count_off += estride; + } while (reg_off <= reg_last); + reg_off = 0; + reg_n++; + } while (count_off <= count_last); + + clear_helper_retaddr(); + } +} + +void HELPER(sve2p1_st1bb_c)(CPUARMState *env, void *vd, target_ulong addr, + uint32_t png, uint32_t desc) +{ + sve2p1_st1_c(env, vd, addr, png, desc, GETPC(), MO_8, + sve_st1bb_host, sve_st1bb_tlb); +} + +#define DO_ST1_2(NAME, ESZ) \ +void HELPER(sve2p1_##NAME##_le_c)(CPUARMState *env, void *vd, \ + target_ulong addr, uint32_t png, \ + uint32_t desc) \ +{ \ + sve2p1_st1_c(env, vd, addr, png, desc, GETPC(), ESZ, \ + sve_##NAME##_le_host, sve_##NAME##_le_tlb); \ +} \ +void HELPER(sve2p1_##NAME##_be_c)(CPUARMState *env, void *vd, \ + target_ulong addr, uint32_t png, \ + uint32_t desc) \ +{ \ + sve2p1_st1_c(env, vd, addr, png, desc, GETPC(), ESZ, \ + sve_##NAME##_be_host, sve_##NAME##_be_tlb); \ +} + +DO_ST1_2(st1hh, MO_16) +DO_ST1_2(st1ss, MO_32) +DO_ST1_2(st1dd, MO_64) + +#undef DO_ST1_2 + void HELPER(sve2_eor3)(void *vd, void *vn, void *vm, void *vk, uint32_t desc) { intptr_t i, opr_sz = simd_oprsz(desc) / 8; @@ -7715,3 +8502,31 @@ DO_FCVTLT(sve2_fcvtlt_sd, uint64_t, uint32_t, H1_8, H1_4, float32_to_float64) #undef DO_FCVTLT #undef DO_FCVTNT + +void HELPER(pext)(void *vd, uint32_t png, uint32_t desc) +{ + int pl = FIELD_EX32(desc, PREDDESC, OPRSZ); + int vl = pl * 8; + unsigned v_esz = FIELD_EX32(desc, PREDDESC, ESZ); + int part = FIELD_EX32(desc, PREDDESC, DATA); + DecodeCounter p = decode_counter(png, vl, v_esz); + uint64_t mask = pred_esz_masks[v_esz + p.lg2_stride]; + ARMPredicateReg *d = vd; + + /* + * Convert from element count to byte count and adjust + * for the portion of the 4*VL counter to be extracted. + */ + int b_count = (p.count << v_esz) - vl * part; + + memset(d, 0, sizeof(*d)); + if (p.invert) { + if (b_count <= 0) { + do_whilel(vd, mask, vl, vl); + } else if (b_count < vl) { + do_whileg(vd, mask, vl - b_count, vl); + } + } else if (b_count > 0) { + do_whilel(vd, mask, MIN(b_count, vl), vl); + } +} diff --git a/target/arm/tcg/sve_ldst_internal.h b/target/arm/tcg/sve_ldst_internal.h index f2243da..c67cda9 100644 --- a/target/arm/tcg/sve_ldst_internal.h +++ b/target/arm/tcg/sve_ldst_internal.h @@ -116,6 +116,94 @@ DO_ST_PRIM_2(sd, H1_8, uint64_t, uint32_t, stl) DO_LD_PRIM_2(dd, H1_8, uint64_t, uint64_t, ldq) DO_ST_PRIM_2(dd, H1_8, uint64_t, uint64_t, stq) +#define DO_LD_PRIM_3(NAME, FUNC) \ + static inline void sve_##NAME##_host(void *vd, \ + intptr_t reg_off, void *host) \ + { sve_##FUNC##_host(vd, reg_off, host); \ + *(uint64_t *)(vd + reg_off + 8) = 0; } \ + static inline void sve_##NAME##_tlb(CPUARMState *env, void *vd, \ + intptr_t reg_off, target_ulong addr, uintptr_t ra) \ + { sve_##FUNC##_tlb(env, vd, reg_off, addr, ra); \ + *(uint64_t *)(vd + reg_off + 8) = 0; } + +DO_LD_PRIM_3(ld1squ_be, ld1sdu_be) +DO_LD_PRIM_3(ld1squ_le, ld1sdu_le) +DO_LD_PRIM_3(ld1dqu_be, ld1dd_be) +DO_LD_PRIM_3(ld1dqu_le, ld1dd_le) + +#define sve_st1sq_be_host sve_st1sd_be_host +#define sve_st1sq_le_host sve_st1sd_le_host +#define sve_st1sq_be_tlb sve_st1sd_be_tlb +#define sve_st1sq_le_tlb sve_st1sd_le_tlb + +#define sve_st1dq_be_host sve_st1dd_be_host +#define sve_st1dq_le_host sve_st1dd_le_host +#define sve_st1dq_be_tlb sve_st1dd_be_tlb +#define sve_st1dq_le_tlb sve_st1dd_le_tlb + +/* + * The ARMVectorReg elements are stored in host-endian 64-bit units. + * For 128-bit quantities, the sequence defined by the Elem[] pseudocode + * corresponds to storing the two 64-bit pieces in little-endian order. + */ +/* FIXME: Nothing in this file makes any effort at atomicity. */ + +static inline void sve_ld1qq_be_host(void *vd, intptr_t reg_off, void *host) +{ + sve_ld1dd_be_host(vd, reg_off + 8, host); + sve_ld1dd_be_host(vd, reg_off, host + 8); +} + +static inline void sve_ld1qq_le_host(void *vd, intptr_t reg_off, void *host) +{ + sve_ld1dd_le_host(vd, reg_off, host); + sve_ld1dd_le_host(vd, reg_off + 8, host + 8); +} + +static inline void +sve_ld1qq_be_tlb(CPUARMState *env, void *vd, intptr_t reg_off, + target_ulong addr, uintptr_t ra) +{ + sve_ld1dd_be_tlb(env, vd, reg_off + 8, addr, ra); + sve_ld1dd_be_tlb(env, vd, reg_off, addr + 8, ra); +} + +static inline void +sve_ld1qq_le_tlb(CPUARMState *env, void *vd, intptr_t reg_off, + target_ulong addr, uintptr_t ra) +{ + sve_ld1dd_le_tlb(env, vd, reg_off, addr, ra); + sve_ld1dd_le_tlb(env, vd, reg_off + 8, addr + 8, ra); +} + +static inline void sve_st1qq_be_host(void *vd, intptr_t reg_off, void *host) +{ + sve_st1dd_be_host(vd, reg_off + 8, host); + sve_st1dd_be_host(vd, reg_off, host + 8); +} + +static inline void sve_st1qq_le_host(void *vd, intptr_t reg_off, void *host) +{ + sve_st1dd_le_host(vd, reg_off, host); + sve_st1dd_le_host(vd, reg_off + 8, host + 8); +} + +static inline void +sve_st1qq_be_tlb(CPUARMState *env, void *vd, intptr_t reg_off, + target_ulong addr, uintptr_t ra) +{ + sve_st1dd_be_tlb(env, vd, reg_off + 8, addr, ra); + sve_st1dd_be_tlb(env, vd, reg_off, addr + 8, ra); +} + +static inline void +sve_st1qq_le_tlb(CPUARMState *env, void *vd, intptr_t reg_off, + target_ulong addr, uintptr_t ra) +{ + sve_st1dd_le_tlb(env, vd, reg_off, addr, ra); + sve_st1dd_le_tlb(env, vd, reg_off + 8, addr + 8, ra); +} + #undef DO_LD_TLB #undef DO_ST_TLB #undef DO_LD_HOST @@ -123,6 +211,7 @@ DO_ST_PRIM_2(dd, H1_8, uint64_t, uint64_t, stq) #undef DO_ST_PRIM_1 #undef DO_LD_PRIM_2 #undef DO_ST_PRIM_2 +#undef DO_LD_PRIM_3 /* * Resolve the guest virtual address to info->host and info->flags. diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 815225b..dbf4759 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -1381,11 +1381,8 @@ static bool fp_access_check_only(DisasContext *s) return true; } -static bool fp_access_check(DisasContext *s) +static bool nonstreaming_check(DisasContext *s) { - if (!fp_access_check_only(s)) { - return false; - } if (s->sme_trap_nonstreaming && s->is_nonstreaming) { gen_exception_insn(s, 0, EXCP_UDEF, syn_smetrap(SME_ET_Streaming, false)); @@ -1394,6 +1391,11 @@ static bool fp_access_check(DisasContext *s) return true; } +static bool fp_access_check(DisasContext *s) +{ + return fp_access_check_only(s) && nonstreaming_check(s); +} + /* * Return <0 for non-supported element sizes, with MO_16 controlled by * FEAT_FP16; return 0 for fp disabled; otherwise return >0 for success. @@ -1444,14 +1446,24 @@ static int fp_access_check_vector_hsd(DisasContext *s, bool is_q, MemOp esz) */ bool sve_access_check(DisasContext *s) { - if (s->pstate_sm || !dc_isar_feature(aa64_sve, s)) { + if (dc_isar_feature(aa64_sme, s)) { bool ret; - assert(dc_isar_feature(aa64_sme, s)); - ret = sme_sm_enabled_check(s); + if (s->pstate_sm) { + ret = sme_enabled_check(s); + } else if (dc_isar_feature(aa64_sve, s)) { + goto continue_sve; + } else { + ret = sme_sm_enabled_check(s); + } + if (ret) { + ret = nonstreaming_check(s); + } s->sve_access_checked = (ret ? 1 : -1); return ret; } + + continue_sve: if (s->sve_excp_el) { /* Assert that we only raise one exception per instruction. */ assert(!s->sve_access_checked); @@ -1488,7 +1500,8 @@ bool sme_enabled_check(DisasContext *s) * to be zero when fp_excp_el has priority. This is because we need * sme_excp_el by itself for cpregs access checks. */ - if (!s->fp_excp_el || s->sme_excp_el < s->fp_excp_el) { + if (s->sme_excp_el + && (!s->fp_excp_el || s->sme_excp_el <= s->fp_excp_el)) { bool ret = sme_access_check(s); s->fp_access_checked = (ret ? 1 : -1); return ret; @@ -6101,9 +6114,9 @@ static bool do_dot_vector_env(DisasContext *s, arg_qrrr_e *a, return true; } -TRANS_FEAT(SDOT_v, aa64_dp, do_dot_vector, a, gen_helper_gvec_sdot_b) -TRANS_FEAT(UDOT_v, aa64_dp, do_dot_vector, a, gen_helper_gvec_udot_b) -TRANS_FEAT(USDOT_v, aa64_i8mm, do_dot_vector, a, gen_helper_gvec_usdot_b) +TRANS_FEAT(SDOT_v, aa64_dp, do_dot_vector, a, gen_helper_gvec_sdot_4b) +TRANS_FEAT(UDOT_v, aa64_dp, do_dot_vector, a, gen_helper_gvec_udot_4b) +TRANS_FEAT(USDOT_v, aa64_i8mm, do_dot_vector, a, gen_helper_gvec_usdot_4b) TRANS_FEAT(BFDOT_v, aa64_bf16, do_dot_vector_env, a, gen_helper_gvec_bfdot) TRANS_FEAT(BFMMLA, aa64_bf16, do_dot_vector_env, a, gen_helper_gvec_bfmmla) TRANS_FEAT(SMMLA, aa64_i8mm, do_dot_vector, a, gen_helper_gvec_smmla_b) @@ -6863,12 +6876,12 @@ static bool do_dot_vector_idx_env(DisasContext *s, arg_qrrx_e *a, return true; } -TRANS_FEAT(SDOT_vi, aa64_dp, do_dot_vector_idx, a, gen_helper_gvec_sdot_idx_b) -TRANS_FEAT(UDOT_vi, aa64_dp, do_dot_vector_idx, a, gen_helper_gvec_udot_idx_b) +TRANS_FEAT(SDOT_vi, aa64_dp, do_dot_vector_idx, a, gen_helper_gvec_sdot_idx_4b) +TRANS_FEAT(UDOT_vi, aa64_dp, do_dot_vector_idx, a, gen_helper_gvec_udot_idx_4b) TRANS_FEAT(SUDOT_vi, aa64_i8mm, do_dot_vector_idx, a, - gen_helper_gvec_sudot_idx_b) + gen_helper_gvec_sudot_idx_4b) TRANS_FEAT(USDOT_vi, aa64_i8mm, do_dot_vector_idx, a, - gen_helper_gvec_usdot_idx_b) + gen_helper_gvec_usdot_idx_4b) TRANS_FEAT(BFDOT_vi, aa64_bf16, do_dot_vector_idx_env, a, gen_helper_gvec_bfdot_idx) @@ -10126,8 +10139,10 @@ static void aarch64_tr_init_disas_context(DisasContextBase *dcbase, dc->trap_eret = EX_TBFLAG_A64(tb_flags, TRAP_ERET); dc->sve_excp_el = EX_TBFLAG_A64(tb_flags, SVEEXC_EL); dc->sme_excp_el = EX_TBFLAG_A64(tb_flags, SMEEXC_EL); + dc->zt0_excp_el = EX_TBFLAG_A64(tb_flags, ZT0EXC_EL); dc->vl = (EX_TBFLAG_A64(tb_flags, VL) + 1) * 16; dc->svl = (EX_TBFLAG_A64(tb_flags, SVL) + 1) * 16; + dc->max_svl = arm_cpu->sme_max_vq * 16; dc->pauth_active = EX_TBFLAG_A64(tb_flags, PAUTH_ACTIVE); dc->bt = EX_TBFLAG_A64(tb_flags, BT); dc->btype = EX_TBFLAG_A64(tb_flags, BTYPE); diff --git a/target/arm/tcg/translate-a64.h b/target/arm/tcg/translate-a64.h index b2420f5..993dde6 100644 --- a/target/arm/tcg/translate-a64.h +++ b/target/arm/tcg/translate-a64.h @@ -225,7 +225,13 @@ void gen_gvec_usqadd_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); -void gen_sve_ldr(DisasContext *s, TCGv_ptr, int vofs, int len, int rn, int imm); -void gen_sve_str(DisasContext *s, TCGv_ptr, int vofs, int len, int rn, int imm); +void gen_gvec_sve2_sqdmulh(unsigned vece, uint32_t rd_ofs, + uint32_t rn_ofs, uint32_t rm_ofs, + uint32_t opr_sz, uint32_t max_sz); + +void gen_sve_ldr(DisasContext *s, TCGv_ptr, int vofs, + int len, int rn, int imm, MemOp align); +void gen_sve_str(DisasContext *s, TCGv_ptr, int vofs, + int len, int rn, int imm, MemOp align); #endif /* TARGET_ARM_TRANSLATE_A64_H */ diff --git a/target/arm/tcg/translate-neon.c b/target/arm/tcg/translate-neon.c index c4fecb8..844d2e2 100644 --- a/target/arm/tcg/translate-neon.c +++ b/target/arm/tcg/translate-neon.c @@ -271,7 +271,7 @@ static bool trans_VSDOT(DisasContext *s, arg_VSDOT *a) return false; } return do_neon_ddda(s, a->q * 7, a->vd, a->vn, a->vm, 0, - gen_helper_gvec_sdot_b); + gen_helper_gvec_sdot_4b); } static bool trans_VUDOT(DisasContext *s, arg_VUDOT *a) @@ -280,7 +280,7 @@ static bool trans_VUDOT(DisasContext *s, arg_VUDOT *a) return false; } return do_neon_ddda(s, a->q * 7, a->vd, a->vn, a->vm, 0, - gen_helper_gvec_udot_b); + gen_helper_gvec_udot_4b); } static bool trans_VUSDOT(DisasContext *s, arg_VUSDOT *a) @@ -289,7 +289,7 @@ static bool trans_VUSDOT(DisasContext *s, arg_VUSDOT *a) return false; } return do_neon_ddda(s, a->q * 7, a->vd, a->vn, a->vm, 0, - gen_helper_gvec_usdot_b); + gen_helper_gvec_usdot_4b); } static bool trans_VDOT_b16(DisasContext *s, arg_VDOT_b16 *a) @@ -356,7 +356,7 @@ static bool trans_VSDOT_scalar(DisasContext *s, arg_VSDOT_scalar *a) return false; } return do_neon_ddda(s, a->q * 6, a->vd, a->vn, a->vm, a->index, - gen_helper_gvec_sdot_idx_b); + gen_helper_gvec_sdot_idx_4b); } static bool trans_VUDOT_scalar(DisasContext *s, arg_VUDOT_scalar *a) @@ -365,7 +365,7 @@ static bool trans_VUDOT_scalar(DisasContext *s, arg_VUDOT_scalar *a) return false; } return do_neon_ddda(s, a->q * 6, a->vd, a->vn, a->vm, a->index, - gen_helper_gvec_udot_idx_b); + gen_helper_gvec_udot_idx_4b); } static bool trans_VUSDOT_scalar(DisasContext *s, arg_VUSDOT_scalar *a) @@ -374,7 +374,7 @@ static bool trans_VUSDOT_scalar(DisasContext *s, arg_VUSDOT_scalar *a) return false; } return do_neon_ddda(s, a->q * 6, a->vd, a->vn, a->vm, a->index, - gen_helper_gvec_usdot_idx_b); + gen_helper_gvec_usdot_idx_4b); } static bool trans_VSUDOT_scalar(DisasContext *s, arg_VSUDOT_scalar *a) @@ -383,7 +383,7 @@ static bool trans_VSUDOT_scalar(DisasContext *s, arg_VSUDOT_scalar *a) return false; } return do_neon_ddda(s, a->q * 6, a->vd, a->vn, a->vm, a->index, - gen_helper_gvec_sudot_idx_b); + gen_helper_gvec_sudot_idx_4b); } static bool trans_VDOT_b16_scal(DisasContext *s, arg_VDOT_b16_scal *a) @@ -1010,8 +1010,8 @@ DO_3S_FP_GVEC(VACGE, gen_helper_gvec_facge_s, gen_helper_gvec_facge_h) DO_3S_FP_GVEC(VACGT, gen_helper_gvec_facgt_s, gen_helper_gvec_facgt_h) DO_3S_FP_GVEC(VMAX, gen_helper_gvec_fmax_s, gen_helper_gvec_fmax_h) DO_3S_FP_GVEC(VMIN, gen_helper_gvec_fmin_s, gen_helper_gvec_fmin_h) -DO_3S_FP_GVEC(VMLA, gen_helper_gvec_fmla_s, gen_helper_gvec_fmla_h) -DO_3S_FP_GVEC(VMLS, gen_helper_gvec_fmls_s, gen_helper_gvec_fmls_h) +DO_3S_FP_GVEC(VMLA, gen_helper_gvec_fmla_nf_s, gen_helper_gvec_fmla_nf_h) +DO_3S_FP_GVEC(VMLS, gen_helper_gvec_fmls_nf_s, gen_helper_gvec_fmls_nf_h) DO_3S_FP_GVEC(VFMA, gen_helper_gvec_vfma_s, gen_helper_gvec_vfma_h) DO_3S_FP_GVEC(VFMS, gen_helper_gvec_vfms_s, gen_helper_gvec_vfms_h) DO_3S_FP_GVEC(VRECPS, gen_helper_gvec_recps_nf_s, gen_helper_gvec_recps_nf_h) diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c index fcbb350..65fc8bc 100644 --- a/target/arm/tcg/translate-sme.c +++ b/target/arm/tcg/translate-sme.c @@ -27,16 +27,25 @@ #include "decode-sme.c.inc" +static bool sme2_zt0_enabled_check(DisasContext *s) +{ + if (!sme_za_enabled_check(s)) { + return false; + } + if (s->zt0_excp_el) { + gen_exception_insn_el(s, 0, EXCP_UDEF, + syn_smetrap(SME_ET_InaccessibleZT0, false), + s->zt0_excp_el); + return false; + } + return true; +} -/* - * Resolve tile.size[index] to a host pointer, where tile and index - * are always decoded together, dependent on the element size. - */ +/* Resolve tile.size[rs+imm] to a host pointer. */ static TCGv_ptr get_tile_rowcol(DisasContext *s, int esz, int rs, - int tile_index, bool vertical) + int tile, int imm, int div_len, + int vec_mod, bool vertical) { - int tile = tile_index >> (4 - esz); - int index = esz == MO_128 ? 0 : extract32(tile_index, 0, 4 - esz); int pos, len, offset; TCGv_i32 tmp; TCGv_ptr addr; @@ -44,10 +53,23 @@ static TCGv_ptr get_tile_rowcol(DisasContext *s, int esz, int rs, /* Compute the final index, which is Rs+imm. */ tmp = tcg_temp_new_i32(); tcg_gen_trunc_tl_i32(tmp, cpu_reg(s, rs)); - tcg_gen_addi_i32(tmp, tmp, index); + /* + * Round the vector index down to a multiple of vec_mod if necessary. + * We do this before adding the offset, to handle cases like + * MOVA (tile to vector, 2 registers) where we want to call this + * several times in a loop with an increasing offset. We rely on + * the instruction encodings always forcing the initial offset in + * [rs + offset] to be a multiple of vec_mod. The pseudocode usually + * does the round-down after adding the offset rather than before, + * but MOVA is an exception. + */ + if (vec_mod > 1) { + tcg_gen_andc_i32(tmp, tmp, tcg_constant_i32(vec_mod - 1)); + } + tcg_gen_addi_i32(tmp, tmp, imm); /* Prepare a power-of-two modulo via extraction of @len bits. */ - len = ctz32(streaming_vec_reg_size(s)) - esz; + len = ctz32(streaming_vec_reg_size(s) / div_len) - esz; if (!len) { /* @@ -92,7 +114,7 @@ static TCGv_ptr get_tile_rowcol(DisasContext *s, int esz, int rs, offset = tile * sizeof(ARMVectorReg); /* Include the byte offset of zarray to make this relative to env. */ - offset += offsetof(CPUARMState, zarray); + offset += offsetof(CPUARMState, za_state.za); tcg_gen_addi_i32(tmp, tmp, offset); /* Add the byte offset to env to produce the final pointer. */ @@ -103,6 +125,14 @@ static TCGv_ptr get_tile_rowcol(DisasContext *s, int esz, int rs, return addr; } +/* Resolve ZArray[rs+imm] to a host pointer. */ +static TCGv_ptr get_zarray(DisasContext *s, int rs, int imm, + int div_len, int vec_mod) +{ + /* ZA[n] equates to ZA0H.B[n]. */ + return get_tile_rowcol(s, MO_8, rs, 0, imm, div_len, vec_mod, false); +} + /* * Resolve tile.size[0] to a host pointer. * Used by e.g. outer product insns where we require the entire tile. @@ -112,7 +142,7 @@ static TCGv_ptr get_tile(DisasContext *s, int esz, int tile) TCGv_ptr addr = tcg_temp_new_ptr(); int offset; - offset = tile * sizeof(ARMVectorReg) + offsetof(CPUARMState, zarray); + offset = tile * sizeof(ARMVectorReg) + offsetof(CPUARMState, za_state.za); tcg_gen_addi_ptr(addr, tcg_env, offset); return addr; @@ -130,7 +160,40 @@ static bool trans_ZERO(DisasContext *s, arg_ZERO *a) return true; } -static bool trans_MOVA(DisasContext *s, arg_MOVA *a) +static bool trans_ZERO_zt0(DisasContext *s, arg_ZERO_zt0 *a) +{ + if (!dc_isar_feature(aa64_sme2, s)) { + return false; + } + if (sme_enabled_check(s) && sme2_zt0_enabled_check(s)) { + tcg_gen_gvec_dup_imm(MO_64, offsetof(CPUARMState, za_state.zt0), + sizeof_field(CPUARMState, za_state.zt0), + sizeof_field(CPUARMState, za_state.zt0), 0); + } + return true; +} + +static bool trans_ZERO_za(DisasContext *s, arg_ZERO_za *a) +{ + if (!dc_isar_feature(aa64_sme2p1, s)) { + return false; + } + if (sme_smza_enabled_check(s)) { + int svl = streaming_vec_reg_size(s); + int vstride = svl / a->ngrp; + TCGv_ptr t_za = get_zarray(s, a->rv, a->off, a->ngrp, a->nvec); + + for (int r = 0; r < a->ngrp; ++r) { + for (int i = 0; i < a->nvec; ++i) { + int o_za = (r * vstride + i) * sizeof(ARMVectorReg); + tcg_gen_gvec_dup_imm_var(MO_64, t_za, o_za, svl, svl, 0); + } + } + } + return true; +} + +static bool do_mova_tile(DisasContext *s, arg_mova_p *a, bool to_vec) { static gen_helper_gvec_4 * const h_fns[5] = { gen_helper_sve_sel_zpzz_b, gen_helper_sve_sel_zpzz_h, @@ -152,14 +215,11 @@ static bool trans_MOVA(DisasContext *s, arg_MOVA *a) TCGv_i32 t_desc; int svl; - if (!dc_isar_feature(aa64_sme, s)) { - return false; - } if (!sme_smza_enabled_check(s)) { return true; } - t_za = get_tile_rowcol(s, a->esz, a->rs, a->za_imm, a->v); + t_za = get_tile_rowcol(s, a->esz, a->rs, a->za, a->off, 1, 0, a->v); t_zr = vec_full_reg_ptr(s, a->zr); t_pg = pred_full_reg_ptr(s, a->pg); @@ -168,14 +228,14 @@ static bool trans_MOVA(DisasContext *s, arg_MOVA *a) if (a->v) { /* Vertical slice -- use sme mova helpers. */ - if (a->to_vec) { + if (to_vec) { zc_fns[a->esz](t_zr, t_za, t_pg, t_desc); } else { cz_fns[a->esz](t_za, t_zr, t_pg, t_desc); } } else { /* Horizontal slice -- reuse sve sel helpers. */ - if (a->to_vec) { + if (to_vec) { h_fns[a->esz](t_zr, t_za, t_zr, t_pg, t_desc); } else { h_fns[a->esz](t_za, t_zr, t_za, t_pg, t_desc); @@ -184,6 +244,147 @@ static bool trans_MOVA(DisasContext *s, arg_MOVA *a) return true; } +TRANS_FEAT(MOVA_tz, aa64_sme, do_mova_tile, a, false) +TRANS_FEAT(MOVA_zt, aa64_sme, do_mova_tile, a, true) + +static bool do_mova_tile_n(DisasContext *s, arg_mova_t *a, int n, + bool to_vec, bool zero) +{ + static gen_helper_gvec_2 * const cz_fns[] = { + gen_helper_sme2_mova_cz_b, gen_helper_sme2_mova_cz_h, + gen_helper_sme2_mova_cz_s, gen_helper_sme2_mova_cz_d, + }; + static gen_helper_gvec_2 * const zc_fns[] = { + gen_helper_sme2_mova_zc_b, gen_helper_sme2_mova_zc_h, + gen_helper_sme2_mova_zc_s, gen_helper_sme2_mova_zc_d, + }; + static gen_helper_gvec_2 * const zc_z_fns[] = { + gen_helper_sme2p1_movaz_zc_b, gen_helper_sme2p1_movaz_zc_h, + gen_helper_sme2p1_movaz_zc_s, gen_helper_sme2p1_movaz_zc_d, + gen_helper_sme2p1_movaz_zc_q, + }; + TCGv_ptr t_za; + int svl, bytes_per_op = n << a->esz; + + /* + * The MaxImplementedSVL check happens in the decode pseudocode, + * before the SM+ZA enabled check in the operation pseudocode. + * This will (currently) only fail for NREG=4, ESZ=MO_64. + */ + if (s->max_svl < bytes_per_op) { + unallocated_encoding(s); + return true; + } + + assert(a->esz <= MO_64 + zero); + + if (!sme_smza_enabled_check(s)) { + return true; + } + + svl = streaming_vec_reg_size(s); + + /* + * The CurrentVL check happens in the operation pseudocode, + * after the SM+ZA enabled check. + */ + if (svl < bytes_per_op) { + unallocated_encoding(s); + return true; + } + + if (a->v) { + TCGv_i32 t_desc = tcg_constant_i32(simd_desc(svl, svl, 0)); + + for (int i = 0; i < n; ++i) { + TCGv_ptr t_zr = vec_full_reg_ptr(s, a->zr * n + i); + t_za = get_tile_rowcol(s, a->esz, a->rs, a->za, + a->off * n + i, 1, n, a->v); + if (zero) { + zc_z_fns[a->esz](t_zr, t_za, t_desc); + } else if (to_vec) { + zc_fns[a->esz](t_zr, t_za, t_desc); + } else { + cz_fns[a->esz](t_za, t_zr, t_desc); + } + } + } else { + for (int i = 0; i < n; ++i) { + int o_zr = vec_full_reg_offset(s, a->zr * n + i); + t_za = get_tile_rowcol(s, a->esz, a->rs, a->za, + a->off * n + i, 1, n, a->v); + if (to_vec) { + tcg_gen_gvec_mov_var(MO_8, tcg_env, o_zr, t_za, 0, svl, svl); + if (zero) { + tcg_gen_gvec_dup_imm_var(MO_8, t_za, 0, svl, svl, 0); + } + } else { + tcg_gen_gvec_mov_var(MO_8, t_za, 0, tcg_env, o_zr, svl, svl); + } + } + } + return true; +} + +TRANS_FEAT(MOVA_tz2, aa64_sme2, do_mova_tile_n, a, 2, false, false) +TRANS_FEAT(MOVA_tz4, aa64_sme2, do_mova_tile_n, a, 4, false, false) +TRANS_FEAT(MOVA_zt2, aa64_sme2, do_mova_tile_n, a, 2, true, false) +TRANS_FEAT(MOVA_zt4, aa64_sme2, do_mova_tile_n, a, 4, true, false) + +TRANS_FEAT(MOVAZ_zt, aa64_sme2p1, do_mova_tile_n, a, 1, true, true) +TRANS_FEAT(MOVAZ_zt2, aa64_sme2p1, do_mova_tile_n, a, 2, true, true) +TRANS_FEAT(MOVAZ_zt4, aa64_sme2p1, do_mova_tile_n, a, 4, true, true) + +static bool do_mova_array_n(DisasContext *s, arg_mova_a *a, int n, + bool to_vec, bool zero) +{ + TCGv_ptr t_za; + int svl; + + if (!sme_smza_enabled_check(s)) { + return true; + } + + svl = streaming_vec_reg_size(s); + t_za = get_zarray(s, a->rv, a->off, n, 0); + + for (int i = 0; i < n; ++i) { + int o_za = (svl / n * sizeof(ARMVectorReg)) * i; + int o_zr = vec_full_reg_offset(s, a->zr * n + i); + + if (to_vec) { + tcg_gen_gvec_mov_var(MO_8, tcg_env, o_zr, t_za, o_za, svl, svl); + if (zero) { + tcg_gen_gvec_dup_imm_var(MO_8, t_za, o_za, svl, svl, 0); + } + } else { + tcg_gen_gvec_mov_var(MO_8, t_za, o_za, tcg_env, o_zr, svl, svl); + } + } + return true; +} + +TRANS_FEAT(MOVA_az2, aa64_sme2, do_mova_array_n, a, 2, false, false) +TRANS_FEAT(MOVA_az4, aa64_sme2, do_mova_array_n, a, 4, false, false) +TRANS_FEAT(MOVA_za2, aa64_sme2, do_mova_array_n, a, 2, true, false) +TRANS_FEAT(MOVA_za4, aa64_sme2, do_mova_array_n, a, 4, true, false) + +TRANS_FEAT(MOVAZ_za2, aa64_sme2p1, do_mova_array_n, a, 2, true, true) +TRANS_FEAT(MOVAZ_za4, aa64_sme2p1, do_mova_array_n, a, 4, true, true) + +static bool do_movt(DisasContext *s, arg_MOVT_rzt *a, + void (*func)(TCGv_i64, TCGv_ptr, tcg_target_long)) +{ + if (sme2_zt0_enabled_check(s)) { + func(cpu_reg(s, a->rt), tcg_env, + offsetof(CPUARMState, za_state.zt0) + a->off * 8); + } + return true; +} + +TRANS_FEAT(MOVT_rzt, aa64_sme2, do_movt, a, tcg_gen_ld_i64) +TRANS_FEAT(MOVT_ztr, aa64_sme2, do_movt, a, tcg_gen_st_i64) + static bool trans_LDST1(DisasContext *s, arg_LDST1 *a) { typedef void GenLdSt1(TCGv_env, TCGv_ptr, TCGv_ptr, TCGv, TCGv_i32); @@ -225,7 +426,7 @@ static bool trans_LDST1(DisasContext *s, arg_LDST1 *a) return true; } - t_za = get_tile_rowcol(s, a->esz, a->rs, a->za_imm, a->v); + t_za = get_tile_rowcol(s, a->esz, a->rs, a->za, a->off, 1, 0, a->v); t_pg = pred_full_reg_ptr(s, a->pg); addr = tcg_temp_new_i64(); @@ -243,28 +444,37 @@ static bool trans_LDST1(DisasContext *s, arg_LDST1 *a) return true; } -typedef void GenLdStR(DisasContext *, TCGv_ptr, int, int, int, int); +typedef void GenLdStR(DisasContext *, TCGv_ptr, int, int, int, int, MemOp); static bool do_ldst_r(DisasContext *s, arg_ldstr *a, GenLdStR *fn) { - int svl = streaming_vec_reg_size(s); - int imm = a->imm; - TCGv_ptr base; + if (sme_za_enabled_check(s)) { + int svl = streaming_vec_reg_size(s); + int imm = a->imm; + TCGv_ptr base = get_zarray(s, a->rv, imm, 1, 0); - if (!sme_za_enabled_check(s)) { - return true; + fn(s, base, 0, svl, a->rn, imm * svl, + s->align_mem ? MO_ALIGN_16 : MO_UNALN); } - - /* ZA[n] equates to ZA0H.B[n]. */ - base = get_tile_rowcol(s, MO_8, a->rv, imm, false); - - fn(s, base, 0, svl, a->rn, imm * svl); return true; } TRANS_FEAT(LDR, aa64_sme, do_ldst_r, a, gen_sve_ldr) TRANS_FEAT(STR, aa64_sme, do_ldst_r, a, gen_sve_str) +static bool do_ldst_zt0(DisasContext *s, arg_ldstzt0 *a, GenLdStR *fn) +{ + if (sme2_zt0_enabled_check(s)) { + fn(s, tcg_env, offsetof(CPUARMState, za_state.zt0), + sizeof_field(CPUARMState, za_state.zt0), a->rn, 0, + s->align_mem ? MO_ALIGN_16 : MO_UNALN); + } + return true; +} + +TRANS_FEAT(LDR_zt0, aa64_sme2, do_ldst_zt0, a, gen_sve_ldr) +TRANS_FEAT(STR_zt0, aa64_sme2, do_ldst_zt0, a, gen_sve_str) + static bool do_adda(DisasContext *s, arg_adda *a, MemOp esz, gen_helper_gvec_4 *fn) { @@ -316,7 +526,7 @@ static bool do_outprod_fpst(DisasContext *s, arg_op *a, MemOp esz, gen_helper_gvec_5_ptr *fn) { int svl = streaming_vec_reg_size(s); - uint32_t desc = simd_desc(svl, svl, a->sub); + uint32_t desc = simd_desc(svl, svl, 0); TCGv_ptr za, zn, zm, pn, pm, fpst; if (!sme_smza_enabled_check(s)) { @@ -338,7 +548,7 @@ static bool do_outprod_env(DisasContext *s, arg_op *a, MemOp esz, gen_helper_gvec_5_ptr *fn) { int svl = streaming_vec_reg_size(s); - uint32_t desc = simd_desc(svl, svl, a->sub); + uint32_t desc = simd_desc(svl, svl, 0); TCGv_ptr za, zn, zm, pn, pm; if (!sme_smza_enabled_check(s)) { @@ -355,14 +565,32 @@ static bool do_outprod_env(DisasContext *s, arg_op *a, MemOp esz, return true; } -TRANS_FEAT(FMOPA_h, aa64_sme, do_outprod_env, a, - MO_32, gen_helper_sme_fmopa_h) -TRANS_FEAT(FMOPA_s, aa64_sme, do_outprod_fpst, a, - MO_32, FPST_A64, gen_helper_sme_fmopa_s) -TRANS_FEAT(FMOPA_d, aa64_sme_f64f64, do_outprod_fpst, a, - MO_64, FPST_A64, gen_helper_sme_fmopa_d) +TRANS_FEAT(FMOPA_w_h, aa64_sme, do_outprod_env, a, MO_32, + !a->sub ? gen_helper_sme_fmopa_w_h + : !s->fpcr_ah ? gen_helper_sme_fmops_w_h + : gen_helper_sme_ah_fmops_w_h) +TRANS_FEAT(FMOPA_h, aa64_sme_f16f16, do_outprod_fpst, a, MO_16, FPST_ZA_F16, + !a->sub ? gen_helper_sme_fmopa_h + : !s->fpcr_ah ? gen_helper_sme_fmops_h + : gen_helper_sme_ah_fmops_h) +TRANS_FEAT(FMOPA_s, aa64_sme, do_outprod_fpst, a, MO_32, FPST_ZA, + !a->sub ? gen_helper_sme_fmopa_s + : !s->fpcr_ah ? gen_helper_sme_fmops_s + : gen_helper_sme_ah_fmops_s) +TRANS_FEAT(FMOPA_d, aa64_sme_f64f64, do_outprod_fpst, a, MO_64, FPST_ZA, + !a->sub ? gen_helper_sme_fmopa_d + : !s->fpcr_ah ? gen_helper_sme_fmops_d + : gen_helper_sme_ah_fmops_d) + +TRANS_FEAT(BFMOPA, aa64_sme_b16b16, do_outprod_fpst, a, MO_16, FPST_ZA, + !a->sub ? gen_helper_sme_bfmopa + : !s->fpcr_ah ? gen_helper_sme_bfmops + : gen_helper_sme_ah_bfmops) -TRANS_FEAT(BFMOPA, aa64_sme, do_outprod_env, a, MO_32, gen_helper_sme_bfmopa) +TRANS_FEAT(BFMOPA_w, aa64_sme, do_outprod_env, a, MO_32, + !a->sub ? gen_helper_sme_bfmopa_w + : !s->fpcr_ah ? gen_helper_sme_bfmops_w + : gen_helper_sme_ah_bfmops_w) TRANS_FEAT(SMOPA_s, aa64_sme, do_outprod, a, MO_32, gen_helper_sme_smopa_s) TRANS_FEAT(UMOPA_s, aa64_sme, do_outprod, a, MO_32, gen_helper_sme_umopa_s) @@ -373,3 +601,1173 @@ TRANS_FEAT(SMOPA_d, aa64_sme_i16i64, do_outprod, a, MO_64, gen_helper_sme_smopa_ TRANS_FEAT(UMOPA_d, aa64_sme_i16i64, do_outprod, a, MO_64, gen_helper_sme_umopa_d) TRANS_FEAT(SUMOPA_d, aa64_sme_i16i64, do_outprod, a, MO_64, gen_helper_sme_sumopa_d) TRANS_FEAT(USMOPA_d, aa64_sme_i16i64, do_outprod, a, MO_64, gen_helper_sme_usmopa_d) + +TRANS_FEAT(BMOPA, aa64_sme2, do_outprod, a, MO_32, gen_helper_sme2_bmopa_s) +TRANS_FEAT(SMOPA2_s, aa64_sme2, do_outprod, a, MO_32, gen_helper_sme2_smopa2_s) +TRANS_FEAT(UMOPA2_s, aa64_sme2, do_outprod, a, MO_32, gen_helper_sme2_umopa2_s) + +static bool do_z2z_n1(DisasContext *s, arg_z2z_en *a, GVecGen3Fn *fn) +{ + int esz, dn, vsz, mofs, n; + bool overlap = false; + + if (!sme_sm_enabled_check(s)) { + return true; + } + + esz = a->esz; + n = a->n; + dn = a->zdn; + mofs = vec_full_reg_offset(s, a->zm); + vsz = streaming_vec_reg_size(s); + + for (int i = 0; i < n; i++) { + int dofs = vec_full_reg_offset(s, dn + i); + if (dofs == mofs) { + overlap = true; + } else { + fn(esz, dofs, dofs, mofs, vsz, vsz); + } + } + if (overlap) { + fn(esz, mofs, mofs, mofs, vsz, vsz); + } + return true; +} + +static void gen_sme2_srshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static gen_helper_gvec_3 * const fns[] = { + gen_helper_gvec_srshl_b, gen_helper_sme2_srshl_h, + gen_helper_sme2_srshl_s, gen_helper_sme2_srshl_d, + }; + tcg_debug_assert(vece <= MO_64); + tcg_gen_gvec_3_ool(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, 0, fns[vece]); +} + +static void gen_sme2_urshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static gen_helper_gvec_3 * const fns[] = { + gen_helper_gvec_urshl_b, gen_helper_sme2_urshl_h, + gen_helper_sme2_urshl_s, gen_helper_sme2_urshl_d, + }; + tcg_debug_assert(vece <= MO_64); + tcg_gen_gvec_3_ool(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, 0, fns[vece]); +} + +TRANS_FEAT(ADD_n1, aa64_sme2, do_z2z_n1, a, tcg_gen_gvec_add) +TRANS_FEAT(SMAX_n1, aa64_sme2, do_z2z_n1, a, tcg_gen_gvec_smax) +TRANS_FEAT(SMIN_n1, aa64_sme2, do_z2z_n1, a, tcg_gen_gvec_smin) +TRANS_FEAT(UMAX_n1, aa64_sme2, do_z2z_n1, a, tcg_gen_gvec_umax) +TRANS_FEAT(UMIN_n1, aa64_sme2, do_z2z_n1, a, tcg_gen_gvec_umin) +TRANS_FEAT(SRSHL_n1, aa64_sme2, do_z2z_n1, a, gen_sme2_srshl) +TRANS_FEAT(URSHL_n1, aa64_sme2, do_z2z_n1, a, gen_sme2_urshl) +TRANS_FEAT(SQDMULH_n1, aa64_sme2, do_z2z_n1, a, gen_gvec_sve2_sqdmulh) + +static bool do_z2z_nn(DisasContext *s, arg_z2z_en *a, GVecGen3Fn *fn) +{ + int esz, dn, dm, vsz, n; + + if (!sme_sm_enabled_check(s)) { + return true; + } + + esz = a->esz; + n = a->n; + dn = a->zdn; + dm = a->zm; + vsz = streaming_vec_reg_size(s); + + for (int i = 0; i < n; i++) { + int dofs = vec_full_reg_offset(s, dn + i); + int mofs = vec_full_reg_offset(s, dm + i); + + fn(esz, dofs, dofs, mofs, vsz, vsz); + } + return true; +} + +TRANS_FEAT(SMAX_nn, aa64_sme2, do_z2z_nn, a, tcg_gen_gvec_smax) +TRANS_FEAT(SMIN_nn, aa64_sme2, do_z2z_nn, a, tcg_gen_gvec_smin) +TRANS_FEAT(UMAX_nn, aa64_sme2, do_z2z_nn, a, tcg_gen_gvec_umax) +TRANS_FEAT(UMIN_nn, aa64_sme2, do_z2z_nn, a, tcg_gen_gvec_umin) +TRANS_FEAT(SRSHL_nn, aa64_sme2, do_z2z_nn, a, gen_sme2_srshl) +TRANS_FEAT(URSHL_nn, aa64_sme2, do_z2z_nn, a, gen_sme2_urshl) +TRANS_FEAT(SQDMULH_nn, aa64_sme2, do_z2z_nn, a, gen_gvec_sve2_sqdmulh) + +static bool do_z2z_n1_fpst(DisasContext *s, arg_z2z_en *a, + gen_helper_gvec_3_ptr * const fns[4]) +{ + int esz = a->esz, n, dn, vsz, mofs; + bool overlap = false; + gen_helper_gvec_3_ptr *fn; + TCGv_ptr fpst; + + /* These insns use MO_8 to encode BFloat16. */ + if (esz == MO_8 && !dc_isar_feature(aa64_sme_b16b16, s)) { + return false; + } + if (!sme_sm_enabled_check(s)) { + return true; + } + + fpst = fpstatus_ptr(esz == MO_16 ? FPST_A64_F16 : FPST_A64); + fn = fns[esz]; + n = a->n; + dn = a->zdn; + mofs = vec_full_reg_offset(s, a->zm); + vsz = streaming_vec_reg_size(s); + + for (int i = 0; i < n; i++) { + int dofs = vec_full_reg_offset(s, dn + i); + if (dofs == mofs) { + overlap = true; + } else { + tcg_gen_gvec_3_ptr(dofs, dofs, mofs, fpst, vsz, vsz, 0, fn); + } + } + if (overlap) { + tcg_gen_gvec_3_ptr(mofs, mofs, mofs, fpst, vsz, vsz, 0, fn); + } + return true; +} + +static bool do_z2z_nn_fpst(DisasContext *s, arg_z2z_en *a, + gen_helper_gvec_3_ptr * const fns[4]) +{ + int esz = a->esz, n, dn, dm, vsz; + gen_helper_gvec_3_ptr *fn; + TCGv_ptr fpst; + + if (esz == MO_8 && !dc_isar_feature(aa64_sme_b16b16, s)) { + return false; + } + if (!sme_sm_enabled_check(s)) { + return true; + } + + fpst = fpstatus_ptr(esz == MO_16 ? FPST_A64_F16 : FPST_A64); + fn = fns[esz]; + n = a->n; + dn = a->zdn; + dm = a->zm; + vsz = streaming_vec_reg_size(s); + + for (int i = 0; i < n; i++) { + int dofs = vec_full_reg_offset(s, dn + i); + int mofs = vec_full_reg_offset(s, dm + i); + + tcg_gen_gvec_3_ptr(dofs, dofs, mofs, fpst, vsz, vsz, 0, fn); + } + return true; +} + +static gen_helper_gvec_3_ptr * const f_vector_fmax[2][4] = { + { gen_helper_gvec_fmax_b16, + gen_helper_gvec_fmax_h, + gen_helper_gvec_fmax_s, + gen_helper_gvec_fmax_d }, + { gen_helper_gvec_ah_fmax_b16, + gen_helper_gvec_ah_fmax_h, + gen_helper_gvec_ah_fmax_s, + gen_helper_gvec_ah_fmax_d }, +}; +TRANS_FEAT(FMAX_n1, aa64_sme2, do_z2z_n1_fpst, a, f_vector_fmax[s->fpcr_ah]) +TRANS_FEAT(FMAX_nn, aa64_sme2, do_z2z_nn_fpst, a, f_vector_fmax[s->fpcr_ah]) + +static gen_helper_gvec_3_ptr * const f_vector_fmin[2][4] = { + { gen_helper_gvec_fmin_b16, + gen_helper_gvec_fmin_h, + gen_helper_gvec_fmin_s, + gen_helper_gvec_fmin_d }, + { gen_helper_gvec_ah_fmin_b16, + gen_helper_gvec_ah_fmin_h, + gen_helper_gvec_ah_fmin_s, + gen_helper_gvec_ah_fmin_d }, +}; +TRANS_FEAT(FMIN_n1, aa64_sme2, do_z2z_n1_fpst, a, f_vector_fmin[s->fpcr_ah]) +TRANS_FEAT(FMIN_nn, aa64_sme2, do_z2z_nn_fpst, a, f_vector_fmin[s->fpcr_ah]) + +static gen_helper_gvec_3_ptr * const f_vector_fmaxnm[4] = { + gen_helper_gvec_fmaxnum_b16, + gen_helper_gvec_fmaxnum_h, + gen_helper_gvec_fmaxnum_s, + gen_helper_gvec_fmaxnum_d, +}; +TRANS_FEAT(FMAXNM_n1, aa64_sme2, do_z2z_n1_fpst, a, f_vector_fmaxnm) +TRANS_FEAT(FMAXNM_nn, aa64_sme2, do_z2z_nn_fpst, a, f_vector_fmaxnm) + +static gen_helper_gvec_3_ptr * const f_vector_fminnm[4] = { + gen_helper_gvec_fminnum_b16, + gen_helper_gvec_fminnum_h, + gen_helper_gvec_fminnum_s, + gen_helper_gvec_fminnum_d, +}; +TRANS_FEAT(FMINNM_n1, aa64_sme2, do_z2z_n1_fpst, a, f_vector_fminnm) +TRANS_FEAT(FMINNM_nn, aa64_sme2, do_z2z_nn_fpst, a, f_vector_fminnm) + +/* Add/Sub vector Z[m] to each Z[n*N] with result in ZA[d*N]. */ +static bool do_azz_n1(DisasContext *s, arg_azz_n *a, int esz, + GVecGen3FnVar *fn) +{ + TCGv_ptr t_za; + int svl, n, o_zm; + + if (!sme_smza_enabled_check(s)) { + return true; + } + + n = a->n; + t_za = get_zarray(s, a->rv, a->off, n, 0); + o_zm = vec_full_reg_offset(s, a->zm); + svl = streaming_vec_reg_size(s); + + for (int i = 0; i < n; ++i) { + int o_za = (svl / n * sizeof(ARMVectorReg)) * i; + int o_zn = vec_full_reg_offset(s, (a->zn + i) % 32); + + fn(esz, t_za, o_za, tcg_env, o_zn, tcg_env, o_zm, svl, svl); + } + return true; +} + +TRANS_FEAT(ADD_azz_n1_s, aa64_sme2, do_azz_n1, a, MO_32, tcg_gen_gvec_add_var) +TRANS_FEAT(SUB_azz_n1_s, aa64_sme2, do_azz_n1, a, MO_32, tcg_gen_gvec_sub_var) +TRANS_FEAT(ADD_azz_n1_d, aa64_sme2_i16i64, do_azz_n1, a, MO_64, tcg_gen_gvec_add_var) +TRANS_FEAT(SUB_azz_n1_d, aa64_sme2_i16i64, do_azz_n1, a, MO_64, tcg_gen_gvec_sub_var) + +/* Add/Sub each vector Z[m*N] to each Z[n*N] with result in ZA[d*N]. */ +static bool do_azz_nn(DisasContext *s, arg_azz_n *a, int esz, + GVecGen3FnVar *fn) +{ + TCGv_ptr t_za; + int svl, n; + + if (!sme_smza_enabled_check(s)) { + return true; + } + + n = a->n; + t_za = get_zarray(s, a->rv, a->off, n, 1); + svl = streaming_vec_reg_size(s); + + for (int i = 0; i < n; ++i) { + int o_za = (svl / n * sizeof(ARMVectorReg)) * i; + int o_zn = vec_full_reg_offset(s, a->zn + i); + int o_zm = vec_full_reg_offset(s, a->zm + i); + + fn(esz, t_za, o_za, tcg_env, o_zn, tcg_env, o_zm, svl, svl); + } + return true; +} + +TRANS_FEAT(ADD_azz_nn_s, aa64_sme2, do_azz_nn, a, MO_32, tcg_gen_gvec_add_var) +TRANS_FEAT(SUB_azz_nn_s, aa64_sme2, do_azz_nn, a, MO_32, tcg_gen_gvec_sub_var) +TRANS_FEAT(ADD_azz_nn_d, aa64_sme2_i16i64, do_azz_nn, a, MO_64, tcg_gen_gvec_add_var) +TRANS_FEAT(SUB_azz_nn_d, aa64_sme2_i16i64, do_azz_nn, a, MO_64, tcg_gen_gvec_sub_var) + +/* Add/Sub each ZA[d*N] += Z[m*N] */ +static bool do_aaz(DisasContext *s, arg_az_n *a, int esz, GVecGen3FnVar *fn) +{ + TCGv_ptr t_za; + int svl, n; + + if (!sme_smza_enabled_check(s)) { + return true; + } + + n = a->n; + t_za = get_zarray(s, a->rv, a->off, n, 0); + svl = streaming_vec_reg_size(s); + + for (int i = 0; i < n; ++i) { + int o_za = (svl / n * sizeof(ARMVectorReg)) * i; + int o_zm = vec_full_reg_offset(s, a->zm + i); + + fn(esz, t_za, o_za, t_za, o_za, tcg_env, o_zm, svl, svl); + } + return true; +} + +TRANS_FEAT(ADD_aaz_s, aa64_sme2, do_aaz, a, MO_32, tcg_gen_gvec_add_var) +TRANS_FEAT(SUB_aaz_s, aa64_sme2, do_aaz, a, MO_32, tcg_gen_gvec_sub_var) +TRANS_FEAT(ADD_aaz_d, aa64_sme2_i16i64, do_aaz, a, MO_64, tcg_gen_gvec_add_var) +TRANS_FEAT(SUB_aaz_d, aa64_sme2_i16i64, do_aaz, a, MO_64, tcg_gen_gvec_sub_var) + +/* + * Expand array multi-vector single (n1), array multi-vector (nn), + * and array multi-vector indexed (nx), for floating-point accumulate. + * multi: true for nn, false for n1. + * fpst: >= 0 to set ptr argument for FPST_*, < 0 for ENV. + * data: stuff for simd_data, including any index. + */ +#define FPST_ENV -1 + +static bool do_azz_fp(DisasContext *s, int nreg, int nsel, + int rv, int off, int zn, int zm, + int data, int shsel, bool multi, int fpst, + gen_helper_gvec_3_ptr *fn) +{ + if (sme_smza_enabled_check(s)) { + int svl = streaming_vec_reg_size(s); + int vstride = svl / nreg; + TCGv_ptr t_za = get_zarray(s, rv, off, nreg, nsel); + TCGv_ptr t, ptr; + + if (fpst >= 0) { + ptr = fpstatus_ptr(fpst); + } else { + ptr = tcg_env; + } + t = tcg_temp_new_ptr(); + + for (int r = 0; r < nreg; ++r) { + TCGv_ptr t_zn = vec_full_reg_ptr(s, zn); + TCGv_ptr t_zm = vec_full_reg_ptr(s, zm); + + for (int i = 0; i < nsel; ++i) { + int o_za = (r * vstride + i) * sizeof(ARMVectorReg); + int desc = simd_desc(svl, svl, data | (i << shsel)); + + tcg_gen_addi_ptr(t, t_za, o_za); + fn(t, t_zn, t_zm, ptr, tcg_constant_i32(desc)); + } + + /* + * For multiple-and-single vectors, Zn may wrap. + * For multiple vectors, both Zn and Zm are aligned. + */ + zn = (zn + 1) % 32; + zm += multi; + } + } + return true; +} + +static bool do_azz_acc_fp(DisasContext *s, int nreg, int nsel, + int rv, int off, int zn, int zm, + int data, int shsel, bool multi, int fpst, + gen_helper_gvec_4_ptr *fn) +{ + if (sme_smza_enabled_check(s)) { + int svl = streaming_vec_reg_size(s); + int vstride = svl / nreg; + TCGv_ptr t_za = get_zarray(s, rv, off, nreg, nsel); + TCGv_ptr t, ptr; + + if (fpst >= 0) { + ptr = fpstatus_ptr(fpst); + } else { + ptr = tcg_env; + } + t = tcg_temp_new_ptr(); + + for (int r = 0; r < nreg; ++r) { + TCGv_ptr t_zn = vec_full_reg_ptr(s, zn); + TCGv_ptr t_zm = vec_full_reg_ptr(s, zm); + + for (int i = 0; i < nsel; ++i) { + int o_za = (r * vstride + i) * sizeof(ARMVectorReg); + int desc = simd_desc(svl, svl, data | (i << shsel)); + + tcg_gen_addi_ptr(t, t_za, o_za); + fn(t, t_zn, t_zm, t, ptr, tcg_constant_i32(desc)); + } + + /* + * For multiple-and-single vectors, Zn may wrap. + * For multiple vectors, both Zn and Zm are aligned. + */ + zn = (zn + 1) % 32; + zm += multi; + } + } + return true; +} + +static bool do_fmlal(DisasContext *s, arg_azz_n *a, bool sub, bool multi) +{ + return do_azz_acc_fp(s, a->n, 2, a->rv, a->off, a->zn, a->zm, + (1 << 2) | sub, 1, + multi, FPST_ENV, gen_helper_sve2_fmlal_zzzw_s); +} + +TRANS_FEAT(FMLAL_n1, aa64_sme2, do_fmlal, a, false, false) +TRANS_FEAT(FMLSL_n1, aa64_sme2, do_fmlal, a, true, false) +TRANS_FEAT(FMLAL_nn, aa64_sme2, do_fmlal, a, false, true) +TRANS_FEAT(FMLSL_nn, aa64_sme2, do_fmlal, a, true, true) + +static bool do_fmlal_nx(DisasContext *s, arg_azx_n *a, bool sub) +{ + return do_azz_acc_fp(s, a->n, 2, a->rv, a->off, a->zn, a->zm, + (a->idx << 3) | (1 << 2) | sub, 1, + false, FPST_ENV, gen_helper_sve2_fmlal_zzxw_s); +} + +TRANS_FEAT(FMLAL_nx, aa64_sme2, do_fmlal_nx, a, false) +TRANS_FEAT(FMLSL_nx, aa64_sme2, do_fmlal_nx, a, true) + +static bool do_bfmlal(DisasContext *s, arg_azz_n *a, bool sub, bool multi) +{ + return do_azz_acc_fp(s, a->n, 2, a->rv, a->off, a->zn, a->zm, + 0, 0, multi, FPST_ZA, + (!sub ? gen_helper_gvec_bfmlal + : s->fpcr_ah ? gen_helper_gvec_ah_bfmlsl + : gen_helper_gvec_bfmlsl)); +} + +TRANS_FEAT(BFMLAL_n1, aa64_sme2, do_bfmlal, a, false, false) +TRANS_FEAT(BFMLSL_n1, aa64_sme2, do_bfmlal, a, true, false) +TRANS_FEAT(BFMLAL_nn, aa64_sme2, do_bfmlal, a, false, true) +TRANS_FEAT(BFMLSL_nn, aa64_sme2, do_bfmlal, a, true, true) + +static bool do_bfmlal_nx(DisasContext *s, arg_azx_n *a, bool sub) +{ + return do_azz_acc_fp(s, a->n, 2, a->rv, a->off, a->zn, a->zm, + a->idx << 1, 0, false, FPST_ZA, + !sub ? gen_helper_gvec_bfmlal_idx + : s->fpcr_ah ? gen_helper_gvec_ah_bfmlsl_idx + : gen_helper_gvec_bfmlsl_idx); +} + +TRANS_FEAT(BFMLAL_nx, aa64_sme2, do_bfmlal_nx, a, false) +TRANS_FEAT(BFMLSL_nx, aa64_sme2, do_bfmlal_nx, a, true) + +static bool do_fdot(DisasContext *s, arg_azz_n *a, bool multi) +{ + return do_azz_acc_fp(s, a->n, 1, a->rv, a->off, a->zn, a->zm, 1, 0, + multi, FPST_ENV, gen_helper_sme2_fdot_h); +} + +TRANS_FEAT(FDOT_n1, aa64_sme2, do_fdot, a, false) +TRANS_FEAT(FDOT_nn, aa64_sme2, do_fdot, a, true) + +static bool do_fdot_nx(DisasContext *s, arg_azx_n *a) +{ + return do_azz_acc_fp(s, a->n, 1, a->rv, a->off, a->zn, a->zm, + a->idx | (1 << 2), 0, false, FPST_ENV, + gen_helper_sme2_fdot_idx_h); +} + +TRANS_FEAT(FDOT_nx, aa64_sme2, do_fdot_nx, a) + +static bool do_bfdot(DisasContext *s, arg_azz_n *a, bool multi) +{ + return do_azz_acc_fp(s, a->n, 1, a->rv, a->off, a->zn, a->zm, 0, 0, + multi, FPST_ENV, gen_helper_gvec_bfdot); +} + +TRANS_FEAT(BFDOT_n1, aa64_sme2, do_bfdot, a, false) +TRANS_FEAT(BFDOT_nn, aa64_sme2, do_bfdot, a, true) + +static bool do_bfdot_nx(DisasContext *s, arg_azx_n *a) +{ + return do_azz_acc_fp(s, a->n, 1, a->rv, a->off, a->zn, a->zm, a->idx, 0, + false, FPST_ENV, gen_helper_gvec_bfdot_idx); +} + +TRANS_FEAT(BFDOT_nx, aa64_sme2, do_bfdot_nx, a) + +static bool do_vdot(DisasContext *s, arg_azx_n *a, gen_helper_gvec_4_ptr *fn) +{ + if (sme_smza_enabled_check(s)) { + int svl = streaming_vec_reg_size(s); + int vstride = svl / 2; + TCGv_ptr t_za = get_zarray(s, a->rv, a->off, 2, 1); + TCGv_ptr t_zn = vec_full_reg_ptr(s, a->zn); + TCGv_ptr t_zm = vec_full_reg_ptr(s, a->zm); + TCGv_ptr t = tcg_temp_new_ptr(); + + for (int i = 0; i < 2; ++i) { + int o_za = i * vstride * sizeof(ARMVectorReg); + int desc = simd_desc(svl, svl, a->idx | (i << 2)); + + tcg_gen_addi_ptr(t, t_za, o_za); + fn(t, t_zn, t_zm, t, tcg_env, tcg_constant_i32(desc)); + } + } + return true; +} + +TRANS_FEAT(FVDOT, aa64_sme, do_vdot, a, gen_helper_sme2_fvdot_idx_h) +TRANS_FEAT(BFVDOT, aa64_sme, do_vdot, a, gen_helper_sme2_bfvdot_idx) + +static bool do_fmla(DisasContext *s, arg_azz_n *a, bool multi, + ARMFPStatusFlavour fpst, gen_helper_gvec_3_ptr *fn) +{ + return do_azz_fp(s, a->n, 1, a->rv, a->off, a->zn, a->zm, + 0, 0, multi, fpst, fn); +} + +TRANS_FEAT(FMLA_n1_h, aa64_sme_f16f16, do_fmla, a, false, FPST_ZA_F16, + gen_helper_gvec_vfma_h) +TRANS_FEAT(FMLS_n1_h, aa64_sme_f16f16, do_fmla, a, false, FPST_ZA_F16, + s->fpcr_ah ? gen_helper_gvec_ah_vfms_h : gen_helper_gvec_vfms_h) +TRANS_FEAT(FMLA_nn_h, aa64_sme_f16f16, do_fmla, a, true, FPST_ZA_F16, + gen_helper_gvec_vfma_h) +TRANS_FEAT(FMLS_nn_h, aa64_sme_f16f16, do_fmla, a, true, FPST_ZA_F16, + s->fpcr_ah ? gen_helper_gvec_ah_vfms_h : gen_helper_gvec_vfms_h) + +TRANS_FEAT(FMLA_n1_s, aa64_sme2, do_fmla, a, false, FPST_ZA, + gen_helper_gvec_vfma_s) +TRANS_FEAT(FMLS_n1_s, aa64_sme2, do_fmla, a, false, FPST_ZA, + s->fpcr_ah ? gen_helper_gvec_ah_vfms_s : gen_helper_gvec_vfms_s) +TRANS_FEAT(FMLA_nn_s, aa64_sme2, do_fmla, a, true, FPST_ZA, + gen_helper_gvec_vfma_s) +TRANS_FEAT(FMLS_nn_s, aa64_sme2, do_fmla, a, true, FPST_ZA, + s->fpcr_ah ? gen_helper_gvec_ah_vfms_s : gen_helper_gvec_vfms_s) + +TRANS_FEAT(FMLA_n1_d, aa64_sme2_f64f64, do_fmla, a, false, FPST_ZA, + gen_helper_gvec_vfma_d) +TRANS_FEAT(FMLS_n1_d, aa64_sme2_f64f64, do_fmla, a, false, FPST_ZA, + s->fpcr_ah ? gen_helper_gvec_ah_vfms_d : gen_helper_gvec_vfms_d) +TRANS_FEAT(FMLA_nn_d, aa64_sme2_f64f64, do_fmla, a, true, FPST_ZA, + gen_helper_gvec_vfma_d) +TRANS_FEAT(FMLS_nn_d, aa64_sme2_f64f64, do_fmla, a, true, FPST_ZA, + s->fpcr_ah ? gen_helper_gvec_ah_vfms_d : gen_helper_gvec_vfms_d) + +TRANS_FEAT(BFMLA_n1, aa64_sme_b16b16, do_fmla, a, false, FPST_ZA, + gen_helper_gvec_bfmla) +TRANS_FEAT(BFMLS_n1, aa64_sme_b16b16, do_fmla, a, false, FPST_ZA, + s->fpcr_ah ? gen_helper_gvec_ah_bfmls : gen_helper_gvec_bfmls) +TRANS_FEAT(BFMLA_nn, aa64_sme_b16b16, do_fmla, a, true, FPST_ZA, + gen_helper_gvec_bfmla) +TRANS_FEAT(BFMLS_nn, aa64_sme_b16b16, do_fmla, a, true, FPST_ZA, + s->fpcr_ah ? gen_helper_gvec_ah_bfmls : gen_helper_gvec_bfmls) + +static bool do_fmla_nx(DisasContext *s, arg_azx_n *a, + ARMFPStatusFlavour fpst, gen_helper_gvec_4_ptr *fn) +{ + return do_azz_acc_fp(s, a->n, 1, a->rv, a->off, a->zn, a->zm, + a->idx, 0, false, fpst, fn); +} + +TRANS_FEAT(FMLA_nx_h, aa64_sme_f16f16, do_fmla_nx, a, FPST_ZA_F16, + gen_helper_gvec_fmla_idx_h) +TRANS_FEAT(FMLS_nx_h, aa64_sme_f16f16, do_fmla_nx, a, FPST_ZA_F16, + s->fpcr_ah ? gen_helper_gvec_ah_fmls_idx_h : gen_helper_gvec_fmls_idx_h) +TRANS_FEAT(FMLA_nx_s, aa64_sme2, do_fmla_nx, a, FPST_ZA, + gen_helper_gvec_fmla_idx_s) +TRANS_FEAT(FMLS_nx_s, aa64_sme2, do_fmla_nx, a, FPST_ZA, + s->fpcr_ah ? gen_helper_gvec_ah_fmls_idx_s : gen_helper_gvec_fmls_idx_s) +TRANS_FEAT(FMLA_nx_d, aa64_sme2_f64f64, do_fmla_nx, a, FPST_ZA, + gen_helper_gvec_fmla_idx_d) +TRANS_FEAT(FMLS_nx_d, aa64_sme2_f64f64, do_fmla_nx, a, FPST_ZA, + s->fpcr_ah ? gen_helper_gvec_ah_fmls_idx_d : gen_helper_gvec_fmls_idx_d) + +TRANS_FEAT(BFMLA_nx, aa64_sme_b16b16, do_fmla_nx, a, FPST_ZA, + gen_helper_gvec_bfmla_idx) +TRANS_FEAT(BFMLS_nx, aa64_sme_b16b16, do_fmla_nx, a, FPST_ZA, + s->fpcr_ah ? gen_helper_gvec_ah_bfmls_idx : gen_helper_gvec_bfmls_idx) + +static bool do_faddsub(DisasContext *s, arg_az_n *a, ARMFPStatusFlavour fpst, + gen_helper_gvec_3_ptr *fn) +{ + if (sme_smza_enabled_check(s)) { + int svl = streaming_vec_reg_size(s); + int n = a->n; + int zm = a->zm; + int vstride = svl / n; + TCGv_ptr t_za = get_zarray(s, a->rv, a->off, n, 0); + TCGv_ptr ptr = fpstatus_ptr(fpst); + TCGv_ptr t = tcg_temp_new_ptr(); + + for (int r = 0; r < n; ++r) { + TCGv_ptr t_zm = vec_full_reg_ptr(s, zm + r); + int o_za = r * vstride * sizeof(ARMVectorReg); + int desc = simd_desc(svl, svl, 0); + + tcg_gen_addi_ptr(t, t_za, o_za); + fn(t, t, t_zm, ptr, tcg_constant_i32(desc)); + } + } + return true; +} + +TRANS_FEAT(FADD_nn_h, aa64_sme_f16f16, do_faddsub, a, + FPST_ZA_F16, gen_helper_gvec_fadd_h) +TRANS_FEAT(FSUB_nn_h, aa64_sme_f16f16, do_faddsub, a, + FPST_ZA_F16, gen_helper_gvec_fsub_h) + +TRANS_FEAT(FADD_nn_s, aa64_sme2, do_faddsub, a, + FPST_ZA, gen_helper_gvec_fadd_s) +TRANS_FEAT(FSUB_nn_s, aa64_sme2, do_faddsub, a, + FPST_ZA, gen_helper_gvec_fsub_s) + +TRANS_FEAT(FADD_nn_d, aa64_sme2_f64f64, do_faddsub, a, + FPST_ZA, gen_helper_gvec_fadd_d) +TRANS_FEAT(FSUB_nn_d, aa64_sme2_f64f64, do_faddsub, a, + FPST_ZA, gen_helper_gvec_fsub_d) + +TRANS_FEAT(BFADD_nn, aa64_sme_b16b16, do_faddsub, a, + FPST_ZA, gen_helper_gvec_bfadd) +TRANS_FEAT(BFSUB_nn, aa64_sme_b16b16, do_faddsub, a, + FPST_ZA, gen_helper_gvec_bfsub) + +/* + * Expand array multi-vector single (n1), array multi-vector (nn), + * and array multi-vector indexed (nx), for integer accumulate. + * multi: true for nn, false for n1. + * data: stuff for simd_data, including any index. + */ +static bool do_azz_acc(DisasContext *s, int nreg, int nsel, + int rv, int off, int zn, int zm, + int data, int shsel, bool multi, + gen_helper_gvec_4 *fn) +{ + if (sme_smza_enabled_check(s)) { + int svl = streaming_vec_reg_size(s); + int vstride = svl / nreg; + TCGv_ptr t_za = get_zarray(s, rv, off, nreg, nsel); + TCGv_ptr t = tcg_temp_new_ptr(); + + for (int r = 0; r < nreg; ++r) { + TCGv_ptr t_zn = vec_full_reg_ptr(s, zn); + TCGv_ptr t_zm = vec_full_reg_ptr(s, zm); + + for (int i = 0; i < nsel; ++i) { + int o_za = (r * vstride + i) * sizeof(ARMVectorReg); + int desc = simd_desc(svl, svl, data | (i << shsel)); + + tcg_gen_addi_ptr(t, t_za, o_za); + fn(t, t_zn, t_zm, t, tcg_constant_i32(desc)); + } + + /* + * For multiple-and-single vectors, Zn may wrap. + * For multiple vectors, both Zn and Zm are aligned. + */ + zn = (zn + 1) % 32; + zm += multi; + } + } + return true; +} + +static bool do_dot(DisasContext *s, arg_azz_n *a, bool multi, + gen_helper_gvec_4 *fn) +{ + return do_azz_acc(s, a->n, 1, a->rv, a->off, a->zn, a->zm, + 0, 0, multi, fn); +} + +static void gen_helper_gvec_sudot_4b(TCGv_ptr d, TCGv_ptr n, TCGv_ptr m, + TCGv_ptr a, TCGv_i32 desc) +{ + gen_helper_gvec_usdot_4b(d, m, n, a, desc); +} + +TRANS_FEAT(USDOT_n1, aa64_sme2, do_dot, a, false, gen_helper_gvec_usdot_4b) +TRANS_FEAT(SUDOT_n1, aa64_sme2, do_dot, a, false, gen_helper_gvec_sudot_4b) +TRANS_FEAT(SDOT_n1_2h, aa64_sme2, do_dot, a, false, gen_helper_gvec_sdot_2h) +TRANS_FEAT(UDOT_n1_2h, aa64_sme2, do_dot, a, false, gen_helper_gvec_udot_2h) +TRANS_FEAT(SDOT_n1_4b, aa64_sme2, do_dot, a, false, gen_helper_gvec_sdot_4b) +TRANS_FEAT(UDOT_n1_4b, aa64_sme2, do_dot, a, false, gen_helper_gvec_udot_4b) +TRANS_FEAT(SDOT_n1_4h, aa64_sme2_i16i64, do_dot, a, false, gen_helper_gvec_sdot_4h) +TRANS_FEAT(UDOT_n1_4h, aa64_sme2_i16i64, do_dot, a, false, gen_helper_gvec_udot_4h) + +TRANS_FEAT(USDOT_nn, aa64_sme2, do_dot, a, true, gen_helper_gvec_usdot_4b) +TRANS_FEAT(SDOT_nn_2h, aa64_sme2, do_dot, a, true, gen_helper_gvec_sdot_2h) +TRANS_FEAT(UDOT_nn_2h, aa64_sme2, do_dot, a, true, gen_helper_gvec_udot_2h) +TRANS_FEAT(SDOT_nn_4b, aa64_sme2, do_dot, a, true, gen_helper_gvec_sdot_4b) +TRANS_FEAT(UDOT_nn_4b, aa64_sme2, do_dot, a, true, gen_helper_gvec_udot_4b) +TRANS_FEAT(SDOT_nn_4h, aa64_sme2_i16i64, do_dot, a, true, gen_helper_gvec_sdot_4h) +TRANS_FEAT(UDOT_nn_4h, aa64_sme2_i16i64, do_dot, a, true, gen_helper_gvec_udot_4h) + +static bool do_dot_nx(DisasContext *s, arg_azx_n *a, gen_helper_gvec_4 *fn) +{ + return do_azz_acc(s, a->n, 1, a->rv, a->off, a->zn, a->zm, + a->idx, 0, false, fn); +} + +TRANS_FEAT(USDOT_nx, aa64_sme2, do_dot_nx, a, gen_helper_gvec_usdot_idx_4b) +TRANS_FEAT(SUDOT_nx, aa64_sme2, do_dot_nx, a, gen_helper_gvec_sudot_idx_4b) +TRANS_FEAT(SDOT_nx_2h, aa64_sme2, do_dot_nx, a, gen_helper_gvec_sdot_idx_2h) +TRANS_FEAT(UDOT_nx_2h, aa64_sme2, do_dot_nx, a, gen_helper_gvec_udot_idx_2h) +TRANS_FEAT(SDOT_nx_4b, aa64_sme2, do_dot_nx, a, gen_helper_gvec_sdot_idx_4b) +TRANS_FEAT(UDOT_nx_4b, aa64_sme2, do_dot_nx, a, gen_helper_gvec_udot_idx_4b) +TRANS_FEAT(SDOT_nx_4h, aa64_sme2_i16i64, do_dot_nx, a, gen_helper_gvec_sdot_idx_4h) +TRANS_FEAT(UDOT_nx_4h, aa64_sme2_i16i64, do_dot_nx, a, gen_helper_gvec_udot_idx_4h) + +static bool do_vdot_nx(DisasContext *s, arg_azx_n *a, gen_helper_gvec_3 *fn) +{ + if (sme_smza_enabled_check(s)) { + int svl = streaming_vec_reg_size(s); + fn(get_zarray(s, a->rv, a->off, a->n, 0), + vec_full_reg_ptr(s, a->zn), + vec_full_reg_ptr(s, a->zm), + tcg_constant_i32(simd_desc(svl, svl, a->idx))); + } + return true; +} + +TRANS_FEAT(SVDOT_nx_2h, aa64_sme2, do_vdot_nx, a, gen_helper_sme2_svdot_idx_2h) +TRANS_FEAT(SVDOT_nx_4b, aa64_sme2, do_vdot_nx, a, gen_helper_sme2_svdot_idx_4b) +TRANS_FEAT(SVDOT_nx_4h, aa64_sme2, do_vdot_nx, a, gen_helper_sme2_svdot_idx_4h) + +TRANS_FEAT(UVDOT_nx_2h, aa64_sme2, do_vdot_nx, a, gen_helper_sme2_uvdot_idx_2h) +TRANS_FEAT(UVDOT_nx_4b, aa64_sme2, do_vdot_nx, a, gen_helper_sme2_uvdot_idx_4b) +TRANS_FEAT(UVDOT_nx_4h, aa64_sme2, do_vdot_nx, a, gen_helper_sme2_uvdot_idx_4h) + +TRANS_FEAT(SUVDOT_nx_4b, aa64_sme2, do_vdot_nx, a, gen_helper_sme2_suvdot_idx_4b) +TRANS_FEAT(USVDOT_nx_4b, aa64_sme2, do_vdot_nx, a, gen_helper_sme2_usvdot_idx_4b) + +static bool do_smlal(DisasContext *s, arg_azz_n *a, bool multi, + gen_helper_gvec_4 *fn) +{ + return do_azz_acc(s, a->n, 2, a->rv, a->off, a->zn, a->zm, + 0, 0, multi, fn); +} + +TRANS_FEAT(SMLAL_n1, aa64_sme2, do_smlal, a, false, gen_helper_sve2_smlal_zzzw_s) +TRANS_FEAT(SMLSL_n1, aa64_sme2, do_smlal, a, false, gen_helper_sve2_smlsl_zzzw_s) +TRANS_FEAT(UMLAL_n1, aa64_sme2, do_smlal, a, false, gen_helper_sve2_umlal_zzzw_s) +TRANS_FEAT(UMLSL_n1, aa64_sme2, do_smlal, a, false, gen_helper_sve2_umlsl_zzzw_s) + +TRANS_FEAT(SMLAL_nn, aa64_sme2, do_smlal, a, true, gen_helper_sve2_smlal_zzzw_s) +TRANS_FEAT(SMLSL_nn, aa64_sme2, do_smlal, a, true, gen_helper_sve2_smlsl_zzzw_s) +TRANS_FEAT(UMLAL_nn, aa64_sme2, do_smlal, a, true, gen_helper_sve2_umlal_zzzw_s) +TRANS_FEAT(UMLSL_nn, aa64_sme2, do_smlal, a, true, gen_helper_sve2_umlsl_zzzw_s) + +static bool do_smlal_nx(DisasContext *s, arg_azx_n *a, + gen_helper_gvec_4 *fn) +{ + return do_azz_acc(s, a->n, 2, a->rv, a->off, a->zn, a->zm, + a->idx << 1, 0, false, fn); +} + +TRANS_FEAT(SMLAL_nx, aa64_sme2, do_smlal_nx, a, gen_helper_sve2_smlal_idx_s) +TRANS_FEAT(SMLSL_nx, aa64_sme2, do_smlal_nx, a, gen_helper_sve2_smlsl_idx_s) +TRANS_FEAT(UMLAL_nx, aa64_sme2, do_smlal_nx, a, gen_helper_sve2_umlal_idx_s) +TRANS_FEAT(UMLSL_nx, aa64_sme2, do_smlal_nx, a, gen_helper_sve2_umlsl_idx_s) + +static bool do_smlall(DisasContext *s, arg_azz_n *a, bool multi, + gen_helper_gvec_4 *fn) +{ + return do_azz_acc(s, a->n, 4, a->rv, a->off, a->zn, a->zm, + 0, 0, multi, fn); +} + +static void gen_helper_sme2_sumlall_s(TCGv_ptr d, TCGv_ptr n, TCGv_ptr m, + TCGv_ptr a, TCGv_i32 desc) +{ + gen_helper_sme2_usmlall_s(d, m, n, a, desc); +} + +TRANS_FEAT(SMLALL_n1_s, aa64_sme2, do_smlall, a, false, gen_helper_sme2_smlall_s) +TRANS_FEAT(SMLSLL_n1_s, aa64_sme2, do_smlall, a, false, gen_helper_sme2_smlsll_s) +TRANS_FEAT(UMLALL_n1_s, aa64_sme2, do_smlall, a, false, gen_helper_sme2_umlall_s) +TRANS_FEAT(UMLSLL_n1_s, aa64_sme2, do_smlall, a, false, gen_helper_sme2_umlsll_s) +TRANS_FEAT(USMLALL_n1_s, aa64_sme2, do_smlall, a, false, gen_helper_sme2_usmlall_s) +TRANS_FEAT(SUMLALL_n1_s, aa64_sme2, do_smlall, a, false, gen_helper_sme2_sumlall_s) + +TRANS_FEAT(SMLALL_n1_d, aa64_sme2_i16i64, do_smlall, a, false, gen_helper_sme2_smlall_d) +TRANS_FEAT(SMLSLL_n1_d, aa64_sme2_i16i64, do_smlall, a, false, gen_helper_sme2_smlsll_d) +TRANS_FEAT(UMLALL_n1_d, aa64_sme2_i16i64, do_smlall, a, false, gen_helper_sme2_umlall_d) +TRANS_FEAT(UMLSLL_n1_d, aa64_sme2_i16i64, do_smlall, a, false, gen_helper_sme2_umlsll_d) + +TRANS_FEAT(SMLALL_nn_s, aa64_sme2, do_smlall, a, true, gen_helper_sme2_smlall_s) +TRANS_FEAT(SMLSLL_nn_s, aa64_sme2, do_smlall, a, true, gen_helper_sme2_smlsll_s) +TRANS_FEAT(UMLALL_nn_s, aa64_sme2, do_smlall, a, true, gen_helper_sme2_umlall_s) +TRANS_FEAT(UMLSLL_nn_s, aa64_sme2, do_smlall, a, true, gen_helper_sme2_umlsll_s) +TRANS_FEAT(USMLALL_nn_s, aa64_sme2, do_smlall, a, true, gen_helper_sme2_usmlall_s) + +TRANS_FEAT(SMLALL_nn_d, aa64_sme2_i16i64, do_smlall, a, true, gen_helper_sme2_smlall_d) +TRANS_FEAT(SMLSLL_nn_d, aa64_sme2_i16i64, do_smlall, a, true, gen_helper_sme2_smlsll_d) +TRANS_FEAT(UMLALL_nn_d, aa64_sme2_i16i64, do_smlall, a, true, gen_helper_sme2_umlall_d) +TRANS_FEAT(UMLSLL_nn_d, aa64_sme2_i16i64, do_smlall, a, true, gen_helper_sme2_umlsll_d) + +static bool do_smlall_nx(DisasContext *s, arg_azx_n *a, + gen_helper_gvec_4 *fn) +{ + return do_azz_acc(s, a->n, 4, a->rv, a->off, a->zn, a->zm, + a->idx << 2, 0, false, fn); +} + +TRANS_FEAT(SMLALL_nx_s, aa64_sme2, do_smlall_nx, a, gen_helper_sme2_smlall_idx_s) +TRANS_FEAT(SMLSLL_nx_s, aa64_sme2, do_smlall_nx, a, gen_helper_sme2_smlsll_idx_s) +TRANS_FEAT(UMLALL_nx_s, aa64_sme2, do_smlall_nx, a, gen_helper_sme2_umlall_idx_s) +TRANS_FEAT(UMLSLL_nx_s, aa64_sme2, do_smlall_nx, a, gen_helper_sme2_umlsll_idx_s) +TRANS_FEAT(USMLALL_nx_s, aa64_sme2, do_smlall_nx, a, gen_helper_sme2_usmlall_idx_s) +TRANS_FEAT(SUMLALL_nx_s, aa64_sme2, do_smlall_nx, a, gen_helper_sme2_sumlall_idx_s) + +TRANS_FEAT(SMLALL_nx_d, aa64_sme2_i16i64, do_smlall_nx, a, gen_helper_sme2_smlall_idx_d) +TRANS_FEAT(SMLSLL_nx_d, aa64_sme2_i16i64, do_smlall_nx, a, gen_helper_sme2_smlsll_idx_d) +TRANS_FEAT(UMLALL_nx_d, aa64_sme2_i16i64, do_smlall_nx, a, gen_helper_sme2_umlall_idx_d) +TRANS_FEAT(UMLSLL_nx_d, aa64_sme2_i16i64, do_smlall_nx, a, gen_helper_sme2_umlsll_idx_d) + +static bool do_zz_fpst(DisasContext *s, arg_zz_n *a, int data, + ARMFPStatusFlavour type, gen_helper_gvec_2_ptr *fn) +{ + if (sme_sm_enabled_check(s)) { + int svl = streaming_vec_reg_size(s); + TCGv_ptr fpst = fpstatus_ptr(type); + + for (int i = 0, n = a->n; i < n; ++i) { + tcg_gen_gvec_2_ptr(vec_full_reg_offset(s, a->zd + i), + vec_full_reg_offset(s, a->zn + i), + fpst, svl, svl, data, fn); + } + } + return true; +} + +TRANS_FEAT(BFCVT, aa64_sme2, do_zz_fpst, a, 0, + FPST_A64, gen_helper_sme2_bfcvt) +TRANS_FEAT(BFCVTN, aa64_sme2, do_zz_fpst, a, 0, + FPST_A64, gen_helper_sme2_bfcvtn) +TRANS_FEAT(FCVT_n, aa64_sme2, do_zz_fpst, a, 0, + FPST_A64, gen_helper_sme2_fcvt_n) +TRANS_FEAT(FCVTN, aa64_sme2, do_zz_fpst, a, 0, + FPST_A64, gen_helper_sme2_fcvtn) + +TRANS_FEAT(FCVT_w, aa64_sme_f16f16, do_zz_fpst, a, 0, + FPST_A64_F16, gen_helper_sme2_fcvt_w) +TRANS_FEAT(FCVTL, aa64_sme_f16f16, do_zz_fpst, a, 0, + FPST_A64_F16, gen_helper_sme2_fcvtl) + +TRANS_FEAT(FCVTZS, aa64_sme2, do_zz_fpst, a, 0, + FPST_A64, gen_helper_gvec_vcvt_rz_fs) +TRANS_FEAT(FCVTZU, aa64_sme2, do_zz_fpst, a, 0, + FPST_A64, gen_helper_gvec_vcvt_rz_fu) + +TRANS_FEAT(SCVTF, aa64_sme2, do_zz_fpst, a, 0, + FPST_A64, gen_helper_sme2_scvtf) +TRANS_FEAT(UCVTF, aa64_sme2, do_zz_fpst, a, 0, + FPST_A64, gen_helper_sme2_ucvtf) + +TRANS_FEAT(FRINTN, aa64_sme2, do_zz_fpst, a, float_round_nearest_even, + FPST_A64, gen_helper_gvec_vrint_rm_s) +TRANS_FEAT(FRINTP, aa64_sme2, do_zz_fpst, a, float_round_up, + FPST_A64, gen_helper_gvec_vrint_rm_s) +TRANS_FEAT(FRINTM, aa64_sme2, do_zz_fpst, a, float_round_down, + FPST_A64, gen_helper_gvec_vrint_rm_s) +TRANS_FEAT(FRINTA, aa64_sme2, do_zz_fpst, a, float_round_ties_away, + FPST_A64, gen_helper_gvec_vrint_rm_s) + +static bool do_zz(DisasContext *s, arg_zz_n *a, int data, + gen_helper_gvec_2 *fn) +{ + if (sme_sm_enabled_check(s)) { + int svl = streaming_vec_reg_size(s); + + for (int i = 0, n = a->n; i < n; ++i) { + tcg_gen_gvec_2_ool(vec_full_reg_offset(s, a->zd + i), + vec_full_reg_offset(s, a->zn + i), + svl, svl, data, fn); + } + } + return true; +} + +TRANS_FEAT(SQCVT_sh, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sqcvt_sh) +TRANS_FEAT(UQCVT_sh, aa64_sme2, do_zz, a, 0, gen_helper_sme2_uqcvt_sh) +TRANS_FEAT(SQCVTU_sh, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sqcvtu_sh) + +TRANS_FEAT(SQCVT_sb, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sqcvt_sb) +TRANS_FEAT(UQCVT_sb, aa64_sme2, do_zz, a, 0, gen_helper_sme2_uqcvt_sb) +TRANS_FEAT(SQCVTU_sb, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sqcvtu_sb) + +TRANS_FEAT(SQCVT_dh, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sqcvt_dh) +TRANS_FEAT(UQCVT_dh, aa64_sme2, do_zz, a, 0, gen_helper_sme2_uqcvt_dh) +TRANS_FEAT(SQCVTU_dh, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sqcvtu_dh) + +TRANS_FEAT(SQCVTN_sb, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sqcvtn_sb) +TRANS_FEAT(UQCVTN_sb, aa64_sme2, do_zz, a, 0, gen_helper_sme2_uqcvtn_sb) +TRANS_FEAT(SQCVTUN_sb, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sqcvtun_sb) + +TRANS_FEAT(SQCVTN_dh, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sqcvtn_dh) +TRANS_FEAT(UQCVTN_dh, aa64_sme2, do_zz, a, 0, gen_helper_sme2_uqcvtn_dh) +TRANS_FEAT(SQCVTUN_dh, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sqcvtun_dh) + +TRANS_FEAT(SUNPK_2bh, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sunpk2_bh) +TRANS_FEAT(SUNPK_2hs, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sunpk2_hs) +TRANS_FEAT(SUNPK_2sd, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sunpk2_sd) + +TRANS_FEAT(SUNPK_4bh, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sunpk4_bh) +TRANS_FEAT(SUNPK_4hs, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sunpk4_hs) +TRANS_FEAT(SUNPK_4sd, aa64_sme2, do_zz, a, 0, gen_helper_sme2_sunpk4_sd) + +TRANS_FEAT(UUNPK_2bh, aa64_sme2, do_zz, a, 0, gen_helper_sme2_uunpk2_bh) +TRANS_FEAT(UUNPK_2hs, aa64_sme2, do_zz, a, 0, gen_helper_sme2_uunpk2_hs) +TRANS_FEAT(UUNPK_2sd, aa64_sme2, do_zz, a, 0, gen_helper_sme2_uunpk2_sd) + +TRANS_FEAT(UUNPK_4bh, aa64_sme2, do_zz, a, 0, gen_helper_sme2_uunpk4_bh) +TRANS_FEAT(UUNPK_4hs, aa64_sme2, do_zz, a, 0, gen_helper_sme2_uunpk4_hs) +TRANS_FEAT(UUNPK_4sd, aa64_sme2, do_zz, a, 0, gen_helper_sme2_uunpk4_sd) + +static bool do_zipuzp_4(DisasContext *s, arg_zz_e *a, + gen_helper_gvec_2 * const fn[5]) +{ + int bytes_per_op = 4 << a->esz; + + /* Both MO_64 and MO_128 can fail the size test. */ + if (s->max_svl < bytes_per_op) { + unallocated_encoding(s); + } else if (sme_sm_enabled_check(s)) { + int svl = streaming_vec_reg_size(s); + if (svl < bytes_per_op) { + unallocated_encoding(s); + } else { + tcg_gen_gvec_2_ool(vec_full_reg_offset(s, a->zd), + vec_full_reg_offset(s, a->zn), + svl, svl, 0, fn[a->esz]); + } + } + return true; +} + +static gen_helper_gvec_2 * const zip4_fns[] = { + gen_helper_sme2_zip4_b, + gen_helper_sme2_zip4_h, + gen_helper_sme2_zip4_s, + gen_helper_sme2_zip4_d, + gen_helper_sme2_zip4_q, +}; +TRANS_FEAT(ZIP_4, aa64_sme2, do_zipuzp_4, a, zip4_fns) + +static gen_helper_gvec_2 * const uzp4_fns[] = { + gen_helper_sme2_uzp4_b, + gen_helper_sme2_uzp4_h, + gen_helper_sme2_uzp4_s, + gen_helper_sme2_uzp4_d, + gen_helper_sme2_uzp4_q, +}; +TRANS_FEAT(UZP_4, aa64_sme2, do_zipuzp_4, a, uzp4_fns) + +static bool do_zz_rshr(DisasContext *s, arg_rshr *a, gen_helper_gvec_2 *fn) +{ + if (sve_access_check(s)) { + int vl = vec_full_reg_size(s); + tcg_gen_gvec_2_ool(vec_full_reg_offset(s, a->zd), + vec_full_reg_offset(s, a->zn), + vl, vl, a->shift, fn); + } + return true; +} + +TRANS_FEAT(SQRSHR_sh, aa64_sme2, do_zz_rshr, a, gen_helper_sme2_sqrshr_sh) +TRANS_FEAT(UQRSHR_sh, aa64_sme2, do_zz_rshr, a, gen_helper_sme2_uqrshr_sh) +TRANS_FEAT(SQRSHRU_sh, aa64_sme2, do_zz_rshr, a, gen_helper_sme2_sqrshru_sh) + +TRANS_FEAT(SQRSHR_sb, aa64_sme2, do_zz_rshr, a, gen_helper_sme2_sqrshr_sb) +TRANS_FEAT(SQRSHR_dh, aa64_sme2, do_zz_rshr, a, gen_helper_sme2_sqrshr_dh) +TRANS_FEAT(UQRSHR_sb, aa64_sme2, do_zz_rshr, a, gen_helper_sme2_uqrshr_sb) +TRANS_FEAT(UQRSHR_dh, aa64_sme2, do_zz_rshr, a, gen_helper_sme2_uqrshr_dh) +TRANS_FEAT(SQRSHRU_sb, aa64_sme2, do_zz_rshr, a, gen_helper_sme2_sqrshru_sb) +TRANS_FEAT(SQRSHRU_dh, aa64_sme2, do_zz_rshr, a, gen_helper_sme2_sqrshru_dh) + +TRANS_FEAT(SQRSHRN_sh, aa64_sme2_or_sve2p1, do_zz_rshr, a, gen_helper_sme2_sqrshrn_sh) +TRANS_FEAT(UQRSHRN_sh, aa64_sme2_or_sve2p1, do_zz_rshr, a, gen_helper_sme2_uqrshrn_sh) +TRANS_FEAT(SQRSHRUN_sh, aa64_sme2_or_sve2p1, do_zz_rshr, a, gen_helper_sme2_sqrshrun_sh) + +TRANS_FEAT(SQRSHRN_sb, aa64_sme2, do_zz_rshr, a, gen_helper_sme2_sqrshrn_sb) +TRANS_FEAT(SQRSHRN_dh, aa64_sme2, do_zz_rshr, a, gen_helper_sme2_sqrshrn_dh) +TRANS_FEAT(UQRSHRN_sb, aa64_sme2, do_zz_rshr, a, gen_helper_sme2_uqrshrn_sb) +TRANS_FEAT(UQRSHRN_dh, aa64_sme2, do_zz_rshr, a, gen_helper_sme2_uqrshrn_dh) +TRANS_FEAT(SQRSHRUN_sb, aa64_sme2, do_zz_rshr, a, gen_helper_sme2_sqrshrun_sb) +TRANS_FEAT(SQRSHRUN_dh, aa64_sme2, do_zz_rshr, a, gen_helper_sme2_sqrshrun_dh) + +static bool do_zipuzp_2(DisasContext *s, arg_zzz_e *a, + gen_helper_gvec_3 * const fn[5]) +{ + int bytes_per_op = 2 << a->esz; + + /* MO_128 can fail the size test. */ + if (s->max_svl < bytes_per_op) { + unallocated_encoding(s); + } else if (sme_sm_enabled_check(s)) { + int svl = streaming_vec_reg_size(s); + if (svl < bytes_per_op) { + unallocated_encoding(s); + } else { + tcg_gen_gvec_3_ool(vec_full_reg_offset(s, a->zd), + vec_full_reg_offset(s, a->zn), + vec_full_reg_offset(s, a->zm), + svl, svl, 0, fn[a->esz]); + } + } + return true; +} + +static gen_helper_gvec_3 * const zip2_fns[] = { + gen_helper_sme2_zip2_b, + gen_helper_sme2_zip2_h, + gen_helper_sme2_zip2_s, + gen_helper_sme2_zip2_d, + gen_helper_sme2_zip2_q, +}; +TRANS_FEAT(ZIP_2, aa64_sme2, do_zipuzp_2, a, zip2_fns) + +static gen_helper_gvec_3 * const uzp2_fns[] = { + gen_helper_sme2_uzp2_b, + gen_helper_sme2_uzp2_h, + gen_helper_sme2_uzp2_s, + gen_helper_sme2_uzp2_d, + gen_helper_sme2_uzp2_q, +}; +TRANS_FEAT(UZP_2, aa64_sme2, do_zipuzp_2, a, uzp2_fns) + +static bool trans_FCLAMP(DisasContext *s, arg_zzz_en *a) +{ + static gen_helper_gvec_3_ptr * const fn[] = { + gen_helper_sme2_bfclamp, + gen_helper_sme2_fclamp_h, + gen_helper_sme2_fclamp_s, + gen_helper_sme2_fclamp_d, + }; + TCGv_ptr fpst; + int vl; + + if (!dc_isar_feature(aa64_sme2, s)) { + return false; + } + /* This insn uses MO_8 to encode BFloat16. */ + if (a->esz == MO_8 && !dc_isar_feature(aa64_sme_b16b16, s)) { + return false; + } + if (!sme_sm_enabled_check(s)) { + return true; + } + + fpst = fpstatus_ptr(a->esz == MO_16 ? FPST_A64_F16 : FPST_A64); + vl = vec_full_reg_size(s); + + tcg_gen_gvec_3_ptr(vec_full_reg_offset(s, a->zd), + vec_full_reg_offset(s, a->zn), + vec_full_reg_offset(s, a->zm), + fpst, vl, vl, a->n, fn[a->esz]); + return true; +} + +static bool do_clamp(DisasContext *s, arg_zzz_en *a, + gen_helper_gvec_3 * const fn[4]) +{ + int vl; + + if (!dc_isar_feature(aa64_sme2, s)) { + return false; + } + if (!sme_sm_enabled_check(s)) { + return true; + } + + /* + * Clamp is just a min+max, easily supported by most host + * vector operations -- we already have such an expansion in + * translate-sve.c for a single output. + * TODO: Add support in gvec for multiple simultaneous output, + * and/or copy to temporary upon overlap. + */ + vl = vec_full_reg_size(s); + tcg_gen_gvec_3_ool(vec_full_reg_offset(s, a->zd), + vec_full_reg_offset(s, a->zn), + vec_full_reg_offset(s, a->zm), + vl, vl, a->n, fn[a->esz]); + return true; +} + +static gen_helper_gvec_3 * const sclamp_fns[] = { + gen_helper_sme2_sclamp_b, + gen_helper_sme2_sclamp_h, + gen_helper_sme2_sclamp_s, + gen_helper_sme2_sclamp_d, +}; +TRANS(SCLAMP, do_clamp, a, sclamp_fns) + +static gen_helper_gvec_3 * const uclamp_fns[] = { + gen_helper_sme2_uclamp_b, + gen_helper_sme2_uclamp_h, + gen_helper_sme2_uclamp_s, + gen_helper_sme2_uclamp_d, +}; +TRANS(UCLAMP, do_clamp, a, uclamp_fns) + +static bool trans_SEL(DisasContext *s, arg_SEL *a) +{ + typedef void sme_sel_fn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32, TCGv_i32); + static sme_sel_fn * const fns[4] = { + gen_helper_sme2_sel_b, gen_helper_sme2_sel_h, + gen_helper_sme2_sel_s, gen_helper_sme2_sel_d + }; + + if (!dc_isar_feature(aa64_sme2, s)) { + return false; + } + if (sme_sm_enabled_check(s)) { + int svl = streaming_vec_reg_size(s); + uint32_t desc = simd_desc(svl, svl, a->n); + TCGv_ptr t_d = tcg_temp_new_ptr(); + TCGv_ptr t_n = tcg_temp_new_ptr(); + TCGv_ptr t_m = tcg_temp_new_ptr(); + TCGv_i32 png = tcg_temp_new_i32(); + + tcg_gen_addi_ptr(t_d, tcg_env, vec_full_reg_offset(s, a->zd)); + tcg_gen_addi_ptr(t_n, tcg_env, vec_full_reg_offset(s, a->zn)); + tcg_gen_addi_ptr(t_m, tcg_env, vec_full_reg_offset(s, a->zm)); + + tcg_gen_ld16u_i32(png, tcg_env, pred_full_reg_offset(s, a->pg) + ^ (HOST_BIG_ENDIAN ? 6 : 0)); + + fns[a->esz](t_d, t_n, t_m, png, tcg_constant_i32(desc)); + } + return true; +} + +static bool do_lut(DisasContext *s, arg_lut *a, + gen_helper_gvec_2_ptr *fn, bool strided) +{ + if (sme_sm_enabled_check(s) && sme2_zt0_enabled_check(s)) { + int svl = streaming_vec_reg_size(s); + tcg_gen_gvec_2_ptr(vec_full_reg_offset(s, a->zd), + vec_full_reg_offset(s, a->zn), + tcg_env, svl, svl, strided | (a->idx << 1), fn); + } + return true; +} + +TRANS_FEAT(LUTI2_c_1b, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_1b, false) +TRANS_FEAT(LUTI2_c_1h, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_1h, false) +TRANS_FEAT(LUTI2_c_1s, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_1s, false) + +TRANS_FEAT(LUTI2_c_2b, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_2b, false) +TRANS_FEAT(LUTI2_c_2h, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_2h, false) +TRANS_FEAT(LUTI2_c_2s, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_2s, false) + +TRANS_FEAT(LUTI2_c_4b, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_4b, false) +TRANS_FEAT(LUTI2_c_4h, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_4h, false) +TRANS_FEAT(LUTI2_c_4s, aa64_sme2, do_lut, a, gen_helper_sme2_luti2_4s, false) + +TRANS_FEAT(LUTI4_c_1b, aa64_sme2, do_lut, a, gen_helper_sme2_luti4_1b, false) +TRANS_FEAT(LUTI4_c_1h, aa64_sme2, do_lut, a, gen_helper_sme2_luti4_1h, false) +TRANS_FEAT(LUTI4_c_1s, aa64_sme2, do_lut, a, gen_helper_sme2_luti4_1s, false) + +TRANS_FEAT(LUTI4_c_2b, aa64_sme2, do_lut, a, gen_helper_sme2_luti4_2b, false) +TRANS_FEAT(LUTI4_c_2h, aa64_sme2, do_lut, a, gen_helper_sme2_luti4_2h, false) +TRANS_FEAT(LUTI4_c_2s, aa64_sme2, do_lut, a, gen_helper_sme2_luti4_2s, false) + +TRANS_FEAT(LUTI4_c_4h, aa64_sme2, do_lut, a, gen_helper_sme2_luti4_4h, false) +TRANS_FEAT(LUTI4_c_4s, aa64_sme2, do_lut, a, gen_helper_sme2_luti4_4s, false) + +static bool do_lut_s4(DisasContext *s, arg_lut *a, gen_helper_gvec_2_ptr *fn) +{ + return !(a->zd & 0b01100) && do_lut(s, a, fn, true); +} + +static bool do_lut_s8(DisasContext *s, arg_lut *a, gen_helper_gvec_2_ptr *fn) +{ + return !(a->zd & 0b01000) && do_lut(s, a, fn, true); +} + +TRANS_FEAT(LUTI2_s_2b, aa64_sme2p1, do_lut_s8, a, gen_helper_sme2_luti2_2b) +TRANS_FEAT(LUTI2_s_2h, aa64_sme2p1, do_lut_s8, a, gen_helper_sme2_luti2_2h) + +TRANS_FEAT(LUTI2_s_4b, aa64_sme2p1, do_lut_s4, a, gen_helper_sme2_luti2_4b) +TRANS_FEAT(LUTI2_s_4h, aa64_sme2p1, do_lut_s4, a, gen_helper_sme2_luti2_4h) + +TRANS_FEAT(LUTI4_s_2b, aa64_sme2p1, do_lut_s8, a, gen_helper_sme2_luti4_2b) +TRANS_FEAT(LUTI4_s_2h, aa64_sme2p1, do_lut_s8, a, gen_helper_sme2_luti4_2h) + +TRANS_FEAT(LUTI4_s_4h, aa64_sme2p1, do_lut_s4, a, gen_helper_sme2_luti4_4h) diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c index f3cf028..7b57573 100644 --- a/target/arm/tcg/translate-sve.c +++ b/target/arm/tcg/translate-sve.c @@ -89,7 +89,7 @@ static inline int expand_imm_sh8u(DisasContext *s, int x) */ static inline int msz_dtype(DisasContext *s, int msz) { - static const uint8_t dtype[4] = { 0, 5, 10, 15 }; + static const uint8_t dtype[5] = { 0, 5, 10, 15, 18 }; return dtype[msz]; } @@ -778,6 +778,9 @@ DO_ZPZ(NOT_zpz, aa64_sve, sve_not_zpz) DO_ZPZ(ABS, aa64_sve, sve_abs) DO_ZPZ(NEG, aa64_sve, sve_neg) DO_ZPZ(RBIT, aa64_sve, sve_rbit) +DO_ZPZ(ORQV, aa64_sme2p1_or_sve2p1, sve2p1_orqv) +DO_ZPZ(EORQV, aa64_sme2p1_or_sve2p1, sve2p1_eorqv) +DO_ZPZ(ANDQV, aa64_sme2p1_or_sve2p1, sve2p1_andqv) static gen_helper_gvec_3 * const fabs_fns[4] = { NULL, gen_helper_sve_fabs_h, @@ -828,6 +831,41 @@ TRANS_FEAT(SXTW, aa64_sve, gen_gvec_ool_arg_zpz, TRANS_FEAT(UXTW, aa64_sve, gen_gvec_ool_arg_zpz, a->esz == 3 ? gen_helper_sve_uxtw_d : NULL, a, 0) +static gen_helper_gvec_3 * const addqv_fns[4] = { + gen_helper_sve2p1_addqv_b, gen_helper_sve2p1_addqv_h, + gen_helper_sve2p1_addqv_s, gen_helper_sve2p1_addqv_d, +}; +TRANS_FEAT(ADDQV, aa64_sme2p1_or_sve2p1, + gen_gvec_ool_arg_zpz, addqv_fns[a->esz], a, 0) + +static gen_helper_gvec_3 * const smaxqv_fns[4] = { + gen_helper_sve2p1_smaxqv_b, gen_helper_sve2p1_smaxqv_h, + gen_helper_sve2p1_smaxqv_s, gen_helper_sve2p1_smaxqv_d, +}; +TRANS_FEAT(SMAXQV, aa64_sme2p1_or_sve2p1, + gen_gvec_ool_arg_zpz, smaxqv_fns[a->esz], a, 0) + +static gen_helper_gvec_3 * const sminqv_fns[4] = { + gen_helper_sve2p1_sminqv_b, gen_helper_sve2p1_sminqv_h, + gen_helper_sve2p1_sminqv_s, gen_helper_sve2p1_sminqv_d, +}; +TRANS_FEAT(SMINQV, aa64_sme2p1_or_sve2p1, + gen_gvec_ool_arg_zpz, sminqv_fns[a->esz], a, 0) + +static gen_helper_gvec_3 * const umaxqv_fns[4] = { + gen_helper_sve2p1_umaxqv_b, gen_helper_sve2p1_umaxqv_h, + gen_helper_sve2p1_umaxqv_s, gen_helper_sve2p1_umaxqv_d, +}; +TRANS_FEAT(UMAXQV, aa64_sme2p1_or_sve2p1, + gen_gvec_ool_arg_zpz, umaxqv_fns[a->esz], a, 0) + +static gen_helper_gvec_3 * const uminqv_fns[4] = { + gen_helper_sve2p1_uminqv_b, gen_helper_sve2p1_uminqv_h, + gen_helper_sve2p1_uminqv_s, gen_helper_sve2p1_uminqv_d, +}; +TRANS_FEAT(UMINQV, aa64_sme2p1_or_sve2p1, + gen_gvec_ool_arg_zpz, uminqv_fns[a->esz], a, 0) + /* *** SVE Integer Reduction Group */ @@ -1679,6 +1717,22 @@ static bool do_predset(DisasContext *s, int esz, int rd, int pat, bool setflag) TRANS_FEAT(PTRUE, aa64_sve, do_predset, a->esz, a->rd, a->pat, a->s) +static bool trans_PTRUE_cnt(DisasContext *s, arg_PTRUE_cnt *a) +{ + if (!dc_isar_feature(aa64_sme2_or_sve2p1, s)) { + return false; + } + if (sve_access_check(s)) { + /* Canonical TRUE is 0 count, invert bit, plus element size. */ + int val = (1 << 15) | (1 << a->esz); + + /* Write val to the first uint64_t; clear all of the rest. */ + tcg_gen_gvec_dup_imm(MO_64, pred_full_reg_offset(s, a->rd), + 8, size_for_gvec(pred_full_reg_size(s)), val); + } + return true; +} + /* Note pat == 31 is #all, to set all elements. */ TRANS_FEAT_NONSTREAMING(SETFFR, aa64_sve, do_predset, 0, FFR_PRED_NUM, 31, false) @@ -2148,6 +2202,55 @@ static bool do_EXT(DisasContext *s, int rd, int rn, int rm, int imm) TRANS_FEAT(EXT, aa64_sve, do_EXT, a->rd, a->rn, a->rm, a->imm) TRANS_FEAT(EXT_sve2, aa64_sve2, do_EXT, a->rd, a->rn, (a->rn + 1) % 32, a->imm) +static bool trans_EXTQ(DisasContext *s, arg_EXTQ *a) +{ + unsigned vl, dofs, sofs0, sofs1, sofs2, imm; + + if (!dc_isar_feature(aa64_sme2p1_or_sve2p1, s)) { + return false; + } + if (!sve_access_check(s)) { + return true; + } + + imm = a->imm; + if (imm == 0) { + /* So far we never optimize Zdn with MOVPRFX, so zd = zn is a nop. */ + return true; + } + + vl = vec_full_reg_size(s); + dofs = vec_full_reg_offset(s, a->rd); + sofs2 = vec_full_reg_offset(s, a->rn); + + if (imm & 8) { + sofs0 = dofs + 8; + sofs1 = sofs2; + sofs2 += 8; + } else { + sofs0 = dofs; + sofs1 = dofs + 8; + } + imm = (imm & 7) << 3; + + for (unsigned i = 0; i < vl; i += 16) { + TCGv_i64 s0 = tcg_temp_new_i64(); + TCGv_i64 s1 = tcg_temp_new_i64(); + TCGv_i64 s2 = tcg_temp_new_i64(); + + tcg_gen_ld_i64(s0, tcg_env, sofs0 + i); + tcg_gen_ld_i64(s1, tcg_env, sofs1 + i); + tcg_gen_ld_i64(s2, tcg_env, sofs2 + i); + + tcg_gen_extract2_i64(s0, s0, s1, imm); + tcg_gen_extract2_i64(s1, s1, s2, imm); + + tcg_gen_st_i64(s0, tcg_env, dofs + i); + tcg_gen_st_i64(s1, tcg_env, dofs + i + 8); + } + return true; +} + /* *** SVE Permute - Unpredicated Group */ @@ -2195,6 +2298,27 @@ static bool trans_DUP_x(DisasContext *s, arg_DUP_x *a) return true; } +static bool trans_DUPQ(DisasContext *s, arg_DUPQ *a) +{ + unsigned vl, dofs, nofs; + + if (!dc_isar_feature(aa64_sme2p1_or_sve2p1, s)) { + return false; + } + if (!sve_access_check(s)) { + return true; + } + + vl = vec_full_reg_size(s); + dofs = vec_full_reg_offset(s, a->rd); + nofs = vec_reg_offset(s, a->rn, a->imm, a->esz); + + for (unsigned i = 0; i < vl; i += 16) { + tcg_gen_gvec_dup_mem(a->esz, dofs + i, nofs + i, 16, 16); + } + return true; +} + static void do_insr_i64(DisasContext *s, arg_rrr_esz *a, TCGv_i64 val) { typedef void gen_insr(TCGv_ptr, TCGv_ptr, TCGv_i64, TCGv_i32); @@ -2256,12 +2380,124 @@ static gen_helper_gvec_4 * const sve2_tbl_fns[4] = { TRANS_FEAT(TBL_sve2, aa64_sve2, gen_gvec_ool_zzzz, sve2_tbl_fns[a->esz], a->rd, a->rn, (a->rn + 1) % 32, a->rm, 0) +static gen_helper_gvec_3 * const tblq_fns[4] = { + gen_helper_sve2p1_tblq_b, gen_helper_sve2p1_tblq_h, + gen_helper_sve2p1_tblq_s, gen_helper_sve2p1_tblq_d +}; +TRANS_FEAT(TBLQ, aa64_sme2p1_or_sve2p1, gen_gvec_ool_arg_zzz, + tblq_fns[a->esz], a, 0) + static gen_helper_gvec_3 * const tbx_fns[4] = { gen_helper_sve2_tbx_b, gen_helper_sve2_tbx_h, gen_helper_sve2_tbx_s, gen_helper_sve2_tbx_d }; TRANS_FEAT(TBX, aa64_sve2, gen_gvec_ool_arg_zzz, tbx_fns[a->esz], a, 0) +static gen_helper_gvec_3 * const tbxq_fns[4] = { + gen_helper_sve2p1_tbxq_b, gen_helper_sve2p1_tbxq_h, + gen_helper_sve2p1_tbxq_s, gen_helper_sve2p1_tbxq_d +}; +TRANS_FEAT(TBXQ, aa64_sme2p1_or_sve2p1, gen_gvec_ool_arg_zzz, + tbxq_fns[a->esz], a, 0) + +static bool trans_PMOV_pv(DisasContext *s, arg_PMOV_pv *a) +{ + static gen_helper_gvec_2 * const fns[4] = { + NULL, gen_helper_pmov_pv_h, + gen_helper_pmov_pv_s, gen_helper_pmov_pv_d + }; + unsigned vl, pl, vofs, pofs; + TCGv_i64 tmp; + + if (!dc_isar_feature(aa64_sme2p1_or_sve2p1, s)) { + return false; + } + if (!sve_access_check(s)) { + return true; + } + + vl = vec_full_reg_size(s); + if (a->esz != MO_8) { + tcg_gen_gvec_2_ool(pred_full_reg_offset(s, a->rd), + vec_full_reg_offset(s, a->rn), + vl, vl, a->imm, fns[a->esz]); + return true; + } + + /* + * Copy the low PL bytes from vector Zn, zero-extending to a + * multiple of 8 bytes, so that Pd is properly cleared. + */ + + pl = vl / 8; + pofs = pred_full_reg_offset(s, a->rd); + vofs = vec_full_reg_offset(s, a->rn); + + QEMU_BUILD_BUG_ON(sizeof(ARMPredicateReg) != 32); + for (unsigned i = 32; i >= 8; i >>= 1) { + if (pl & i) { + tcg_gen_gvec_mov(MO_64, pofs, vofs, i, i); + pofs += i; + vofs += i; + } + } + switch (pl & 7) { + case 0: + return true; + case 2: + tmp = tcg_temp_new_i64(); + tcg_gen_ld16u_i64(tmp, tcg_env, vofs + (HOST_BIG_ENDIAN ? 6 : 0)); + break; + case 4: + tmp = tcg_temp_new_i64(); + tcg_gen_ld32u_i64(tmp, tcg_env, vofs + (HOST_BIG_ENDIAN ? 4 : 0)); + break; + case 6: + tmp = tcg_temp_new_i64(); + tcg_gen_ld_i64(tmp, tcg_env, vofs); + tcg_gen_extract_i64(tmp, tmp, 0, 48); + break; + default: + g_assert_not_reached(); + } + tcg_gen_st_i64(tmp, tcg_env, pofs); + return true; +} + +static bool trans_PMOV_vp(DisasContext *s, arg_PMOV_pv *a) +{ + static gen_helper_gvec_2 * const fns[4] = { + NULL, gen_helper_pmov_vp_h, + gen_helper_pmov_vp_s, gen_helper_pmov_vp_d + }; + unsigned vl; + + if (!dc_isar_feature(aa64_sme2p1_or_sve2p1, s)) { + return false; + } + if (!sve_access_check(s)) { + return true; + } + + vl = vec_full_reg_size(s); + + if (a->esz == MO_8) { + /* + * The low PL bytes are copied from Pn to Zd unchanged. + * We know that the unused portion of Pn is zero, and + * that imm == 0, so the balance of Zd must be zeroed. + */ + tcg_gen_gvec_mov(MO_64, vec_full_reg_offset(s, a->rd), + pred_full_reg_offset(s, a->rn), + size_for_gvec(vl / 8), vl); + } else { + tcg_gen_gvec_2_ool(vec_full_reg_offset(s, a->rd), + pred_full_reg_offset(s, a->rn), + vl, vl, a->imm, fns[a->esz]); + } + return true; +} + static bool trans_UNPK(DisasContext *s, arg_UNPK *a) { static gen_helper_gvec_2 * const fns[4][2] = { @@ -2352,6 +2588,23 @@ TRANS_FEAT(PUNPKHI, aa64_sve, do_perm_pred2, a, 1, gen_helper_sve_punpk_p) *** SVE Permute - Interleaving Group */ +static bool do_interleave_q(DisasContext *s, gen_helper_gvec_3 *fn, + arg_rrr_esz *a, int data) +{ + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + if (vsz < 32) { + unallocated_encoding(s); + } else { + tcg_gen_gvec_3_ool(vec_full_reg_offset(s, a->rd), + vec_full_reg_offset(s, a->rn), + vec_full_reg_offset(s, a->rm), + vsz, vsz, data, fn); + } + } + return true; +} + static gen_helper_gvec_3 * const zip_fns[4] = { gen_helper_sve_zip_b, gen_helper_sve_zip_h, gen_helper_sve_zip_s, gen_helper_sve_zip_d, @@ -2361,26 +2614,43 @@ TRANS_FEAT(ZIP1_z, aa64_sve, gen_gvec_ool_arg_zzz, TRANS_FEAT(ZIP2_z, aa64_sve, gen_gvec_ool_arg_zzz, zip_fns[a->esz], a, vec_full_reg_size(s) / 2) -TRANS_FEAT(ZIP1_q, aa64_sve_f64mm, gen_gvec_ool_arg_zzz, - gen_helper_sve2_zip_q, a, 0) -TRANS_FEAT(ZIP2_q, aa64_sve_f64mm, gen_gvec_ool_arg_zzz, - gen_helper_sve2_zip_q, a, - QEMU_ALIGN_DOWN(vec_full_reg_size(s), 32) / 2) +TRANS_FEAT_NONSTREAMING(ZIP1_q, aa64_sve_f64mm, do_interleave_q, + gen_helper_sve2_zip_q, a, 0) +TRANS_FEAT_NONSTREAMING(ZIP2_q, aa64_sve_f64mm, do_interleave_q, + gen_helper_sve2_zip_q, a, + QEMU_ALIGN_DOWN(vec_full_reg_size(s), 32) / 2) + +static gen_helper_gvec_3 * const zipq_fns[4] = { + gen_helper_sve2p1_zipq_b, gen_helper_sve2p1_zipq_h, + gen_helper_sve2p1_zipq_s, gen_helper_sve2p1_zipq_d, +}; +TRANS_FEAT(ZIPQ1, aa64_sme2p1_or_sve2p1, gen_gvec_ool_arg_zzz, + zipq_fns[a->esz], a, 0) +TRANS_FEAT(ZIPQ2, aa64_sme2p1_or_sve2p1, gen_gvec_ool_arg_zzz, + zipq_fns[a->esz], a, 16 / 2) static gen_helper_gvec_3 * const uzp_fns[4] = { gen_helper_sve_uzp_b, gen_helper_sve_uzp_h, gen_helper_sve_uzp_s, gen_helper_sve_uzp_d, }; - TRANS_FEAT(UZP1_z, aa64_sve, gen_gvec_ool_arg_zzz, uzp_fns[a->esz], a, 0) TRANS_FEAT(UZP2_z, aa64_sve, gen_gvec_ool_arg_zzz, uzp_fns[a->esz], a, 1 << a->esz) -TRANS_FEAT(UZP1_q, aa64_sve_f64mm, gen_gvec_ool_arg_zzz, - gen_helper_sve2_uzp_q, a, 0) -TRANS_FEAT(UZP2_q, aa64_sve_f64mm, gen_gvec_ool_arg_zzz, - gen_helper_sve2_uzp_q, a, 16) +TRANS_FEAT_NONSTREAMING(UZP1_q, aa64_sve_f64mm, do_interleave_q, + gen_helper_sve2_uzp_q, a, 0) +TRANS_FEAT_NONSTREAMING(UZP2_q, aa64_sve_f64mm, do_interleave_q, + gen_helper_sve2_uzp_q, a, 16) + +static gen_helper_gvec_3 * const uzpq_fns[4] = { + gen_helper_sve2p1_uzpq_b, gen_helper_sve2p1_uzpq_h, + gen_helper_sve2p1_uzpq_s, gen_helper_sve2p1_uzpq_d, +}; +TRANS_FEAT(UZPQ1, aa64_sme2p1_or_sve2p1, gen_gvec_ool_arg_zzz, + uzpq_fns[a->esz], a, 0) +TRANS_FEAT(UZPQ2, aa64_sme2p1_or_sve2p1, gen_gvec_ool_arg_zzz, + uzpq_fns[a->esz], a, 1 << a->esz) static gen_helper_gvec_3 * const trn_fns[4] = { gen_helper_sve_trn_b, gen_helper_sve_trn_h, @@ -2392,10 +2662,10 @@ TRANS_FEAT(TRN1_z, aa64_sve, gen_gvec_ool_arg_zzz, TRANS_FEAT(TRN2_z, aa64_sve, gen_gvec_ool_arg_zzz, trn_fns[a->esz], a, 1 << a->esz) -TRANS_FEAT(TRN1_q, aa64_sve_f64mm, gen_gvec_ool_arg_zzz, - gen_helper_sve2_trn_q, a, 0) -TRANS_FEAT(TRN2_q, aa64_sve_f64mm, gen_gvec_ool_arg_zzz, - gen_helper_sve2_trn_q, a, 16) +TRANS_FEAT_NONSTREAMING(TRN1_q, aa64_sve_f64mm, do_interleave_q, + gen_helper_sve2_trn_q, a, 0) +TRANS_FEAT_NONSTREAMING(TRN2_q, aa64_sve_f64mm, do_interleave_q, + gen_helper_sve2_trn_q, a, 16) /* *** SVE Permute Vector - Predicated Group @@ -2981,6 +3251,36 @@ static bool trans_CNTP(DisasContext *s, arg_CNTP *a) return true; } +static bool trans_CNTP_c(DisasContext *s, arg_CNTP_c *a) +{ + TCGv_i32 t_png; + uint32_t desc = 0; + + if (dc_isar_feature(aa64_sve2p1, s)) { + if (!sve_access_check(s)) { + return true; + } + } else if (dc_isar_feature(aa64_sme2, s)) { + if (!sme_sm_enabled_check(s)) { + return true; + } + } else { + return false; + } + + t_png = tcg_temp_new_i32(); + tcg_gen_ld16u_i32(t_png, tcg_env, + pred_full_reg_offset(s, a->rn) ^ + (HOST_BIG_ENDIAN ? 6 : 0)); + + desc = FIELD_DP32(desc, PREDDESC, OPRSZ, pred_full_reg_size(s)); + desc = FIELD_DP32(desc, PREDDESC, ESZ, a->esz); + desc = FIELD_DP32(desc, PREDDESC, DATA, a->vl); + + gen_helper_sve2p1_cntp_c(cpu_reg(s, a->rd), t_png, tcg_constant_i32(desc)); + return true; +} + static bool trans_INCDECP_r(DisasContext *s, arg_incdec_pred *a) { if (!dc_isar_feature(aa64_sve, s)) { @@ -3091,7 +3391,9 @@ static bool trans_CTERM(DisasContext *s, arg_CTERM *a) return true; } -static bool trans_WHILE(DisasContext *s, arg_WHILE *a) +typedef void gen_while_fn(TCGv_i32, TCGv_ptr, TCGv_i32, TCGv_i32); +static bool do_WHILE(DisasContext *s, arg_while *a, + bool lt, int scale, int data, gen_while_fn *fn) { TCGv_i64 op0, op1, t0, t1, tmax; TCGv_i32 t2; @@ -3101,14 +3403,8 @@ static bool trans_WHILE(DisasContext *s, arg_WHILE *a) TCGCond cond; uint64_t maxval; /* Note that GE/HS has a->eq == 0 and GT/HI has a->eq == 1. */ - bool eq = a->eq == a->lt; + bool eq = a->eq == lt; - /* The greater-than conditions are all SVE2. */ - if (a->lt - ? !dc_isar_feature(aa64_sve, s) - : !dc_isar_feature(aa64_sve2, s)) { - return false; - } if (!sve_access_check(s)) { return true; } @@ -3132,7 +3428,7 @@ static bool trans_WHILE(DisasContext *s, arg_WHILE *a) t0 = tcg_temp_new_i64(); t1 = tcg_temp_new_i64(); - if (a->lt) { + if (lt) { tcg_gen_sub_i64(t0, op1, op0); if (a->u) { maxval = a->sf ? UINT64_MAX : UINT32_MAX; @@ -3152,7 +3448,7 @@ static bool trans_WHILE(DisasContext *s, arg_WHILE *a) } } - tmax = tcg_constant_i64(vsz >> a->esz); + tmax = tcg_constant_i64((vsz << scale) >> a->esz); if (eq) { /* Equality means one more iteration. */ tcg_gen_addi_i64(t0, t0, 1); @@ -3181,24 +3477,38 @@ static bool trans_WHILE(DisasContext *s, arg_WHILE *a) t2 = tcg_temp_new_i32(); tcg_gen_extrl_i64_i32(t2, t0); - /* Scale elements to bits. */ - tcg_gen_shli_i32(t2, t2, a->esz); - desc = FIELD_DP32(desc, PREDDESC, OPRSZ, vsz / 8); desc = FIELD_DP32(desc, PREDDESC, ESZ, a->esz); + desc = FIELD_DP32(desc, PREDDESC, DATA, data); ptr = tcg_temp_new_ptr(); tcg_gen_addi_ptr(ptr, tcg_env, pred_full_reg_offset(s, a->rd)); - if (a->lt) { - gen_helper_sve_whilel(t2, ptr, t2, tcg_constant_i32(desc)); - } else { - gen_helper_sve_whileg(t2, ptr, t2, tcg_constant_i32(desc)); - } + fn(t2, ptr, t2, tcg_constant_i32(desc)); + do_pred_flags(t2); return true; } +TRANS_FEAT(WHILE_lt, aa64_sve, do_WHILE, + a, true, 0, 0, gen_helper_sve_whilel) +TRANS_FEAT(WHILE_gt, aa64_sve2, do_WHILE, + a, false, 0, 0, gen_helper_sve_whileg) + +TRANS_FEAT(WHILE_lt_pair, aa64_sme2_or_sve2p1, do_WHILE, + a, true, 1, 0, gen_helper_sve_while2l) +TRANS_FEAT(WHILE_gt_pair, aa64_sme2_or_sve2p1, do_WHILE, + a, false, 1, 0, gen_helper_sve_while2g) + +TRANS_FEAT(WHILE_lt_cnt2, aa64_sme2_or_sve2p1, do_WHILE, + a, true, 1, 1, gen_helper_sve_whilecl) +TRANS_FEAT(WHILE_lt_cnt4, aa64_sme2_or_sve2p1, do_WHILE, + a, true, 2, 2, gen_helper_sve_whilecl) +TRANS_FEAT(WHILE_gt_cnt2, aa64_sme2_or_sve2p1, do_WHILE, + a, false, 1, 1, gen_helper_sve_whilecg) +TRANS_FEAT(WHILE_gt_cnt4, aa64_sme2_or_sve2p1, do_WHILE, + a, false, 2, 2, gen_helper_sve_whilecg) + static bool trans_WHILE_ptr(DisasContext *s, arg_WHILE_ptr *a) { TCGv_i64 op0, op1, diff, t1, tmax; @@ -3217,7 +3527,7 @@ static bool trans_WHILE_ptr(DisasContext *s, arg_WHILE_ptr *a) op0 = read_cpu_reg(s, a->rn, 1); op1 = read_cpu_reg(s, a->rm, 1); - tmax = tcg_constant_i64(vsz); + tmax = tcg_constant_i64(vsz >> a->esz); diff = tcg_temp_new_i64(); if (a->rw) { @@ -3227,15 +3537,15 @@ static bool trans_WHILE_ptr(DisasContext *s, arg_WHILE_ptr *a) tcg_gen_sub_i64(diff, op0, op1); tcg_gen_sub_i64(t1, op1, op0); tcg_gen_movcond_i64(TCG_COND_GEU, diff, op0, op1, diff, t1); - /* Round down to a multiple of ESIZE. */ - tcg_gen_andi_i64(diff, diff, -1 << a->esz); + /* Divide, rounding down, by ESIZE. */ + tcg_gen_shri_i64(diff, diff, a->esz); /* If op1 == op0, diff == 0, and the condition is always true. */ tcg_gen_movcond_i64(TCG_COND_EQ, diff, op0, op1, tmax, diff); } else { /* WHILEWR */ tcg_gen_sub_i64(diff, op1, op0); - /* Round down to a multiple of ESIZE. */ - tcg_gen_andi_i64(diff, diff, -1 << a->esz); + /* Divide, rounding down, by ESIZE. */ + tcg_gen_shri_i64(diff, diff, a->esz); /* If op0 >= op1, diff <= 0, the condition is always true. */ tcg_gen_movcond_i64(TCG_COND_GEU, diff, op0, op1, tmax, diff); } @@ -3258,6 +3568,42 @@ static bool trans_WHILE_ptr(DisasContext *s, arg_WHILE_ptr *a) return true; } +static bool do_pext(DisasContext *s, arg_pext *a, int n) +{ + TCGv_i32 t_png; + TCGv_ptr t_pd; + int pl; + + if (!sve_access_check(s)) { + return true; + } + + t_png = tcg_temp_new_i32(); + tcg_gen_ld16u_i32(t_png, tcg_env, + pred_full_reg_offset(s, a->rn) ^ + (HOST_BIG_ENDIAN ? 6 : 0)); + + t_pd = tcg_temp_new_ptr(); + pl = pred_full_reg_size(s); + + for (int i = 0; i < n; ++i) { + int rd = (a->rd + i) % 16; + int part = a->imm * n + i; + unsigned desc = 0; + + desc = FIELD_DP32(desc, PREDDESC, OPRSZ, pl); + desc = FIELD_DP32(desc, PREDDESC, ESZ, a->esz); + desc = FIELD_DP32(desc, PREDDESC, DATA, part); + + tcg_gen_addi_ptr(t_pd, tcg_env, pred_full_reg_offset(s, rd)); + gen_helper_pext(t_pd, t_png, tcg_constant_i32(desc)); + } + return true; +} + +TRANS_FEAT(PEXT_1, aa64_sme2_or_sve2p1, do_pext, a, 1) +TRANS_FEAT(PEXT_2, aa64_sme2_or_sve2p1, do_pext, a, 2) + /* *** SVE Integer Wide Immediate - Unpredicated Group */ @@ -3385,8 +3731,8 @@ DO_ZZI(UMIN, umin) #undef DO_ZZI static gen_helper_gvec_4 * const dot_fns[2][2] = { - { gen_helper_gvec_sdot_b, gen_helper_gvec_sdot_h }, - { gen_helper_gvec_udot_b, gen_helper_gvec_udot_h } + { gen_helper_gvec_sdot_4b, gen_helper_gvec_sdot_4h }, + { gen_helper_gvec_udot_4b, gen_helper_gvec_udot_4h } }; TRANS_FEAT(DOT_zzzz, aa64_sve, gen_gvec_ool_zzzz, dot_fns[a->u][a->sz], a->rd, a->rn, a->rm, a->ra, 0) @@ -3395,19 +3741,24 @@ TRANS_FEAT(DOT_zzzz, aa64_sve, gen_gvec_ool_zzzz, * SVE Multiply - Indexed */ -TRANS_FEAT(SDOT_zzxw_s, aa64_sve, gen_gvec_ool_arg_zzxz, - gen_helper_gvec_sdot_idx_b, a) -TRANS_FEAT(SDOT_zzxw_d, aa64_sve, gen_gvec_ool_arg_zzxz, - gen_helper_gvec_sdot_idx_h, a) -TRANS_FEAT(UDOT_zzxw_s, aa64_sve, gen_gvec_ool_arg_zzxz, - gen_helper_gvec_udot_idx_b, a) -TRANS_FEAT(UDOT_zzxw_d, aa64_sve, gen_gvec_ool_arg_zzxz, - gen_helper_gvec_udot_idx_h, a) - -TRANS_FEAT(SUDOT_zzxw_s, aa64_sve_i8mm, gen_gvec_ool_arg_zzxz, - gen_helper_gvec_sudot_idx_b, a) -TRANS_FEAT(USDOT_zzxw_s, aa64_sve_i8mm, gen_gvec_ool_arg_zzxz, - gen_helper_gvec_usdot_idx_b, a) +TRANS_FEAT(SDOT_zzxw_4s, aa64_sve, gen_gvec_ool_arg_zzxz, + gen_helper_gvec_sdot_idx_4b, a) +TRANS_FEAT(SDOT_zzxw_4d, aa64_sve, gen_gvec_ool_arg_zzxz, + gen_helper_gvec_sdot_idx_4h, a) +TRANS_FEAT(UDOT_zzxw_4s, aa64_sve, gen_gvec_ool_arg_zzxz, + gen_helper_gvec_udot_idx_4b, a) +TRANS_FEAT(UDOT_zzxw_4d, aa64_sve, gen_gvec_ool_arg_zzxz, + gen_helper_gvec_udot_idx_4h, a) + +TRANS_FEAT(SUDOT_zzxw_4s, aa64_sve_i8mm, gen_gvec_ool_arg_zzxz, + gen_helper_gvec_sudot_idx_4b, a) +TRANS_FEAT(USDOT_zzxw_4s, aa64_sve_i8mm, gen_gvec_ool_arg_zzxz, + gen_helper_gvec_usdot_idx_4b, a) + +TRANS_FEAT(SDOT_zzxw_2s, aa64_sme2_or_sve2p1, gen_gvec_ool_arg_zzxz, + gen_helper_gvec_sdot_idx_2h, a) +TRANS_FEAT(UDOT_zzxw_2s, aa64_sme2_or_sve2p1, gen_gvec_ool_arg_zzxz, + gen_helper_gvec_udot_idx_2h, a) #define DO_SVE2_RRX(NAME, FUNC) \ TRANS_FEAT(NAME, aa64_sve, gen_gvec_ool_zzz, FUNC, \ @@ -3621,6 +3972,54 @@ DO_VPZ_AH(FMAXV, fmaxv) #undef DO_VPZ +static gen_helper_gvec_3_ptr * const faddqv_fns[4] = { + NULL, gen_helper_sve2p1_faddqv_h, + gen_helper_sve2p1_faddqv_s, gen_helper_sve2p1_faddqv_d, +}; +TRANS_FEAT(FADDQV, aa64_sme2p1_or_sve2p1, gen_gvec_fpst_arg_zpz, + faddqv_fns[a->esz], a, 0, + a->esz == MO_16 ? FPST_A64_F16 : FPST_A64) + +static gen_helper_gvec_3_ptr * const fmaxnmqv_fns[4] = { + NULL, gen_helper_sve2p1_fmaxnmqv_h, + gen_helper_sve2p1_fmaxnmqv_s, gen_helper_sve2p1_fmaxnmqv_d, +}; +TRANS_FEAT(FMAXNMQV, aa64_sme2p1_or_sve2p1, gen_gvec_fpst_arg_zpz, + fmaxnmqv_fns[a->esz], a, 0, + a->esz == MO_16 ? FPST_A64_F16 : FPST_A64) + +static gen_helper_gvec_3_ptr * const fminnmqv_fns[4] = { + NULL, gen_helper_sve2p1_fminnmqv_h, + gen_helper_sve2p1_fminnmqv_s, gen_helper_sve2p1_fminnmqv_d, +}; +TRANS_FEAT(FMINNMQV, aa64_sme2p1_or_sve2p1, gen_gvec_fpst_arg_zpz, + fminnmqv_fns[a->esz], a, 0, + a->esz == MO_16 ? FPST_A64_F16 : FPST_A64) + +static gen_helper_gvec_3_ptr * const fmaxqv_fns[4] = { + NULL, gen_helper_sve2p1_fmaxqv_h, + gen_helper_sve2p1_fmaxqv_s, gen_helper_sve2p1_fmaxqv_d, +}; +static gen_helper_gvec_3_ptr * const fmaxqv_ah_fns[4] = { + NULL, gen_helper_sve2p1_ah_fmaxqv_h, + gen_helper_sve2p1_ah_fmaxqv_s, gen_helper_sve2p1_ah_fmaxqv_d, +}; +TRANS_FEAT(FMAXQV, aa64_sme2p1_or_sve2p1, gen_gvec_fpst_arg_zpz, + (s->fpcr_ah ? fmaxqv_fns : fmaxqv_ah_fns)[a->esz], a, 0, + a->esz == MO_16 ? FPST_A64_F16 : FPST_A64) + +static gen_helper_gvec_3_ptr * const fminqv_fns[4] = { + NULL, gen_helper_sve2p1_fminqv_h, + gen_helper_sve2p1_fminqv_s, gen_helper_sve2p1_fminqv_d, +}; +static gen_helper_gvec_3_ptr * const fminqv_ah_fns[4] = { + NULL, gen_helper_sve2p1_ah_fminqv_h, + gen_helper_sve2p1_ah_fminqv_s, gen_helper_sve2p1_ah_fminqv_d, +}; +TRANS_FEAT(FMINQV, aa64_sme2p1_or_sve2p1, gen_gvec_fpst_arg_zpz, + (s->fpcr_ah ? fminqv_fns : fminqv_ah_fns)[a->esz], a, 0, + a->esz == MO_16 ? FPST_A64_F16 : FPST_A64) + /* *** SVE Floating Point Unary Operations - Unpredicated Group */ @@ -4143,7 +4542,7 @@ TRANS_FEAT(UCVTF_dd, aa64_sve, gen_gvec_fpst_arg_zpz, */ void gen_sve_ldr(DisasContext *s, TCGv_ptr base, int vofs, - int len, int rn, int imm) + int len, int rn, int imm, MemOp align) { int len_align = QEMU_ALIGN_DOWN(len, 16); int len_remain = len % 16; @@ -4172,12 +4571,15 @@ void gen_sve_ldr(DisasContext *s, TCGv_ptr base, int vofs, for (i = 0; i < len_align; i += 16) { tcg_gen_qemu_ld_i128(t16, clean_addr, midx, - MO_LE | MO_128 | MO_ATOM_NONE); + MO_LE | MO_128 | MO_ATOM_NONE | align); tcg_gen_extr_i128_i64(t0, t1, t16); tcg_gen_st_i64(t0, base, vofs + i); tcg_gen_st_i64(t1, base, vofs + i + 8); tcg_gen_addi_i64(clean_addr, clean_addr, 16); } + if (len_align) { + align = MO_UNALN; + } } else { TCGLabel *loop = gen_new_label(); TCGv_ptr tp, i = tcg_temp_new_ptr(); @@ -4187,7 +4589,7 @@ void gen_sve_ldr(DisasContext *s, TCGv_ptr base, int vofs, t16 = tcg_temp_new_i128(); tcg_gen_qemu_ld_i128(t16, clean_addr, midx, - MO_LE | MO_128 | MO_ATOM_NONE); + MO_LE | MO_128 | MO_ATOM_NONE | align); tcg_gen_addi_i64(clean_addr, clean_addr, 16); tp = tcg_temp_new_ptr(); @@ -4202,6 +4604,7 @@ void gen_sve_ldr(DisasContext *s, TCGv_ptr base, int vofs, tcg_gen_st_i64(t1, tp, vofs + 8); tcg_gen_brcondi_ptr(TCG_COND_LTU, i, len_align, loop); + align = MO_UNALN; } /* @@ -4210,7 +4613,9 @@ void gen_sve_ldr(DisasContext *s, TCGv_ptr base, int vofs, */ if (len_remain >= 8) { t0 = tcg_temp_new_i64(); - tcg_gen_qemu_ld_i64(t0, clean_addr, midx, MO_LEUQ | MO_ATOM_NONE); + tcg_gen_qemu_ld_i64(t0, clean_addr, midx, + MO_LEUQ | MO_ATOM_NONE | align); + align = MO_UNALN; tcg_gen_st_i64(t0, base, vofs + len_align); len_remain -= 8; len_align += 8; @@ -4225,12 +4630,14 @@ void gen_sve_ldr(DisasContext *s, TCGv_ptr base, int vofs, case 4: case 8: tcg_gen_qemu_ld_i64(t0, clean_addr, midx, - MO_LE | ctz32(len_remain) | MO_ATOM_NONE); + MO_LE | ctz32(len_remain) + | MO_ATOM_NONE | align); break; case 6: t1 = tcg_temp_new_i64(); - tcg_gen_qemu_ld_i64(t0, clean_addr, midx, MO_LEUL | MO_ATOM_NONE); + tcg_gen_qemu_ld_i64(t0, clean_addr, midx, + MO_LEUL | MO_ATOM_NONE | align); tcg_gen_addi_i64(clean_addr, clean_addr, 4); tcg_gen_qemu_ld_i64(t1, clean_addr, midx, MO_LEUW | MO_ATOM_NONE); tcg_gen_deposit_i64(t0, t0, t1, 32, 32); @@ -4245,7 +4652,7 @@ void gen_sve_ldr(DisasContext *s, TCGv_ptr base, int vofs, /* Similarly for stores. */ void gen_sve_str(DisasContext *s, TCGv_ptr base, int vofs, - int len, int rn, int imm) + int len, int rn, int imm, MemOp align) { int len_align = QEMU_ALIGN_DOWN(len, 16); int len_remain = len % 16; @@ -4277,9 +4684,12 @@ void gen_sve_str(DisasContext *s, TCGv_ptr base, int vofs, tcg_gen_ld_i64(t1, base, vofs + i + 8); tcg_gen_concat_i64_i128(t16, t0, t1); tcg_gen_qemu_st_i128(t16, clean_addr, midx, - MO_LE | MO_128 | MO_ATOM_NONE); + MO_LE | MO_128 | MO_ATOM_NONE | align); tcg_gen_addi_i64(clean_addr, clean_addr, 16); } + if (len_align) { + align = MO_UNALN; + } } else { TCGLabel *loop = gen_new_label(); TCGv_ptr tp, i = tcg_temp_new_ptr(); @@ -4303,13 +4713,16 @@ void gen_sve_str(DisasContext *s, TCGv_ptr base, int vofs, tcg_gen_addi_i64(clean_addr, clean_addr, 16); tcg_gen_brcondi_ptr(TCG_COND_LTU, i, len_align, loop); + align = MO_UNALN; } /* Predicate register stores can be any multiple of 2. */ if (len_remain >= 8) { t0 = tcg_temp_new_i64(); tcg_gen_ld_i64(t0, base, vofs + len_align); - tcg_gen_qemu_st_i64(t0, clean_addr, midx, MO_LEUQ | MO_ATOM_NONE); + tcg_gen_qemu_st_i64(t0, clean_addr, midx, + MO_LEUQ | MO_ATOM_NONE | align); + align = MO_UNALN; len_remain -= 8; len_align += 8; if (len_remain) { @@ -4325,11 +4738,13 @@ void gen_sve_str(DisasContext *s, TCGv_ptr base, int vofs, case 4: case 8: tcg_gen_qemu_st_i64(t0, clean_addr, midx, - MO_LE | ctz32(len_remain) | MO_ATOM_NONE); + MO_LE | ctz32(len_remain) + | MO_ATOM_NONE | align); break; case 6: - tcg_gen_qemu_st_i64(t0, clean_addr, midx, MO_LEUL | MO_ATOM_NONE); + tcg_gen_qemu_st_i64(t0, clean_addr, midx, + MO_LEUL | MO_ATOM_NONE | align); tcg_gen_addi_i64(clean_addr, clean_addr, 4); tcg_gen_shri_i64(t0, t0, 32); tcg_gen_qemu_st_i64(t0, clean_addr, midx, MO_LEUW | MO_ATOM_NONE); @@ -4349,7 +4764,8 @@ static bool trans_LDR_zri(DisasContext *s, arg_rri *a) if (sve_access_check(s)) { int size = vec_full_reg_size(s); int off = vec_full_reg_offset(s, a->rd); - gen_sve_ldr(s, tcg_env, off, size, a->rn, a->imm * size); + gen_sve_ldr(s, tcg_env, off, size, a->rn, a->imm * size, + s->align_mem ? MO_ALIGN_16 : MO_UNALN); } return true; } @@ -4362,7 +4778,8 @@ static bool trans_LDR_pri(DisasContext *s, arg_rri *a) if (sve_access_check(s)) { int size = pred_full_reg_size(s); int off = pred_full_reg_offset(s, a->rd); - gen_sve_ldr(s, tcg_env, off, size, a->rn, a->imm * size); + gen_sve_ldr(s, tcg_env, off, size, a->rn, a->imm * size, + s->align_mem ? MO_ALIGN_2 : MO_UNALN); } return true; } @@ -4375,7 +4792,8 @@ static bool trans_STR_zri(DisasContext *s, arg_rri *a) if (sve_access_check(s)) { int size = vec_full_reg_size(s); int off = vec_full_reg_offset(s, a->rd); - gen_sve_str(s, tcg_env, off, size, a->rn, a->imm * size); + gen_sve_str(s, tcg_env, off, size, a->rn, a->imm * size, + s->align_mem ? MO_ALIGN_16 : MO_UNALN); } return true; } @@ -4388,7 +4806,8 @@ static bool trans_STR_pri(DisasContext *s, arg_rri *a) if (sve_access_check(s)) { int size = pred_full_reg_size(s); int off = pred_full_reg_offset(s, a->rd); - gen_sve_str(s, tcg_env, off, size, a->rn, a->imm * size); + gen_sve_str(s, tcg_env, off, size, a->rn, a->imm * size, + s->align_mem ? MO_ALIGN_2 : MO_UNALN); } return true; } @@ -4398,21 +4817,25 @@ static bool trans_STR_pri(DisasContext *s, arg_rri *a) */ /* The memory mode of the dtype. */ -static const MemOp dtype_mop[16] = { +static const MemOp dtype_mop[19] = { MO_UB, MO_UB, MO_UB, MO_UB, MO_SL, MO_UW, MO_UW, MO_UW, MO_SW, MO_SW, MO_UL, MO_UL, - MO_SB, MO_SB, MO_SB, MO_UQ + MO_SB, MO_SB, MO_SB, MO_UQ, + /* Artificial values used by decode */ + MO_UL, MO_UQ, MO_128, }; #define dtype_msz(x) (dtype_mop[x] & MO_SIZE) /* The vector element size of dtype. */ -static const uint8_t dtype_esz[16] = { +static const uint8_t dtype_esz[19] = { 0, 1, 2, 3, 3, 1, 2, 3, 3, 2, 2, 3, - 3, 2, 1, 3 + 3, 2, 1, 3, + /* Artificial values used by decode */ + 4, 4, 4, }; uint32_t make_svemte_desc(DisasContext *s, unsigned vsz, uint32_t nregs, @@ -4463,7 +4886,7 @@ static void do_mem_zpa(DisasContext *s, int zt, int pg, TCGv_i64 addr, } /* Indexed by [mte][be][dtype][nreg] */ -static gen_helper_gvec_mem * const ldr_fns[2][2][16][4] = { +static gen_helper_gvec_mem * const ldr_fns[2][2][19][4] = { { /* mte inactive, little-endian */ { { gen_helper_sve_ld1bb_r, gen_helper_sve_ld2bb_r, gen_helper_sve_ld3bb_r, gen_helper_sve_ld4bb_r }, @@ -4487,7 +4910,13 @@ static gen_helper_gvec_mem * const ldr_fns[2][2][16][4] = { { gen_helper_sve_ld1bss_r, NULL, NULL, NULL }, { gen_helper_sve_ld1bhs_r, NULL, NULL, NULL }, { gen_helper_sve_ld1dd_le_r, gen_helper_sve_ld2dd_le_r, - gen_helper_sve_ld3dd_le_r, gen_helper_sve_ld4dd_le_r } }, + gen_helper_sve_ld3dd_le_r, gen_helper_sve_ld4dd_le_r }, + + { gen_helper_sve_ld1squ_le_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1dqu_le_r, NULL, NULL, NULL }, + { NULL, gen_helper_sve_ld2qq_le_r, + gen_helper_sve_ld3qq_le_r, gen_helper_sve_ld4qq_le_r }, + }, /* mte inactive, big-endian */ { { gen_helper_sve_ld1bb_r, gen_helper_sve_ld2bb_r, @@ -4512,7 +4941,14 @@ static gen_helper_gvec_mem * const ldr_fns[2][2][16][4] = { { gen_helper_sve_ld1bss_r, NULL, NULL, NULL }, { gen_helper_sve_ld1bhs_r, NULL, NULL, NULL }, { gen_helper_sve_ld1dd_be_r, gen_helper_sve_ld2dd_be_r, - gen_helper_sve_ld3dd_be_r, gen_helper_sve_ld4dd_be_r } } }, + gen_helper_sve_ld3dd_be_r, gen_helper_sve_ld4dd_be_r }, + + { gen_helper_sve_ld1squ_be_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1dqu_be_r, NULL, NULL, NULL }, + { NULL, gen_helper_sve_ld2qq_be_r, + gen_helper_sve_ld3qq_be_r, gen_helper_sve_ld4qq_be_r }, + }, + }, { /* mte active, little-endian */ { { gen_helper_sve_ld1bb_r_mte, @@ -4545,7 +4981,15 @@ static gen_helper_gvec_mem * const ldr_fns[2][2][16][4] = { { gen_helper_sve_ld1dd_le_r_mte, gen_helper_sve_ld2dd_le_r_mte, gen_helper_sve_ld3dd_le_r_mte, - gen_helper_sve_ld4dd_le_r_mte } }, + gen_helper_sve_ld4dd_le_r_mte }, + + { gen_helper_sve_ld1squ_le_r_mte, NULL, NULL, NULL }, + { gen_helper_sve_ld1dqu_le_r_mte, NULL, NULL, NULL }, + { NULL, + gen_helper_sve_ld2qq_le_r_mte, + gen_helper_sve_ld3qq_le_r_mte, + gen_helper_sve_ld4qq_le_r_mte }, + }, /* mte active, big-endian */ { { gen_helper_sve_ld1bb_r_mte, @@ -4578,7 +5022,16 @@ static gen_helper_gvec_mem * const ldr_fns[2][2][16][4] = { { gen_helper_sve_ld1dd_be_r_mte, gen_helper_sve_ld2dd_be_r_mte, gen_helper_sve_ld3dd_be_r_mte, - gen_helper_sve_ld4dd_be_r_mte } } }, + gen_helper_sve_ld4dd_be_r_mte }, + + { gen_helper_sve_ld1squ_be_r_mte, NULL, NULL, NULL }, + { gen_helper_sve_ld1dqu_be_r_mte, NULL, NULL, NULL }, + { NULL, + gen_helper_sve_ld2qq_be_r_mte, + gen_helper_sve_ld3qq_be_r_mte, + gen_helper_sve_ld4qq_be_r_mte }, + }, + }, }; static void do_ld_zpa(DisasContext *s, int zt, int pg, @@ -4597,9 +5050,32 @@ static void do_ld_zpa(DisasContext *s, int zt, int pg, static bool trans_LD_zprr(DisasContext *s, arg_rprr_load *a) { - if (a->rm == 31 || !dc_isar_feature(aa64_sve, s)) { + if (a->rm == 31) { return false; } + + /* dtypes 16-18 are artificial, representing 128-bit element */ + switch (a->dtype) { + case 0 ... 15: + if (!dc_isar_feature(aa64_sve, s)) { + return false; + } + break; + case 16: case 17: + if (!dc_isar_feature(aa64_sve2p1, s)) { + return false; + } + s->is_nonstreaming = true; + break; + case 18: + if (!dc_isar_feature(aa64_sme2p1_or_sve2p1, s)) { + return false; + } + break; + default: + g_assert_not_reached(); + } + if (sve_access_check(s)) { TCGv_i64 addr = tcg_temp_new_i64(); tcg_gen_shli_i64(addr, cpu_reg(s, a->rm), dtype_msz(a->dtype)); @@ -4611,9 +5087,28 @@ static bool trans_LD_zprr(DisasContext *s, arg_rprr_load *a) static bool trans_LD_zpri(DisasContext *s, arg_rpri_load *a) { - if (!dc_isar_feature(aa64_sve, s)) { - return false; + /* dtypes 16-18 are artificial, representing 128-bit element */ + switch (a->dtype) { + case 0 ... 15: + if (!dc_isar_feature(aa64_sve, s)) { + return false; + } + break; + case 16: case 17: + if (!dc_isar_feature(aa64_sve2p1, s)) { + return false; + } + s->is_nonstreaming = true; + break; + case 18: + if (!dc_isar_feature(aa64_sme2p1_or_sve2p1, s)) { + return false; + } + break; + default: + g_assert_not_reached(); } + if (sve_access_check(s)) { int vsz = vec_full_reg_size(s); int elements = vsz >> dtype_esz[a->dtype]; @@ -5060,7 +5555,7 @@ static bool trans_LD1R_zpri(DisasContext *s, arg_rpri_load *a) static void do_st_zpa(DisasContext *s, int zt, int pg, TCGv_i64 addr, int msz, int esz, int nreg) { - static gen_helper_gvec_mem * const fn_single[2][2][4][4] = { + static gen_helper_gvec_mem * const fn_single[2][2][4][5] = { { { { gen_helper_sve_st1bb_r, gen_helper_sve_st1bh_r, gen_helper_sve_st1bs_r, @@ -5071,9 +5566,11 @@ static void do_st_zpa(DisasContext *s, int zt, int pg, TCGv_i64 addr, gen_helper_sve_st1hd_le_r }, { NULL, NULL, gen_helper_sve_st1ss_le_r, - gen_helper_sve_st1sd_le_r }, + gen_helper_sve_st1sd_le_r, + gen_helper_sve_st1sq_le_r, }, { NULL, NULL, NULL, - gen_helper_sve_st1dd_le_r } }, + gen_helper_sve_st1dd_le_r, + gen_helper_sve_st1dq_le_r, } }, { { gen_helper_sve_st1bb_r, gen_helper_sve_st1bh_r, gen_helper_sve_st1bs_r, @@ -5084,9 +5581,11 @@ static void do_st_zpa(DisasContext *s, int zt, int pg, TCGv_i64 addr, gen_helper_sve_st1hd_be_r }, { NULL, NULL, gen_helper_sve_st1ss_be_r, - gen_helper_sve_st1sd_be_r }, + gen_helper_sve_st1sd_be_r, + gen_helper_sve_st1sq_be_r }, { NULL, NULL, NULL, - gen_helper_sve_st1dd_be_r } } }, + gen_helper_sve_st1dd_be_r, + gen_helper_sve_st1dq_be_r } } }, { { { gen_helper_sve_st1bb_r_mte, gen_helper_sve_st1bh_r_mte, @@ -5098,9 +5597,11 @@ static void do_st_zpa(DisasContext *s, int zt, int pg, TCGv_i64 addr, gen_helper_sve_st1hd_le_r_mte }, { NULL, NULL, gen_helper_sve_st1ss_le_r_mte, - gen_helper_sve_st1sd_le_r_mte }, + gen_helper_sve_st1sd_le_r_mte, + gen_helper_sve_st1sq_le_r_mte }, { NULL, NULL, NULL, - gen_helper_sve_st1dd_le_r_mte } }, + gen_helper_sve_st1dd_le_r_mte, + gen_helper_sve_st1dq_le_r_mte } }, { { gen_helper_sve_st1bb_r_mte, gen_helper_sve_st1bh_r_mte, gen_helper_sve_st1bs_r_mte, @@ -5111,59 +5612,73 @@ static void do_st_zpa(DisasContext *s, int zt, int pg, TCGv_i64 addr, gen_helper_sve_st1hd_be_r_mte }, { NULL, NULL, gen_helper_sve_st1ss_be_r_mte, - gen_helper_sve_st1sd_be_r_mte }, + gen_helper_sve_st1sd_be_r_mte, + gen_helper_sve_st1sq_be_r_mte }, { NULL, NULL, NULL, - gen_helper_sve_st1dd_be_r_mte } } }, + gen_helper_sve_st1dd_be_r_mte, + gen_helper_sve_st1dq_be_r_mte } } }, }; - static gen_helper_gvec_mem * const fn_multiple[2][2][3][4] = { + static gen_helper_gvec_mem * const fn_multiple[2][2][3][5] = { { { { gen_helper_sve_st2bb_r, gen_helper_sve_st2hh_le_r, gen_helper_sve_st2ss_le_r, - gen_helper_sve_st2dd_le_r }, + gen_helper_sve_st2dd_le_r, + gen_helper_sve_st2qq_le_r }, { gen_helper_sve_st3bb_r, gen_helper_sve_st3hh_le_r, gen_helper_sve_st3ss_le_r, - gen_helper_sve_st3dd_le_r }, + gen_helper_sve_st3dd_le_r, + gen_helper_sve_st3qq_le_r }, { gen_helper_sve_st4bb_r, gen_helper_sve_st4hh_le_r, gen_helper_sve_st4ss_le_r, - gen_helper_sve_st4dd_le_r } }, + gen_helper_sve_st4dd_le_r, + gen_helper_sve_st4qq_le_r } }, { { gen_helper_sve_st2bb_r, gen_helper_sve_st2hh_be_r, gen_helper_sve_st2ss_be_r, - gen_helper_sve_st2dd_be_r }, + gen_helper_sve_st2dd_be_r, + gen_helper_sve_st2qq_be_r }, { gen_helper_sve_st3bb_r, gen_helper_sve_st3hh_be_r, gen_helper_sve_st3ss_be_r, - gen_helper_sve_st3dd_be_r }, + gen_helper_sve_st3dd_be_r, + gen_helper_sve_st3qq_be_r }, { gen_helper_sve_st4bb_r, gen_helper_sve_st4hh_be_r, gen_helper_sve_st4ss_be_r, - gen_helper_sve_st4dd_be_r } } }, + gen_helper_sve_st4dd_be_r, + gen_helper_sve_st4qq_be_r } } }, { { { gen_helper_sve_st2bb_r_mte, gen_helper_sve_st2hh_le_r_mte, gen_helper_sve_st2ss_le_r_mte, - gen_helper_sve_st2dd_le_r_mte }, + gen_helper_sve_st2dd_le_r_mte, + gen_helper_sve_st2qq_le_r_mte }, { gen_helper_sve_st3bb_r_mte, gen_helper_sve_st3hh_le_r_mte, gen_helper_sve_st3ss_le_r_mte, - gen_helper_sve_st3dd_le_r_mte }, + gen_helper_sve_st3dd_le_r_mte, + gen_helper_sve_st3qq_le_r_mte }, { gen_helper_sve_st4bb_r_mte, gen_helper_sve_st4hh_le_r_mte, gen_helper_sve_st4ss_le_r_mte, - gen_helper_sve_st4dd_le_r_mte } }, + gen_helper_sve_st4dd_le_r_mte, + gen_helper_sve_st4qq_le_r_mte } }, { { gen_helper_sve_st2bb_r_mte, gen_helper_sve_st2hh_be_r_mte, gen_helper_sve_st2ss_be_r_mte, - gen_helper_sve_st2dd_be_r_mte }, + gen_helper_sve_st2dd_be_r_mte, + gen_helper_sve_st2qq_be_r_mte }, { gen_helper_sve_st3bb_r_mte, gen_helper_sve_st3hh_be_r_mte, gen_helper_sve_st3ss_be_r_mte, - gen_helper_sve_st3dd_be_r_mte }, + gen_helper_sve_st3dd_be_r_mte, + gen_helper_sve_st3qq_be_r_mte }, { gen_helper_sve_st4bb_r_mte, gen_helper_sve_st4hh_be_r_mte, gen_helper_sve_st4ss_be_r_mte, - gen_helper_sve_st4dd_be_r_mte } } }, + gen_helper_sve_st4dd_be_r_mte, + gen_helper_sve_st4qq_be_r_mte } } }, }; gen_helper_gvec_mem *fn; int be = s->be_data == MO_BE; @@ -5182,12 +5697,32 @@ static void do_st_zpa(DisasContext *s, int zt, int pg, TCGv_i64 addr, static bool trans_ST_zprr(DisasContext *s, arg_rprr_store *a) { - if (!dc_isar_feature(aa64_sve, s)) { - return false; - } if (a->rm == 31 || a->msz > a->esz) { return false; } + switch (a->esz) { + case MO_8 ... MO_64: + if (!dc_isar_feature(aa64_sve, s)) { + return false; + } + break; + case MO_128: + if (a->nreg == 0) { + assert(a->msz < a->esz); + if (!dc_isar_feature(aa64_sve2p1, s)) { + return false; + } + s->is_nonstreaming = true; + } else { + if (!dc_isar_feature(aa64_sme2p1_or_sve2p1, s)) { + return false; + } + } + break; + default: + g_assert_not_reached(); + } + if (sve_access_check(s)) { TCGv_i64 addr = tcg_temp_new_i64(); tcg_gen_shli_i64(addr, cpu_reg(s, a->rm), a->msz); @@ -5199,12 +5734,32 @@ static bool trans_ST_zprr(DisasContext *s, arg_rprr_store *a) static bool trans_ST_zpri(DisasContext *s, arg_rpri_store *a) { - if (!dc_isar_feature(aa64_sve, s)) { - return false; - } if (a->msz > a->esz) { return false; } + switch (a->esz) { + case MO_8 ... MO_64: + if (!dc_isar_feature(aa64_sve, s)) { + return false; + } + break; + case MO_128: + if (a->nreg == 0) { + assert(a->msz < a->esz); + if (!dc_isar_feature(aa64_sve2p1, s)) { + return false; + } + s->is_nonstreaming = true; + } else { + if (!dc_isar_feature(aa64_sme2p1_or_sve2p1, s)) { + return false; + } + } + break; + default: + g_assert_not_reached(); + } + if (sve_access_check(s)) { int vsz = vec_full_reg_size(s); int elements = vsz >> a->esz; @@ -5566,13 +6121,23 @@ gather_load_fn64[2][2][2][3][2][4] = { gen_helper_sve_ldffdd_be_zd_mte, } } } } }, }; +static gen_helper_gvec_mem_scatter * const +gather_load_fn128[2][2] = { + { gen_helper_sve_ldqq_le_zd, + gen_helper_sve_ldqq_be_zd }, + { gen_helper_sve_ldqq_le_zd_mte, + gen_helper_sve_ldqq_be_zd_mte } +}; + static bool trans_LD1_zprz(DisasContext *s, arg_LD1_zprz *a) { gen_helper_gvec_mem_scatter *fn = NULL; bool be = s->be_data == MO_BE; bool mte = s->mte_active[0]; - if (!dc_isar_feature(aa64_sve, s)) { + if (a->esz < MO_128 + ? !dc_isar_feature(aa64_sve, s) + : !dc_isar_feature(aa64_sve2p1, s)) { return false; } s->is_nonstreaming = true; @@ -5587,6 +6152,12 @@ static bool trans_LD1_zprz(DisasContext *s, arg_LD1_zprz *a) case MO_64: fn = gather_load_fn64[mte][be][a->ff][a->xs][a->u][a->msz]; break; + case MO_128: + assert(!a->ff && a->u && a->xs == 2 && a->msz == MO_128); + fn = gather_load_fn128[mte][be]; + break; + default: + g_assert_not_reached(); } assert(fn != NULL); @@ -5754,6 +6325,14 @@ static gen_helper_gvec_mem_scatter * const scatter_store_fn64[2][2][3][4] = { gen_helper_sve_stdd_be_zd_mte, } } }, }; +static gen_helper_gvec_mem_scatter * const +scatter_store_fn128[2][2] = { + { gen_helper_sve_stqq_le_zd, + gen_helper_sve_stqq_be_zd }, + { gen_helper_sve_stqq_le_zd_mte, + gen_helper_sve_stqq_be_zd_mte } +}; + static bool trans_ST1_zprz(DisasContext *s, arg_ST1_zprz *a) { gen_helper_gvec_mem_scatter *fn; @@ -5763,7 +6342,9 @@ static bool trans_ST1_zprz(DisasContext *s, arg_ST1_zprz *a) if (a->esz < a->msz || (a->msz == 0 && a->scale)) { return false; } - if (!dc_isar_feature(aa64_sve, s)) { + if (a->esz < MO_128 + ? !dc_isar_feature(aa64_sve, s) + : !dc_isar_feature(aa64_sve2p1, s)) { return false; } s->is_nonstreaming = true; @@ -5777,6 +6358,10 @@ static bool trans_ST1_zprz(DisasContext *s, arg_ST1_zprz *a) case MO_64: fn = scatter_store_fn64[mte][be][a->xs][a->msz]; break; + case MO_128: + assert(a->xs == 2 && a->msz == MO_128); + fn = scatter_store_fn128[mte][be]; + break; default: g_assert_not_reached(); } @@ -5911,6 +6496,7 @@ TRANS_FEAT(MOVPRFX_z, aa64_sve, do_movz_zpz, a->rd, a->rn, a->pg, a->esz, false) */ TRANS_FEAT(MUL_zzz, aa64_sve2, gen_gvec_fn_arg_zzz, tcg_gen_gvec_mul, a) +TRANS_FEAT(SQDMULH_zzz, aa64_sve2, gen_gvec_fn_arg_zzz, gen_gvec_sve2_sqdmulh, a) static gen_helper_gvec_3 * const smulh_zzz_fns[4] = { gen_helper_gvec_smulh_b, gen_helper_gvec_smulh_h, @@ -5929,13 +6515,6 @@ TRANS_FEAT(UMULH_zzz, aa64_sve2, gen_gvec_ool_arg_zzz, TRANS_FEAT(PMUL_zzz, aa64_sve2, gen_gvec_ool_arg_zzz, gen_helper_gvec_pmul_b, a, 0) -static gen_helper_gvec_3 * const sqdmulh_zzz_fns[4] = { - gen_helper_sve2_sqdmulh_b, gen_helper_sve2_sqdmulh_h, - gen_helper_sve2_sqdmulh_s, gen_helper_sve2_sqdmulh_d, -}; -TRANS_FEAT(SQDMULH_zzz, aa64_sve2, gen_gvec_ool_arg_zzz, - sqdmulh_zzz_fns[a->esz], a, 0) - static gen_helper_gvec_3 * const sqrdmulh_zzz_fns[4] = { gen_helper_sve2_sqrdmulh_b, gen_helper_sve2_sqrdmulh_h, gen_helper_sve2_sqrdmulh_s, gen_helper_sve2_sqrdmulh_d, @@ -7008,17 +7587,26 @@ DO_ZPZZ_FP(FMINNMP, aa64_sve2, sve2_fminnmp_zpzz) DO_ZPZZ_FP(FMAXP, aa64_sve2, sve2_fmaxp_zpzz) DO_ZPZZ_FP(FMINP, aa64_sve2, sve2_fminp_zpzz) +static bool do_fmmla(DisasContext *s, arg_rrrr_esz *a, + gen_helper_gvec_4_ptr *fn) +{ + if (sve_access_check(s)) { + if (vec_full_reg_size(s) < 4 * memop_size(a->esz)) { + unallocated_encoding(s); + } else { + gen_gvec_fpst_zzzz(s, fn, a->rd, a->rn, a->rm, a->ra, 0, FPST_A64); + } + } + return true; +} + +TRANS_FEAT_NONSTREAMING(FMMLA_s, aa64_sve_f32mm, do_fmmla, a, gen_helper_fmmla_s) +TRANS_FEAT_NONSTREAMING(FMMLA_d, aa64_sve_f64mm, do_fmmla, a, gen_helper_fmmla_d) + /* * SVE Integer Multiply-Add (unpredicated) */ -TRANS_FEAT_NONSTREAMING(FMMLA_s, aa64_sve_f32mm, gen_gvec_fpst_zzzz, - gen_helper_fmmla_s, a->rd, a->rn, a->rm, a->ra, - 0, FPST_A64) -TRANS_FEAT_NONSTREAMING(FMMLA_d, aa64_sve_f64mm, gen_gvec_fpst_zzzz, - gen_helper_fmmla_d, a->rd, a->rn, a->rm, a->ra, - 0, FPST_A64) - static gen_helper_gvec_4 * const sqdmlal_zzzw_fns[] = { NULL, gen_helper_sve2_sqdmlal_zzzw_h, gen_helper_sve2_sqdmlal_zzzw_s, gen_helper_sve2_sqdmlal_zzzw_d, @@ -7111,8 +7699,13 @@ static gen_helper_gvec_4 * const sqrdcmlah_fns[] = { TRANS_FEAT(SQRDCMLAH_zzzz, aa64_sve2, gen_gvec_ool_zzzz, sqrdcmlah_fns[a->esz], a->rd, a->rn, a->rm, a->ra, a->rot) -TRANS_FEAT(USDOT_zzzz, aa64_sve_i8mm, gen_gvec_ool_arg_zzzz, - a->esz == 2 ? gen_helper_gvec_usdot_b : NULL, a, 0) +TRANS_FEAT(USDOT_zzzz_4s, aa64_sve_i8mm, gen_gvec_ool_arg_zzzz, + gen_helper_gvec_usdot_4b, a, 0) + +TRANS_FEAT(SDOT_zzzz_2s, aa64_sme2_or_sve2p1, gen_gvec_ool_arg_zzzz, + gen_helper_gvec_sdot_2h, a, 0) +TRANS_FEAT(UDOT_zzzz_2s, aa64_sme2_or_sve2p1, gen_gvec_ool_arg_zzzz, + gen_helper_gvec_udot_2h, a, 0) TRANS_FEAT_NONSTREAMING(AESMC, aa64_sve2_aes, gen_gvec_ool_zz, gen_helper_crypto_aesmc, a->rd, a->rd, 0) @@ -7174,7 +7767,7 @@ static bool do_FMLAL_zzxw(DisasContext *s, arg_rrxr_esz *a, bool sub, bool sel) { return gen_gvec_ptr_zzzz(s, gen_helper_sve2_fmlal_zzxw_s, a->rd, a->rn, a->rm, a->ra, - (a->index << 2) | (sel << 1) | sub, tcg_env); + (a->index << 3) | (sel << 1) | sub, tcg_env); } TRANS_FEAT(FMLALB_zzxw, aa64_sve2, do_FMLAL_zzxw, a, false, false) @@ -7189,6 +7782,11 @@ TRANS_FEAT_NONSTREAMING(USMMLA, aa64_sve_i8mm, gen_gvec_ool_arg_zzzz, TRANS_FEAT_NONSTREAMING(UMMLA, aa64_sve_i8mm, gen_gvec_ool_arg_zzzz, gen_helper_gvec_ummla_b, a, 0) +TRANS_FEAT(FDOT_zzzz, aa64_sme2_or_sve2p1, gen_gvec_env_arg_zzzz, + gen_helper_sme2_fdot_h, a, 0) +TRANS_FEAT(FDOT_zzxz, aa64_sme2_or_sve2p1, gen_gvec_env_arg_zzxz, + gen_helper_sme2_fdot_idx_h, a) + TRANS_FEAT(BFDOT_zzzz, aa64_sve_bf16, gen_gvec_env_arg_zzzz, gen_helper_gvec_bfdot, a, 0) TRANS_FEAT(BFDOT_zzxz, aa64_sve_bf16, gen_gvec_env_arg_zzxz, @@ -7218,6 +7816,36 @@ static bool do_BFMLAL_zzxw(DisasContext *s, arg_rrxr_esz *a, bool sel) TRANS_FEAT(BFMLALB_zzxw, aa64_sve_bf16, do_BFMLAL_zzxw, a, false) TRANS_FEAT(BFMLALT_zzxw, aa64_sve_bf16, do_BFMLAL_zzxw, a, true) +static bool do_BFMLSL_zzzw(DisasContext *s, arg_rrrr_esz *a, bool sel) +{ + if (s->fpcr_ah) { + return gen_gvec_fpst_zzzz(s, gen_helper_gvec_ah_bfmlsl, + a->rd, a->rn, a->rm, a->ra, sel, FPST_AH); + } else { + return gen_gvec_fpst_zzzz(s, gen_helper_gvec_bfmlsl, + a->rd, a->rn, a->rm, a->ra, sel, FPST_A64); + } +} + +TRANS_FEAT(BFMLSLB_zzzw, aa64_sme2_or_sve2p1, do_BFMLSL_zzzw, a, false) +TRANS_FEAT(BFMLSLT_zzzw, aa64_sme2_or_sve2p1, do_BFMLSL_zzzw, a, true) + +static bool do_BFMLSL_zzxw(DisasContext *s, arg_rrxr_esz *a, bool sel) +{ + if (s->fpcr_ah) { + return gen_gvec_fpst_zzzz(s, gen_helper_gvec_ah_bfmlsl_idx, + a->rd, a->rn, a->rm, a->ra, + (a->index << 1) | sel, FPST_AH); + } else { + return gen_gvec_fpst_zzzz(s, gen_helper_gvec_bfmlsl_idx, + a->rd, a->rn, a->rm, a->ra, + (a->index << 1) | sel, FPST_A64); + } +} + +TRANS_FEAT(BFMLSLB_zzxw, aa64_sme2_or_sve2p1, do_BFMLSL_zzxw, a, false) +TRANS_FEAT(BFMLSLT_zzxw, aa64_sme2_or_sve2p1, do_BFMLSL_zzxw, a, true) + static bool trans_PSEL(DisasContext *s, arg_psel *a) { int vl = vec_full_reg_size(s); @@ -7226,7 +7854,7 @@ static bool trans_PSEL(DisasContext *s, arg_psel *a) TCGv_i64 tmp, didx, dbit; TCGv_ptr ptr; - if (!dc_isar_feature(aa64_sme, s)) { + if (!dc_isar_feature(aa64_sme_or_sve2p1, s)) { return false; } if (!sve_access_check(s)) { @@ -7265,6 +7893,7 @@ static bool trans_PSEL(DisasContext *s, arg_psel *a) tcg_gen_neg_i64(tmp, tmp); /* Apply to either copy the source, or write zeros. */ + pl = size_for_gvec(pl); tcg_gen_gvec_ands(MO_64, pred_full_reg_offset(s, a->pd), pred_full_reg_offset(s, a->pn), tmp, pl, pl); return true; @@ -7319,7 +7948,7 @@ static void gen_sclamp(unsigned vece, uint32_t d, uint32_t n, uint32_t m, tcg_gen_gvec_4(d, n, m, a, oprsz, maxsz, &ops[vece]); } -TRANS_FEAT(SCLAMP, aa64_sme, gen_gvec_fn_arg_zzzz, gen_sclamp, a) +TRANS_FEAT(SCLAMP, aa64_sme_or_sve2p1, gen_gvec_fn_arg_zzzz, gen_sclamp, a) static void gen_uclamp_i32(TCGv_i32 d, TCGv_i32 n, TCGv_i32 m, TCGv_i32 a) { @@ -7370,4 +7999,136 @@ static void gen_uclamp(unsigned vece, uint32_t d, uint32_t n, uint32_t m, tcg_gen_gvec_4(d, n, m, a, oprsz, maxsz, &ops[vece]); } -TRANS_FEAT(UCLAMP, aa64_sme, gen_gvec_fn_arg_zzzz, gen_uclamp, a) +TRANS_FEAT(UCLAMP, aa64_sme_or_sve2p1, gen_gvec_fn_arg_zzzz, gen_uclamp, a) + +static bool trans_FCLAMP(DisasContext *s, arg_FCLAMP *a) +{ + static gen_helper_gvec_3_ptr * const fn[] = { + gen_helper_sme2_bfclamp, + gen_helper_sme2_fclamp_h, + gen_helper_sme2_fclamp_s, + gen_helper_sme2_fclamp_d, + }; + + /* This insn uses MO_8 to encode BFloat16. */ + if (a->esz == MO_8 + ? !dc_isar_feature(aa64_sve_b16b16, s) + : !dc_isar_feature(aa64_sme2_or_sve2p1, s)) { + return false; + } + + /* So far we never optimize rda with MOVPRFX */ + assert(a->rd == a->ra); + return gen_gvec_fpst_zzz(s, fn[a->esz], a->rd, a->rn, a->rm, 1, + a->esz == MO_16 ? FPST_A64_F16 : FPST_A64); +} + +TRANS_FEAT(SQCVTN_sh, aa64_sme2_or_sve2p1, gen_gvec_ool_zz, + gen_helper_sme2_sqcvtn_sh, a->rd, a->rn, 0) +TRANS_FEAT(UQCVTN_sh, aa64_sme2_or_sve2p1, gen_gvec_ool_zz, + gen_helper_sme2_uqcvtn_sh, a->rd, a->rn, 0) +TRANS_FEAT(SQCVTUN_sh, aa64_sme2_or_sve2p1, gen_gvec_ool_zz, + gen_helper_sme2_sqcvtun_sh, a->rd, a->rn, 0) + +static bool gen_ldst_c(DisasContext *s, TCGv_i64 addr, int zd, int png, + MemOp esz, bool is_write, int n, bool strided) +{ + typedef void ldst_c_fn(TCGv_env, TCGv_ptr, TCGv_i64, + TCGv_i32, TCGv_i32); + static ldst_c_fn * const f_ldst[2][2][4] = { + { { gen_helper_sve2p1_ld1bb_c, + gen_helper_sve2p1_ld1hh_le_c, + gen_helper_sve2p1_ld1ss_le_c, + gen_helper_sve2p1_ld1dd_le_c, }, + { gen_helper_sve2p1_ld1bb_c, + gen_helper_sve2p1_ld1hh_be_c, + gen_helper_sve2p1_ld1ss_be_c, + gen_helper_sve2p1_ld1dd_be_c, } }, + + { { gen_helper_sve2p1_st1bb_c, + gen_helper_sve2p1_st1hh_le_c, + gen_helper_sve2p1_st1ss_le_c, + gen_helper_sve2p1_st1dd_le_c, }, + { gen_helper_sve2p1_st1bb_c, + gen_helper_sve2p1_st1hh_be_c, + gen_helper_sve2p1_st1ss_be_c, + gen_helper_sve2p1_st1dd_be_c, } } + }; + + TCGv_i32 t_png, t_desc; + TCGv_ptr t_zd; + uint32_t desc, lg2_rstride = 0; + bool be = s->be_data == MO_BE; + + assert(n == 2 || n == 4); + if (strided) { + lg2_rstride = 3; + if (n == 4) { + /* Validate ZD alignment. */ + if (zd & 4) { + return false; + } + lg2_rstride = 2; + } + /* Ignore non-temporal bit */ + zd &= ~8; + } + + if (strided || !dc_isar_feature(aa64_sve2p1, s) + ? !sme_sm_enabled_check(s) + : !sve_access_check(s)) { + return true; + } + + if (!s->mte_active[0]) { + addr = clean_data_tbi(s, addr); + } + + desc = n == 2 ? 0 : 1; + desc = desc | (lg2_rstride << 1); + desc = make_svemte_desc(s, vec_full_reg_size(s), 1, esz, is_write, desc); + t_desc = tcg_constant_i32(desc); + + t_png = tcg_temp_new_i32(); + tcg_gen_ld16u_i32(t_png, tcg_env, + pred_full_reg_offset(s, png) ^ + (HOST_BIG_ENDIAN ? 6 : 0)); + + t_zd = tcg_temp_new_ptr(); + tcg_gen_addi_ptr(t_zd, tcg_env, vec_full_reg_offset(s, zd)); + + f_ldst[is_write][be][esz](tcg_env, t_zd, addr, t_png, t_desc); + return true; +} + +static bool gen_ldst_zcrr_c(DisasContext *s, arg_zcrr_ldst *a, + bool is_write, bool strided) +{ + TCGv_i64 addr = tcg_temp_new_i64(); + + tcg_gen_shli_i64(addr, cpu_reg(s, a->rm), a->esz); + tcg_gen_add_i64(addr, addr, cpu_reg_sp(s, a->rn)); + return gen_ldst_c(s, addr, a->rd, a->png, a->esz, is_write, + a->nreg, strided); +} + +static bool gen_ldst_zcri_c(DisasContext *s, arg_zcri_ldst *a, + bool is_write, bool strided) +{ + TCGv_i64 addr = tcg_temp_new_i64(); + + tcg_gen_addi_i64(addr, cpu_reg_sp(s, a->rn), + a->imm * a->nreg * vec_full_reg_size(s)); + return gen_ldst_c(s, addr, a->rd, a->png, a->esz, is_write, + a->nreg, strided); +} + +TRANS_FEAT(LD1_zcrr, aa64_sme2_or_sve2p1, gen_ldst_zcrr_c, a, false, false) +TRANS_FEAT(LD1_zcri, aa64_sme2_or_sve2p1, gen_ldst_zcri_c, a, false, false) +TRANS_FEAT(ST1_zcrr, aa64_sme2_or_sve2p1, gen_ldst_zcrr_c, a, true, false) +TRANS_FEAT(ST1_zcri, aa64_sme2_or_sve2p1, gen_ldst_zcri_c, a, true, false) + +TRANS_FEAT(LD1_zcrr_stride, aa64_sme2, gen_ldst_zcrr_c, a, false, true) +TRANS_FEAT(LD1_zcri_stride, aa64_sme2, gen_ldst_zcri_c, a, false, true) +TRANS_FEAT(ST1_zcrr_stride, aa64_sme2, gen_ldst_zcrr_c, a, true, true) +TRANS_FEAT(ST1_zcri_stride, aa64_sme2, gen_ldst_zcri_c, a, true, true) diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h index 0004a97..f974996 100644 --- a/target/arm/tcg/translate.h +++ b/target/arm/tcg/translate.h @@ -70,8 +70,10 @@ typedef struct DisasContext { int fp_excp_el; /* FP exception EL or 0 if enabled */ int sve_excp_el; /* SVE exception EL or 0 if enabled */ int sme_excp_el; /* SME exception EL or 0 if enabled */ + int zt0_excp_el; /* ZT0 exception EL or 0 if enabled */ int vl; /* current vector length in bytes */ int svl; /* current streaming vector length in bytes */ + int max_svl; /* maximum implemented streaming vector length */ bool vfp_enabled; /* FP enabled via FPSCR.EN */ int vec_len; int vec_stride; @@ -208,6 +210,11 @@ static inline int plus_2(DisasContext *s, int x) return x + 2; } +static inline int plus_8(DisasContext *s, int x) +{ + return x + 8; +} + static inline int plus_12(DisasContext *s, int x) { return x + 12; @@ -636,6 +643,8 @@ typedef void GVecGen3Fn(unsigned, uint32_t, uint32_t, uint32_t, uint32_t, uint32_t); typedef void GVecGen4Fn(unsigned, uint32_t, uint32_t, uint32_t, uint32_t, uint32_t, uint32_t); +typedef void GVecGen3FnVar(unsigned, TCGv_ptr, uint32_t, TCGv_ptr, uint32_t, + TCGv_ptr, uint32_t, uint32_t, uint32_t); /* Function prototype for gen_ functions for calling Neon helpers */ typedef void NeonGenOneOpFn(TCGv_i32, TCGv_i32); diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c index 986eaf8..0603db0 100644 --- a/target/arm/tcg/vec_helper.c +++ b/target/arm/tcg/vec_helper.c @@ -825,11 +825,11 @@ void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \ clear_tail(d, opr_sz, simd_maxsz(desc)); \ } -DO_DOT(gvec_sdot_b, int32_t, int8_t, int8_t) -DO_DOT(gvec_udot_b, uint32_t, uint8_t, uint8_t) -DO_DOT(gvec_usdot_b, uint32_t, uint8_t, int8_t) -DO_DOT(gvec_sdot_h, int64_t, int16_t, int16_t) -DO_DOT(gvec_udot_h, uint64_t, uint16_t, uint16_t) +DO_DOT(gvec_sdot_4b, int32_t, int8_t, int8_t) +DO_DOT(gvec_udot_4b, uint32_t, uint8_t, uint8_t) +DO_DOT(gvec_usdot_4b, uint32_t, uint8_t, int8_t) +DO_DOT(gvec_sdot_4h, int64_t, int16_t, int16_t) +DO_DOT(gvec_udot_4h, uint64_t, uint16_t, uint16_t) #define DO_DOT_IDX(NAME, TYPED, TYPEN, TYPEM, HD) \ void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \ @@ -865,12 +865,63 @@ void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \ clear_tail(d, opr_sz, simd_maxsz(desc)); \ } -DO_DOT_IDX(gvec_sdot_idx_b, int32_t, int8_t, int8_t, H4) -DO_DOT_IDX(gvec_udot_idx_b, uint32_t, uint8_t, uint8_t, H4) -DO_DOT_IDX(gvec_sudot_idx_b, int32_t, int8_t, uint8_t, H4) -DO_DOT_IDX(gvec_usdot_idx_b, int32_t, uint8_t, int8_t, H4) -DO_DOT_IDX(gvec_sdot_idx_h, int64_t, int16_t, int16_t, H8) -DO_DOT_IDX(gvec_udot_idx_h, uint64_t, uint16_t, uint16_t, H8) +DO_DOT_IDX(gvec_sdot_idx_4b, int32_t, int8_t, int8_t, H4) +DO_DOT_IDX(gvec_udot_idx_4b, uint32_t, uint8_t, uint8_t, H4) +DO_DOT_IDX(gvec_sudot_idx_4b, int32_t, int8_t, uint8_t, H4) +DO_DOT_IDX(gvec_usdot_idx_4b, int32_t, uint8_t, int8_t, H4) +DO_DOT_IDX(gvec_sdot_idx_4h, int64_t, int16_t, int16_t, H8) +DO_DOT_IDX(gvec_udot_idx_4h, uint64_t, uint16_t, uint16_t, H8) + +#undef DO_DOT +#undef DO_DOT_IDX + +/* Similar for 2-way dot product */ +#define DO_DOT(NAME, TYPED, TYPEN, TYPEM) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \ +{ \ + intptr_t i, opr_sz = simd_oprsz(desc); \ + TYPED *d = vd, *a = va; \ + TYPEN *n = vn; \ + TYPEM *m = vm; \ + for (i = 0; i < opr_sz / sizeof(TYPED); ++i) { \ + d[i] = (a[i] + \ + (TYPED)n[i * 2 + 0] * m[i * 2 + 0] + \ + (TYPED)n[i * 2 + 1] * m[i * 2 + 1]); \ + } \ + clear_tail(d, opr_sz, simd_maxsz(desc)); \ +} + +#define DO_DOT_IDX(NAME, TYPED, TYPEN, TYPEM, HD) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \ +{ \ + intptr_t i = 0, opr_sz = simd_oprsz(desc); \ + intptr_t opr_sz_n = opr_sz / sizeof(TYPED); \ + intptr_t segend = MIN(16 / sizeof(TYPED), opr_sz_n); \ + intptr_t index = simd_data(desc); \ + TYPED *d = vd, *a = va; \ + TYPEN *n = vn; \ + TYPEM *m_indexed = (TYPEM *)vm + HD(index) * 2; \ + do { \ + TYPED m0 = m_indexed[i * 2 + 0]; \ + TYPED m1 = m_indexed[i * 2 + 1]; \ + do { \ + d[i] = (a[i] + \ + n[i * 2 + 0] * m0 + \ + n[i * 2 + 1] * m1); \ + } while (++i < segend); \ + segend = i + (16 / sizeof(TYPED)); \ + } while (i < opr_sz_n); \ + clear_tail(d, opr_sz, simd_maxsz(desc)); \ +} + +DO_DOT(gvec_sdot_2h, int32_t, int16_t, int16_t) +DO_DOT(gvec_udot_2h, uint32_t, uint16_t, uint16_t) + +DO_DOT_IDX(gvec_sdot_idx_2h, int32_t, int16_t, int16_t, H4) +DO_DOT_IDX(gvec_udot_idx_2h, uint32_t, uint16_t, uint16_t, H4) + +#undef DO_DOT +#undef DO_DOT_IDX void HELPER(gvec_fcaddh)(void *vd, void *vn, void *vm, float_status *fpst, uint32_t desc) @@ -1419,10 +1470,12 @@ void HELPER(NAME)(void *vd, void *vn, void *vm, \ DO_3OP(gvec_fadd_h, float16_add, float16) DO_3OP(gvec_fadd_s, float32_add, float32) DO_3OP(gvec_fadd_d, float64_add, float64) +DO_3OP(gvec_bfadd, bfloat16_add, bfloat16) DO_3OP(gvec_fsub_h, float16_sub, float16) DO_3OP(gvec_fsub_s, float32_sub, float32) DO_3OP(gvec_fsub_d, float64_sub, float64) +DO_3OP(gvec_bfsub, bfloat16_sub, bfloat16) DO_3OP(gvec_fmul_h, float16_mul, float16) DO_3OP(gvec_fmul_s, float32_mul, float32) @@ -1515,6 +1568,13 @@ DO_3OP(gvec_ah_fmin_h, helper_vfp_ah_minh, float16) DO_3OP(gvec_ah_fmin_s, helper_vfp_ah_mins, float32) DO_3OP(gvec_ah_fmin_d, helper_vfp_ah_mind, float64) +DO_3OP(gvec_fmax_b16, bfloat16_max, bfloat16) +DO_3OP(gvec_fmin_b16, bfloat16_min, bfloat16) +DO_3OP(gvec_fmaxnum_b16, bfloat16_maxnum, bfloat16) +DO_3OP(gvec_fminnum_b16, bfloat16_minnum, bfloat16) +DO_3OP(gvec_ah_fmax_b16, helper_sme2_ah_fmax_b16, bfloat16) +DO_3OP(gvec_ah_fmin_b16, helper_sme2_ah_fmin_b16, bfloat16) + #endif #undef DO_3OP @@ -1550,6 +1610,12 @@ static float16 float16_muladd_f(float16 dest, float16 op1, float16 op2, return float16_muladd(op1, op2, dest, 0, stat); } +static bfloat16 bfloat16_muladd_f(bfloat16 dest, bfloat16 op1, bfloat16 op2, + float_status *stat) +{ + return bfloat16_muladd(op1, op2, dest, 0, stat); +} + static float32 float32_muladd_f(float32 dest, float32 op1, float32 op2, float_status *stat) { @@ -1568,6 +1634,12 @@ static float16 float16_mulsub_f(float16 dest, float16 op1, float16 op2, return float16_muladd(float16_chs(op1), op2, dest, 0, stat); } +static bfloat16 bfloat16_mulsub_f(bfloat16 dest, bfloat16 op1, bfloat16 op2, + float_status *stat) +{ + return bfloat16_muladd(bfloat16_chs(op1), op2, dest, 0, stat); +} + static float32 float32_mulsub_f(float32 dest, float32 op1, float32 op2, float_status *stat) { @@ -1586,6 +1658,12 @@ static float16 float16_ah_mulsub_f(float16 dest, float16 op1, float16 op2, return float16_muladd(op1, op2, dest, float_muladd_negate_product, stat); } +static bfloat16 bfloat16_ah_mulsub_f(bfloat16 dest, bfloat16 op1, bfloat16 op2, + float_status *stat) +{ + return bfloat16_muladd(op1, op2, dest, float_muladd_negate_product, stat); +} + static float32 float32_ah_mulsub_f(float32 dest, float32 op1, float32 op2, float_status *stat) { @@ -1610,23 +1688,28 @@ void HELPER(NAME)(void *vd, void *vn, void *vm, \ clear_tail(d, oprsz, simd_maxsz(desc)); \ } -DO_MULADD(gvec_fmla_h, float16_muladd_nf, float16) -DO_MULADD(gvec_fmla_s, float32_muladd_nf, float32) +DO_MULADD(gvec_fmla_nf_h, float16_muladd_nf, float16) +DO_MULADD(gvec_fmla_nf_s, float32_muladd_nf, float32) -DO_MULADD(gvec_fmls_h, float16_mulsub_nf, float16) -DO_MULADD(gvec_fmls_s, float32_mulsub_nf, float32) +DO_MULADD(gvec_fmls_nf_h, float16_mulsub_nf, float16) +DO_MULADD(gvec_fmls_nf_s, float32_mulsub_nf, float32) DO_MULADD(gvec_vfma_h, float16_muladd_f, float16) DO_MULADD(gvec_vfma_s, float32_muladd_f, float32) DO_MULADD(gvec_vfma_d, float64_muladd_f, float64) +DO_MULADD(gvec_bfmla, bfloat16_muladd_f, bfloat16) DO_MULADD(gvec_vfms_h, float16_mulsub_f, float16) DO_MULADD(gvec_vfms_s, float32_mulsub_f, float32) DO_MULADD(gvec_vfms_d, float64_mulsub_f, float64) +DO_MULADD(gvec_bfmls, bfloat16_mulsub_f, bfloat16) DO_MULADD(gvec_ah_vfms_h, float16_ah_mulsub_f, float16) DO_MULADD(gvec_ah_vfms_s, float32_ah_mulsub_f, float32) DO_MULADD(gvec_ah_vfms_d, float64_ah_mulsub_f, float64) +DO_MULADD(gvec_ah_bfmls, bfloat16_ah_mulsub_f, bfloat16) + +#undef DO_MULADD /* For the indexed ops, SVE applies the index per 128-bit vector segment. * For AdvSIMD, there is of course only one such vector segment. @@ -1745,14 +1828,17 @@ void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, \ DO_FMLA_IDX(gvec_fmla_idx_h, float16, H2, 0, 0) DO_FMLA_IDX(gvec_fmla_idx_s, float32, H4, 0, 0) DO_FMLA_IDX(gvec_fmla_idx_d, float64, H8, 0, 0) +DO_FMLA_IDX(gvec_bfmla_idx, bfloat16, H2, 0, 0) DO_FMLA_IDX(gvec_fmls_idx_h, float16, H2, INT16_MIN, 0) DO_FMLA_IDX(gvec_fmls_idx_s, float32, H4, INT32_MIN, 0) DO_FMLA_IDX(gvec_fmls_idx_d, float64, H8, INT64_MIN, 0) +DO_FMLA_IDX(gvec_bfmls_idx, bfloat16, H2, INT16_MIN, 0) DO_FMLA_IDX(gvec_ah_fmls_idx_h, float16, H2, 0, float_muladd_negate_product) DO_FMLA_IDX(gvec_ah_fmls_idx_s, float32, H4, 0, float_muladd_negate_product) DO_FMLA_IDX(gvec_ah_fmls_idx_d, float64, H8, 0, float_muladd_negate_product) +DO_FMLA_IDX(gvec_ah_bfmls_idx, bfloat16, H2, 0, float_muladd_negate_product) #undef DO_FMLA_IDX @@ -2184,7 +2270,8 @@ void HELPER(sve2_fmlal_zzzw_s)(void *vd, void *vn, void *vm, void *va, intptr_t i, oprsz = simd_oprsz(desc); bool is_s = extract32(desc, SIMD_DATA_SHIFT, 1); intptr_t sel = extract32(desc, SIMD_DATA_SHIFT + 1, 1) * sizeof(float16); - float_status *status = &env->vfp.fp_status[FPST_A64]; + bool za = extract32(desc, SIMD_DATA_SHIFT + 2, 1); + float_status *status = &env->vfp.fp_status[za ? FPST_ZA : FPST_A64]; bool fz16 = env->vfp.fpcr & FPCR_FZ16; int negx = 0, negf = 0; @@ -2267,8 +2354,9 @@ void HELPER(sve2_fmlal_zzxw_s)(void *vd, void *vn, void *vm, void *va, intptr_t i, j, oprsz = simd_oprsz(desc); bool is_s = extract32(desc, SIMD_DATA_SHIFT, 1); intptr_t sel = extract32(desc, SIMD_DATA_SHIFT + 1, 1) * sizeof(float16); - intptr_t idx = extract32(desc, SIMD_DATA_SHIFT + 2, 3) * sizeof(float16); - float_status *status = &env->vfp.fp_status[FPST_A64]; + bool za = extract32(desc, SIMD_DATA_SHIFT + 2, 1); + intptr_t idx = extract32(desc, SIMD_DATA_SHIFT + 3, 3) * sizeof(float16); + float_status *status = &env->vfp.fp_status[za ? FPST_ZA : FPST_A64]; bool fz16 = env->vfp.fpcr & FPCR_FZ16; int negx = 0, negf = 0; @@ -2989,31 +3077,62 @@ float32 bfdotadd(float32 sum, uint32_t e1, uint32_t e2, float_status *fpst) float32 bfdotadd_ebf(float32 sum, uint32_t e1, uint32_t e2, float_status *fpst, float_status *fpst_odd) { - /* - * Compare f16_dotadd() in sme_helper.c, but here we have - * bfloat16 inputs. In particular that means that we do not - * want the FPCR.FZ16 flush semantics, so we use the normal - * float_status for the input handling here. - */ - float64 e1r = float32_to_float64(e1 << 16, fpst); - float64 e1c = float32_to_float64(e1 & 0xffff0000u, fpst); - float64 e2r = float32_to_float64(e2 << 16, fpst); - float64 e2c = float32_to_float64(e2 & 0xffff0000u, fpst); - float64 t64; + float32 s1r = e1 << 16; + float32 s1c = e1 & 0xffff0000u; + float32 s2r = e2 << 16; + float32 s2c = e2 & 0xffff0000u; float32 t32; - /* - * The ARM pseudocode function FPDot performs both multiplies - * and the add with a single rounding operation. Emulate this - * by performing the first multiply in round-to-odd, then doing - * the second multiply as fused multiply-add, and rounding to - * float32 all in one step. - */ - t64 = float64_mul(e1r, e2r, fpst_odd); - t64 = float64r32_muladd(e1c, e2c, t64, 0, fpst); + /* C.f. FPProcessNaNs4 */ + if (float32_is_any_nan(s1r) || float32_is_any_nan(s1c) || + float32_is_any_nan(s2r) || float32_is_any_nan(s2c)) { + if (float32_is_signaling_nan(s1r, fpst)) { + t32 = s1r; + } else if (float32_is_signaling_nan(s1c, fpst)) { + t32 = s1c; + } else if (float32_is_signaling_nan(s2r, fpst)) { + t32 = s2r; + } else if (float32_is_signaling_nan(s2c, fpst)) { + t32 = s2c; + } else if (float32_is_any_nan(s1r)) { + t32 = s1r; + } else if (float32_is_any_nan(s1c)) { + t32 = s1c; + } else if (float32_is_any_nan(s2r)) { + t32 = s2r; + } else { + t32 = s2c; + } + /* + * FPConvertNaN(FPProcessNaN(t32)) will be done as part + * of the final addition below. + */ + } else { + /* + * Compare f16_dotadd() in sme_helper.c, but here we have + * bfloat16 inputs. In particular that means that we do not + * want the FPCR.FZ16 flush semantics, so we use the normal + * float_status for the input handling here. + */ + float64 e1r = float32_to_float64(s1r, fpst); + float64 e1c = float32_to_float64(s1c, fpst); + float64 e2r = float32_to_float64(s2r, fpst); + float64 e2c = float32_to_float64(s2c, fpst); + float64 t64; + + /* + * The ARM pseudocode function FPDot performs both multiplies + * and the add with a single rounding operation. Emulate this + * by performing the first multiply in round-to-odd, then doing + * the second multiply as fused multiply-add, and rounding to + * float32 all in one step. + */ + t64 = float64_mul(e1r, e2r, fpst_odd); + t64 = float64r32_muladd(e1c, e2c, t64, 0, fpst); - /* This conversion is exact, because we've already rounded. */ - t32 = float64_to_float32(t64, fpst); + /* This conversion is exact, because we've already rounded. */ + t32 = float64_to_float32(t64, fpst); + } /* The final accumulation step is not fused. */ return float32_add(sum, t32, fpst); @@ -3070,6 +3189,45 @@ void HELPER(gvec_bfdot_idx)(void *vd, void *vn, void *vm, clear_tail(d, opr_sz, simd_maxsz(desc)); } +void HELPER(sme2_bfvdot_idx)(void *vd, void *vn, void *vm, + void *va, CPUARMState *env, uint32_t desc) +{ + intptr_t i, j, opr_sz = simd_oprsz(desc); + intptr_t idx = extract32(desc, SIMD_DATA_SHIFT, 2); + intptr_t sel = extract32(desc, SIMD_DATA_SHIFT + 2, 1); + intptr_t elements = opr_sz / 4; + intptr_t eltspersegment = MIN(16 / 4, elements); + float32 *d = vd, *a = va; + uint16_t *n0 = vn; + uint16_t *n1 = vn + sizeof(ARMVectorReg); + uint32_t *m = vm; + float_status fpst, fpst_odd; + + if (is_ebf(env, &fpst, &fpst_odd)) { + for (i = 0; i < elements; i += eltspersegment) { + uint32_t m_idx = m[i + H4(idx)]; + + for (j = 0; j < eltspersegment; j++) { + uint32_t nn = (n0[H2(2 * (i + j) + sel)]) + | (n1[H2(2 * (i + j) + sel)] << 16); + d[i + H4(j)] = bfdotadd_ebf(a[i + H4(j)], nn, m_idx, + &fpst, &fpst_odd); + } + } + } else { + for (i = 0; i < elements; i += eltspersegment) { + uint32_t m_idx = m[i + H4(idx)]; + + for (j = 0; j < eltspersegment; j++) { + uint32_t nn = (n0[H2(2 * (i + j) + sel)]) + | (n1[H2(2 * (i + j) + sel)] << 16); + d[i + H4(j)] = bfdotadd(a[i + H4(j)], nn, m_idx, &fpst); + } + } + } + clear_tail(d, opr_sz, simd_maxsz(desc)); +} + void HELPER(gvec_bfmmla)(void *vd, void *vn, void *vm, void *va, CPUARMState *env, uint32_t desc) { @@ -3146,44 +3304,76 @@ void HELPER(gvec_bfmmla)(void *vd, void *vn, void *vm, void *va, clear_tail(d, opr_sz, simd_maxsz(desc)); } -void HELPER(gvec_bfmlal)(void *vd, void *vn, void *vm, void *va, - float_status *stat, uint32_t desc) +static void do_bfmlal(float32 *d, bfloat16 *n, bfloat16 *m, float32 *a, + float_status *stat, uint32_t desc, int negx, int negf) { intptr_t i, opr_sz = simd_oprsz(desc); - intptr_t sel = simd_data(desc); - float32 *d = vd, *a = va; - bfloat16 *n = vn, *m = vm; + intptr_t sel = extract32(desc, SIMD_DATA_SHIFT, 1); for (i = 0; i < opr_sz / 4; ++i) { - float32 nn = n[H2(i * 2 + sel)] << 16; + float32 nn = (negx ^ n[H2(i * 2 + sel)]) << 16; float32 mm = m[H2(i * 2 + sel)] << 16; - d[H4(i)] = float32_muladd(nn, mm, a[H4(i)], 0, stat); + d[H4(i)] = float32_muladd(nn, mm, a[H4(i)], negf, stat); } clear_tail(d, opr_sz, simd_maxsz(desc)); } -void HELPER(gvec_bfmlal_idx)(void *vd, void *vn, void *vm, - void *va, float_status *stat, uint32_t desc) +void HELPER(gvec_bfmlal)(void *vd, void *vn, void *vm, void *va, + float_status *stat, uint32_t desc) +{ + do_bfmlal(vd, vn, vm, va, stat, desc, 0, 0); +} + +void HELPER(gvec_bfmlsl)(void *vd, void *vn, void *vm, void *va, + float_status *stat, uint32_t desc) +{ + do_bfmlal(vd, vn, vm, va, stat, desc, 0x8000, 0); +} + +void HELPER(gvec_ah_bfmlsl)(void *vd, void *vn, void *vm, void *va, + float_status *stat, uint32_t desc) +{ + do_bfmlal(vd, vn, vm, va, stat, desc, 0, float_muladd_negate_product); +} + +static void do_bfmlal_idx(float32 *d, bfloat16 *n, bfloat16 *m, float32 *a, + float_status *stat, uint32_t desc, int negx, int negf) { intptr_t i, j, opr_sz = simd_oprsz(desc); intptr_t sel = extract32(desc, SIMD_DATA_SHIFT, 1); intptr_t index = extract32(desc, SIMD_DATA_SHIFT + 1, 3); intptr_t elements = opr_sz / 4; intptr_t eltspersegment = MIN(16 / 4, elements); - float32 *d = vd, *a = va; - bfloat16 *n = vn, *m = vm; for (i = 0; i < elements; i += eltspersegment) { float32 m_idx = m[H2(2 * i + index)] << 16; for (j = i; j < i + eltspersegment; j++) { - float32 n_j = n[H2(2 * j + sel)] << 16; - d[H4(j)] = float32_muladd(n_j, m_idx, a[H4(j)], 0, stat); + float32 n_j = (negx ^ n[H2(2 * j + sel)]) << 16; + d[H4(j)] = float32_muladd(n_j, m_idx, a[H4(j)], negf, stat); } } clear_tail(d, opr_sz, simd_maxsz(desc)); } +void HELPER(gvec_bfmlal_idx)(void *vd, void *vn, void *vm, void *va, + float_status *stat, uint32_t desc) +{ + do_bfmlal_idx(vd, vn, vm, va, stat, desc, 0, 0); +} + +void HELPER(gvec_bfmlsl_idx)(void *vd, void *vn, void *vm, void *va, + float_status *stat, uint32_t desc) +{ + do_bfmlal_idx(vd, vn, vm, va, stat, desc, 0x8000, 0); +} + +void HELPER(gvec_ah_bfmlsl_idx)(void *vd, void *vn, void *vm, void *va, + float_status *stat, uint32_t desc) +{ + do_bfmlal_idx(vd, vn, vm, va, stat, desc, 0, float_muladd_negate_product); +} + #define DO_CLAMP(NAME, TYPE) \ void HELPER(NAME)(void *d, void *n, void *m, void *a, uint32_t desc) \ { \ @@ -3253,3 +3443,91 @@ void HELPER(gvec_ursqrte_s)(void *vd, void *vn, uint32_t desc) } clear_tail(d, opr_sz, simd_maxsz(desc)); } + +static inline void do_lut_b(void *zd, uint64_t *indexes, uint64_t *table, + unsigned elements, unsigned segbase, + unsigned dstride, unsigned isize, + unsigned tsize, unsigned nreg) +{ + for (unsigned r = 0; r < nreg; ++r) { + uint8_t *dst = zd + dstride * r; + unsigned base = segbase + r * elements; + + for (unsigned e = 0; e < elements; ++e) { + unsigned index = extractn(indexes, (base + e) * isize, isize); + dst[H1(e)] = extractn(table, index * tsize, 8); + } + } +} + +static inline void do_lut_h(void *zd, uint64_t *indexes, uint64_t *table, + unsigned elements, unsigned segbase, + unsigned dstride, unsigned isize, + unsigned tsize, unsigned nreg) +{ + for (unsigned r = 0; r < nreg; ++r) { + uint16_t *dst = zd + dstride * r; + unsigned base = segbase + r * elements; + + for (unsigned e = 0; e < elements; ++e) { + unsigned index = extractn(indexes, (base + e) * isize, isize); + dst[H2(e)] = extractn(table, index * tsize, 16); + } + } +} + +static inline void do_lut_s(void *zd, uint64_t *indexes, uint32_t *table, + unsigned elements, unsigned segbase, + unsigned dstride, unsigned isize, + unsigned tsize, unsigned nreg) +{ + for (unsigned r = 0; r < nreg; ++r) { + uint32_t *dst = zd + dstride * r; + unsigned base = segbase + r * elements; + + for (unsigned e = 0; e < elements; ++e) { + unsigned index = extractn(indexes, (base + e) * isize, isize); + dst[H4(e)] = table[H4(index)]; + } + } +} + +#define DO_SME2_LUT(ISIZE, NREG, SUFF, ESIZE) \ +void helper_sme2_luti##ISIZE##_##NREG##SUFF \ + (void *zd, void *zn, CPUARMState *env, uint32_t desc) \ +{ \ + unsigned vl = simd_oprsz(desc); \ + unsigned strided = extract32(desc, SIMD_DATA_SHIFT, 1); \ + unsigned idx = extract32(desc, SIMD_DATA_SHIFT + 1, 4); \ + unsigned elements = vl / ESIZE; \ + unsigned dstride = (!strided ? 1 : NREG == 4 ? 4 : 8); \ + unsigned segments = (ESIZE * 8) / (ISIZE * NREG); \ + unsigned segment = idx & (segments - 1); \ + ARMVectorReg indexes; \ + memcpy(&indexes, zn, vl); \ + do_lut_##SUFF(zd, indexes.d, (void *)env->za_state.zt0, elements, \ + segment * NREG * elements, \ + dstride * sizeof(ARMVectorReg), ISIZE, 32, NREG); \ +} + +DO_SME2_LUT(2,1,b, 1) +DO_SME2_LUT(2,1,h, 2) +DO_SME2_LUT(2,1,s, 4) +DO_SME2_LUT(2,2,b, 1) +DO_SME2_LUT(2,2,h, 2) +DO_SME2_LUT(2,2,s, 4) +DO_SME2_LUT(2,4,b, 1) +DO_SME2_LUT(2,4,h, 2) +DO_SME2_LUT(2,4,s, 4) + +DO_SME2_LUT(4,1,b, 1) +DO_SME2_LUT(4,1,h, 2) +DO_SME2_LUT(4,1,s, 4) +DO_SME2_LUT(4,2,b, 1) +DO_SME2_LUT(4,2,h, 2) +DO_SME2_LUT(4,2,s, 4) +DO_SME2_LUT(4,4,b, 1) +DO_SME2_LUT(4,4,h, 2) +DO_SME2_LUT(4,4,s, 4) + +#undef DO_SME2_LUT diff --git a/target/arm/tcg/vec_internal.h b/target/arm/tcg/vec_internal.h index c02f9c3..cf41b03 100644 --- a/target/arm/tcg/vec_internal.h +++ b/target/arm/tcg/vec_internal.h @@ -223,6 +223,34 @@ int16_t do_sqrdmlah_h(int16_t, int16_t, int16_t, bool, bool, uint32_t *); int32_t do_sqrdmlah_s(int32_t, int32_t, int32_t, bool, bool, uint32_t *); int64_t do_sqrdmlah_d(int64_t, int64_t, int64_t, bool, bool); +#define do_ssat_b(val) MIN(MAX(val, INT8_MIN), INT8_MAX) +#define do_ssat_h(val) MIN(MAX(val, INT16_MIN), INT16_MAX) +#define do_ssat_s(val) MIN(MAX(val, INT32_MIN), INT32_MAX) +#define do_usat_b(val) MIN(MAX(val, 0), UINT8_MAX) +#define do_usat_h(val) MIN(MAX(val, 0), UINT16_MAX) +#define do_usat_s(val) MIN(MAX(val, 0), UINT32_MAX) + +static inline uint64_t do_urshr(uint64_t x, unsigned sh) +{ + if (likely(sh < 64)) { + return (x >> sh) + ((x >> (sh - 1)) & 1); + } else if (sh == 64) { + return x >> 63; + } else { + return 0; + } +} + +static inline int64_t do_srshr(int64_t x, unsigned sh) +{ + if (likely(sh < 64)) { + return (x >> sh) + ((x >> (sh - 1)) & 1); + } else { + /* Rounding the sign bit always produces 0. */ + return 0; + } +} + /** * bfdotadd: * @sum: addend @@ -272,6 +300,11 @@ bool is_ebf(CPUARMState *env, float_status *statusp, float_status *oddstatusp); /* * Negate as for FPCR.AH=1 -- do not negate NaNs. */ +static inline float16 bfloat16_ah_chs(float16 a) +{ + return bfloat16_is_any_nan(a) ? a : bfloat16_chs(a); +} + static inline float16 float16_ah_chs(float16 a) { return float16_is_any_nan(a) ? a : float16_chs(a); @@ -302,4 +335,119 @@ static inline float64 float64_maybe_ah_chs(float64 a, bool fpcr_ah) return fpcr_ah && float64_is_any_nan(a) ? a : float64_chs(a); } +/* Not actually called directly as a helper, but uses similar machinery. */ +bfloat16 helper_sme2_ah_fmax_b16(bfloat16 a, bfloat16 b, float_status *fpst); +bfloat16 helper_sme2_ah_fmin_b16(bfloat16 a, bfloat16 b, float_status *fpst); + +float32 sve_f16_to_f32(float16 f, float_status *fpst); +float16 sve_f32_to_f16(float32 f, float_status *fpst); + +/* + * Decode helper functions for predicate as counter. + */ + +typedef struct { + unsigned count; + unsigned lg2_stride; + bool invert; +} DecodeCounter; + +static inline DecodeCounter +decode_counter(unsigned png, unsigned vl, unsigned v_esz) +{ + DecodeCounter ret = { }; + + /* C.f. Arm pseudocode CounterToPredicate. */ + if (likely(png & 0xf)) { + unsigned p_esz = ctz32(png); + + /* + * maxbit = log2(pl(bits) * 4) + * = log2(vl(bytes) * 4) + * = log2(vl) + 2 + * maxbit_mask = ones<maxbit:0> + * = (1 << (maxbit + 1)) - 1 + * = (1 << (log2(vl) + 2 + 1)) - 1 + * = (1 << (log2(vl) + 3)) - 1 + * = (pow2ceil(vl) << 3) - 1 + */ + ret.count = png & (((unsigned)pow2ceil(vl) << 3) - 1); + ret.count >>= p_esz + 1; + + ret.invert = (png >> 15) & 1; + + /* + * The Arm pseudocode for CounterToPredicate expands the count to + * a set of bits, and then the operation proceeds as for the original + * interpretation of predicates as a set of bits. + * + * We can avoid the expansion by adjusting the count and supplying + * an element stride. + */ + if (unlikely(p_esz != v_esz)) { + if (p_esz < v_esz) { + /* + * For predicate esz < vector esz, the expanded predicate + * will have more bits set than will be consumed. + * Adjust the count down, rounding up. + * Consider p_esz = MO_8, v_esz = MO_64, count 14: + * The expanded predicate would be + * 0011 1111 1111 1111 + * The significant bits are + * ...1 ...1 ...1 ...1 + */ + unsigned shift = v_esz - p_esz; + unsigned trunc = ret.count >> shift; + ret.count = trunc + (ret.count != (trunc << shift)); + } else { + /* + * For predicate esz > vector esz, the expanded predicate + * will have bits set only at power-of-two multiples of + * the vector esz. Bits at other multiples will all be + * false. Adjust the count up, and supply the caller + * with a stride of elements to skip. + */ + unsigned shift = p_esz - v_esz; + ret.count <<= shift; + ret.lg2_stride = shift; + } + } + } + return ret; +} + +/* Extract @len bits from an array of uint64_t at offset @pos bits. */ +static inline uint64_t extractn(uint64_t *p, unsigned pos, unsigned len) +{ + uint64_t x; + + p += pos / 64; + pos = pos % 64; + + x = p[0]; + if (pos + len > 64) { + x = (x >> pos) | (p[1] << (-pos & 63)); + pos = 0; + } + return extract64(x, pos, len); +} + +/* Deposit @len bits into an array of uint64_t at offset @pos bits. */ +static inline void depositn(uint64_t *p, unsigned pos, + unsigned len, uint64_t val) +{ + p += pos / 64; + pos = pos % 64; + + if (pos + len <= 64) { + p[0] = deposit64(p[0], pos, len, val); + } else { + unsigned len0 = 64 - pos; + unsigned len1 = len - len0; + + p[0] = deposit64(p[0], pos, len0, val); + p[1] = deposit64(p[1], 0, len1, val >> len0); + } +} + #endif /* TARGET_ARM_VEC_INTERNAL_H */ diff --git a/target/arm/tcg/vfp_helper.c b/target/arm/tcg/vfp_helper.c index b1324c5..e156e37 100644 --- a/target/arm/tcg/vfp_helper.c +++ b/target/arm/tcg/vfp_helper.c @@ -123,7 +123,7 @@ uint32_t vfp_get_fpsr_from_host(CPUARMState *env) a64_flags |= (get_float_exception_flags(&env->vfp.fp_status[FPST_A64_F16]) & ~(float_flag_input_denormal_flushed | float_flag_input_denormal_used)); /* - * We do not merge in flags from FPST_AH or FPST_AH_F16, because + * We do not merge in flags from FPST_{AH,ZA} or FPST_{AH,ZA}_F16, because * they are used for insns that must not set the cumulative exception bits. */ @@ -196,6 +196,8 @@ void vfp_set_fpcr_to_host(CPUARMState *env, uint32_t val, uint32_t mask) set_float_rounding_mode(i, &env->vfp.fp_status[FPST_A64]); set_float_rounding_mode(i, &env->vfp.fp_status[FPST_A32_F16]); set_float_rounding_mode(i, &env->vfp.fp_status[FPST_A64_F16]); + set_float_rounding_mode(i, &env->vfp.fp_status[FPST_ZA]); + set_float_rounding_mode(i, &env->vfp.fp_status[FPST_ZA_F16]); } if (changed & FPCR_FZ16) { bool ftz_enabled = val & FPCR_FZ16; @@ -203,15 +205,18 @@ void vfp_set_fpcr_to_host(CPUARMState *env, uint32_t val, uint32_t mask) set_flush_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_A64_F16]); set_flush_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_STD_F16]); set_flush_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_AH_F16]); + set_flush_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_ZA_F16]); set_flush_inputs_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_A32_F16]); set_flush_inputs_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_A64_F16]); set_flush_inputs_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_STD_F16]); set_flush_inputs_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_AH_F16]); + set_flush_inputs_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_ZA_F16]); } if (changed & FPCR_FZ) { bool ftz_enabled = val & FPCR_FZ; set_flush_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_A32]); set_flush_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_A64]); + set_flush_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_ZA]); /* FIZ is A64 only so FZ always makes A32 code flush inputs to zero */ set_flush_inputs_to_zero(ftz_enabled, &env->vfp.fp_status[FPST_A32]); } @@ -223,6 +228,7 @@ void vfp_set_fpcr_to_host(CPUARMState *env, uint32_t val, uint32_t mask) bool fitz_enabled = (val & FPCR_FIZ) || (val & (FPCR_FZ | FPCR_AH)) == FPCR_FZ; set_flush_inputs_to_zero(fitz_enabled, &env->vfp.fp_status[FPST_A64]); + set_flush_inputs_to_zero(fitz_enabled, &env->vfp.fp_status[FPST_ZA]); } if (changed & FPCR_DN) { bool dnan_enabled = val & FPCR_DN; @@ -240,9 +246,13 @@ void vfp_set_fpcr_to_host(CPUARMState *env, uint32_t val, uint32_t mask) /* Change behaviours for A64 FP operations */ arm_set_ah_fp_behaviours(&env->vfp.fp_status[FPST_A64]); arm_set_ah_fp_behaviours(&env->vfp.fp_status[FPST_A64_F16]); + arm_set_ah_fp_behaviours(&env->vfp.fp_status[FPST_ZA]); + arm_set_ah_fp_behaviours(&env->vfp.fp_status[FPST_ZA_F16]); } else { arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_A64]); arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_A64_F16]); + arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_ZA]); + arm_set_default_fp_behaviours(&env->vfp.fp_status[FPST_ZA_F16]); } } /* |