From 94c0b26f454da642a76c1a7ebbf1475324671bb4 Mon Sep 17 00:00:00 2001 From: Mayshao Date: Mon, 30 Oct 2023 22:19:12 +0100 Subject: [PATCH] i386: Zhaoxin yongfeng enablement Enable -march/-mtune=yongfeng. Costs and tunings are set according to the characteristics of the processor. Add a new .md file to describe yongfeng processor. gcc/ChangeLog: * common/config/i386/cpuinfo.h (get_zhaoxin_cpu): Recognize yongfeng. * common/config/i386/i386-common.cc: Add yongfeng. * common/config/i386/i386-cpuinfo.h (enum processor_subtypes): Add ZHAOXIN_FAM7H_YONGFENG. * config.gcc: Add yongfeng. * config/i386/driver-i386.cc (host_detect_local_cpu): Let -march=native recognize yongfeng processors. * config/i386/i386-c.cc (ix86_target_macros_internal): Add yongfeng. * config/i386/i386-options.cc (m_YONGFENG): New definition. (m_ZHAOXIN): Ditto. * config/i386/i386.h (enum processor_type): Add PROCESSOR_YONGFENG. * config/i386/i386.md: Add yongfeng. * config/i386/lujiazui.md: Fix typo. * config/i386/x86-tune-costs.h (struct processor_costs): Add yongfeng costs. * config/i386/x86-tune-sched.cc (ix86_issue_rate): Add yongfeng. (ix86_adjust_cost): Ditto. * config/i386/x86-tune.def (X86_TUNE_SCHEDULE): Replace m_LUJIAZUI with m_ZHAOXIN. (X86_TUNE_PARTIAL_REG_DEPENDENCY): Ditto. (X86_TUNE_SSE_PARTIAL_REG_DEPENDENCY): Ditto. (X86_TUNE_SSE_PARTIAL_REG_FP_CONVERTS_DEPENDENCY): Ditto. (X86_TUNE_SSE_PARTIAL_REG_CONVERTS_DEPENDENCY): Ditto. (X86_TUNE_MOVX): Ditto. (X86_TUNE_MEMORY_MISMATCH_STALL): Ditto. (X86_TUNE_FUSE_CMP_AND_BRANCH_32): Ditto. (X86_TUNE_FUSE_CMP_AND_BRANCH_64): Ditto. (X86_TUNE_FUSE_CMP_AND_BRANCH_SOFLAGS): Ditto. (X86_TUNE_FUSE_ALU_AND_BRANCH): Ditto. (X86_TUNE_ACCUMULATE_OUTGOING_ARGS): Ditto. (X86_TUNE_USE_LEAVE): Ditto. (X86_TUNE_PUSH_MEMORY): Ditto. (X86_TUNE_LCP_STALL): Ditto. (X86_TUNE_INTEGER_DFMODE_MOVES): Ditto. (X86_TUNE_OPT_AGU): Ditto. (X86_TUNE_PREFER_KNOWN_REP_MOVSB_STOSB): Ditto. (X86_TUNE_MISALIGNED_MOVE_STRING_PRO_EPILOGUES): Ditto. (X86_TUNE_USE_SAHF): Ditto. (X86_TUNE_USE_BT): Ditto. (X86_TUNE_AVOID_FALSE_DEP_FOR_BMI): Ditto. (X86_TUNE_ONE_IF_CONV_INSN): Ditto. (X86_TUNE_AVOID_MFENCE): Ditto. (X86_TUNE_EXPAND_ABS): Ditto. (X86_TUNE_USE_SIMODE_FIOP): Ditto. (X86_TUNE_USE_FFREEP): Ditto. (X86_TUNE_EXT_80387_CONSTANTS): Ditto. (X86_TUNE_SSE_UNALIGNED_LOAD_OPTIMAL): Ditto. (X86_TUNE_SSE_UNALIGNED_STORE_OPTIMAL): Ditto. (X86_TUNE_SSE_TYPELESS_STORES): Ditto. (X86_TUNE_SSE_LOAD0_BY_PXOR): Ditto. (X86_TUNE_USE_GATHER_2PARTS): Add m_YONGFENG. (X86_TUNE_USE_GATHER_4PARTS): Ditto. (X86_TUNE_USE_GATHER_8PARTS): Ditto. (X86_TUNE_AVOID_128FMA_CHAINS): Ditto. * doc/extend.texi: Add details about yongfeng. * doc/invoke.texi: Ditto. * config/i386/yongfeng.md: New file to describe yongfeng processor. gcc/testsuite/ChangeLog: * g++.target/i386/mv32.C: Handle new -march. * gcc.target/i386/funcspec-56.inc: Ditto. --- gcc/common/config/i386/cpuinfo.h | 6 + gcc/common/config/i386/i386-common.cc | 10 +- gcc/common/config/i386/i386-cpuinfo.h | 1 + gcc/config.gcc | 12 +- gcc/config/i386/driver-i386.cc | 5 + gcc/config/i386/i386-c.cc | 7 + gcc/config/i386/i386-options.cc | 3 + gcc/config/i386/i386.h | 9 + gcc/config/i386/i386.md | 3 +- gcc/config/i386/lujiazui.md | 2 +- gcc/config/i386/x86-tune-costs.h | 116 +++ gcc/config/i386/x86-tune-sched.cc | 27 +- gcc/config/i386/x86-tune.def | 75 +- gcc/config/i386/yongfeng.md | 848 ++++++++++++++++++ gcc/doc/extend.texi | 3 + gcc/doc/invoke.texi | 6 + gcc/testsuite/g++.target/i386/mv32.C | 5 + gcc/testsuite/gcc.target/i386/funcspec-56.inc | 6 +- 18 files changed, 1095 insertions(+), 49 deletions(-) create mode 100644 gcc/config/i386/yongfeng.md diff --git a/gcc/common/config/i386/cpuinfo.h b/gcc/common/config/i386/cpuinfo.h index f7218887c0ff2..7d25479eb892b 100644 --- a/gcc/common/config/i386/cpuinfo.h +++ b/gcc/common/config/i386/cpuinfo.h @@ -663,6 +663,12 @@ get_zhaoxin_cpu (struct __processor_model *cpu_model, reset_cpu_feature (cpu_model, cpu_features2, FEATURE_F16C); cpu_model->__cpu_subtype = ZHAOXIN_FAM7H_LUJIAZUI; } + else if (model >= 0x5b) + { + cpu = "yongfeng"; + CHECK___builtin_cpu_is ("yongfeng"); + cpu_model->__cpu_subtype = ZHAOXIN_FAM7H_YONGFENG; + } break; default: break; diff --git a/gcc/common/config/i386/i386-common.cc b/gcc/common/config/i386/i386-common.cc index 79b1b35ad6c86..1b09499cd267c 100644 --- a/gcc/common/config/i386/i386-common.cc +++ b/gcc/common/config/i386/i386-common.cc @@ -2098,6 +2098,7 @@ const char *const processor_names[] = "pantherlake", "intel", "lujiazui", + "yongfeng", "geode", "k6", "athlon", @@ -2305,12 +2306,11 @@ const pta processor_alias_table[] = PTA_64BIT | PTA_MMX | PTA_SSE | PTA_SSE2 | PTA_SSE3 | PTA_SSSE3 | PTA_SSE4_1 | PTA_FXSR, 0, P_NONE}, {"lujiazui", PROCESSOR_LUJIAZUI, CPU_LUJIAZUI, - PTA_64BIT | PTA_MMX | PTA_SSE | PTA_SSE2 | PTA_SSE3 - | PTA_CX16 | PTA_ABM | PTA_SSSE3 | PTA_SSE4_1 - | PTA_SSE4_2 | PTA_AES | PTA_PCLMUL | PTA_BMI | PTA_BMI2 - | PTA_PRFCHW | PTA_FXSR | PTA_XSAVE | PTA_XSAVEOPT | PTA_FSGSBASE - | PTA_RDRND | PTA_MOVBE | PTA_ADX | PTA_RDSEED | PTA_POPCNT, + PTA_LUJIAZUI, M_CPU_SUBTYPE (ZHAOXIN_FAM7H_LUJIAZUI), P_NONE}, + {"yongfeng", PROCESSOR_YONGFENG, CPU_YONGFENG, + PTA_YONGFENG, + M_CPU_SUBTYPE (ZHAOXIN_FAM7H_YONGFENG), P_NONE}, {"k8", PROCESSOR_K8, CPU_K8, PTA_64BIT | PTA_MMX | PTA_3DNOW | PTA_3DNOW_A | PTA_SSE | PTA_SSE2 | PTA_NO_SAHF | PTA_FXSR, 0, P_NONE}, diff --git a/gcc/common/config/i386/i386-cpuinfo.h b/gcc/common/config/i386/i386-cpuinfo.h index 533b7481c161a..a0552ef99a2ab 100644 --- a/gcc/common/config/i386/i386-cpuinfo.h +++ b/gcc/common/config/i386/i386-cpuinfo.h @@ -103,6 +103,7 @@ enum processor_subtypes INTEL_COREI7_ARROWLAKE, INTEL_COREI7_ARROWLAKE_S, INTEL_COREI7_PANTHERLAKE, + ZHAOXIN_FAM7H_YONGFENG, CPU_SUBTYPE_MAX }; diff --git a/gcc/config.gcc b/gcc/config.gcc index d34ea246a980b..ba6d63e33ac66 100644 --- a/gcc/config.gcc +++ b/gcc/config.gcc @@ -706,7 +706,7 @@ slm nehalem westmere sandybridge ivybridge haswell broadwell bonnell \ silvermont knl knm skylake-avx512 cannonlake icelake-client icelake-server \ skylake goldmont goldmont-plus tremont cascadelake tigerlake cooperlake \ sapphirerapids alderlake rocketlake eden-x2 nano nano-1000 nano-2000 nano-3000 \ -nano-x2 eden-x4 nano-x4 lujiazui x86-64 x86-64-v2 x86-64-v3 x86-64-v4 \ +nano-x2 eden-x4 nano-x4 lujiazui yongfeng x86-64 x86-64-v2 x86-64-v3 x86-64-v4 \ sierraforest graniterapids graniterapids-d grandridge arrowlake arrowlake-s \ clearwaterforest pantherlake native" @@ -3811,6 +3811,10 @@ case ${target} in arch=lujiazui cpu=lujiazui ;; + yongfeng-*) + arch=yongfeng + cpu=yongfeng + ;; pentium2-*) arch=pentium2 cpu=pentium2 @@ -3924,10 +3928,14 @@ case ${target} in arch=k8 cpu=k8 ;; - lujiazui-*) + lujiazui-*) arch=lujiazui cpu=lujiazui ;; + yongfeng-*) + arch=yongfeng + cpu=yongfeng + ;; nocona-*) arch=nocona cpu=nocona diff --git a/gcc/config/i386/driver-i386.cc b/gcc/config/i386/driver-i386.cc index a9e54ef82b5b8..55d40450c6d42 100644 --- a/gcc/config/i386/driver-i386.cc +++ b/gcc/config/i386/driver-i386.cc @@ -530,6 +530,8 @@ const char *host_detect_local_cpu (int argc, const char **argv) case 7: if (model == 0x3b) processor = PROCESSOR_LUJIAZUI; + else if (model >= 0x5b) + processor = PROCESSOR_YONGFENG; break; default: break; @@ -817,6 +819,9 @@ const char *host_detect_local_cpu (int argc, const char **argv) case PROCESSOR_LUJIAZUI: cpu = "lujiazui"; break; + case PROCESSOR_YONGFENG: + cpu = "yongfeng"; + break; default: /* Use something reasonable. */ diff --git a/gcc/config/i386/i386-c.cc b/gcc/config/i386/i386-c.cc index ebe6a63ed41c1..be1d06b2e7996 100644 --- a/gcc/config/i386/i386-c.cc +++ b/gcc/config/i386/i386-c.cc @@ -148,6 +148,10 @@ ix86_target_macros_internal (HOST_WIDE_INT isa_flag, def_or_undef (parse_in, "__lujiazui"); def_or_undef (parse_in, "__lujiazui__"); break; + case PROCESSOR_YONGFENG: + def_or_undef (parse_in, "__yongfeng"); + def_or_undef (parse_in, "__yongfeng__"); + break; case PROCESSOR_PENTIUM4: def_or_undef (parse_in, "__pentium4"); def_or_undef (parse_in, "__pentium4__"); @@ -379,6 +383,9 @@ ix86_target_macros_internal (HOST_WIDE_INT isa_flag, case PROCESSOR_LUJIAZUI: def_or_undef (parse_in, "__tune_lujiazui__"); break; + case PROCESSOR_YONGFENG: + def_or_undef (parse_in, "__tune_yongfeng__"); + break; case PROCESSOR_PENTIUM4: def_or_undef (parse_in, "__tune_pentium4__"); break; diff --git a/gcc/config/i386/i386-options.cc b/gcc/config/i386/i386-options.cc index 072bbc628e244..df7d24352d14c 100644 --- a/gcc/config/i386/i386-options.cc +++ b/gcc/config/i386/i386-options.cc @@ -154,6 +154,8 @@ along with GCC; see the file COPYING3. If not see | m_TIGERLAKE | m_COOPERLAKE | m_ROCKETLAKE) #define m_LUJIAZUI (HOST_WIDE_INT_1U<integer move cost is 2. */ + 8, /* cost for loading QImode using movzbl. */ + {8, 8, 8}, /* cost of loading integer registers + in QImode, HImode and SImode. + Relative to reg-reg move (2). */ + {8, 8, 8}, /* cost of storing integer registers. */ + 2, /* cost of reg,reg fld/fst. */ + {8, 8, 8}, /* cost of loading fp registers + in SFmode, DFmode and XFmode. */ + {8, 8, 8}, /* cost of storing fp registers + in SFmode, DFmode and XFmode. */ + 2, /* cost of moving MMX register. */ + {8, 8}, /* cost of loading MMX registers + in SImode and DImode. */ + {8, 8}, /* cost of storing MMX registers + in SImode and DImode. */ + 2, 3, 4, /* cost of moving XMM,YMM,ZMM register. */ + {8, 8, 8, 10, 15}, /* cost of loading SSE registers + in 32,64,128,256 and 512-bit. */ + {8, 8, 8, 10, 15}, /* cost of storing SSE registers + in 32,64,128,256 and 512-bit. */ + 8, 8, /* SSE->integer and integer->SSE moves. */ + 8, 8, /* mask->integer and integer->mask moves. */ + {8, 8, 8}, /* cost of loading mask register + in QImode, HImode, SImode. */ + {8, 8, 8}, /* cost if storing mask register + in QImode, HImode, SImode. */ + 2, /* cost of moving mask register. */ + /* End of register allocator costs. */ + }, + + COSTS_N_INSNS (1), /* cost of an add instruction. */ + COSTS_N_INSNS (1), /* cost of a lea instruction. */ + COSTS_N_INSNS (1), /* variable shift costs. */ + COSTS_N_INSNS (1), /* constant shift costs. */ + {COSTS_N_INSNS (2), /* cost of starting multiply for QI. */ + COSTS_N_INSNS (3), /* HI. */ + COSTS_N_INSNS (2), /* SI. */ + COSTS_N_INSNS (2), /* DI. */ + COSTS_N_INSNS (3)}, /* other. */ + 0, /* cost of multiply per each bit set. */ + {COSTS_N_INSNS (8), /* cost of a divide/mod for QI. */ + COSTS_N_INSNS (9), /* HI. */ + COSTS_N_INSNS (8), /* SI. */ + COSTS_N_INSNS (41), /* DI. */ + COSTS_N_INSNS (41)}, /* other. */ + COSTS_N_INSNS (1), /* cost of movsx. */ + COSTS_N_INSNS (1), /* cost of movzx. */ + 8, /* "large" insn. */ + 17, /* MOVE_RATIO. */ + 6, /* CLEAR_RATIO. */ + {8, 8, 8}, /* cost of loading integer registers + in QImode, HImode and SImode. + Relative to reg-reg move (2). */ + {8, 8, 8}, /* cost of storing integer registers. */ + {8, 8, 8, 12, 15}, /* cost of loading SSE register + in 32bit, 64bit, 128bit, 256bit and 512bit. */ + {8, 8, 8, 12, 15}, /* cost of storing SSE register + in 32bit, 64bit, 128bit, 256bit and 512bit. */ + {8, 8, 8, 12, 15}, /* cost of unaligned loads. */ + {8, 8, 8, 12, 15}, /* cost of unaligned storess. */ + 2, 3, 4, /* cost of moving XMM,YMM,ZMM register. */ + 8, /* cost of moving SSE register to integer. */ + 18, 6, /* Gather load static, per_elt. */ + 18, 6, /* Gather store static, per_elt. */ + 32, /* size of l1 cache. */ + 256, /* size of l2 cache. */ + 64, /* size of prefetch block. */ + 12, /* number of parallel prefetches. */ + 3, /* Branch cost. */ + COSTS_N_INSNS (3), /* cost of FADD and FSUB insns. */ + COSTS_N_INSNS (3), /* cost of FMUL instruction. */ + COSTS_N_INSNS (14), /* cost of FDIV instruction. */ + COSTS_N_INSNS (1), /* cost of FABS instruction. */ + COSTS_N_INSNS (1), /* cost of FCHS instruction. */ + COSTS_N_INSNS (40), /* cost of FSQRT instruction. */ + + COSTS_N_INSNS (1), /* cost of cheap SSE instruction. */ + COSTS_N_INSNS (3), /* cost of ADDSS/SD SUBSS/SD insns. */ + COSTS_N_INSNS (3), /* cost of MULSS instruction. */ + COSTS_N_INSNS (3), /* cost of MULSD instruction. */ + COSTS_N_INSNS (5), /* cost of FMA SS instruction. */ + COSTS_N_INSNS (5), /* cost of FMA SD instruction. */ + COSTS_N_INSNS (10), /* cost of DIVSS instruction. */ + COSTS_N_INSNS (14), /* cost of DIVSD instruction. */ + COSTS_N_INSNS (20), /* cost of SQRTSS instruction. */ + COSTS_N_INSNS (35), /* cost of SQRTSD instruction. */ + 4, 4, 4, 4, /* reassoc int, fp, vec_int, vec_fp. */ + yongfeng_memcpy, + yongfeng_memset, + COSTS_N_INSNS (3), /* cond_taken_branch_cost. */ + COSTS_N_INSNS (1), /* cond_not_taken_branch_cost. */ + "16:11:8", /* Loop alignment. */ + "16:11:8", /* Jump alignment. */ + "0:0:8", /* Label alignment. */ + "16", /* Func alignment. */ + 4, /* Small unroll limit. */ + 2, /* Small unroll factor. */ +}; + + /* Generic should produce code tuned for Core-i7 (and newer chips) and btver1 (and newer chips). */ diff --git a/gcc/config/i386/x86-tune-sched.cc b/gcc/config/i386/x86-tune-sched.cc index df4113d4eabc6..4f4bf5b3d17f7 100644 --- a/gcc/config/i386/x86-tune-sched.cc +++ b/gcc/config/i386/x86-tune-sched.cc @@ -79,6 +79,7 @@ ix86_issue_rate (void) case PROCESSOR_CASCADELAKE: case PROCESSOR_CANNONLAKE: case PROCESSOR_ALDERLAKE: + case PROCESSOR_YONGFENG: case PROCESSOR_GENERIC: return 4; @@ -384,7 +385,6 @@ ix86_adjust_cost (rtx_insn *insn, int dep_type, rtx_insn *dep_insn, int cost, case PROCESSOR_ATHLON: case PROCESSOR_K8: - case PROCESSOR_LUJIAZUI: memory = get_attr_memory (insn); /* Show ability of reorder buffer to hide latency of load by executing @@ -445,6 +445,31 @@ ix86_adjust_cost (rtx_insn *insn, int dep_type, rtx_insn *dep_insn, int cost, } break; + case PROCESSOR_YONGFENG: + /* Stack engine allows to execute push&pop instructions in parallel. */ + if ((insn_type == TYPE_PUSH || insn_type == TYPE_POP) + && (dep_insn_type == TYPE_PUSH || dep_insn_type == TYPE_POP)) + return 0; + /* FALLTHRU */ + + case PROCESSOR_LUJIAZUI: + memory = get_attr_memory (insn); + + /* Show ability of reorder buffer to hide latency of load by executing + in parallel with previous instruction in case + previous instruction is not needed to compute the address. */ + if ((memory == MEMORY_LOAD || memory == MEMORY_BOTH) + && !ix86_agi_dependent (dep_insn, insn)) + { + int loadcost = 4; + + if (cost >= loadcost) + cost -= loadcost; + else + cost = 0; + } + break; + case PROCESSOR_CORE2: case PROCESSOR_NEHALEM: case PROCESSOR_SANDYBRIDGE: diff --git a/gcc/config/i386/x86-tune.def b/gcc/config/i386/x86-tune.def index 94630fd35a7cd..43fa9e8fd6d2c 100644 --- a/gcc/config/i386/x86-tune.def +++ b/gcc/config/i386/x86-tune.def @@ -41,7 +41,7 @@ see the files COPYING3 and COPYING.RUNTIME respectively. If not, see /* X86_TUNE_SCHEDULE: Enable scheduling. */ DEF_TUNE (X86_TUNE_SCHEDULE, "schedule", m_PENT | m_LAKEMONT | m_PPRO | m_CORE_ALL | m_BONNELL | m_SILVERMONT - | m_INTEL | m_KNL | m_KNM | m_K6_GEODE | m_AMD_MULTIPLE | m_LUJIAZUI + | m_INTEL | m_KNL | m_KNM | m_K6_GEODE | m_AMD_MULTIPLE | m_ZHAOXIN | m_GOLDMONT | m_GOLDMONT_PLUS | m_TREMONT | m_CORE_HYBRID | m_CORE_ATOM | m_GENERIC) @@ -52,7 +52,7 @@ DEF_TUNE (X86_TUNE_SCHEDULE, "schedule", DEF_TUNE (X86_TUNE_PARTIAL_REG_DEPENDENCY, "partial_reg_dependency", m_P4_NOCONA | m_CORE2 | m_NEHALEM | m_SANDYBRIDGE | m_CORE_AVX2 | m_BONNELL | m_SILVERMONT | m_GOLDMONT | m_GOLDMONT_PLUS | m_INTEL - | m_KNL | m_KNM | m_AMD_MULTIPLE | m_LUJIAZUI | m_TREMONT + | m_KNL | m_KNM | m_AMD_MULTIPLE | m_ZHAOXIN | m_TREMONT | m_CORE_HYBRID | m_CORE_ATOM | m_GENERIC) /* X86_TUNE_SSE_PARTIAL_REG_DEPENDENCY: This knob promotes all store @@ -63,7 +63,7 @@ DEF_TUNE (X86_TUNE_PARTIAL_REG_DEPENDENCY, "partial_reg_dependency", that can be partly masked by careful scheduling of moves. */ DEF_TUNE (X86_TUNE_SSE_PARTIAL_REG_DEPENDENCY, "sse_partial_reg_dependency", m_PPRO | m_P4_NOCONA | m_CORE_ALL | m_BONNELL | m_AMDFAM10 - | m_BDVER | m_ZNVER | m_LUJIAZUI | m_TREMONT | m_CORE_HYBRID + | m_BDVER | m_ZNVER | m_ZHAOXIN | m_TREMONT | m_CORE_HYBRID | m_CORE_ATOM | m_GENERIC) /* X86_TUNE_SSE_PARTIAL_REG_FP_CONVERTS_DEPENDENCY: This knob avoids @@ -72,7 +72,7 @@ DEF_TUNE (X86_TUNE_SSE_PARTIAL_REG_DEPENDENCY, "sse_partial_reg_dependency", DEF_TUNE (X86_TUNE_SSE_PARTIAL_REG_FP_CONVERTS_DEPENDENCY, "sse_partial_reg_fp_converts_dependency", m_PPRO | m_P4_NOCONA | m_CORE_ALL | m_BONNELL | m_AMDFAM10 - | m_BDVER | m_ZNVER | m_LUJIAZUI | m_CORE_HYBRID | m_CORE_ATOM + | m_BDVER | m_ZNVER | m_ZHAOXIN | m_CORE_HYBRID | m_CORE_ATOM | m_GENERIC) /* X86_TUNE_SSE_PARTIAL_REG_CONVERTS_DEPENDENCY: This knob avoids partial @@ -80,7 +80,7 @@ DEF_TUNE (X86_TUNE_SSE_PARTIAL_REG_FP_CONVERTS_DEPENDENCY, DEF_TUNE (X86_TUNE_SSE_PARTIAL_REG_CONVERTS_DEPENDENCY, "sse_partial_reg_converts_dependency", m_PPRO | m_P4_NOCONA | m_CORE_ALL | m_BONNELL | m_AMDFAM10 - | m_BDVER | m_ZNVER | m_LUJIAZUI | m_CORE_HYBRID | m_CORE_ATOM + | m_BDVER | m_ZNVER | m_ZHAOXIN | m_CORE_HYBRID | m_CORE_ATOM | m_GENERIC) /* X86_TUNE_DEST_FALSE_DEP_FOR_GLC: This knob inserts zero-idiom before @@ -113,7 +113,7 @@ DEF_TUNE (X86_TUNE_PARTIAL_FLAG_REG_STALL, "partial_flag_reg_stall", DEF_TUNE (X86_TUNE_MOVX, "movx", m_PPRO | m_P4_NOCONA | m_CORE2 | m_NEHALEM | m_SANDYBRIDGE | m_BONNELL | m_SILVERMONT | m_GOLDMONT | m_KNL | m_KNM | m_INTEL - | m_GOLDMONT_PLUS | m_GEODE | m_AMD_MULTIPLE | m_LUJIAZUI + | m_GOLDMONT_PLUS | m_GEODE | m_AMD_MULTIPLE | m_ZHAOXIN | m_CORE_AVX2 | m_TREMONT | m_CORE_HYBRID | m_CORE_ATOM | m_GENERIC) /* X86_TUNE_MEMORY_MISMATCH_STALL: Avoid partial stores that are followed by @@ -121,31 +121,31 @@ DEF_TUNE (X86_TUNE_MOVX, "movx", DEF_TUNE (X86_TUNE_MEMORY_MISMATCH_STALL, "memory_mismatch_stall", m_P4_NOCONA | m_CORE_ALL | m_BONNELL | m_SILVERMONT | m_INTEL | m_KNL | m_KNM | m_GOLDMONT | m_GOLDMONT_PLUS | m_AMD_MULTIPLE - | m_LUJIAZUI | m_TREMONT | m_CORE_HYBRID | m_CORE_ATOM | m_GENERIC) + | m_ZHAOXIN | m_TREMONT | m_CORE_HYBRID | m_CORE_ATOM | m_GENERIC) /* X86_TUNE_FUSE_CMP_AND_BRANCH_32: Fuse compare with a subsequent conditional jump instruction for 32 bit TARGET. */ DEF_TUNE (X86_TUNE_FUSE_CMP_AND_BRANCH_32, "fuse_cmp_and_branch_32", - m_CORE_ALL | m_BDVER | m_ZNVER | m_LUJIAZUI | m_GENERIC) + m_CORE_ALL | m_BDVER | m_ZNVER | m_ZHAOXIN | m_GENERIC) /* X86_TUNE_FUSE_CMP_AND_BRANCH_64: Fuse compare with a subsequent conditional jump instruction for TARGET_64BIT. */ DEF_TUNE (X86_TUNE_FUSE_CMP_AND_BRANCH_64, "fuse_cmp_and_branch_64", m_NEHALEM | m_SANDYBRIDGE | m_CORE_AVX2 | m_BDVER - | m_ZNVER | m_LUJIAZUI | m_GENERIC) + | m_ZNVER | m_ZHAOXIN | m_GENERIC) /* X86_TUNE_FUSE_CMP_AND_BRANCH_SOFLAGS: Fuse compare with a subsequent conditional jump instruction when the condition jump check sign flag (SF) or overflow flag (OF). */ DEF_TUNE (X86_TUNE_FUSE_CMP_AND_BRANCH_SOFLAGS, "fuse_cmp_and_branch_soflags", m_NEHALEM | m_SANDYBRIDGE | m_CORE_AVX2 | m_BDVER - | m_ZNVER | m_LUJIAZUI | m_GENERIC) + | m_ZNVER | m_ZHAOXIN | m_GENERIC) /* X86_TUNE_FUSE_ALU_AND_BRANCH: Fuse alu with a subsequent conditional jump instruction when the alu instruction produces the CCFLAG consumed by the conditional jump instruction. */ DEF_TUNE (X86_TUNE_FUSE_ALU_AND_BRANCH, "fuse_alu_and_branch", - m_SANDYBRIDGE | m_CORE_AVX2 | m_LUJIAZUI | m_GENERIC) + m_SANDYBRIDGE | m_CORE_AVX2 | m_ZHAOXIN | m_GENERIC) /*****************************************************************************/ @@ -162,7 +162,7 @@ DEF_TUNE (X86_TUNE_FUSE_ALU_AND_BRANCH, "fuse_alu_and_branch", DEF_TUNE (X86_TUNE_ACCUMULATE_OUTGOING_ARGS, "accumulate_outgoing_args", m_PPRO | m_P4_NOCONA | m_BONNELL | m_SILVERMONT | m_KNL | m_KNM | m_INTEL - | m_GOLDMONT | m_GOLDMONT_PLUS | m_ATHLON_K8 | m_LUJIAZUI) + | m_GOLDMONT | m_GOLDMONT_PLUS | m_ATHLON_K8 | m_ZHAOXIN) /* X86_TUNE_PROLOGUE_USING_MOVE: Do not use push/pop in prologues that are considered on critical path. */ @@ -176,7 +176,7 @@ DEF_TUNE (X86_TUNE_EPILOGUE_USING_MOVE, "epilogue_using_move", /* X86_TUNE_USE_LEAVE: Use "leave" instruction in epilogues where it fits. */ DEF_TUNE (X86_TUNE_USE_LEAVE, "use_leave", - m_386 | m_CORE_ALL | m_K6_GEODE | m_AMD_MULTIPLE | m_LUJIAZUI + m_386 | m_CORE_ALL | m_K6_GEODE | m_AMD_MULTIPLE | m_ZHAOXIN | m_TREMONT | m_CORE_HYBRID | m_CORE_ATOM | m_GENERIC) /* X86_TUNE_PUSH_MEMORY: Enable generation of "push mem" instructions. @@ -184,7 +184,7 @@ DEF_TUNE (X86_TUNE_USE_LEAVE, "use_leave", and push instructions. */ DEF_TUNE (X86_TUNE_PUSH_MEMORY, "push_memory", m_386 | m_P4_NOCONA | m_CORE_ALL | m_K6_GEODE | m_AMD_MULTIPLE - | m_LUJIAZUI | m_TREMONT | m_CORE_HYBRID | m_CORE_ATOM | m_GENERIC) + | m_ZHAOXIN | m_TREMONT | m_CORE_HYBRID | m_CORE_ATOM | m_GENERIC) /* X86_TUNE_SINGLE_PUSH: Enable if single push insn is preferred over esp subtraction. */ @@ -239,7 +239,7 @@ DEF_TUNE (X86_TUNE_SOFTWARE_PREFETCHING_BENEFICIAL, "software_prefetching_benefi /* X86_TUNE_LCP_STALL: Avoid an expensive length-changing prefix stall on 16-bit immediate moves into memory on Core2 and Corei7. */ -DEF_TUNE (X86_TUNE_LCP_STALL, "lcp_stall", m_CORE_ALL | m_LUJIAZUI | m_GENERIC) +DEF_TUNE (X86_TUNE_LCP_STALL, "lcp_stall", m_CORE_ALL | m_ZHAOXIN | m_GENERIC) /* X86_TUNE_READ_MODIFY: Enable use of read-modify instructions such as "add mem, reg". */ @@ -255,20 +255,20 @@ DEF_TUNE (X86_TUNE_USE_INCDEC, "use_incdec", ~(m_P4_NOCONA | m_CORE2 | m_NEHALEM | m_SANDYBRIDGE | m_BONNELL | m_SILVERMONT | m_INTEL | m_KNL | m_KNM | m_GOLDMONT | m_GOLDMONT_PLUS | m_TREMONT | m_CORE_HYBRID | m_CORE_ATOM - | m_LUJIAZUI | m_GENERIC)) + | m_ZHAOXIN | m_GENERIC)) /* X86_TUNE_INTEGER_DFMODE_MOVES: Enable if integer moves are preferred for DFmode copies */ DEF_TUNE (X86_TUNE_INTEGER_DFMODE_MOVES, "integer_dfmode_moves", ~(m_PPRO | m_P4_NOCONA | m_CORE_ALL | m_BONNELL | m_SILVERMONT - | m_KNL | m_KNM | m_INTEL | m_GEODE | m_AMD_MULTIPLE | m_LUJIAZUI + | m_KNL | m_KNM | m_INTEL | m_GEODE | m_AMD_MULTIPLE | m_ZHAOXIN | m_GOLDMONT | m_GOLDMONT_PLUS | m_TREMONT | m_CORE_HYBRID | m_CORE_ATOM | m_GENERIC)) /* X86_TUNE_OPT_AGU: Optimize for Address Generation Unit. This flag will impact LEA instruction selection. */ DEF_TUNE (X86_TUNE_OPT_AGU, "opt_agu", m_BONNELL | m_SILVERMONT | m_KNL - | m_KNM | m_GOLDMONT | m_GOLDMONT_PLUS | m_INTEL | m_LUJIAZUI) + | m_KNM | m_GOLDMONT | m_GOLDMONT_PLUS | m_INTEL | m_ZHAOXIN) /* X86_TUNE_AVOID_LEA_FOR_ADDR: Avoid lea for address computation. */ DEF_TUNE (X86_TUNE_AVOID_LEA_FOR_ADDR, "avoid_lea_for_addr", @@ -302,7 +302,7 @@ DEF_TUNE (X86_TUNE_SINGLE_STRINGOP, "single_stringop", m_386 | m_P4_NOCONA) DEF_TUNE (X86_TUNE_PREFER_KNOWN_REP_MOVSB_STOSB, "prefer_known_rep_movsb_stosb", m_SKYLAKE | m_CORE_HYBRID | m_CORE_ATOM | m_TREMONT | m_CORE_AVX512 - | m_LUJIAZUI) + | m_ZHAOXIN) /* X86_TUNE_MISALIGNED_MOVE_STRING_PRO_EPILOGUES: Enable generation of compact prologues and epilogues by issuing a misaligned moves. This @@ -311,14 +311,14 @@ DEF_TUNE (X86_TUNE_PREFER_KNOWN_REP_MOVSB_STOSB, FIXME: This may actualy be a win on more targets than listed here. */ DEF_TUNE (X86_TUNE_MISALIGNED_MOVE_STRING_PRO_EPILOGUES, "misaligned_move_string_pro_epilogues", - m_386 | m_486 | m_CORE_ALL | m_AMD_MULTIPLE | m_LUJIAZUI | m_TREMONT + m_386 | m_486 | m_CORE_ALL | m_AMD_MULTIPLE | m_ZHAOXIN | m_TREMONT | m_CORE_HYBRID | m_CORE_ATOM | m_GENERIC) /* X86_TUNE_USE_SAHF: Controls use of SAHF. */ DEF_TUNE (X86_TUNE_USE_SAHF, "use_sahf", m_PPRO | m_P4_NOCONA | m_CORE_ALL | m_BONNELL | m_SILVERMONT | m_KNL | m_KNM | m_INTEL | m_K6_GEODE | m_K8 | m_AMDFAM10 | m_BDVER - | m_BTVER | m_ZNVER | m_LUJIAZUI | m_GOLDMONT | m_GOLDMONT_PLUS + | m_BTVER | m_ZNVER | m_ZHAOXIN | m_GOLDMONT | m_GOLDMONT_PLUS | m_TREMONT | m_CORE_HYBRID | m_CORE_ATOM | m_GENERIC) /* X86_TUNE_USE_CLTD: Controls use of CLTD and CTQO instructions. */ @@ -329,7 +329,7 @@ DEF_TUNE (X86_TUNE_USE_CLTD, "use_cltd", /* X86_TUNE_USE_BT: Enable use of BT (bit test) instructions. */ DEF_TUNE (X86_TUNE_USE_BT, "use_bt", m_CORE_ALL | m_BONNELL | m_SILVERMONT | m_KNL | m_KNM | m_INTEL - | m_LAKEMONT | m_AMD_MULTIPLE | m_LUJIAZUI | m_GOLDMONT + | m_LAKEMONT | m_AMD_MULTIPLE | m_ZHAOXIN | m_GOLDMONT | m_GOLDMONT_PLUS | m_TREMONT | m_CORE_HYBRID | m_CORE_ATOM | m_GENERIC) @@ -338,7 +338,7 @@ DEF_TUNE (X86_TUNE_USE_BT, "use_bt", DEF_TUNE (X86_TUNE_AVOID_FALSE_DEP_FOR_BMI, "avoid_false_dep_for_bmi", m_SANDYBRIDGE | m_HASWELL | m_SKYLAKE | m_SKYLAKE_AVX512 | m_CANNONLAKE | m_CASCADELAKE | m_COOPERLAKE - | m_LUJIAZUI | m_GENERIC) + | m_ZHAOXIN | m_GENERIC) /* X86_TUNE_ADJUST_UNROLL: This enables adjusting the unroll factor based on hardware capabilities. Bdver3 hardware has a loop buffer which makes @@ -351,11 +351,11 @@ DEF_TUNE (X86_TUNE_ADJUST_UNROLL, "adjust_unroll_factor", m_BDVER3 | m_BDVER4) DEF_TUNE (X86_TUNE_ONE_IF_CONV_INSN, "one_if_conv_insn", m_SILVERMONT | m_KNL | m_KNM | m_INTEL | m_CORE_ALL | m_GOLDMONT | m_GOLDMONT_PLUS | m_TREMONT | m_CORE_HYBRID | m_CORE_ATOM - | m_LUJIAZUI | m_GENERIC) + | m_ZHAOXIN | m_GENERIC) /* X86_TUNE_AVOID_MFENCE: Use lock prefixed instructions instead of mfence. */ DEF_TUNE (X86_TUNE_AVOID_MFENCE, "avoid_mfence", - m_CORE_ALL | m_BDVER | m_ZNVER | m_LUJIAZUI | m_TREMONT | m_CORE_HYBRID + m_CORE_ALL | m_BDVER | m_ZNVER | m_ZHAOXIN | m_TREMONT | m_CORE_HYBRID | m_CORE_ATOM | m_GENERIC) /* X86_TUNE_EXPAND_ABS: This enables a new abs pattern by @@ -363,7 +363,7 @@ DEF_TUNE (X86_TUNE_AVOID_MFENCE, "avoid_mfence", (signed) x >> (W-1)) instead of cmove or SSE max/abs instructions. */ DEF_TUNE (X86_TUNE_EXPAND_ABS, "expand_abs", m_CORE_ALL | m_SILVERMONT | m_KNL | m_KNM | m_GOLDMONT - | m_GOLDMONT_PLUS | m_LUJIAZUI) + | m_GOLDMONT_PLUS | m_ZHAOXIN) /*****************************************************************************/ /* 387 instruction selection tuning */ @@ -380,16 +380,16 @@ DEF_TUNE (X86_TUNE_USE_HIMODE_FIOP, "use_himode_fiop", DEF_TUNE (X86_TUNE_USE_SIMODE_FIOP, "use_simode_fiop", ~(m_PENT | m_LAKEMONT | m_PPRO | m_CORE_ALL | m_BONNELL | m_SILVERMONT | m_KNL | m_KNM | m_INTEL | m_AMD_MULTIPLE - | m_LUJIAZUI | m_GOLDMONT | m_GOLDMONT_PLUS | m_TREMONT + | m_ZHAOXIN | m_GOLDMONT | m_GOLDMONT_PLUS | m_TREMONT | m_CORE_HYBRID | m_CORE_ATOM | m_GENERIC)) /* X86_TUNE_USE_FFREEP: Use freep instruction instead of fstp. */ -DEF_TUNE (X86_TUNE_USE_FFREEP, "use_ffreep", m_AMD_MULTIPLE | m_LUJIAZUI) +DEF_TUNE (X86_TUNE_USE_FFREEP, "use_ffreep", m_AMD_MULTIPLE | m_ZHAOXIN) /* X86_TUNE_EXT_80387_CONSTANTS: Use fancy 80387 constants, such as PI. */ DEF_TUNE (X86_TUNE_EXT_80387_CONSTANTS, "ext_80387_constants", m_PPRO | m_P4_NOCONA | m_CORE_ALL | m_BONNELL | m_SILVERMONT - | m_KNL | m_KNM | m_INTEL | m_K6_GEODE | m_ATHLON_K8 | m_LUJIAZUI + | m_KNL | m_KNM | m_INTEL | m_K6_GEODE | m_ATHLON_K8 | m_ZHAOXIN | m_GOLDMONT | m_GOLDMONT_PLUS | m_TREMONT | m_CORE_HYBRID | m_CORE_ATOM | m_GENERIC) @@ -407,7 +407,7 @@ DEF_TUNE (X86_TUNE_GENERAL_REGS_SSE_SPILL, "general_regs_sse_spill", DEF_TUNE (X86_TUNE_SSE_UNALIGNED_LOAD_OPTIMAL, "sse_unaligned_load_optimal", m_NEHALEM | m_SANDYBRIDGE | m_CORE_AVX2 | m_SILVERMONT | m_KNL | m_KNM | m_INTEL | m_GOLDMONT | m_GOLDMONT_PLUS | m_TREMONT | m_CORE_HYBRID - | m_CORE_ATOM | m_AMDFAM10 | m_BDVER | m_BTVER | m_ZNVER | m_LUJIAZUI + | m_CORE_ATOM | m_AMDFAM10 | m_BDVER | m_BTVER | m_ZNVER | m_ZHAOXIN | m_GENERIC) /* X86_TUNE_SSE_UNALIGNED_STORE_OPTIMAL: Use movups for misaligned stores @@ -415,7 +415,7 @@ DEF_TUNE (X86_TUNE_SSE_UNALIGNED_LOAD_OPTIMAL, "sse_unaligned_load_optimal", DEF_TUNE (X86_TUNE_SSE_UNALIGNED_STORE_OPTIMAL, "sse_unaligned_store_optimal", m_NEHALEM | m_SANDYBRIDGE | m_CORE_AVX2 | m_SILVERMONT | m_KNL | m_KNM | m_INTEL | m_GOLDMONT | m_GOLDMONT_PLUS | m_TREMONT | m_CORE_HYBRID - | m_CORE_ATOM | m_BDVER | m_ZNVER | m_LUJIAZUI | m_GENERIC) + | m_CORE_ATOM | m_BDVER | m_ZNVER | m_ZHAOXIN | m_GENERIC) /* X86_TUNE_SSE_PACKED_SINGLE_INSN_OPTIMAL: Use packed single precision 128bit instructions instead of double where possible. */ @@ -424,14 +424,14 @@ DEF_TUNE (X86_TUNE_SSE_PACKED_SINGLE_INSN_OPTIMAL, "sse_packed_single_insn_optim /* X86_TUNE_SSE_TYPELESS_STORES: Always movaps/movups for 128bit stores. */ DEF_TUNE (X86_TUNE_SSE_TYPELESS_STORES, "sse_typeless_stores", - m_AMD_MULTIPLE | m_LUJIAZUI | m_CORE_ALL | m_TREMONT | m_CORE_HYBRID + m_AMD_MULTIPLE | m_ZHAOXIN | m_CORE_ALL | m_TREMONT | m_CORE_HYBRID | m_CORE_ATOM | m_GENERIC) /* X86_TUNE_SSE_LOAD0_BY_PXOR: Always use pxor to load0 as opposed to xorps/xorpd and other variants. */ DEF_TUNE (X86_TUNE_SSE_LOAD0_BY_PXOR, "sse_load0_by_pxor", m_PPRO | m_P4_NOCONA | m_CORE_ALL | m_BDVER | m_BTVER | m_ZNVER - | m_LUJIAZUI | m_TREMONT | m_CORE_HYBRID | m_CORE_ATOM | m_GENERIC) + | m_ZHAOXIN | m_TREMONT | m_CORE_HYBRID | m_CORE_ATOM | m_GENERIC) /* X86_TUNE_INTER_UNIT_MOVES_TO_VEC: Enable moves in from integer to SSE registers. If disabled, the moves will be done by storing @@ -484,7 +484,7 @@ DEF_TUNE (X86_TUNE_AVOID_4BYTE_PREFIXES, "avoid_4byte_prefixes", elements. */ DEF_TUNE (X86_TUNE_USE_GATHER_2PARTS, "use_gather_2parts", ~(m_ZNVER1 | m_ZNVER2 | m_ZNVER3 | m_ZNVER4 | m_CORE_HYBRID - | m_CORE_ATOM | m_GENERIC | m_GDS)) + | m_YONGFENG | m_CORE_ATOM | m_GENERIC | m_GDS)) /* X86_TUNE_USE_SCATTER_2PARTS: Use scater instructions for vectors with 2 elements. */ @@ -495,7 +495,7 @@ DEF_TUNE (X86_TUNE_USE_SCATTER_2PARTS, "use_scatter_2parts", elements. */ DEF_TUNE (X86_TUNE_USE_GATHER_4PARTS, "use_gather_4parts", ~(m_ZNVER1 | m_ZNVER2 | m_ZNVER3 | m_ZNVER4 | m_CORE_HYBRID - | m_CORE_ATOM | m_GENERIC | m_GDS)) + | m_YONGFENG | m_CORE_ATOM | m_GENERIC | m_GDS)) /* X86_TUNE_USE_SCATTER_4PARTS: Use scater instructions for vectors with 4 elements. */ @@ -506,7 +506,7 @@ DEF_TUNE (X86_TUNE_USE_SCATTER_4PARTS, "use_scatter_4parts", elements. */ DEF_TUNE (X86_TUNE_USE_GATHER_8PARTS, "use_gather_8parts", ~(m_ZNVER1 | m_ZNVER2 | m_ZNVER4 | m_CORE_HYBRID | m_CORE_ATOM - | m_GENERIC | m_GDS)) + | m_YONGFENG | m_GENERIC | m_GDS)) /* X86_TUNE_USE_SCATTER: Use scater instructions for vectors with 8 or more elements. */ @@ -515,7 +515,8 @@ DEF_TUNE (X86_TUNE_USE_SCATTER_8PARTS, "use_scatter_8parts", /* X86_TUNE_AVOID_128FMA_CHAINS: Avoid creating loops with tight 128bit or smaller FMA chain. */ -DEF_TUNE (X86_TUNE_AVOID_128FMA_CHAINS, "avoid_fma_chains", m_ZNVER1 | m_ZNVER2 | m_ZNVER3) +DEF_TUNE (X86_TUNE_AVOID_128FMA_CHAINS, "avoid_fma_chains", m_ZNVER1 | m_ZNVER2 | m_ZNVER3 + | m_YONGFENG) /* X86_TUNE_AVOID_256FMA_CHAINS: Avoid creating loops with tight 256bit or smaller FMA chain. */ diff --git a/gcc/config/i386/yongfeng.md b/gcc/config/i386/yongfeng.md new file mode 100644 index 0000000000000..a225b409cf945 --- /dev/null +++ b/gcc/config/i386/yongfeng.md @@ -0,0 +1,848 @@ +;; Copyright (C) 2012-2023 Free Software Foundation, Inc. +;; +;; This file is part of GCC. +;; +;; GCC is free software; you can redistribute it and/or modify +;; it under the terms of the GNU General Public License as published by +;; the Free Software Foundation; either version 3, or (at your option) +;; any later version. +;; +;; GCC is distributed in the hope that it will be useful, +;; but WITHOUT ANY WARRANTY; without even the implied warranty of +;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +;; GNU General Public License for more details. +;; +;; You should have received a copy of the GNU General Public License +;; along with GCC; see the file COPYING3. If not see +;; . +;; + +;; ZHAOXIN yongfeng processor Scheduling +;; Modeling automatons for yongfeng decoders, integer execution pipes, +;; FP execution pipes, AGU pipes, and dividers. +(define_automaton "yongfeng_decoder,yongfeng_ieu,yongfeng_fp,yongfeng_agu,yongfeng_idiv,yongfeng_fdiv") + +;; The rules for the decoder are simple: +;; - an instruction with 1 uop can be decoded by any of the four +;; decoders in one cycle. +;; - an instruction with 2 uops can be decoded by decoder 0 or decoder 1 +;; or decoder 2 but still in only one cycle. +;; - a complex (microcode) instruction can only be decoded by +;; decoder 0, and this takes an unspecified number of cycles. +;; +;; The goal is to schedule such that we have a few-one-two uops sequence +;; in each cycle, to decode as many instructions per cycle as possible. +(define_cpu_unit "yf_decoder0" "yongfeng_decoder") +(define_cpu_unit "yf_decoder1" "yongfeng_decoder") +(define_cpu_unit "yf_decoder2" "yongfeng_decoder") +(define_cpu_unit "yf_decoder3" "yongfeng_decoder") + +;; We first wish to find an instruction for yf_decoder0, so exclude +;; other decoders from being reserved until yf_decoder0 is +;; reserved +(presence_set "yf_decoder1" "yf_decoder0") +(presence_set "yf_decoder2" "yf_decoder0") +(presence_set "yf_decoder3" "yf_decoder0") + +;; Most instructions can be decoded on any of the three decoders. +(define_reservation "yf_decodern" "yf_decoder0|yf_decoder1|yf_decoder2|yf_decoder3") +(define_reservation "yf_decoder012" "yf_decoder0|yf_decoder1|yf_decoder2") + +;; The out-of-order core has ten pipelines. Port 0,1,2,3 are integer execution +;; pipelines, port 4, 5 are responsible for address calculation, load and store, +;; port 6,7,8,9 are FP pipelines. +(define_cpu_unit "yf_p0,yf_p1,yf_p2,yf_p3" "yongfeng_ieu") +(define_cpu_unit "yf_p4,yf_p5" "yongfeng_agu") +(define_cpu_unit "yf_p6,yf_p7,yf_p8,yf_p9" "yongfeng_fp") + +(define_cpu_unit "yf_idiv" "yongfeng_idiv") +(define_cpu_unit "yf_fdiv" "yongfeng_fdiv") + +(define_reservation "yf_ieu" "yf_p0|yf_p1|yf_p2|yf_p3") +(define_reservation "yf_p01" "yf_p0|yf_p1") +(define_reservation "yf_agu" "yf_p4|yf_p5") +(define_reservation "yf_feu" "yf_p6|yf_p7|yf_p8|yf_p9") + +;; Only the irregular instructions have to be modeled here. + +;; Complex instruction. +(define_insn_reservation "yongfeng_complex_insn" 6 + (and (eq_attr "cpu" "yongfeng") + (eq_attr "type" "other,multi,str")) + "yf_decoder0") + +;; Call instruction. +(define_insn_reservation "yongfeng_call" 3 + (and (eq_attr "cpu" "yongfeng") + (eq_attr "type" "call,callv")) + "yf_decoder012,yf_agu,yf_ieu*3") +;; Push and pop. +(define_insn_reservation "yongfeng_push_reg" 1 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "store") + (eq_attr "type" "push"))) + "yf_decodern,yf_agu,yf_ieu") + +(define_insn_reservation "yongfeng_push_mem" 4 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "both") + (eq_attr "type" "push"))) + "yf_decoder012,yf_agu,yf_ieu") + +(define_insn_reservation "yongfeng_pop_reg" 4 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "load") + (eq_attr "type" "pop"))) + "yf_decoder012,yf_p01,yf_agu") + +(define_insn_reservation "yongfeng_pop_mem" 4 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "both") + (eq_attr "type" "pop"))) + "yf_decoder0,yf_agu,yf_ieu") + +(define_insn_reservation "yongfeng_leave" 3 + (and (eq_attr "cpu" "yongfeng") + (eq_attr "type" "leave")) + "yf_decoder0,yf_agu,yf_p01*3") + +;; MOV - integer moves. +(define_insn_reservation "yongfeng_imov" 1 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "none") + (eq_attr "type" "imov,imovx"))) + "yf_decodern,yf_ieu") + +(define_insn_reservation "yongfeng_imov_load" 4 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "load") + (eq_attr "type" "imov"))) + "yf_decodern,yf_agu") + +(define_insn_reservation "yongfeng_imovx_load" 4 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "load") + (eq_attr "type" "imovx"))) + "yf_decoder012,yf_agu,yf_ieu|yf_ieu") + +(define_insn_reservation "yongfeng_imov_store" 1 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "store") + (eq_attr "type" "imov"))) + "yf_decodern,yf_agu,yf_ieu") + +(define_insn_reservation "yongfeng_int_insn" 1 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "none,unknown") + (eq_attr "type" "alu,alu1,icmov,icmp,test,lea,ishift1,rotate,rotate1,setcc,incdec"))) + "yf_decodern,yf_ieu") + +(define_insn_reservation "yongfeng_int_insn_load" 5 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "load") + (eq_attr "type" "alu,alu1,icmov,icmp,test,ishift1,rotate,rotate1,setcc"))) + "yf_decoder012,yf_agu,yf_ieu") + +(define_insn_reservation "yongfeng_int_insn_store" 1 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "store") + (eq_attr "type" "alu,alu1,icmp,test,ishift1,rotate,rotate1,setcc"))) + "yf_decoder012,yf_agu,yf_ieu") + +(define_insn_reservation "yongfeng_int_insn_both" 5 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "both") + (eq_attr "type" "alu,alu1,icmp,test,ishift1,rotate,rotate1,setcc,incdec"))) + "yf_decoder012,yf_agu,yf_ieu") + +(define_insn_reservation "yongfeng_shift_HI" 5 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "none,unknown") + (and (eq_attr "mode" "HI") + (eq_attr "type" "ishift")))) + "yf_decoder0,yf_ieu") + +(define_insn_reservation "yongfeng_shift_SIDI" 2 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "none,unknown") + (and (eq_attr "mode" "SI,DI") + (eq_attr "type" "ishift")))) + "yf_decoder0,yf_ieu") + +(define_insn_reservation "yongfeng_shift_HI_mem" 9 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "!none") + (and (eq_attr "mode" "HI") + (eq_attr "type" "ishift")))) + "yf_decoder0,yf_agu,yf_ieu") + +(define_insn_reservation "yongfeng_shift_SIDI_mem" 6 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "!none") + (and (eq_attr "mode" "SI,DI") + (eq_attr "type" "ishift")))) + "yf_decoder0,yf_agu,yf_ieu") + +(define_insn_reservation "yongfeng_negnot_QIHI" 2 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "none,unknown") + (and (eq_attr "mode" "QI,HI") + (eq_attr "type" "negnot")))) + "yf_decoder012,yf_ieu|yf_ieu") + +(define_insn_reservation "yongfeng_negnot_SIDI" 1 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "none,unknown") + (and (eq_attr "mode" "SI,DI") + (eq_attr "type" "negnot")))) + "yf_decodern,yf_ieu") + +(define_insn_reservation "yongfeng_negnot_QIHI_mem" 6 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "!none") + (and (eq_attr "mode" "QI,HI") + (eq_attr "type" "negnot")))) + "yf_decoder012,yf_agu,yf_ieu") + +(define_insn_reservation "yongfeng_negnot_SIDI_mem" 5 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "!none") + (and (eq_attr "mode" "SI,DI") + (eq_attr "type" "negnot")))) + "yf_decoder012,yf_agu,yf_ieu") + +;; branch instruction +(define_insn_reservation "yongfeng_branch" 3 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "none") + (eq_attr "type" "ibr"))) + "yf_decodern,yf_p2*3") + +(define_insn_reservation "yongfeng_branch_mem" 7 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "!none") + (eq_attr "type" "ibr"))) + "yf_decodern,yf_agu,yf_p2") + +;; Integer Multiplication instructions. + +(define_insn_reservation "yongfeng_imul_QI" 2 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "none") + (and (eq_attr "mode" "QI") + (eq_attr "type" "imul")))) + "yf_decodern,yf_ieu|yf_ieu") + +(define_insn_reservation "yongfeng_imul_HI" 3 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "none") + (and (eq_attr "mode" "HI") + (eq_attr "type" "imul")))) + "yf_decoder0,yf_ieu") + +(define_insn_reservation "yongfeng_imul_SIDI" 2 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "none") + (and (eq_attr "mode" "SI,DI") + (eq_attr "type" "imul")))) + "yf_decoder0,yf_ieu|yf_ieu") + +(define_insn_reservation "yongfeng_imul_QI_mem" 6 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "!none") + (and (eq_attr "mode" "QI") + (eq_attr "type" "imul")))) + "yf_decoder012,yf_agu,yf_ieu") + +(define_insn_reservation "yongfeng_imul_SIDI_mem" 6 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "!none") + (and (eq_attr "mode" "SI,DI") + (eq_attr "type" "imul")))) + "yf_decoder0,yf_agu,yf_ieu") + +(define_insn_reservation "yongfeng_imul_HI_mem" 7 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "!none") + (and (eq_attr "mode" "HI") + (eq_attr "type" "imul")))) + "yf_decoder0,yf_agu,yf_ieu") + +;; Integer Division instructions. + +(define_insn_reservation "yongfeng_idiv_DI" 41 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "none") + (and (eq_attr "mode" "DI") + (eq_attr "type" "idiv")))) + "yf_decoder0,yf_ieu,yf_feu,yf_idiv*41") + +(define_insn_reservation "yongfeng_idiv_HI" 9 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "none") + (and (eq_attr "mode" "HI") + (eq_attr "type" "idiv")))) + "yf_decoder0,yf_ieu,yf_feu,yf_idiv*3") + +(define_insn_reservation "yongfeng_idiv_QISI" 8 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "none") + (and (eq_attr "mode" "QI,SI") + (eq_attr "type" "idiv")))) + "yf_decoder0,yf_ieu,yf_feu,yf_idiv*3") + + +(define_insn_reservation "yongfeng_idiv_mem_DI" 45 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "load") + (and (eq_attr "mode" "DI") + (eq_attr "type" "idiv")))) + "yf_decoder0,yf_agu,yf_ieu,yf_feu,yf_idiv*41") + +(define_insn_reservation "yongfeng_idiv_HI_mem" 13 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "load") + (and (eq_attr "mode" "HI") + (eq_attr "type" "idiv")))) + "yf_decoder0,yf_agu,yf_ieu,yf_feu,yf_idiv*3") + + +(define_insn_reservation "yongfeng_idiv_QISI_mem" 12 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "load") + (and (eq_attr "mode" "QI,SI") + (eq_attr "type" "idiv")))) + "yf_decoder0,yf_agu,yf_ieu,yf_feu,yf_idiv*3") + +;; MMX,SSE,AVX,AVX2 instructions +;; sse moves + +(define_insn_reservation "yongfeng_sse_mov" 1 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "mode" "SF,DF,V4SF,V2DF,TI") + (and (eq_attr "memory" "none") + (eq_attr "type" "ssemov")))) + "yf_decodern,yf_feu") + +(define_insn_reservation "yongfeng_sse_mov_store" 1 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "mode" "SF,DF,V4SF,V2DF,TI") + (and (eq_attr "memory" "store") + (eq_attr "type" "ssemov")))) + "yf_decodern,yf_agu,yf_feu") + +(define_insn_reservation "yongfeng_sse_mov_load" 5 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "mode" "SF,DF,V4SF,V2DF,TI") + (and (eq_attr "memory" "load") + (eq_attr "type" "ssemov")))) + "yf_decodern,yf_agu,yf_feu") + +(define_insn_reservation "yongfeng_avx256_mov" 1 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "mode" "V8SF,V4DF,OI") + (and (eq_attr "memory" "none") + (eq_attr "type" "ssemov")))) + "yf_decoder012,yf_feu") + +(define_insn_reservation "yongfeng_avx256_mov_store" 1 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "mode" "V8SF,V4DF,OI") + (and (eq_attr "memory" "store") + (eq_attr "type" "ssemov")))) + "yf_decoder012,yf_agu,yf_feu") + +(define_insn_reservation "yongfeng_avx256_mov_load" 6 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "mode" "V8SF,V4DF,OI") + (and (eq_attr "memory" "load") + (eq_attr "type" "ssemov")))) + "yf_decoder012,yf_agu,yf_feu") + +;;sse general instructions +(define_insn_reservation "yongfeng_sse_insns" 3 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "mode" "SF,DF,V4SF,V2DF,TI") + (and (eq_attr "memory" "none") + (eq_attr "type" "sseadd,sseadd1,ssemul,ssecmp")))) + "yf_decodern,yf_feu|yf_feu") + +(define_insn_reservation "yongfeng_sse_insns_load" 7 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "mode" "SF,DF,V4SF,V2DF,TI") + (and (eq_attr "memory" "load") + (eq_attr "type" "sseadd,sseadd1,ssemul,ssecmp")))) + "yf_decodern,yf_agu,yf_feu") + +(define_insn_reservation "yongfeng_avx256_insns" 3 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "mode" "V8SF,V4DF,OI") + (and (eq_attr "memory" "none") + (eq_attr "type" "sseadd,sseadd1,ssemul,ssecmp")))) + "yf_decoder012,yf_feu") + +(define_insn_reservation "yongfeng_avx256_insns_load" 8 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "mode" "V8SF,V4DF,OI") + (and (eq_attr "memory" "load") + (eq_attr "type" "sseadd,sseadd1,ssemul,ssecmp")))) + "yf_decoder012,yf_agu,yf_feu") + +(define_insn_reservation "yongfeng_sse_iadd" 1 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "mode" "DI,TI") + (and (eq_attr "memory" "none") + (eq_attr "type" "sseiadd")))) + "yf_decodern,yf_feu") + +(define_insn_reservation "yongfeng_sse_iadd_load" 5 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "mode" "DI,TI") + (and (eq_attr "memory" "load") + (eq_attr "type" "sseiadd")))) + "yf_decodern,yf_agu,yf_feu") + +(define_insn_reservation "yongfeng_avx256_iadd" 1 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "mode" "OI") + (and (eq_attr "memory" "none") + (eq_attr "type" "sseiadd")))) + "yf_decoder012,yf_feu") + +(define_insn_reservation "yongfeng_avx256_iadd_load" 6 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "mode" "OI") + (and (eq_attr "memory" "load") + (eq_attr "type" "sseiadd")))) + "yf_decoder0,yf_agu,yf_feu") + +(define_insn_reservation "yongfeng_sse_iadd1" 2 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "none") + (eq_attr "type" "sseiadd1"))) + "yf_decoder0,yf_feu") + +(define_insn_reservation "yongfeng_sse_iadd1_load" 6 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "load") + (eq_attr "type" "sseiadd1"))) + "yf_decoder0,yf_agu,yf_feu") + +;;sse imul +(define_insn_reservation "yongfeng_sse_imul" 2 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "mode" "DI,TI") + (and (eq_attr "memory" "none") + (eq_attr "type" "sseimul")))) + "yf_decodern,yf_feu") + +(define_insn_reservation "yongfeng_sse_imul_load" 6 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "mode" "DI,TI") + (and (eq_attr "memory" "load") + (eq_attr "type" "sseimul")))) + "yf_decoder012,yf_agu,yf_feu") + +(define_insn_reservation "yongfeng_avx256_imul" 2 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "mode" "OI") + (and (eq_attr "memory" "none") + (eq_attr "type" "sseimul")))) + "yf_decoder012,yf_feu") + +(define_insn_reservation "yongfeng_avx256_imul_load" 7 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "mode" "OI") + (and (eq_attr "memory" "load") + (eq_attr "type" "sseimul")))) + "yf_decoder0,yf_agu,yf_feu") + +;; sse FMA +(define_insn_reservation "yongfeng_sse_fma" 5 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "mode" "SF,DF,V4SF,V2DF") + (and (eq_attr "memory" "none") + (eq_attr "type" "ssemuladd")))) + "yf_decodern,yf_feu") + +(define_insn_reservation "yongfeng_sse_fma_load" 9 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "mode" "SF,DF,V4SF,V2DF") + (and (eq_attr "memory" "load") + (eq_attr "type" "ssemuladd")))) + "yf_decoder012,yf_agu,yf_feu") + +(define_insn_reservation "yongfeng_avx256_fma" 5 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "mode" "V8SF,V4DF") + (and (eq_attr "memory" "none") + (eq_attr "type" "ssemuladd")))) + "yf_decoder012,yf_feu") + +(define_insn_reservation "yongfeng_avx256_fma_load" 10 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "mode" "V8SF,V4DF") + (and (eq_attr "memory" "load") + (eq_attr "type" "ssemuladd")))) + "yf_decoder0,yf_agu,yf_feu") +;; sse div +(define_insn_reservation "yongfeng_ssediv_s" 10 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "mode" "SF,V4SF") + (and (eq_attr "memory" "none") + (eq_attr "type" "ssediv")))) + "yf_decodern,yf_fdiv*2") + +(define_insn_reservation "yongfeng_ssediv_s_load" 14 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "mode" "SF,V4SF") + (and (eq_attr "memory" "load") + (eq_attr "type" "ssediv")))) + "yf_decodern,yf_agu,yf_fdiv*2") + +(define_insn_reservation "yongfeng_ssediv_d" 14 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "mode" "DF,V2DF") + (and (eq_attr "memory" "none") + (eq_attr "type" "ssediv")))) + "yf_decodern,yf_fdiv*3") + +(define_insn_reservation "yongfeng_ssediv_d_load" 18 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "mode" "DF,V2DF") + (and (eq_attr "memory" "load") + (eq_attr "type" "ssediv")))) + "yf_decodern,yf_agu,yf_fdiv*3") + +(define_insn_reservation "yongfeng_ssediv_avx256_s" 10 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "mode" "V8SF") + (and (eq_attr "memory" "none") + (eq_attr "type" "ssediv")))) + "yf_decoder012,yf_fdiv*10") + +(define_insn_reservation "yongfeng_ssediv_avx256_s_load" 15 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "mode" "V8SF") + (and (eq_attr "memory" "none") + (eq_attr "type" "ssediv")))) + "yf_decoder012,yf_agu,yf_fdiv*10") + +(define_insn_reservation "yongfeng_ssediv_avx256_d" 14 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "mode" "V4DF") + (and (eq_attr "memory" "none") + (eq_attr "type" "ssediv")))) + "yf_decoder012,yf_fdiv*14") + +(define_insn_reservation "yongfeng_ssediv_avx256_d_load" 19 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "mode" "V4DF") + (and (eq_attr "memory" "load") + (eq_attr "type" "ssediv")))) + "yf_decoder012,yf_fdiv*14") + +;;sse logical and shuffle instructions +(define_insn_reservation "yongfeng_avx256_log_shuf" 1 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "mode" "V8SF,V4DF,OI") + (and (eq_attr "memory" "none") + (eq_attr "type" "sselog,sselog1,sseshuf,sseshuf1")))) + "yf_decoder012,yf_feu") + +(define_insn_reservation "yongfeng_avx256_log_shuf_load" 6 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "mode" "V8SF,V4DF,OI") + (and (eq_attr "memory" "load") + (eq_attr "type" "sselog,sselog1,sseshuf,sseshuf1")))) + "yf_decoder012,yf_agu,yf_feu") + +(define_insn_reservation "yongfeng_sse_log_shuf" 1 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "none") + (eq_attr "type" "sselog,sselog1,sseshuf,sseshuf1"))) + "yf_decodern,yf_feu") + +(define_insn_reservation "yongfeng_sse_log_shuf_load" 5 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "load") + (eq_attr "type" "sselog,sselog1,sseshuf,sseshuf1"))) + "yf_decodern,yf_agu,yf_feu") +;;sse shift + +(define_insn_reservation "yongfeng_avx256_shift" 1 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "mode" "V8SF,V4DF,OI") + (and (eq_attr "memory" "none") + (eq_attr "type" "sseishft,sseishft1")))) + "yf_decoder012,yf_feu") + +(define_insn_reservation "yongfeng_avx256_shift_load" 6 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "mode" "V8SF,V4DF,OI") + (and (eq_attr "memory" "load") + (eq_attr "type" "sseishft,sseishft1")))) + "yf_decoder0,yf_agu,yf_feu") + +(define_insn_reservation "yongfeng_sse_shift" 1 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "none") + (eq_attr "type" "sseishft,sseishft1"))) + "yf_decodern,yf_feu") + +(define_insn_reservation "yongfeng_sse_shift_load" 5 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "load") + (eq_attr "type" "sseishft,sseishft1"))) + "yf_decodern,yf_agu,yf_feu") +;;sse comi +(define_insn_reservation "yongfeng_avx256_test" 4 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "mode" "V8SF,V4DF,OI") + (and (eq_attr "prefix_extra" "1") + (and (eq_attr "memory" "none") + (eq_attr "type" "ssecomi"))))) + "yf_decoder012,yf_ieu*3") + +(define_insn_reservation "yongfeng_avx256_test_load" 9 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "mode" "V8SF,V4DF,OI") + (and (eq_attr "prefix_extra" "1") + (and (eq_attr "memory" "load") + (eq_attr "type" "ssecomi"))))) + "yf_decoder012,yf_agu,yf_ieu,yf_p6*3") + +(define_insn_reservation "yongfeng_sse_test" 3 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "prefix_extra" "1") + (and (eq_attr "memory" "none") + (eq_attr "type" "ssecomi")))) + "yf_decodern,yf_feu|yf_feu") + +(define_insn_reservation "yongfeng_sse_test_load" 7 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "prefix_extra" "1") + (and (eq_attr "memory" "load") + (eq_attr "type" "ssecomi")))) + "yf_decodern,yf_agu,yf_feu") + +(define_insn_reservation "yongfeng_sse_comi" 1 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "prefix_extra" "0") + (and (eq_attr "memory" "none") + (eq_attr "type" "ssecomi")))) + "yf_decodern,yf_feu|yf_feu") + +(define_insn_reservation "yongfeng_sse_comi_load" 4 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "prefix_extra" "0") + (and (eq_attr "memory" "load") + (eq_attr "type" "ssecomi")))) + "yf_decodern,yf_agu,yf_feu") + +;;sse conversion +(define_insn_reservation "yongfeng_avx_cvt_ps" 4 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "mode" "V4SF") + (and (eq_attr "memory" "none") + (eq_attr "type" "ssecvt")))) + "yf_decoder0,yf_feu") + +(define_insn_reservation "yongfeng_avx_cvt_ps_load" 8 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "mode" "V4SF") + (and (eq_attr "memory" "load") + (eq_attr "type" "ssecvt")))) + "yf_decoder0,yf_agu,yf_feu") + +(define_insn_reservation "yongfeng_avx_cvt_pd" 3 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "mode" "V4DF") + (and (eq_attr "memory" "none") + (eq_attr "type" "ssecvt")))) + "yf_decoder0,yf_feu") + +(define_insn_reservation "yongfeng_avx_cvt_pd_load" 7 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "mode" "V4DF") + (and (eq_attr "memory" "load") + (eq_attr "type" "ssecvt")))) + "yf_decoder0,yf_agu,yf_feu") + +(define_insn_reservation "yongfeng_sse_cvt" 3 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "none") + (eq_attr "type" "ssecvt"))) + "yf_decodern,yf_feu|yf_feu") + +(define_insn_reservation "yongfeng_sse_cvt_load" 7 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "load") + (eq_attr "type" "ssecvt"))) + "yf_decoder012,yf_agu,yf_feu") + +(define_insn_reservation "yongfeng_sse_icvt" 3 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "none") + (eq_attr "type" "sseicvt"))) + "yf_decodern,yf_feu|yf_feu") + +(define_insn_reservation "yongfeng_sse_icvt_load" 7 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "load") + (eq_attr "type" "sseicvt"))) + "yf_decoder012,yf_agu,yf_feu") + +(define_insn_reservation "yongfeng_sse_icvt_SI" 1 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "mode" "SI") + (and (eq_attr "memory" "none") + (eq_attr "type" "sseicvt")))) + "yf_decoder012,yf_feu") + +(define_insn_reservation "yongfeng_sse_icvt_SI_load" 5 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "mode" "SI") + (and (eq_attr "memory" "load") + (eq_attr "type" "sseicvt")))) + "yf_decoder012,yf_agu,yf_feu") + +(define_insn_reservation "yongfeng_sse_icvt_DI" 2 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "mode" "DI") + (and (eq_attr "memory" "none") + (eq_attr "type" "sseicvt")))) + "yf_decoder0,yf_feu") + +(define_insn_reservation "yongfeng_sse_icvt_DI_load" 6 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "mode" "DI") + (and (eq_attr "memory" "load") + (eq_attr "type" "sseicvt")))) + "yf_decoder0,yf_agu,yf_feu") +;; MMX +(define_insn_reservation "yongfeng_mmx_move" 1 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "none") + (eq_attr "type" "mmxmov"))) + "yf_decodern,yf_p0") + +(define_insn_reservation "yongfeng_mmx_move_load" 5 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "load") + (eq_attr "type" "mmxmov"))) + "yf_decodern,yf_agu,yf_p0") + +(define_insn_reservation "yongfeng_mmx_move_store" 1 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "store") + (eq_attr "type" "mmxmov"))) + "yf_decodern,yf_agu,yf_p0") + +(define_insn_reservation "yongfeng_mmx_mul" 2 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "none") + (eq_attr "type" "mmxmul"))) + "yf_decodern,yf_feu") + +(define_insn_reservation "yongfeng_mmx_mul_load" 6 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "load") + (eq_attr "type" "mmxmul"))) + "yf_decoder012,yf_agu,yf_feu") + +;; MMX general instructions +(define_insn_reservation "yongfeng_mmx_insns" 1 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "none") + (eq_attr "type" "mmxadd,mmxshft,mmxcmp,mmx,mmxcvt"))) + "yf_decodern,yf_feu|yf_feu") + +(define_insn_reservation "yongfeng_mmx_insns_load" 5 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "load") + (eq_attr "type" "mmxadd,mmxshft,mmxcmp,mmx,mmxcvt"))) + "yf_decodern,yf_agu,yf_feu|yf_feu") + +(define_insn_reservation "yongfeng_mmx_insns_store" 1 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "store") + (eq_attr "type" "mmxadd,mmxshft,mmxcmp,mmx,mmxcvt"))) + "yf_decodern,yf_agu,yf_feu") + +;; x87 floating point operations. + +(define_insn_reservation "yongfeng_fxch" 1 + (and (eq_attr "cpu" "yongfeng") + (eq_attr "type" "fxch")) + "yf_decodern,yf_p0|yf_p1") + +(define_insn_reservation "yongfeng_fcmov_sgn" 1 + (and (eq_attr "cpu" "yongfeng") + (eq_attr "type" "fcmov,fsgn")) + "yf_decodern,yf_p0|yf_p1,yf_feu") + +(define_insn_reservation "yongfeng_fcmp" 1 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "none") + (eq_attr "type" "fcmp"))) + "yf_decodern,yf_feu") + +(define_insn_reservation "yongfeng_fcmp_load" 5 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "load") + (eq_attr "type" "fcmp"))) + "yf_decodern,yf_agu,yf_feu") + +(define_insn_reservation "yongfeng_fmov" 1 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "none") + (eq_attr "type" "fmov"))) + "yf_decodern,yf_feu") + +(define_insn_reservation "yongfeng_fmov_store" 1 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "store") + (eq_attr "type" "fmov"))) + "yf_decoder0,yf_agu,yf_feu") + +(define_insn_reservation "yongfeng_fmov_load" 5 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "load") + (eq_attr "type" "fmov"))) + "yf_decoder0,yf_agu,yf_feu") + +(define_insn_reservation "yongfeng_fistp" 5 + (and (eq_attr "cpu" "yongfeng") + (eq_attr "type" "fistp,fisttp")) + "yf_decoder012,yf_agu,yf_feu") + +(define_insn_reservation "yongfeng_fop_mul" 3 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "none,unknown") + (eq_attr "type" "fop,fmul"))) + "yf_decodern,yf_feu") + +(define_insn_reservation "yongfeng_fop_mul_load" 7 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "load,both") + (eq_attr "type" "fop,fmul"))) + "yf_decoder012,yf_agu,yf_feu") + +(define_insn_reservation "yf_fop_store" 3 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "store") + (eq_attr "type" "fop"))) + "yf_decodern,yf_agu,yf_feu") + +(define_insn_reservation "yongfeng_fdiv_fpspc" 14 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "none") + (eq_attr "type" "fdiv,fpspc"))) + "yf_decodern,yf_fdiv*7") + +(define_insn_reservation "yongfeng_fdiv_fpspc_load" 18 + (and (eq_attr "cpu" "yongfeng") + (and (eq_attr "memory" "load") + (eq_attr "type" "fdiv,fpspc"))) + "yf_decoder012,yf_agu,yf_fdiv*7") diff --git a/gcc/doc/extend.texi b/gcc/doc/extend.texi index f5c44bb52b82e..cf0d0c63cce4e 100644 --- a/gcc/doc/extend.texi +++ b/gcc/doc/extend.texi @@ -22724,6 +22724,9 @@ Intel Knights Mill CPU. @item lujiazui ZHAOXIN lujiazui CPU. +@item yongfeng +ZHAOXIN yongfeng CPU. + @item amdfam10h AMD Family 10h CPU. diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi index 5a9284d635ccb..53ae784647bc9 100644 --- a/gcc/doc/invoke.texi +++ b/gcc/doc/invoke.texi @@ -33313,6 +33313,12 @@ ZHAOXIN lujiazui CPU with x86-64, MOVBE, MMX, SSE, SSE2, SSE3, SSSE3, SSE4.1, SSE4.2, AVX, POPCNT, AES, PCLMUL, RDRND, XSAVE, XSAVEOPT, FSGSBASE, CX16, ABM, BMI, BMI2, F16C, FXSR, RDSEED instruction set support. +@item yongfeng +ZHAOXIN yongfeng CPU with x86-64, MOVBE, MMX, SSE, SSE2, SSE3, SSSE3, SSE4.1, +SSE4.2, AVX, POPCNT, AES, PCLMUL, RDRND, XSAVE, XSAVEOPT, FSGSBASE, CX16, +ABM, BMI, BMI2, F16C, FXSR, RDSEED, AVX2, FMA, SHA, LZCNT +instruction set support. + @item geode AMD Geode embedded processor with MMX and 3DNow!@: instruction set support. @end table diff --git a/gcc/testsuite/g++.target/i386/mv32.C b/gcc/testsuite/g++.target/i386/mv32.C index 8f74352eb502f..6c993218d01c3 100644 --- a/gcc/testsuite/g++.target/i386/mv32.C +++ b/gcc/testsuite/g++.target/i386/mv32.C @@ -17,6 +17,9 @@ int __attribute__ ((target("arch=lujiazui"))) foo () { return 1; } +int __attribute__ ((target("arch=yongfeng"))) foo () { + return 2; +} int main () { @@ -24,6 +27,8 @@ int main () if (__builtin_cpu_is ("lujiazui")) assert (val == 1); + else if (__builtin_cpu_is ("yongfeng")) + assert (val == 2); else assert (val == 0); diff --git a/gcc/testsuite/gcc.target/i386/funcspec-56.inc b/gcc/testsuite/gcc.target/i386/funcspec-56.inc index eae6b13cb7847..210da1d1a8a5f 100644 --- a/gcc/testsuite/gcc.target/i386/funcspec-56.inc +++ b/gcc/testsuite/gcc.target/i386/funcspec-56.inc @@ -218,7 +218,8 @@ extern void test_arch_graniterapids_d (void) __attribute__((__target__("arch=gra extern void test_arch_arrowlake (void) __attribute__((__target__("arch=arrowlake"))); extern void test_arch_arrowlake_s (void) __attribute__((__target__("arch=arrowlake-s"))); extern void test_arch_pantherlake (void) __attribute__((__target__("arch=pantherlake"))); -extern void test_arch_lujiazui (void) __attribute__((__target__("arch=lujiazui"))); +extern void test_arch_lujiazui (void) __attribute__((__target__("arch=lujiazui"))); +extern void test_arch_yongfeng (void) __attribute__((__target__("arch=yongfeng"))); extern void test_arch_k8 (void) __attribute__((__target__("arch=k8"))); extern void test_arch_k8_sse3 (void) __attribute__((__target__("arch=k8-sse3"))); extern void test_arch_opteron (void) __attribute__((__target__("arch=opteron"))); @@ -241,7 +242,8 @@ extern void test_tune_core2 (void) __attribute__((__target__("tune=core2"))); extern void test_tune_corei7 (void) __attribute__((__target__("tune=corei7"))); extern void test_tune_corei7_avx (void) __attribute__((__target__("tune=corei7-avx"))); extern void test_tune_core_avx2 (void) __attribute__((__target__("tune=core-avx2"))); -extern void test_tune_lujiazui (void) __attribute__((__target__("tune=lujiazui"))); +extern void test_tune_lujiazui (void) __attribute__((__target__("tune=lujiazui"))); +extern void test_tune_yongfeng (void) __attribute__((__target__("tune=yongfeng"))); extern void test_tune_k8 (void) __attribute__((__target__("tune=k8"))); extern void test_tune_k8_sse3 (void) __attribute__((__target__("tune=k8-sse3"))); extern void test_tune_opteron (void) __attribute__((__target__("tune=opteron")));