diff options
Diffstat (limited to 'gcc/config/i386')
| -rw-r--r-- | gcc/config/i386/i386-options.cc | 4 | ||||
| -rw-r--r-- | gcc/config/i386/i386.cc | 18 | ||||
| -rw-r--r-- | gcc/config/i386/i386.h | 10 | ||||
| -rw-r--r-- | gcc/config/i386/x86-tune-costs.h | 2 | ||||
| -rw-r--r-- | gcc/config/i386/x86-tune-sched.cc | 15 |
5 files changed, 32 insertions, 17 deletions
diff --git a/gcc/config/i386/i386-options.cc b/gcc/config/i386/i386-options.cc index a9fac01..964449f 100644 --- a/gcc/config/i386/i386-options.cc +++ b/gcc/config/i386/i386-options.cc @@ -2828,8 +2828,8 @@ ix86_option_override_internal (bool main_args_p, if (flag_nop_mcount) error ("%<-mnop-mcount%> is not compatible with this target"); #endif - if (flag_nop_mcount && flag_pic) - error ("%<-mnop-mcount%> is not implemented for %<-fPIC%>"); + if (flag_nop_mcount && flag_pic && !flag_plt) + error ("%<-mnop-mcount%> is not implemented for %<-fno-plt%>"); /* Accept -msseregparm only if at least SSE support is enabled. */ if (TARGET_SSEREGPARM_P (opts->x_target_flags) diff --git a/gcc/config/i386/i386.cc b/gcc/config/i386/i386.cc index 4f8380c4..38df84f 100644 --- a/gcc/config/i386/i386.cc +++ b/gcc/config/i386/i386.cc @@ -458,6 +458,9 @@ int ix86_arch_specified; indirect thunk pushes the return address onto stack, destroying red-zone. + NB: Don't use red-zone for functions with no_caller_saved_registers + and 32 GPRs since 128-byte red-zone is too small for 31 GPRs. + TODO: If we can reserve the first 2 WORDs, for PUSH and, another for CALL, in red-zone, we can allow local indirect jumps with indirect thunk. */ @@ -467,6 +470,9 @@ ix86_using_red_zone (void) { return (TARGET_RED_ZONE && !TARGET_64BIT_MS_ABI + && (!TARGET_APX_EGPR + || (cfun->machine->call_saved_registers + != TYPE_NO_CALLER_SAVED_REGISTERS)) && (!cfun->machine->has_local_indirect_jump || cfun->machine->indirect_branch_type == indirect_branch_keep)); } @@ -23158,6 +23164,12 @@ x86_print_call_or_nop (FILE *file, const char *target) if (flag_nop_mcount || !strcmp (target, "nop")) /* 5 byte nop: nopl 0(%[re]ax,%[re]ax,1) */ fprintf (file, "1:" ASM_BYTE "0x0f, 0x1f, 0x44, 0x00, 0x00\n"); + else if (!TARGET_PECOFF && flag_pic) + { + gcc_assert (flag_plt); + + fprintf (file, "1:\tcall\t%s@PLT\n", target); + } else fprintf (file, "1:\tcall\t%s\n", target); } @@ -23321,7 +23333,7 @@ x86_function_profiler (FILE *file, int labelno ATTRIBUTE_UNUSED) break; case CM_SMALL_PIC: case CM_MEDIUM_PIC: - if (!ix86_direct_extern_access) + if (!flag_plt) { if (ASSEMBLER_DIALECT == ASM_INTEL) fprintf (file, "1:\tcall\t[QWORD PTR %s@GOTPCREL[rip]]\n", @@ -23352,7 +23364,9 @@ x86_function_profiler (FILE *file, int labelno ATTRIBUTE_UNUSED) "\tleal\t%sP%d@GOTOFF(%%ebx), %%" PROFILE_COUNT_REGISTER "\n", LPREFIX, labelno); #endif - if (ASSEMBLER_DIALECT == ASM_INTEL) + if (flag_plt) + x86_print_call_or_nop (file, mcount_name); + else if (ASSEMBLER_DIALECT == ASM_INTEL) fprintf (file, "1:\tcall\t[DWORD PTR %s@GOT[ebx]]\n", mcount_name); else fprintf (file, "1:\tcall\t*%s@GOT(%%ebx)\n", mcount_name); diff --git a/gcc/config/i386/i386.h b/gcc/config/i386/i386.h index 13da3d8..8507243 100644 --- a/gcc/config/i386/i386.h +++ b/gcc/config/i386/i386.h @@ -2449,11 +2449,11 @@ constexpr wide_int_bitmask PTA_DIAMONDRAPIDS = PTA_SKYLAKE | PTA_PKU | PTA_SHA | PTA_WBNOINVD | PTA_CLWB | PTA_MOVDIRI | PTA_MOVDIR64B | PTA_ENQCMD | PTA_CLDEMOTE | PTA_PTWRITE | PTA_WAITPKG | PTA_SERIALIZE | PTA_TSXLDTRK | PTA_AMX_TILE | PTA_AMX_INT8 | PTA_AMX_BF16 | PTA_UINTR | PTA_AVXVNNI - | PTA_AMX_FP16 | PTA_PREFETCHI | PTA_AMX_COMPLEX | PTA_AVX10_1 - | PTA_AVXIFMA | PTA_AVXNECONVERT | PTA_AVXVNNIINT16 | PTA_AVXVNNIINT8 - | PTA_CMPCCXADD | PTA_SHA512 | PTA_SM3 | PTA_SM4 | PTA_AVX10_2 - | PTA_APX_F | PTA_AMX_AVX512 | PTA_AMX_FP8 | PTA_AMX_TF32 | PTA_AMX_TRANSPOSE - | PTA_MOVRS | PTA_AMX_MOVRS | PTA_USER_MSR; + | PTA_AMX_FP16 | PTA_PREFETCHI | PTA_AMX_COMPLEX | PTA_AVX10_1_256 + | PTA_AVX10_1 | PTA_AVXIFMA | PTA_AVXNECONVERT | PTA_AVXVNNIINT16 + | PTA_AVXVNNIINT8 | PTA_CMPCCXADD | PTA_SHA512 | PTA_SM3 | PTA_SM4 + | PTA_AVX10_2 | PTA_APX_F | PTA_AMX_AVX512 | PTA_AMX_FP8 | PTA_AMX_TF32 + | PTA_AMX_TRANSPOSE | PTA_MOVRS | PTA_AMX_MOVRS | PTA_USER_MSR; constexpr wide_int_bitmask PTA_BDVER1 = PTA_64BIT | PTA_MMX | PTA_SSE | PTA_SSE2 | PTA_SSE3 | PTA_SSE4A | PTA_CX16 | PTA_ABM | PTA_SSSE3 diff --git a/gcc/config/i386/x86-tune-costs.h b/gcc/config/i386/x86-tune-costs.h index 7c8cb73..9477345 100644 --- a/gcc/config/i386/x86-tune-costs.h +++ b/gcc/config/i386/x86-tune-costs.h @@ -2120,7 +2120,7 @@ struct processor_costs znver5_cost = { COSTS_N_INSNS (1), /* cost of cheap SSE instruction. */ /* ADDSS has throughput 2 and latency 2 (in some cases when source is another addition). */ - COSTS_N_INSNS (2), /* cost of ADDSS/SD SUBSS/SD insns. */ + COSTS_N_INSNS (3), /* cost of ADDSS/SD SUBSS/SD insns. */ /* MULSS has throughput 2 and latency 3. */ COSTS_N_INSNS (3), /* cost of MULSS instruction. */ COSTS_N_INSNS (3), /* cost of MULSD instruction. */ diff --git a/gcc/config/i386/x86-tune-sched.cc b/gcc/config/i386/x86-tune-sched.cc index 685a83c..15d3d91 100644 --- a/gcc/config/i386/x86-tune-sched.cc +++ b/gcc/config/i386/x86-tune-sched.cc @@ -81,6 +81,14 @@ ix86_issue_rate (void) case PROCESSOR_YONGFENG: case PROCESSOR_SHIJIDADAO: case PROCESSOR_GENERIC: + /* For znver5 decoder can handle 4 or 8 instructions per cycle, + op cache 12 instruction/cycle, dispatch 8 instructions + integer rename 8 instructions and Fp 6 instructions. + + The scheduler, without understanding out of order nature of the CPU + is not going to be able to use more than 4 instructions since that + is limits of the decoders. */ + case PROCESSOR_ZNVER5: return 4; case PROCESSOR_ICELAKE_CLIENT: @@ -91,13 +99,6 @@ ix86_issue_rate (void) return 5; case PROCESSOR_SAPPHIRERAPIDS: - /* For znver5 decoder can handle 4 or 8 instructions per cycle, - op cache 12 instruction/cycle, dispatch 8 instructions - integer rename 8 instructions and Fp 6 instructions. - - The scheduler, without understanding out of order nature of the CPU - is unlikely going to be able to fill all of these. */ - case PROCESSOR_ZNVER5: return 6; default: |