target/arm: Implement SVE Integer Wide Immediate - Unpredicated Group

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20180613015641.5667-18-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

4 files changed, 236 insertions, 0 deletions

diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h
index 1863106..97bfe0f 100644
--- a/target/arm/helper-sve.h
+++ b/target/arm/helper-sve.h
@@ -680,3 +680,28 @@ 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_3(sve_while, 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)
+DEF_HELPER_FLAGS_4(sve_subri_d, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+
+DEF_HELPER_FLAGS_4(sve_smaxi_b, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(sve_smaxi_h, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(sve_smaxi_s, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(sve_smaxi_d, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+
+DEF_HELPER_FLAGS_4(sve_smini_b, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(sve_smini_h, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(sve_smini_s, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(sve_smini_d, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+
+DEF_HELPER_FLAGS_4(sve_umaxi_b, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(sve_umaxi_h, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(sve_umaxi_s, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(sve_umaxi_d, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+
+DEF_HELPER_FLAGS_4(sve_umini_b, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(sve_umini_h, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(sve_umini_s, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
+DEF_HELPER_FLAGS_4(sve_umini_d, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index b8bd22a..eee8726 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -42,6 +42,8 @@
 
 # Signed 8-bit immediate, optionally shifted left by 8.
 %sh8_i8s        5:9 !function=expand_imm_sh8s
+# Unsigned 8-bit immediate, optionally shifted left by 8.
+%sh8_i8u        5:9 !function=expand_imm_sh8u
 
 # Either a copy of rd (at bit 0), or a different source
 # as propagated via the MOVPRFX instruction.
@@ -95,6 +97,12 @@
 @pd_pn_pm       ........ esz:2 .. rm:4 ....... rn:4 . rd:4      &rrr_esz
 @rdn_rm         ........ esz:2 ...... ...... rm:5 rd:5 \
                 &rrr_esz rn=%reg_movprfx
+@rdn_sh_i8u     ........ esz:2 ...... ...... ..... rd:5 \
+                &rri_esz rn=%reg_movprfx imm=%sh8_i8u
+@rdn_i8u        ........ esz:2 ...... ... imm:8 rd:5 \
+                &rri_esz rn=%reg_movprfx
+@rdn_i8s        ........ esz:2 ...... ... imm:s8 rd:5 \
+                &rri_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
@@ -622,6 +630,24 @@ FDUP            00100101 esz:2 111 00 1110 imm:8 rd:5
 # SVE broadcast integer immediate (unpredicated)
 DUP_i           00100101 esz:2 111 00 011 . ........ rd:5       imm=%sh8_i8s
 
+# SVE integer add/subtract immediate (unpredicated)
+ADD_zzi         00100101 .. 100 000 11 . ........ .....         @rdn_sh_i8u
+SUB_zzi         00100101 .. 100 001 11 . ........ .....         @rdn_sh_i8u
+SUBR_zzi        00100101 .. 100 011 11 . ........ .....         @rdn_sh_i8u
+SQADD_zzi       00100101 .. 100 100 11 . ........ .....         @rdn_sh_i8u
+UQADD_zzi       00100101 .. 100 101 11 . ........ .....         @rdn_sh_i8u
+SQSUB_zzi       00100101 .. 100 110 11 . ........ .....         @rdn_sh_i8u
+UQSUB_zzi       00100101 .. 100 111 11 . ........ .....         @rdn_sh_i8u
+
+# SVE integer min/max immediate (unpredicated)
+SMAX_zzi        00100101 .. 101 000 110 ........ .....          @rdn_i8s
+UMAX_zzi        00100101 .. 101 001 110 ........ .....          @rdn_i8u
+SMIN_zzi        00100101 .. 101 010 110 ........ .....          @rdn_i8s
+UMIN_zzi        00100101 .. 101 011 110 ........ .....          @rdn_i8u
+
+# SVE integer multiply immediate (unpredicated)
+MUL_zzi         00100101 .. 110 000 110 ........ .....          @rdn_i8s
+
 ### SVE Memory - 32-bit Gather and Unsized Contiguous Group
 
 # SVE load predicate register
diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index 8539595..128bbf9 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -804,6 +804,46 @@ DO_VPZ_D(sve_uminv_d, uint64_t, uint64_t, -1, DO_MIN)
 #undef DO_VPZ
 #undef DO_VPZ_D
 
+/* 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)   \
+{                                                                    \
+    intptr_t i, opr_sz = simd_oprsz(desc) / sizeof(TYPE);            \
+    TYPE s = s64, *d = vd, *n = vn;                                  \
+    for (i = 0; i < opr_sz; ++i) {                                   \
+        d[i] = OP(n[i], s);                                          \
+    }                                                                \
+}
+
+#define DO_SUBR(X, Y)   (Y - X)
+
+DO_ZZI(sve_subri_b, uint8_t, DO_SUBR)
+DO_ZZI(sve_subri_h, uint16_t, DO_SUBR)
+DO_ZZI(sve_subri_s, uint32_t, DO_SUBR)
+DO_ZZI(sve_subri_d, uint64_t, DO_SUBR)
+
+DO_ZZI(sve_smaxi_b, int8_t, DO_MAX)
+DO_ZZI(sve_smaxi_h, int16_t, DO_MAX)
+DO_ZZI(sve_smaxi_s, int32_t, DO_MAX)
+DO_ZZI(sve_smaxi_d, int64_t, DO_MAX)
+
+DO_ZZI(sve_smini_b, int8_t, DO_MIN)
+DO_ZZI(sve_smini_h, int16_t, DO_MIN)
+DO_ZZI(sve_smini_s, int32_t, DO_MIN)
+DO_ZZI(sve_smini_d, int64_t, DO_MIN)
+
+DO_ZZI(sve_umaxi_b, uint8_t, DO_MAX)
+DO_ZZI(sve_umaxi_h, uint16_t, DO_MAX)
+DO_ZZI(sve_umaxi_s, uint32_t, DO_MAX)
+DO_ZZI(sve_umaxi_d, uint64_t, DO_MAX)
+
+DO_ZZI(sve_umini_b, uint8_t, DO_MIN)
+DO_ZZI(sve_umini_h, uint16_t, DO_MIN)
+DO_ZZI(sve_umini_s, uint32_t, DO_MIN)
+DO_ZZI(sve_umini_d, uint64_t, DO_MIN)
+
+#undef DO_ZZI
+
 #undef DO_AND
 #undef DO_ORR
 #undef DO_EOR
@@ -818,6 +858,7 @@ DO_VPZ_D(sve_uminv_d, uint64_t, uint64_t, -1, DO_MIN)
 #undef DO_ASR
 #undef DO_LSR
 #undef DO_LSL
+#undef DO_SUBR
 
 /* Similar to the ARM LastActiveElement pseudocode function, except the
    result is multiplied by the element size.  This includes the not found
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index 13d5eff..afd0b16 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -77,6 +77,11 @@ static inline int expand_imm_sh8s(int x)
     return (int8_t)x << (x & 0x100 ? 8 : 0);
 }
 
+static inline int expand_imm_sh8u(int x)
+{
+    return (uint8_t)x << (x & 0x100 ? 8 : 0);
+}
+
 /*
  * Include the generated decoder.
  */
@@ -3228,6 +3233,145 @@ static bool trans_DUP_i(DisasContext *s, arg_DUP_i *a, uint32_t insn)
     return true;
 }
 
+static bool trans_ADD_zzi(DisasContext *s, arg_rri_esz *a, uint32_t insn)
+{
+    if (a->esz == 0 && extract32(insn, 13, 1)) {
+        return false;
+    }
+    if (sve_access_check(s)) {
+        unsigned vsz = vec_full_reg_size(s);
+        tcg_gen_gvec_addi(a->esz, vec_full_reg_offset(s, a->rd),
+                          vec_full_reg_offset(s, a->rn), a->imm, vsz, vsz);
+    }
+    return true;
+}
+
+static bool trans_SUB_zzi(DisasContext *s, arg_rri_esz *a, uint32_t insn)
+{
+    a->imm = -a->imm;
+    return trans_ADD_zzi(s, a, insn);
+}
+
+static bool trans_SUBR_zzi(DisasContext *s, arg_rri_esz *a, uint32_t insn)
+{
+    static const GVecGen2s op[4] = {
+        { .fni8 = tcg_gen_vec_sub8_i64,
+          .fniv = tcg_gen_sub_vec,
+          .fno = gen_helper_sve_subri_b,
+          .opc = INDEX_op_sub_vec,
+          .vece = MO_8,
+          .scalar_first = true },
+        { .fni8 = tcg_gen_vec_sub16_i64,
+          .fniv = tcg_gen_sub_vec,
+          .fno = gen_helper_sve_subri_h,
+          .opc = INDEX_op_sub_vec,
+          .vece = MO_16,
+          .scalar_first = true },
+        { .fni4 = tcg_gen_sub_i32,
+          .fniv = tcg_gen_sub_vec,
+          .fno = gen_helper_sve_subri_s,
+          .opc = INDEX_op_sub_vec,
+          .vece = MO_32,
+          .scalar_first = true },
+        { .fni8 = tcg_gen_sub_i64,
+          .fniv = tcg_gen_sub_vec,
+          .fno = gen_helper_sve_subri_d,
+          .opc = INDEX_op_sub_vec,
+          .prefer_i64 = TCG_TARGET_REG_BITS == 64,
+          .vece = MO_64,
+          .scalar_first = true }
+    };
+
+    if (a->esz == 0 && extract32(insn, 13, 1)) {
+        return false;
+    }
+    if (sve_access_check(s)) {
+        unsigned vsz = vec_full_reg_size(s);
+        TCGv_i64 c = tcg_const_i64(a->imm);
+        tcg_gen_gvec_2s(vec_full_reg_offset(s, a->rd),
+                        vec_full_reg_offset(s, a->rn),
+                        vsz, vsz, c, &op[a->esz]);
+        tcg_temp_free_i64(c);
+    }
+    return true;
+}
+
+static bool trans_MUL_zzi(DisasContext *s, arg_rri_esz *a, uint32_t insn)
+{
+    if (sve_access_check(s)) {
+        unsigned vsz = vec_full_reg_size(s);
+        tcg_gen_gvec_muli(a->esz, vec_full_reg_offset(s, a->rd),
+                          vec_full_reg_offset(s, a->rn), a->imm, vsz, vsz);
+    }
+    return true;
+}
+
+static bool do_zzi_sat(DisasContext *s, arg_rri_esz *a, uint32_t insn,
+                       bool u, bool d)
+{
+    if (a->esz == 0 && extract32(insn, 13, 1)) {
+        return false;
+    }
+    if (sve_access_check(s)) {
+        TCGv_i64 val = tcg_const_i64(a->imm);
+        do_sat_addsub_vec(s, a->esz, a->rd, a->rn, val, u, d);
+        tcg_temp_free_i64(val);
+    }
+    return true;
+}
+
+static bool trans_SQADD_zzi(DisasContext *s, arg_rri_esz *a, uint32_t insn)
+{
+    return do_zzi_sat(s, a, insn, false, false);
+}
+
+static bool trans_UQADD_zzi(DisasContext *s, arg_rri_esz *a, uint32_t insn)
+{
+    return do_zzi_sat(s, a, insn, true, false);
+}
+
+static bool trans_SQSUB_zzi(DisasContext *s, arg_rri_esz *a, uint32_t insn)
+{
+    return do_zzi_sat(s, a, insn, false, true);
+}
+
+static bool trans_UQSUB_zzi(DisasContext *s, arg_rri_esz *a, uint32_t insn)
+{
+    return do_zzi_sat(s, a, insn, true, true);
+}
+
+static bool do_zzi_ool(DisasContext *s, arg_rri_esz *a, gen_helper_gvec_2i *fn)
+{
+    if (sve_access_check(s)) {
+        unsigned vsz = vec_full_reg_size(s);
+        TCGv_i64 c = tcg_const_i64(a->imm);
+
+        tcg_gen_gvec_2i_ool(vec_full_reg_offset(s, a->rd),
+                            vec_full_reg_offset(s, a->rn),
+                            c, vsz, vsz, 0, fn);
+        tcg_temp_free_i64(c);
+    }
+    return true;
+}
+
+#define DO_ZZI(NAME, name) \
+static bool trans_##NAME##_zzi(DisasContext *s, arg_rri_esz *a,         \
+                               uint32_t insn)                           \
+{                                                                       \
+    static gen_helper_gvec_2i * const fns[4] = {                        \
+        gen_helper_sve_##name##i_b, gen_helper_sve_##name##i_h,         \
+        gen_helper_sve_##name##i_s, gen_helper_sve_##name##i_d,         \
+    };                                                                  \
+    return do_zzi_ool(s, a, fns[a->esz]);                               \
+}
+
+DO_ZZI(SMAX, smax)
+DO_ZZI(UMAX, umax)
+DO_ZZI(SMIN, smin)
+DO_ZZI(UMIN, umin)
+
+#undef DO_ZZI
+
 /*
  *** SVE Memory - 32-bit Gather and Unsized Contiguous Group
  */