forked from OSchip/llvm-project
1477 lines
72 KiB
TableGen
1477 lines
72 KiB
TableGen
//===-- X86.td - Target definition file for the Intel X86 --*- tablegen -*-===//
|
|
//
|
|
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
|
|
// See https://llvm.org/LICENSE.txt for license information.
|
|
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// This is a target description file for the Intel i386 architecture, referred
|
|
// to here as the "X86" architecture.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
// Get the target-independent interfaces which we are implementing...
|
|
//
|
|
include "llvm/Target/Target.td"
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// X86 Subtarget state
|
|
//
|
|
|
|
def Mode64Bit : SubtargetFeature<"64bit-mode", "In64BitMode", "true",
|
|
"64-bit mode (x86_64)">;
|
|
def Mode32Bit : SubtargetFeature<"32bit-mode", "In32BitMode", "true",
|
|
"32-bit mode (80386)">;
|
|
def Mode16Bit : SubtargetFeature<"16bit-mode", "In16BitMode", "true",
|
|
"16-bit mode (i8086)">;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// X86 Subtarget features
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
def FeatureX87 : SubtargetFeature<"x87","HasX87", "true",
|
|
"Enable X87 float instructions">;
|
|
|
|
def FeatureNOPL : SubtargetFeature<"nopl", "HasNOPL", "true",
|
|
"Enable NOPL instruction">;
|
|
|
|
def FeatureCMOV : SubtargetFeature<"cmov","HasCMov", "true",
|
|
"Enable conditional move instructions">;
|
|
|
|
def FeatureCMPXCHG8B : SubtargetFeature<"cx8", "HasCmpxchg8b", "true",
|
|
"Support CMPXCHG8B instructions">;
|
|
|
|
def FeaturePOPCNT : SubtargetFeature<"popcnt", "HasPOPCNT", "true",
|
|
"Support POPCNT instruction">;
|
|
|
|
def FeatureFXSR : SubtargetFeature<"fxsr", "HasFXSR", "true",
|
|
"Support fxsave/fxrestore instructions">;
|
|
|
|
def FeatureXSAVE : SubtargetFeature<"xsave", "HasXSAVE", "true",
|
|
"Support xsave instructions">;
|
|
|
|
def FeatureXSAVEOPT: SubtargetFeature<"xsaveopt", "HasXSAVEOPT", "true",
|
|
"Support xsaveopt instructions",
|
|
[FeatureXSAVE]>;
|
|
|
|
def FeatureXSAVEC : SubtargetFeature<"xsavec", "HasXSAVEC", "true",
|
|
"Support xsavec instructions",
|
|
[FeatureXSAVE]>;
|
|
|
|
def FeatureXSAVES : SubtargetFeature<"xsaves", "HasXSAVES", "true",
|
|
"Support xsaves instructions",
|
|
[FeatureXSAVE]>;
|
|
|
|
def FeatureSSE1 : SubtargetFeature<"sse", "X86SSELevel", "SSE1",
|
|
"Enable SSE instructions">;
|
|
def FeatureSSE2 : SubtargetFeature<"sse2", "X86SSELevel", "SSE2",
|
|
"Enable SSE2 instructions",
|
|
[FeatureSSE1]>;
|
|
def FeatureSSE3 : SubtargetFeature<"sse3", "X86SSELevel", "SSE3",
|
|
"Enable SSE3 instructions",
|
|
[FeatureSSE2]>;
|
|
def FeatureSSSE3 : SubtargetFeature<"ssse3", "X86SSELevel", "SSSE3",
|
|
"Enable SSSE3 instructions",
|
|
[FeatureSSE3]>;
|
|
def FeatureSSE41 : SubtargetFeature<"sse4.1", "X86SSELevel", "SSE41",
|
|
"Enable SSE 4.1 instructions",
|
|
[FeatureSSSE3]>;
|
|
def FeatureSSE42 : SubtargetFeature<"sse4.2", "X86SSELevel", "SSE42",
|
|
"Enable SSE 4.2 instructions",
|
|
[FeatureSSE41]>;
|
|
// The MMX subtarget feature is separate from the rest of the SSE features
|
|
// because it's important (for odd compatibility reasons) to be able to
|
|
// turn it off explicitly while allowing SSE+ to be on.
|
|
def FeatureMMX : SubtargetFeature<"mmx","X863DNowLevel", "MMX",
|
|
"Enable MMX instructions">;
|
|
def Feature3DNow : SubtargetFeature<"3dnow", "X863DNowLevel", "ThreeDNow",
|
|
"Enable 3DNow! instructions",
|
|
[FeatureMMX]>;
|
|
def Feature3DNowA : SubtargetFeature<"3dnowa", "X863DNowLevel", "ThreeDNowA",
|
|
"Enable 3DNow! Athlon instructions",
|
|
[Feature3DNow]>;
|
|
// All x86-64 hardware has SSE2, but we don't mark SSE2 as an implied
|
|
// feature, because SSE2 can be disabled (e.g. for compiling OS kernels)
|
|
// without disabling 64-bit mode. Nothing should imply this feature bit. It
|
|
// is used to enforce that only 64-bit capable CPUs are used in 64-bit mode.
|
|
def Feature64Bit : SubtargetFeature<"64bit", "HasX86_64", "true",
|
|
"Support 64-bit instructions">;
|
|
def FeatureCMPXCHG16B : SubtargetFeature<"cx16", "HasCmpxchg16b", "true",
|
|
"64-bit with cmpxchg16b",
|
|
[FeatureCMPXCHG8B]>;
|
|
def FeatureSlowSHLD : SubtargetFeature<"slow-shld", "IsSHLDSlow", "true",
|
|
"SHLD instruction is slow">;
|
|
def FeatureSlowPMULLD : SubtargetFeature<"slow-pmulld", "IsPMULLDSlow", "true",
|
|
"PMULLD instruction is slow">;
|
|
def FeatureSlowPMADDWD : SubtargetFeature<"slow-pmaddwd", "IsPMADDWDSlow",
|
|
"true",
|
|
"PMADDWD is slower than PMULLD">;
|
|
// FIXME: This should not apply to CPUs that do not have SSE.
|
|
def FeatureSlowUAMem16 : SubtargetFeature<"slow-unaligned-mem-16",
|
|
"IsUAMem16Slow", "true",
|
|
"Slow unaligned 16-byte memory access">;
|
|
def FeatureSlowUAMem32 : SubtargetFeature<"slow-unaligned-mem-32",
|
|
"IsUAMem32Slow", "true",
|
|
"Slow unaligned 32-byte memory access">;
|
|
def FeatureSSE4A : SubtargetFeature<"sse4a", "HasSSE4A", "true",
|
|
"Support SSE 4a instructions",
|
|
[FeatureSSE3]>;
|
|
|
|
def FeatureAVX : SubtargetFeature<"avx", "X86SSELevel", "AVX",
|
|
"Enable AVX instructions",
|
|
[FeatureSSE42]>;
|
|
def FeatureAVX2 : SubtargetFeature<"avx2", "X86SSELevel", "AVX2",
|
|
"Enable AVX2 instructions",
|
|
[FeatureAVX]>;
|
|
def FeatureFMA : SubtargetFeature<"fma", "HasFMA", "true",
|
|
"Enable three-operand fused multiple-add",
|
|
[FeatureAVX]>;
|
|
def FeatureF16C : SubtargetFeature<"f16c", "HasF16C", "true",
|
|
"Support 16-bit floating point conversion instructions",
|
|
[FeatureAVX]>;
|
|
def FeatureAVX512 : SubtargetFeature<"avx512f", "X86SSELevel", "AVX512F",
|
|
"Enable AVX-512 instructions",
|
|
[FeatureAVX2, FeatureFMA, FeatureF16C]>;
|
|
def FeatureERI : SubtargetFeature<"avx512er", "HasERI", "true",
|
|
"Enable AVX-512 Exponential and Reciprocal Instructions",
|
|
[FeatureAVX512]>;
|
|
def FeatureCDI : SubtargetFeature<"avx512cd", "HasCDI", "true",
|
|
"Enable AVX-512 Conflict Detection Instructions",
|
|
[FeatureAVX512]>;
|
|
def FeatureVPOPCNTDQ : SubtargetFeature<"avx512vpopcntdq", "HasVPOPCNTDQ",
|
|
"true", "Enable AVX-512 Population Count Instructions",
|
|
[FeatureAVX512]>;
|
|
def FeaturePFI : SubtargetFeature<"avx512pf", "HasPFI", "true",
|
|
"Enable AVX-512 PreFetch Instructions",
|
|
[FeatureAVX512]>;
|
|
def FeaturePREFETCHWT1 : SubtargetFeature<"prefetchwt1", "HasPREFETCHWT1",
|
|
"true",
|
|
"Prefetch with Intent to Write and T1 Hint">;
|
|
def FeatureDQI : SubtargetFeature<"avx512dq", "HasDQI", "true",
|
|
"Enable AVX-512 Doubleword and Quadword Instructions",
|
|
[FeatureAVX512]>;
|
|
def FeatureBWI : SubtargetFeature<"avx512bw", "HasBWI", "true",
|
|
"Enable AVX-512 Byte and Word Instructions",
|
|
[FeatureAVX512]>;
|
|
def FeatureVLX : SubtargetFeature<"avx512vl", "HasVLX", "true",
|
|
"Enable AVX-512 Vector Length eXtensions",
|
|
[FeatureAVX512]>;
|
|
def FeatureVBMI : SubtargetFeature<"avx512vbmi", "HasVBMI", "true",
|
|
"Enable AVX-512 Vector Byte Manipulation Instructions",
|
|
[FeatureBWI]>;
|
|
def FeatureVBMI2 : SubtargetFeature<"avx512vbmi2", "HasVBMI2", "true",
|
|
"Enable AVX-512 further Vector Byte Manipulation Instructions",
|
|
[FeatureBWI]>;
|
|
def FeatureIFMA : SubtargetFeature<"avx512ifma", "HasIFMA", "true",
|
|
"Enable AVX-512 Integer Fused Multiple-Add",
|
|
[FeatureAVX512]>;
|
|
def FeaturePKU : SubtargetFeature<"pku", "HasPKU", "true",
|
|
"Enable protection keys">;
|
|
def FeatureVNNI : SubtargetFeature<"avx512vnni", "HasVNNI", "true",
|
|
"Enable AVX-512 Vector Neural Network Instructions",
|
|
[FeatureAVX512]>;
|
|
def FeatureAVXVNNI : SubtargetFeature<"avxvnni", "HasAVXVNNI", "true",
|
|
"Support AVX_VNNI encoding",
|
|
[FeatureAVX2]>;
|
|
def FeatureBF16 : SubtargetFeature<"avx512bf16", "HasBF16", "true",
|
|
"Support bfloat16 floating point",
|
|
[FeatureBWI]>;
|
|
def FeatureBITALG : SubtargetFeature<"avx512bitalg", "HasBITALG", "true",
|
|
"Enable AVX-512 Bit Algorithms",
|
|
[FeatureBWI]>;
|
|
def FeatureVP2INTERSECT : SubtargetFeature<"avx512vp2intersect",
|
|
"HasVP2INTERSECT", "true",
|
|
"Enable AVX-512 vp2intersect",
|
|
[FeatureAVX512]>;
|
|
def FeaturePCLMUL : SubtargetFeature<"pclmul", "HasPCLMUL", "true",
|
|
"Enable packed carry-less multiplication instructions",
|
|
[FeatureSSE2]>;
|
|
def FeatureGFNI : SubtargetFeature<"gfni", "HasGFNI", "true",
|
|
"Enable Galois Field Arithmetic Instructions",
|
|
[FeatureSSE2]>;
|
|
def FeatureVPCLMULQDQ : SubtargetFeature<"vpclmulqdq", "HasVPCLMULQDQ", "true",
|
|
"Enable vpclmulqdq instructions",
|
|
[FeatureAVX, FeaturePCLMUL]>;
|
|
def FeatureFMA4 : SubtargetFeature<"fma4", "HasFMA4", "true",
|
|
"Enable four-operand fused multiple-add",
|
|
[FeatureAVX, FeatureSSE4A]>;
|
|
def FeatureXOP : SubtargetFeature<"xop", "HasXOP", "true",
|
|
"Enable XOP instructions",
|
|
[FeatureFMA4]>;
|
|
def FeatureSSEUnalignedMem : SubtargetFeature<"sse-unaligned-mem",
|
|
"HasSSEUnalignedMem", "true",
|
|
"Allow unaligned memory operands with SSE instructions">;
|
|
def FeatureAES : SubtargetFeature<"aes", "HasAES", "true",
|
|
"Enable AES instructions",
|
|
[FeatureSSE2]>;
|
|
def FeatureVAES : SubtargetFeature<"vaes", "HasVAES", "true",
|
|
"Promote selected AES instructions to AVX512/AVX registers",
|
|
[FeatureAVX, FeatureAES]>;
|
|
def FeatureTBM : SubtargetFeature<"tbm", "HasTBM", "true",
|
|
"Enable TBM instructions">;
|
|
def FeatureLWP : SubtargetFeature<"lwp", "HasLWP", "true",
|
|
"Enable LWP instructions">;
|
|
def FeatureMOVBE : SubtargetFeature<"movbe", "HasMOVBE", "true",
|
|
"Support MOVBE instruction">;
|
|
def FeatureRDRAND : SubtargetFeature<"rdrnd", "HasRDRAND", "true",
|
|
"Support RDRAND instruction">;
|
|
def FeatureFSGSBase : SubtargetFeature<"fsgsbase", "HasFSGSBase", "true",
|
|
"Support FS/GS Base instructions">;
|
|
def FeatureLZCNT : SubtargetFeature<"lzcnt", "HasLZCNT", "true",
|
|
"Support LZCNT instruction">;
|
|
def FeatureBMI : SubtargetFeature<"bmi", "HasBMI", "true",
|
|
"Support BMI instructions">;
|
|
def FeatureBMI2 : SubtargetFeature<"bmi2", "HasBMI2", "true",
|
|
"Support BMI2 instructions">;
|
|
def FeatureRTM : SubtargetFeature<"rtm", "HasRTM", "true",
|
|
"Support RTM instructions">;
|
|
def FeatureADX : SubtargetFeature<"adx", "HasADX", "true",
|
|
"Support ADX instructions">;
|
|
def FeatureSHA : SubtargetFeature<"sha", "HasSHA", "true",
|
|
"Enable SHA instructions",
|
|
[FeatureSSE2]>;
|
|
def FeatureSHSTK : SubtargetFeature<"shstk", "HasSHSTK", "true",
|
|
"Support CET Shadow-Stack instructions">;
|
|
def FeaturePRFCHW : SubtargetFeature<"prfchw", "HasPRFCHW", "true",
|
|
"Support PRFCHW instructions">;
|
|
def FeatureRDSEED : SubtargetFeature<"rdseed", "HasRDSEED", "true",
|
|
"Support RDSEED instruction">;
|
|
def FeatureLAHFSAHF : SubtargetFeature<"sahf", "HasLAHFSAHF64", "true",
|
|
"Support LAHF and SAHF instructions in 64-bit mode">;
|
|
def FeatureMWAITX : SubtargetFeature<"mwaitx", "HasMWAITX", "true",
|
|
"Enable MONITORX/MWAITX timer functionality">;
|
|
def FeatureCLZERO : SubtargetFeature<"clzero", "HasCLZERO", "true",
|
|
"Enable Cache Line Zero">;
|
|
def FeatureCLDEMOTE : SubtargetFeature<"cldemote", "HasCLDEMOTE", "true",
|
|
"Enable Cache Demote">;
|
|
def FeaturePTWRITE : SubtargetFeature<"ptwrite", "HasPTWRITE", "true",
|
|
"Support ptwrite instruction">;
|
|
def FeatureAMXTILE : SubtargetFeature<"amx-tile", "HasAMXTILE", "true",
|
|
"Support AMX-TILE instructions">;
|
|
def FeatureAMXINT8 : SubtargetFeature<"amx-int8", "HasAMXINT8", "true",
|
|
"Support AMX-INT8 instructions",
|
|
[FeatureAMXTILE]>;
|
|
def FeatureAMXBF16 : SubtargetFeature<"amx-bf16", "HasAMXBF16", "true",
|
|
"Support AMX-BF16 instructions",
|
|
[FeatureAMXTILE]>;
|
|
def FeatureLEAForSP : SubtargetFeature<"lea-sp", "UseLeaForSP", "true",
|
|
"Use LEA for adjusting the stack pointer">;
|
|
def FeatureSlowDivide32 : SubtargetFeature<"idivl-to-divb",
|
|
"HasSlowDivide32", "true",
|
|
"Use 8-bit divide for positive values less than 256">;
|
|
def FeatureSlowDivide64 : SubtargetFeature<"idivq-to-divl",
|
|
"HasSlowDivide64", "true",
|
|
"Use 32-bit divide for positive values less than 2^32">;
|
|
def FeaturePadShortFunctions : SubtargetFeature<"pad-short-functions",
|
|
"PadShortFunctions", "true",
|
|
"Pad short functions">;
|
|
def FeatureINVPCID : SubtargetFeature<"invpcid", "HasINVPCID", "true",
|
|
"Invalidate Process-Context Identifier">;
|
|
def FeatureSGX : SubtargetFeature<"sgx", "HasSGX", "true",
|
|
"Enable Software Guard Extensions">;
|
|
def FeatureCLFLUSHOPT : SubtargetFeature<"clflushopt", "HasCLFLUSHOPT", "true",
|
|
"Flush A Cache Line Optimized">;
|
|
def FeatureCLWB : SubtargetFeature<"clwb", "HasCLWB", "true",
|
|
"Cache Line Write Back">;
|
|
def FeatureWBNOINVD : SubtargetFeature<"wbnoinvd", "HasWBNOINVD", "true",
|
|
"Write Back No Invalidate">;
|
|
def FeatureRDPID : SubtargetFeature<"rdpid", "HasRDPID", "true",
|
|
"Support RDPID instructions">;
|
|
def FeatureWAITPKG : SubtargetFeature<"waitpkg", "HasWAITPKG", "true",
|
|
"Wait and pause enhancements">;
|
|
def FeatureENQCMD : SubtargetFeature<"enqcmd", "HasENQCMD", "true",
|
|
"Has ENQCMD instructions">;
|
|
def FeatureKL : SubtargetFeature<"kl", "HasKL", "true",
|
|
"Support Key Locker kl Instructions",
|
|
[FeatureSSE2]>;
|
|
def FeatureWIDEKL : SubtargetFeature<"widekl", "HasWIDEKL", "true",
|
|
"Support Key Locker wide Instructions",
|
|
[FeatureKL]>;
|
|
def FeatureHRESET : SubtargetFeature<"hreset", "HasHRESET", "true",
|
|
"Has hreset instruction">;
|
|
def FeatureSERIALIZE : SubtargetFeature<"serialize", "HasSERIALIZE", "true",
|
|
"Has serialize instruction">;
|
|
def FeatureTSXLDTRK : SubtargetFeature<"tsxldtrk", "HasTSXLDTRK", "true",
|
|
"Support TSXLDTRK instructions">;
|
|
def FeatureUINTR : SubtargetFeature<"uintr", "HasUINTR", "true",
|
|
"Has UINTR Instructions">;
|
|
// On some processors, instructions that implicitly take two memory operands are
|
|
// slow. In practice, this means that CALL, PUSH, and POP with memory operands
|
|
// should be avoided in favor of a MOV + register CALL/PUSH/POP.
|
|
def FeatureSlowTwoMemOps : SubtargetFeature<"slow-two-mem-ops",
|
|
"SlowTwoMemOps", "true",
|
|
"Two memory operand instructions are slow">;
|
|
def FeatureLEAUsesAG : SubtargetFeature<"lea-uses-ag", "LEAUsesAG", "true",
|
|
"LEA instruction needs inputs at AG stage">;
|
|
def FeatureSlowLEA : SubtargetFeature<"slow-lea", "SlowLEA", "true",
|
|
"LEA instruction with certain arguments is slow">;
|
|
def FeatureSlow3OpsLEA : SubtargetFeature<"slow-3ops-lea", "Slow3OpsLEA", "true",
|
|
"LEA instruction with 3 ops or certain registers is slow">;
|
|
def FeatureSlowIncDec : SubtargetFeature<"slow-incdec", "SlowIncDec", "true",
|
|
"INC and DEC instructions are slower than ADD and SUB">;
|
|
def FeatureSoftFloat
|
|
: SubtargetFeature<"soft-float", "UseSoftFloat", "true",
|
|
"Use software floating point features">;
|
|
def FeaturePOPCNTFalseDeps : SubtargetFeature<"false-deps-popcnt",
|
|
"HasPOPCNTFalseDeps", "true",
|
|
"POPCNT has a false dependency on dest register">;
|
|
def FeatureLZCNTFalseDeps : SubtargetFeature<"false-deps-lzcnt-tzcnt",
|
|
"HasLZCNTFalseDeps", "true",
|
|
"LZCNT/TZCNT have a false dependency on dest register">;
|
|
def FeaturePCONFIG : SubtargetFeature<"pconfig", "HasPCONFIG", "true",
|
|
"platform configuration instruction">;
|
|
// On recent X86 (port bound) processors, its preferable to combine to a single shuffle
|
|
// using a variable mask over multiple fixed shuffles.
|
|
def FeatureFastVariableShuffle
|
|
: SubtargetFeature<"fast-variable-shuffle",
|
|
"HasFastVariableShuffle",
|
|
"true", "Shuffles with variable masks are fast">;
|
|
// On some X86 processors, a vzeroupper instruction should be inserted after
|
|
// using ymm/zmm registers before executing code that may use SSE instructions.
|
|
def FeatureInsertVZEROUPPER
|
|
: SubtargetFeature<"vzeroupper",
|
|
"InsertVZEROUPPER",
|
|
"true", "Should insert vzeroupper instructions">;
|
|
// FeatureFastScalarFSQRT should be enabled if scalar FSQRT has shorter latency
|
|
// than the corresponding NR code. FeatureFastVectorFSQRT should be enabled if
|
|
// vector FSQRT has higher throughput than the corresponding NR code.
|
|
// The idea is that throughput bound code is likely to be vectorized, so for
|
|
// vectorized code we should care about the throughput of SQRT operations.
|
|
// But if the code is scalar that probably means that the code has some kind of
|
|
// dependency and we should care more about reducing the latency.
|
|
def FeatureFastScalarFSQRT
|
|
: SubtargetFeature<"fast-scalar-fsqrt", "HasFastScalarFSQRT",
|
|
"true", "Scalar SQRT is fast (disable Newton-Raphson)">;
|
|
def FeatureFastVectorFSQRT
|
|
: SubtargetFeature<"fast-vector-fsqrt", "HasFastVectorFSQRT",
|
|
"true", "Vector SQRT is fast (disable Newton-Raphson)">;
|
|
// If lzcnt has equivalent latency/throughput to most simple integer ops, it can
|
|
// be used to replace test/set sequences.
|
|
def FeatureFastLZCNT
|
|
: SubtargetFeature<
|
|
"fast-lzcnt", "HasFastLZCNT", "true",
|
|
"LZCNT instructions are as fast as most simple integer ops">;
|
|
// If the target can efficiently decode NOPs upto 7-bytes in length.
|
|
def FeatureFast7ByteNOP
|
|
: SubtargetFeature<
|
|
"fast-7bytenop", "HasFast7ByteNOP", "true",
|
|
"Target can quickly decode up to 7 byte NOPs">;
|
|
// If the target can efficiently decode NOPs upto 11-bytes in length.
|
|
def FeatureFast11ByteNOP
|
|
: SubtargetFeature<
|
|
"fast-11bytenop", "HasFast11ByteNOP", "true",
|
|
"Target can quickly decode up to 11 byte NOPs">;
|
|
// If the target can efficiently decode NOPs upto 15-bytes in length.
|
|
def FeatureFast15ByteNOP
|
|
: SubtargetFeature<
|
|
"fast-15bytenop", "HasFast15ByteNOP", "true",
|
|
"Target can quickly decode up to 15 byte NOPs">;
|
|
// Sandy Bridge and newer processors can use SHLD with the same source on both
|
|
// inputs to implement rotate to avoid the partial flag update of the normal
|
|
// rotate instructions.
|
|
def FeatureFastSHLDRotate
|
|
: SubtargetFeature<
|
|
"fast-shld-rotate", "HasFastSHLDRotate", "true",
|
|
"SHLD can be used as a faster rotate">;
|
|
|
|
// Ivy Bridge and newer processors have enhanced REP MOVSB and STOSB (aka
|
|
// "string operations"). See "REP String Enhancement" in the Intel Software
|
|
// Development Manual. This feature essentially means that REP MOVSB will copy
|
|
// using the largest available size instead of copying bytes one by one, making
|
|
// it at least as fast as REPMOVS{W,D,Q}.
|
|
def FeatureERMSB
|
|
: SubtargetFeature<
|
|
"ermsb", "HasERMSB", "true",
|
|
"REP MOVS/STOS are fast">;
|
|
|
|
// Icelake and newer processors have Fast Short REP MOV.
|
|
def FeatureFSRM
|
|
: SubtargetFeature<
|
|
"fsrm", "HasFSRM", "true",
|
|
"REP MOVSB of short lengths is faster">;
|
|
|
|
// Bulldozer and newer processors can merge CMP/TEST (but not other
|
|
// instructions) with conditional branches.
|
|
def FeatureBranchFusion
|
|
: SubtargetFeature<"branchfusion", "HasBranchFusion", "true",
|
|
"CMP/TEST can be fused with conditional branches">;
|
|
|
|
// Sandy Bridge and newer processors have many instructions that can be
|
|
// fused with conditional branches and pass through the CPU as a single
|
|
// operation.
|
|
def FeatureMacroFusion
|
|
: SubtargetFeature<"macrofusion", "HasMacroFusion", "true",
|
|
"Various instructions can be fused with conditional branches">;
|
|
|
|
// Gather is available since Haswell (AVX2 set). So technically, we can
|
|
// generate Gathers on all AVX2 processors. But the overhead on HSW is high.
|
|
// Skylake Client processor has faster Gathers than HSW and performance is
|
|
// similar to Skylake Server (AVX-512).
|
|
def FeatureHasFastGather
|
|
: SubtargetFeature<"fast-gather", "HasFastGather", "true",
|
|
"Indicates if gather is reasonably fast">;
|
|
|
|
def FeaturePrefer128Bit
|
|
: SubtargetFeature<"prefer-128-bit", "Prefer128Bit", "true",
|
|
"Prefer 128-bit AVX instructions">;
|
|
|
|
def FeaturePrefer256Bit
|
|
: SubtargetFeature<"prefer-256-bit", "Prefer256Bit", "true",
|
|
"Prefer 256-bit AVX instructions">;
|
|
|
|
def FeaturePreferMaskRegisters
|
|
: SubtargetFeature<"prefer-mask-registers", "PreferMaskRegisters", "true",
|
|
"Prefer AVX512 mask registers over PTEST/MOVMSK">;
|
|
|
|
// Lower indirect calls using a special construct called a `retpoline` to
|
|
// mitigate potential Spectre v2 attacks against them.
|
|
def FeatureRetpolineIndirectCalls
|
|
: SubtargetFeature<
|
|
"retpoline-indirect-calls", "UseRetpolineIndirectCalls", "true",
|
|
"Remove speculation of indirect calls from the generated code">;
|
|
|
|
// Lower indirect branches and switches either using conditional branch trees
|
|
// or using a special construct called a `retpoline` to mitigate potential
|
|
// Spectre v2 attacks against them.
|
|
def FeatureRetpolineIndirectBranches
|
|
: SubtargetFeature<
|
|
"retpoline-indirect-branches", "UseRetpolineIndirectBranches", "true",
|
|
"Remove speculation of indirect branches from the generated code">;
|
|
|
|
// Deprecated umbrella feature for enabling both `retpoline-indirect-calls` and
|
|
// `retpoline-indirect-branches` above.
|
|
def FeatureRetpoline
|
|
: SubtargetFeature<"retpoline", "DeprecatedUseRetpoline", "true",
|
|
"Remove speculation of indirect branches from the "
|
|
"generated code, either by avoiding them entirely or "
|
|
"lowering them with a speculation blocking construct",
|
|
[FeatureRetpolineIndirectCalls,
|
|
FeatureRetpolineIndirectBranches]>;
|
|
|
|
// Rely on external thunks for the emitted retpoline calls. This allows users
|
|
// to provide their own custom thunk definitions in highly specialized
|
|
// environments such as a kernel that does boot-time hot patching.
|
|
def FeatureRetpolineExternalThunk
|
|
: SubtargetFeature<
|
|
"retpoline-external-thunk", "UseRetpolineExternalThunk", "true",
|
|
"When lowering an indirect call or branch using a `retpoline`, rely "
|
|
"on the specified user provided thunk rather than emitting one "
|
|
"ourselves. Only has effect when combined with some other retpoline "
|
|
"feature", [FeatureRetpolineIndirectCalls]>;
|
|
|
|
// Mitigate LVI attacks against indirect calls/branches and call returns
|
|
def FeatureLVIControlFlowIntegrity
|
|
: SubtargetFeature<
|
|
"lvi-cfi", "UseLVIControlFlowIntegrity", "true",
|
|
"Prevent indirect calls/branches from using a memory operand, and "
|
|
"precede all indirect calls/branches from a register with an "
|
|
"LFENCE instruction to serialize control flow. Also decompose RET "
|
|
"instructions into a POP+LFENCE+JMP sequence.">;
|
|
|
|
// Enable SESES to mitigate speculative execution attacks
|
|
def FeatureSpeculativeExecutionSideEffectSuppression
|
|
: SubtargetFeature<
|
|
"seses", "UseSpeculativeExecutionSideEffectSuppression", "true",
|
|
"Prevent speculative execution side channel timing attacks by "
|
|
"inserting a speculation barrier before memory reads, memory writes, "
|
|
"and conditional branches. Implies LVI Control Flow integrity.",
|
|
[FeatureLVIControlFlowIntegrity]>;
|
|
|
|
// Mitigate LVI attacks against data loads
|
|
def FeatureLVILoadHardening
|
|
: SubtargetFeature<
|
|
"lvi-load-hardening", "UseLVILoadHardening", "true",
|
|
"Insert LFENCE instructions to prevent data speculatively injected "
|
|
"into loads from being used maliciously.">;
|
|
|
|
// Direct Move instructions.
|
|
def FeatureMOVDIRI : SubtargetFeature<"movdiri", "HasMOVDIRI", "true",
|
|
"Support movdiri instruction">;
|
|
def FeatureMOVDIR64B : SubtargetFeature<"movdir64b", "HasMOVDIR64B", "true",
|
|
"Support movdir64b instruction">;
|
|
|
|
def FeatureFastBEXTR : SubtargetFeature<"fast-bextr", "HasFastBEXTR", "true",
|
|
"Indicates that the BEXTR instruction is implemented as a single uop "
|
|
"with good throughput">;
|
|
|
|
// Combine vector math operations with shuffles into horizontal math
|
|
// instructions if a CPU implements horizontal operations (introduced with
|
|
// SSE3) with better latency/throughput than the alternative sequence.
|
|
def FeatureFastHorizontalOps
|
|
: SubtargetFeature<
|
|
"fast-hops", "HasFastHorizontalOps", "true",
|
|
"Prefer horizontal vector math instructions (haddp, phsub, etc.) over "
|
|
"normal vector instructions with shuffles">;
|
|
|
|
def FeatureFastScalarShiftMasks
|
|
: SubtargetFeature<
|
|
"fast-scalar-shift-masks", "HasFastScalarShiftMasks", "true",
|
|
"Prefer a left/right scalar logical shift pair over a shift+and pair">;
|
|
|
|
def FeatureFastVectorShiftMasks
|
|
: SubtargetFeature<
|
|
"fast-vector-shift-masks", "HasFastVectorShiftMasks", "true",
|
|
"Prefer a left/right vector logical shift pair over a shift+and pair">;
|
|
|
|
def FeatureUseGLMDivSqrtCosts
|
|
: SubtargetFeature<"use-glm-div-sqrt-costs", "UseGLMDivSqrtCosts", "true",
|
|
"Use Goldmont specific floating point div/sqrt costs">;
|
|
|
|
// Enable use of alias analysis during code generation.
|
|
def FeatureUseAA : SubtargetFeature<"use-aa", "UseAA", "true",
|
|
"Use alias analysis during codegen">;
|
|
|
|
// Bonnell
|
|
def ProcIntelAtom : SubtargetFeature<"", "X86ProcFamily", "IntelAtom", "">;
|
|
// Silvermont
|
|
def ProcIntelSLM : SubtargetFeature<"", "X86ProcFamily", "IntelSLM", "">;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Register File Description
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
include "X86RegisterInfo.td"
|
|
include "X86RegisterBanks.td"
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Instruction Descriptions
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
include "X86Schedule.td"
|
|
include "X86InstrInfo.td"
|
|
include "X86SchedPredicates.td"
|
|
|
|
def X86InstrInfo : InstrInfo;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// X86 Scheduler Models
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
include "X86ScheduleAtom.td"
|
|
include "X86SchedSandyBridge.td"
|
|
include "X86SchedHaswell.td"
|
|
include "X86SchedBroadwell.td"
|
|
include "X86ScheduleSLM.td"
|
|
include "X86ScheduleZnver1.td"
|
|
include "X86ScheduleZnver2.td"
|
|
include "X86ScheduleBdVer2.td"
|
|
include "X86ScheduleBtVer2.td"
|
|
include "X86SchedSkylakeClient.td"
|
|
include "X86SchedSkylakeServer.td"
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// X86 Processor Feature Lists
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
def ProcessorFeatures {
|
|
// x86-64 and x86-64-v[234]
|
|
list<SubtargetFeature> X86_64V1Features = [
|
|
FeatureX87, FeatureCMPXCHG8B, FeatureCMOV, FeatureMMX, FeatureSSE2,
|
|
FeatureFXSR, FeatureNOPL, Feature64Bit
|
|
];
|
|
list<SubtargetFeature> X86_64V2Features = !listconcat(
|
|
X86_64V1Features,
|
|
[FeatureCMPXCHG16B, FeatureLAHFSAHF, FeaturePOPCNT, FeatureSSE42]);
|
|
list<SubtargetFeature> X86_64V3Features = !listconcat(X86_64V2Features, [
|
|
FeatureAVX2, FeatureBMI, FeatureBMI2, FeatureF16C, FeatureFMA, FeatureLZCNT,
|
|
FeatureMOVBE, FeatureXSAVE
|
|
]);
|
|
list<SubtargetFeature> X86_64V4Features = !listconcat(X86_64V3Features, [
|
|
FeatureBWI,
|
|
FeatureCDI,
|
|
FeatureDQI,
|
|
FeatureVLX,
|
|
]);
|
|
|
|
// Nehalem
|
|
list<SubtargetFeature> NHMFeatures = X86_64V2Features;
|
|
list<SubtargetFeature> NHMTuning = [FeatureMacroFusion,
|
|
FeatureInsertVZEROUPPER];
|
|
|
|
// Westmere
|
|
list<SubtargetFeature> WSMAdditionalFeatures = [FeaturePCLMUL];
|
|
list<SubtargetFeature> WSMTuning = NHMTuning;
|
|
list<SubtargetFeature> WSMFeatures =
|
|
!listconcat(NHMFeatures, WSMAdditionalFeatures);
|
|
|
|
// Sandybridge
|
|
list<SubtargetFeature> SNBAdditionalFeatures = [FeatureAVX,
|
|
FeatureXSAVE,
|
|
FeatureXSAVEOPT];
|
|
list<SubtargetFeature> SNBTuning = [FeatureMacroFusion,
|
|
FeatureSlow3OpsLEA,
|
|
FeatureSlowDivide64,
|
|
FeatureSlowUAMem32,
|
|
FeatureFastScalarFSQRT,
|
|
FeatureFastSHLDRotate,
|
|
FeatureFast15ByteNOP,
|
|
FeaturePOPCNTFalseDeps,
|
|
FeatureInsertVZEROUPPER];
|
|
list<SubtargetFeature> SNBFeatures =
|
|
!listconcat(WSMFeatures, SNBAdditionalFeatures);
|
|
|
|
// Ivybridge
|
|
list<SubtargetFeature> IVBAdditionalFeatures = [FeatureRDRAND,
|
|
FeatureF16C,
|
|
FeatureFSGSBase];
|
|
list<SubtargetFeature> IVBTuning = SNBTuning;
|
|
list<SubtargetFeature> IVBFeatures =
|
|
!listconcat(SNBFeatures, IVBAdditionalFeatures);
|
|
|
|
// Haswell
|
|
list<SubtargetFeature> HSWAdditionalFeatures = [FeatureAVX2,
|
|
FeatureBMI,
|
|
FeatureBMI2,
|
|
FeatureERMSB,
|
|
FeatureFMA,
|
|
FeatureINVPCID,
|
|
FeatureLZCNT,
|
|
FeatureMOVBE];
|
|
list<SubtargetFeature> HSWTuning = [FeatureMacroFusion,
|
|
FeatureSlow3OpsLEA,
|
|
FeatureSlowDivide64,
|
|
FeatureFastScalarFSQRT,
|
|
FeatureFastSHLDRotate,
|
|
FeatureFast15ByteNOP,
|
|
FeatureFastVariableShuffle,
|
|
FeaturePOPCNTFalseDeps,
|
|
FeatureLZCNTFalseDeps,
|
|
FeatureInsertVZEROUPPER];
|
|
list<SubtargetFeature> HSWFeatures =
|
|
!listconcat(IVBFeatures, HSWAdditionalFeatures);
|
|
|
|
// Broadwell
|
|
list<SubtargetFeature> BDWAdditionalFeatures = [FeatureADX,
|
|
FeatureRDSEED,
|
|
FeaturePRFCHW];
|
|
list<SubtargetFeature> BDWTuning = HSWTuning;
|
|
list<SubtargetFeature> BDWFeatures =
|
|
!listconcat(HSWFeatures, BDWAdditionalFeatures);
|
|
|
|
// Skylake
|
|
list<SubtargetFeature> SKLAdditionalFeatures = [FeatureAES,
|
|
FeatureXSAVEC,
|
|
FeatureXSAVES,
|
|
FeatureCLFLUSHOPT,
|
|
FeatureSGX];
|
|
list<SubtargetFeature> SKLTuning = [FeatureHasFastGather,
|
|
FeatureMacroFusion,
|
|
FeatureSlow3OpsLEA,
|
|
FeatureSlowDivide64,
|
|
FeatureFastScalarFSQRT,
|
|
FeatureFastVectorFSQRT,
|
|
FeatureFastSHLDRotate,
|
|
FeatureFast15ByteNOP,
|
|
FeatureFastVariableShuffle,
|
|
FeaturePOPCNTFalseDeps,
|
|
FeatureInsertVZEROUPPER];
|
|
list<SubtargetFeature> SKLFeatures =
|
|
!listconcat(BDWFeatures, SKLAdditionalFeatures);
|
|
|
|
// Skylake-AVX512
|
|
list<SubtargetFeature> SKXAdditionalFeatures = [FeatureAES,
|
|
FeatureXSAVEC,
|
|
FeatureXSAVES,
|
|
FeatureCLFLUSHOPT,
|
|
FeatureAVX512,
|
|
FeatureCDI,
|
|
FeatureDQI,
|
|
FeatureBWI,
|
|
FeatureVLX,
|
|
FeaturePKU,
|
|
FeatureCLWB];
|
|
list<SubtargetFeature> SKXTuning = [FeatureHasFastGather,
|
|
FeatureMacroFusion,
|
|
FeatureSlow3OpsLEA,
|
|
FeatureSlowDivide64,
|
|
FeatureFastScalarFSQRT,
|
|
FeatureFastVectorFSQRT,
|
|
FeatureFastSHLDRotate,
|
|
FeatureFast15ByteNOP,
|
|
FeatureFastVariableShuffle,
|
|
FeaturePrefer256Bit,
|
|
FeaturePOPCNTFalseDeps,
|
|
FeatureInsertVZEROUPPER];
|
|
list<SubtargetFeature> SKXFeatures =
|
|
!listconcat(BDWFeatures, SKXAdditionalFeatures);
|
|
|
|
// Cascadelake
|
|
list<SubtargetFeature> CLXAdditionalFeatures = [FeatureVNNI];
|
|
list<SubtargetFeature> CLXTuning = SKXTuning;
|
|
list<SubtargetFeature> CLXFeatures =
|
|
!listconcat(SKXFeatures, CLXAdditionalFeatures);
|
|
|
|
// Cooperlake
|
|
list<SubtargetFeature> CPXAdditionalFeatures = [FeatureBF16];
|
|
list<SubtargetFeature> CPXTuning = SKXTuning;
|
|
list<SubtargetFeature> CPXFeatures =
|
|
!listconcat(CLXFeatures, CPXAdditionalFeatures);
|
|
|
|
// Cannonlake
|
|
list<SubtargetFeature> CNLAdditionalFeatures = [FeatureAVX512,
|
|
FeatureCDI,
|
|
FeatureDQI,
|
|
FeatureBWI,
|
|
FeatureVLX,
|
|
FeaturePKU,
|
|
FeatureVBMI,
|
|
FeatureIFMA,
|
|
FeatureSHA];
|
|
list<SubtargetFeature> CNLTuning = [FeatureHasFastGather,
|
|
FeatureMacroFusion,
|
|
FeatureSlow3OpsLEA,
|
|
FeatureSlowDivide64,
|
|
FeatureFastScalarFSQRT,
|
|
FeatureFastVectorFSQRT,
|
|
FeatureFastSHLDRotate,
|
|
FeatureFast15ByteNOP,
|
|
FeatureFastVariableShuffle,
|
|
FeaturePrefer256Bit,
|
|
FeatureInsertVZEROUPPER];
|
|
list<SubtargetFeature> CNLFeatures =
|
|
!listconcat(SKLFeatures, CNLAdditionalFeatures);
|
|
|
|
// Icelake
|
|
list<SubtargetFeature> ICLAdditionalFeatures = [FeatureBITALG,
|
|
FeatureVAES,
|
|
FeatureVBMI2,
|
|
FeatureVNNI,
|
|
FeatureVPCLMULQDQ,
|
|
FeatureVPOPCNTDQ,
|
|
FeatureGFNI,
|
|
FeatureCLWB,
|
|
FeatureRDPID,
|
|
FeatureFSRM];
|
|
list<SubtargetFeature> ICLTuning = CNLTuning;
|
|
list<SubtargetFeature> ICLFeatures =
|
|
!listconcat(CNLFeatures, ICLAdditionalFeatures);
|
|
|
|
// Icelake Server
|
|
list<SubtargetFeature> ICXAdditionalFeatures = [FeaturePCONFIG,
|
|
FeatureWBNOINVD];
|
|
list<SubtargetFeature> ICXTuning = CNLTuning;
|
|
list<SubtargetFeature> ICXFeatures =
|
|
!listconcat(ICLFeatures, ICXAdditionalFeatures);
|
|
|
|
//Tigerlake
|
|
list<SubtargetFeature> TGLAdditionalFeatures = [FeatureVP2INTERSECT,
|
|
FeatureMOVDIRI,
|
|
FeatureMOVDIR64B,
|
|
FeatureSHSTK];
|
|
list<SubtargetFeature> TGLTuning = CNLTuning;
|
|
list<SubtargetFeature> TGLFeatures =
|
|
!listconcat(ICLFeatures, TGLAdditionalFeatures );
|
|
|
|
//Sapphirerapids
|
|
list<SubtargetFeature> SPRAdditionalFeatures = [FeatureAMXTILE,
|
|
FeatureAMXINT8,
|
|
FeatureAMXBF16,
|
|
FeatureBF16,
|
|
FeatureSERIALIZE,
|
|
FeatureCLDEMOTE,
|
|
FeatureWAITPKG,
|
|
FeaturePTWRITE,
|
|
FeatureAVXVNNI,
|
|
FeatureTSXLDTRK,
|
|
FeatureENQCMD,
|
|
FeatureSHSTK,
|
|
FeatureVP2INTERSECT,
|
|
FeatureMOVDIRI,
|
|
FeatureMOVDIR64B,
|
|
FeatureUINTR];
|
|
list<SubtargetFeature> SPRTuning = ICXTuning;
|
|
list<SubtargetFeature> SPRFeatures =
|
|
!listconcat(ICXFeatures, SPRAdditionalFeatures);
|
|
|
|
// Alderlake
|
|
list<SubtargetFeature> ADLAdditionalFeatures = [FeatureAVXVNNI,
|
|
FeatureCLDEMOTE,
|
|
FeatureHRESET,
|
|
FeaturePTWRITE,
|
|
FeatureSERIALIZE,
|
|
FeatureWAITPKG];
|
|
list<SubtargetFeature> ADLTuning = SKLTuning;
|
|
list<SubtargetFeature> ADLFeatures =
|
|
!listconcat(SKLFeatures, ADLAdditionalFeatures);
|
|
|
|
// Atom
|
|
list<SubtargetFeature> AtomFeatures = [FeatureX87,
|
|
FeatureCMPXCHG8B,
|
|
FeatureCMOV,
|
|
FeatureMMX,
|
|
FeatureSSSE3,
|
|
FeatureFXSR,
|
|
FeatureNOPL,
|
|
Feature64Bit,
|
|
FeatureCMPXCHG16B,
|
|
FeatureMOVBE,
|
|
FeatureLAHFSAHF];
|
|
list<SubtargetFeature> AtomTuning = [ProcIntelAtom,
|
|
FeatureSlowUAMem16,
|
|
FeatureLEAForSP,
|
|
FeatureSlowDivide32,
|
|
FeatureSlowDivide64,
|
|
FeatureSlowTwoMemOps,
|
|
FeatureLEAUsesAG,
|
|
FeaturePadShortFunctions,
|
|
FeatureInsertVZEROUPPER];
|
|
|
|
// Silvermont
|
|
list<SubtargetFeature> SLMAdditionalFeatures = [FeatureSSE42,
|
|
FeaturePOPCNT,
|
|
FeaturePCLMUL,
|
|
FeaturePRFCHW,
|
|
FeatureRDRAND];
|
|
list<SubtargetFeature> SLMTuning = [ProcIntelSLM,
|
|
FeatureSlowTwoMemOps,
|
|
FeatureSlowLEA,
|
|
FeatureSlowIncDec,
|
|
FeatureSlowDivide64,
|
|
FeatureSlowPMULLD,
|
|
FeatureFast7ByteNOP,
|
|
FeaturePOPCNTFalseDeps,
|
|
FeatureInsertVZEROUPPER];
|
|
list<SubtargetFeature> SLMFeatures =
|
|
!listconcat(AtomFeatures, SLMAdditionalFeatures);
|
|
|
|
// Goldmont
|
|
list<SubtargetFeature> GLMAdditionalFeatures = [FeatureAES,
|
|
FeatureSHA,
|
|
FeatureRDSEED,
|
|
FeatureXSAVE,
|
|
FeatureXSAVEOPT,
|
|
FeatureXSAVEC,
|
|
FeatureXSAVES,
|
|
FeatureCLFLUSHOPT,
|
|
FeatureFSGSBase];
|
|
list<SubtargetFeature> GLMTuning = [FeatureUseGLMDivSqrtCosts,
|
|
FeatureSlowTwoMemOps,
|
|
FeatureSlowLEA,
|
|
FeatureSlowIncDec,
|
|
FeaturePOPCNTFalseDeps,
|
|
FeatureInsertVZEROUPPER];
|
|
list<SubtargetFeature> GLMFeatures =
|
|
!listconcat(SLMFeatures, GLMAdditionalFeatures);
|
|
|
|
// Goldmont Plus
|
|
list<SubtargetFeature> GLPAdditionalFeatures = [FeaturePTWRITE,
|
|
FeatureRDPID,
|
|
FeatureSGX];
|
|
list<SubtargetFeature> GLPTuning = [FeatureUseGLMDivSqrtCosts,
|
|
FeatureSlowTwoMemOps,
|
|
FeatureSlowLEA,
|
|
FeatureSlowIncDec,
|
|
FeatureInsertVZEROUPPER];
|
|
list<SubtargetFeature> GLPFeatures =
|
|
!listconcat(GLMFeatures, GLPAdditionalFeatures);
|
|
|
|
// Tremont
|
|
list<SubtargetFeature> TRMAdditionalFeatures = [FeatureCLWB,
|
|
FeatureGFNI];
|
|
list<SubtargetFeature> TRMTuning = GLPTuning;
|
|
list<SubtargetFeature> TRMFeatures =
|
|
!listconcat(GLPFeatures, TRMAdditionalFeatures);
|
|
|
|
// Knights Landing
|
|
list<SubtargetFeature> KNLFeatures = [FeatureX87,
|
|
FeatureCMPXCHG8B,
|
|
FeatureCMOV,
|
|
FeatureMMX,
|
|
FeatureFXSR,
|
|
FeatureNOPL,
|
|
Feature64Bit,
|
|
FeatureCMPXCHG16B,
|
|
FeaturePOPCNT,
|
|
FeaturePCLMUL,
|
|
FeatureXSAVE,
|
|
FeatureXSAVEOPT,
|
|
FeatureLAHFSAHF,
|
|
FeatureAES,
|
|
FeatureRDRAND,
|
|
FeatureF16C,
|
|
FeatureFSGSBase,
|
|
FeatureAVX512,
|
|
FeatureERI,
|
|
FeatureCDI,
|
|
FeaturePFI,
|
|
FeaturePREFETCHWT1,
|
|
FeatureADX,
|
|
FeatureRDSEED,
|
|
FeatureMOVBE,
|
|
FeatureLZCNT,
|
|
FeatureBMI,
|
|
FeatureBMI2,
|
|
FeatureFMA,
|
|
FeaturePRFCHW];
|
|
list<SubtargetFeature> KNLTuning = [FeatureSlowDivide64,
|
|
FeatureSlow3OpsLEA,
|
|
FeatureSlowIncDec,
|
|
FeatureSlowTwoMemOps,
|
|
FeaturePreferMaskRegisters,
|
|
FeatureHasFastGather,
|
|
FeatureSlowPMADDWD];
|
|
// TODO Add AVX5124FMAPS/AVX5124VNNIW features
|
|
list<SubtargetFeature> KNMFeatures =
|
|
!listconcat(KNLFeatures, [FeatureVPOPCNTDQ]);
|
|
|
|
// Barcelona
|
|
list<SubtargetFeature> BarcelonaFeatures = [FeatureX87,
|
|
FeatureCMPXCHG8B,
|
|
FeatureSSE4A,
|
|
Feature3DNowA,
|
|
FeatureFXSR,
|
|
FeatureNOPL,
|
|
FeatureCMPXCHG16B,
|
|
FeaturePRFCHW,
|
|
FeatureLZCNT,
|
|
FeaturePOPCNT,
|
|
FeatureLAHFSAHF,
|
|
FeatureCMOV,
|
|
Feature64Bit];
|
|
list<SubtargetFeature> BarcelonaTuning = [FeatureFastScalarShiftMasks,
|
|
FeatureSlowSHLD,
|
|
FeatureInsertVZEROUPPER];
|
|
|
|
// Bobcat
|
|
list<SubtargetFeature> BtVer1Features = [FeatureX87,
|
|
FeatureCMPXCHG8B,
|
|
FeatureCMOV,
|
|
FeatureMMX,
|
|
FeatureSSSE3,
|
|
FeatureSSE4A,
|
|
FeatureFXSR,
|
|
FeatureNOPL,
|
|
Feature64Bit,
|
|
FeatureCMPXCHG16B,
|
|
FeaturePRFCHW,
|
|
FeatureLZCNT,
|
|
FeaturePOPCNT,
|
|
FeatureLAHFSAHF];
|
|
list<SubtargetFeature> BtVer1Tuning = [FeatureFast15ByteNOP,
|
|
FeatureFastScalarShiftMasks,
|
|
FeatureFastVectorShiftMasks,
|
|
FeatureSlowSHLD,
|
|
FeatureInsertVZEROUPPER];
|
|
|
|
// Jaguar
|
|
list<SubtargetFeature> BtVer2AdditionalFeatures = [FeatureAVX,
|
|
FeatureAES,
|
|
FeaturePCLMUL,
|
|
FeatureBMI,
|
|
FeatureF16C,
|
|
FeatureMOVBE,
|
|
FeatureXSAVE,
|
|
FeatureXSAVEOPT];
|
|
list<SubtargetFeature> BtVer2Tuning = [FeatureFastLZCNT,
|
|
FeatureFastBEXTR,
|
|
FeatureFastHorizontalOps,
|
|
FeatureFast15ByteNOP,
|
|
FeatureFastScalarShiftMasks,
|
|
FeatureFastVectorShiftMasks,
|
|
FeatureSlowSHLD];
|
|
list<SubtargetFeature> BtVer2Features =
|
|
!listconcat(BtVer1Features, BtVer2AdditionalFeatures);
|
|
|
|
// Bulldozer
|
|
list<SubtargetFeature> BdVer1Features = [FeatureX87,
|
|
FeatureCMPXCHG8B,
|
|
FeatureCMOV,
|
|
FeatureXOP,
|
|
Feature64Bit,
|
|
FeatureCMPXCHG16B,
|
|
FeatureAES,
|
|
FeaturePRFCHW,
|
|
FeaturePCLMUL,
|
|
FeatureMMX,
|
|
FeatureFXSR,
|
|
FeatureNOPL,
|
|
FeatureLZCNT,
|
|
FeaturePOPCNT,
|
|
FeatureXSAVE,
|
|
FeatureLWP,
|
|
FeatureLAHFSAHF];
|
|
list<SubtargetFeature> BdVer1Tuning = [FeatureSlowSHLD,
|
|
FeatureFast11ByteNOP,
|
|
FeatureFastScalarShiftMasks,
|
|
FeatureBranchFusion,
|
|
FeatureInsertVZEROUPPER];
|
|
|
|
// PileDriver
|
|
list<SubtargetFeature> BdVer2AdditionalFeatures = [FeatureF16C,
|
|
FeatureBMI,
|
|
FeatureTBM,
|
|
FeatureFMA,
|
|
FeatureFastBEXTR];
|
|
list<SubtargetFeature> BdVer2Tuning = BdVer1Tuning;
|
|
list<SubtargetFeature> BdVer2Features =
|
|
!listconcat(BdVer1Features, BdVer2AdditionalFeatures);
|
|
|
|
// Steamroller
|
|
list<SubtargetFeature> BdVer3AdditionalFeatures = [FeatureXSAVEOPT,
|
|
FeatureFSGSBase];
|
|
list<SubtargetFeature> BdVer3Tuning = BdVer2Tuning;
|
|
list<SubtargetFeature> BdVer3Features =
|
|
!listconcat(BdVer2Features, BdVer3AdditionalFeatures);
|
|
|
|
// Excavator
|
|
list<SubtargetFeature> BdVer4AdditionalFeatures = [FeatureAVX2,
|
|
FeatureBMI2,
|
|
FeatureMOVBE,
|
|
FeatureRDRAND,
|
|
FeatureMWAITX];
|
|
list<SubtargetFeature> BdVer4Tuning = BdVer3Tuning;
|
|
list<SubtargetFeature> BdVer4Features =
|
|
!listconcat(BdVer3Features, BdVer4AdditionalFeatures);
|
|
|
|
|
|
// AMD Zen Processors common ISAs
|
|
list<SubtargetFeature> ZNFeatures = [FeatureADX,
|
|
FeatureAES,
|
|
FeatureAVX2,
|
|
FeatureBMI,
|
|
FeatureBMI2,
|
|
FeatureCLFLUSHOPT,
|
|
FeatureCLZERO,
|
|
FeatureCMOV,
|
|
Feature64Bit,
|
|
FeatureCMPXCHG16B,
|
|
FeatureF16C,
|
|
FeatureFMA,
|
|
FeatureFSGSBase,
|
|
FeatureFXSR,
|
|
FeatureNOPL,
|
|
FeatureLAHFSAHF,
|
|
FeatureLZCNT,
|
|
FeatureMMX,
|
|
FeatureMOVBE,
|
|
FeatureMWAITX,
|
|
FeaturePCLMUL,
|
|
FeaturePOPCNT,
|
|
FeaturePRFCHW,
|
|
FeatureRDRAND,
|
|
FeatureRDSEED,
|
|
FeatureSHA,
|
|
FeatureSSE4A,
|
|
FeatureX87,
|
|
FeatureXSAVE,
|
|
FeatureXSAVEC,
|
|
FeatureXSAVEOPT,
|
|
FeatureXSAVES];
|
|
list<SubtargetFeature> ZNTuning = [FeatureFastLZCNT,
|
|
FeatureFastBEXTR,
|
|
FeatureFast15ByteNOP,
|
|
FeatureBranchFusion,
|
|
FeatureFastScalarShiftMasks,
|
|
FeatureSlowSHLD,
|
|
FeatureInsertVZEROUPPER];
|
|
list<SubtargetFeature> ZN2AdditionalFeatures = [FeatureCLWB,
|
|
FeatureRDPID,
|
|
FeatureWBNOINVD];
|
|
list<SubtargetFeature> ZN2Tuning = ZNTuning;
|
|
list<SubtargetFeature> ZN2Features =
|
|
!listconcat(ZNFeatures, ZN2AdditionalFeatures);
|
|
list<SubtargetFeature> ZN3AdditionalFeatures = [FeatureINVPCID,
|
|
FeaturePKU,
|
|
FeatureVAES,
|
|
FeatureVPCLMULQDQ];
|
|
list<SubtargetFeature> ZN3Tuning = ZNTuning;
|
|
list<SubtargetFeature> ZN3Features =
|
|
!listconcat(ZN2Features, ZN3AdditionalFeatures);
|
|
}
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// X86 processors supported.
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
class Proc<string Name, list<SubtargetFeature> Features,
|
|
list<SubtargetFeature> TuneFeatures>
|
|
: ProcessorModel<Name, GenericModel, Features, TuneFeatures>;
|
|
|
|
class ProcModel<string Name, SchedMachineModel Model,
|
|
list<SubtargetFeature> Features,
|
|
list<SubtargetFeature> TuneFeatures>
|
|
: ProcessorModel<Name, Model, Features, TuneFeatures>;
|
|
|
|
// NOTE: CMPXCHG8B is here for legacy compatibility so that it is only disabled
|
|
// if i386/i486 is specifically requested.
|
|
// NOTE: 64Bit is here as "generic" is the default llc CPU. The X86Subtarget
|
|
// constructor checks that any CPU used in 64-bit mode has Feature64Bit enabled.
|
|
// It has no effect on code generation.
|
|
def : ProcModel<"generic", SandyBridgeModel,
|
|
[FeatureX87, FeatureCMPXCHG8B, Feature64Bit],
|
|
[FeatureSlow3OpsLEA,
|
|
FeatureSlowDivide64,
|
|
FeatureSlowIncDec,
|
|
FeatureMacroFusion,
|
|
FeatureInsertVZEROUPPER]>;
|
|
|
|
def : Proc<"i386", [FeatureX87],
|
|
[FeatureSlowUAMem16, FeatureInsertVZEROUPPER]>;
|
|
def : Proc<"i486", [FeatureX87],
|
|
[FeatureSlowUAMem16, FeatureInsertVZEROUPPER]>;
|
|
def : Proc<"i586", [FeatureX87, FeatureCMPXCHG8B],
|
|
[FeatureSlowUAMem16, FeatureInsertVZEROUPPER]>;
|
|
def : Proc<"pentium", [FeatureX87, FeatureCMPXCHG8B],
|
|
[FeatureSlowUAMem16, FeatureInsertVZEROUPPER]>;
|
|
def : Proc<"pentium-mmx", [FeatureX87, FeatureCMPXCHG8B, FeatureMMX],
|
|
[FeatureSlowUAMem16, FeatureInsertVZEROUPPER]>;
|
|
|
|
def : Proc<"i686", [FeatureX87, FeatureCMPXCHG8B, FeatureCMOV],
|
|
[FeatureSlowUAMem16, FeatureInsertVZEROUPPER]>;
|
|
def : Proc<"pentiumpro", [FeatureX87, FeatureCMPXCHG8B, FeatureCMOV,
|
|
FeatureNOPL],
|
|
[FeatureSlowUAMem16, FeatureInsertVZEROUPPER]>;
|
|
|
|
def : Proc<"pentium2", [FeatureX87, FeatureCMPXCHG8B, FeatureMMX, FeatureCMOV,
|
|
FeatureFXSR, FeatureNOPL],
|
|
[FeatureSlowUAMem16, FeatureInsertVZEROUPPER]>;
|
|
|
|
foreach P = ["pentium3", "pentium3m"] in {
|
|
def : Proc<P, [FeatureX87, FeatureCMPXCHG8B, FeatureMMX,
|
|
FeatureSSE1, FeatureFXSR, FeatureNOPL, FeatureCMOV],
|
|
[FeatureSlowUAMem16, FeatureInsertVZEROUPPER]>;
|
|
}
|
|
|
|
// Enable the PostRAScheduler for SSE2 and SSE3 class cpus.
|
|
// The intent is to enable it for pentium4 which is the current default
|
|
// processor in a vanilla 32-bit clang compilation when no specific
|
|
// architecture is specified. This generally gives a nice performance
|
|
// increase on silvermont, with largely neutral behavior on other
|
|
// contemporary large core processors.
|
|
// pentium-m, pentium4m, prescott and nocona are included as a preventative
|
|
// measure to avoid performance surprises, in case clang's default cpu
|
|
// changes slightly.
|
|
|
|
def : ProcModel<"pentium-m", GenericPostRAModel,
|
|
[FeatureX87, FeatureCMPXCHG8B, FeatureMMX, FeatureSSE2,
|
|
FeatureFXSR, FeatureNOPL, FeatureCMOV],
|
|
[FeatureSlowUAMem16, FeatureInsertVZEROUPPER]>;
|
|
|
|
foreach P = ["pentium4", "pentium4m"] in {
|
|
def : ProcModel<P, GenericPostRAModel,
|
|
[FeatureX87, FeatureCMPXCHG8B, FeatureMMX, FeatureSSE2,
|
|
FeatureFXSR, FeatureNOPL, FeatureCMOV],
|
|
[FeatureSlowUAMem16, FeatureInsertVZEROUPPER]>;
|
|
}
|
|
|
|
// Intel Quark.
|
|
def : Proc<"lakemont", [FeatureCMPXCHG8B],
|
|
[FeatureSlowUAMem16, FeatureInsertVZEROUPPER]>;
|
|
|
|
// Intel Core Duo.
|
|
def : ProcModel<"yonah", SandyBridgeModel,
|
|
[FeatureX87, FeatureCMPXCHG8B, FeatureMMX, FeatureSSE3,
|
|
FeatureFXSR, FeatureNOPL, FeatureCMOV],
|
|
[FeatureSlowUAMem16, FeatureInsertVZEROUPPER]>;
|
|
|
|
// NetBurst.
|
|
def : ProcModel<"prescott", GenericPostRAModel,
|
|
[FeatureX87, FeatureCMPXCHG8B, FeatureMMX, FeatureSSE3,
|
|
FeatureFXSR, FeatureNOPL, FeatureCMOV],
|
|
[FeatureSlowUAMem16, FeatureInsertVZEROUPPER]>;
|
|
def : ProcModel<"nocona", GenericPostRAModel, [
|
|
FeatureX87,
|
|
FeatureCMPXCHG8B,
|
|
FeatureCMOV,
|
|
FeatureMMX,
|
|
FeatureSSE3,
|
|
FeatureFXSR,
|
|
FeatureNOPL,
|
|
Feature64Bit,
|
|
FeatureCMPXCHG16B,
|
|
],
|
|
[
|
|
FeatureSlowUAMem16,
|
|
FeatureInsertVZEROUPPER
|
|
]>;
|
|
|
|
// Intel Core 2 Solo/Duo.
|
|
def : ProcModel<"core2", SandyBridgeModel, [
|
|
FeatureX87,
|
|
FeatureCMPXCHG8B,
|
|
FeatureCMOV,
|
|
FeatureMMX,
|
|
FeatureSSSE3,
|
|
FeatureFXSR,
|
|
FeatureNOPL,
|
|
Feature64Bit,
|
|
FeatureCMPXCHG16B,
|
|
FeatureLAHFSAHF
|
|
],
|
|
[
|
|
FeatureMacroFusion,
|
|
FeatureSlowUAMem16,
|
|
FeatureInsertVZEROUPPER
|
|
]>;
|
|
def : ProcModel<"penryn", SandyBridgeModel, [
|
|
FeatureX87,
|
|
FeatureCMPXCHG8B,
|
|
FeatureCMOV,
|
|
FeatureMMX,
|
|
FeatureSSE41,
|
|
FeatureFXSR,
|
|
FeatureNOPL,
|
|
Feature64Bit,
|
|
FeatureCMPXCHG16B,
|
|
FeatureLAHFSAHF
|
|
],
|
|
[
|
|
FeatureMacroFusion,
|
|
FeatureSlowUAMem16,
|
|
FeatureInsertVZEROUPPER
|
|
]>;
|
|
|
|
// Atom CPUs.
|
|
foreach P = ["bonnell", "atom"] in {
|
|
def : ProcModel<P, AtomModel, ProcessorFeatures.AtomFeatures,
|
|
ProcessorFeatures.AtomTuning>;
|
|
}
|
|
|
|
foreach P = ["silvermont", "slm"] in {
|
|
def : ProcModel<P, SLMModel, ProcessorFeatures.SLMFeatures,
|
|
ProcessorFeatures.SLMTuning>;
|
|
}
|
|
|
|
def : ProcModel<"goldmont", SLMModel, ProcessorFeatures.GLMFeatures,
|
|
ProcessorFeatures.GLMTuning>;
|
|
def : ProcModel<"goldmont-plus", SLMModel, ProcessorFeatures.GLPFeatures,
|
|
ProcessorFeatures.GLPTuning>;
|
|
def : ProcModel<"tremont", SLMModel, ProcessorFeatures.TRMFeatures,
|
|
ProcessorFeatures.TRMTuning>;
|
|
|
|
// "Arrandale" along with corei3 and corei5
|
|
foreach P = ["nehalem", "corei7"] in {
|
|
def : ProcModel<P, SandyBridgeModel, ProcessorFeatures.NHMFeatures,
|
|
ProcessorFeatures.NHMTuning>;
|
|
}
|
|
|
|
// Westmere is the corei3/i5/i7 path from nehalem to sandybridge
|
|
def : ProcModel<"westmere", SandyBridgeModel, ProcessorFeatures.WSMFeatures,
|
|
ProcessorFeatures.WSMTuning>;
|
|
|
|
foreach P = ["sandybridge", "corei7-avx"] in {
|
|
def : ProcModel<P, SandyBridgeModel, ProcessorFeatures.SNBFeatures,
|
|
ProcessorFeatures.SNBTuning>;
|
|
}
|
|
|
|
foreach P = ["ivybridge", "core-avx-i"] in {
|
|
def : ProcModel<P, SandyBridgeModel, ProcessorFeatures.IVBFeatures,
|
|
ProcessorFeatures.IVBTuning>;
|
|
}
|
|
|
|
foreach P = ["haswell", "core-avx2"] in {
|
|
def : ProcModel<P, HaswellModel, ProcessorFeatures.HSWFeatures,
|
|
ProcessorFeatures.HSWTuning>;
|
|
}
|
|
|
|
def : ProcModel<"broadwell", BroadwellModel, ProcessorFeatures.BDWFeatures,
|
|
ProcessorFeatures.BDWTuning>;
|
|
|
|
def : ProcModel<"skylake", SkylakeClientModel, ProcessorFeatures.SKLFeatures,
|
|
ProcessorFeatures.SKLTuning>;
|
|
|
|
// FIXME: define KNL scheduler model
|
|
def : ProcModel<"knl", HaswellModel, ProcessorFeatures.KNLFeatures,
|
|
ProcessorFeatures.KNLTuning>;
|
|
def : ProcModel<"knm", HaswellModel, ProcessorFeatures.KNMFeatures,
|
|
ProcessorFeatures.KNLTuning>;
|
|
|
|
foreach P = ["skylake-avx512", "skx"] in {
|
|
def : ProcModel<P, SkylakeServerModel, ProcessorFeatures.SKXFeatures,
|
|
ProcessorFeatures.SKXTuning>;
|
|
}
|
|
|
|
def : ProcModel<"cascadelake", SkylakeServerModel,
|
|
ProcessorFeatures.CLXFeatures, ProcessorFeatures.CLXTuning>;
|
|
def : ProcModel<"cooperlake", SkylakeServerModel,
|
|
ProcessorFeatures.CPXFeatures, ProcessorFeatures.CPXTuning>;
|
|
def : ProcModel<"cannonlake", SkylakeServerModel,
|
|
ProcessorFeatures.CNLFeatures, ProcessorFeatures.CNLTuning>;
|
|
def : ProcModel<"icelake-client", SkylakeServerModel,
|
|
ProcessorFeatures.ICLFeatures, ProcessorFeatures.ICLTuning>;
|
|
def : ProcModel<"icelake-server", SkylakeServerModel,
|
|
ProcessorFeatures.ICXFeatures, ProcessorFeatures.ICXTuning>;
|
|
def : ProcModel<"tigerlake", SkylakeServerModel,
|
|
ProcessorFeatures.TGLFeatures, ProcessorFeatures.TGLTuning>;
|
|
def : ProcModel<"sapphirerapids", SkylakeServerModel,
|
|
ProcessorFeatures.SPRFeatures, ProcessorFeatures.SPRTuning>;
|
|
def : ProcModel<"alderlake", SkylakeClientModel,
|
|
ProcessorFeatures.ADLFeatures, ProcessorFeatures.ADLTuning>;
|
|
|
|
// AMD CPUs.
|
|
|
|
def : Proc<"k6", [FeatureX87, FeatureCMPXCHG8B, FeatureMMX],
|
|
[FeatureSlowUAMem16, FeatureInsertVZEROUPPER]>;
|
|
def : Proc<"k6-2", [FeatureX87, FeatureCMPXCHG8B, Feature3DNow],
|
|
[FeatureSlowUAMem16, FeatureInsertVZEROUPPER]>;
|
|
def : Proc<"k6-3", [FeatureX87, FeatureCMPXCHG8B, Feature3DNow],
|
|
[FeatureSlowUAMem16, FeatureInsertVZEROUPPER]>;
|
|
|
|
foreach P = ["athlon", "athlon-tbird"] in {
|
|
def : Proc<P, [FeatureX87, FeatureCMPXCHG8B, FeatureCMOV, Feature3DNowA,
|
|
FeatureNOPL],
|
|
[FeatureSlowSHLD, FeatureSlowUAMem16, FeatureInsertVZEROUPPER]>;
|
|
}
|
|
|
|
foreach P = ["athlon-4", "athlon-xp", "athlon-mp"] in {
|
|
def : Proc<P, [FeatureX87, FeatureCMPXCHG8B, FeatureCMOV,
|
|
FeatureSSE1, Feature3DNowA, FeatureFXSR, FeatureNOPL],
|
|
[FeatureSlowSHLD, FeatureSlowUAMem16, FeatureInsertVZEROUPPER]>;
|
|
}
|
|
|
|
foreach P = ["k8", "opteron", "athlon64", "athlon-fx"] in {
|
|
def : Proc<P, [FeatureX87, FeatureCMPXCHG8B, FeatureSSE2, Feature3DNowA,
|
|
FeatureFXSR, FeatureNOPL, Feature64Bit, FeatureCMOV],
|
|
[FeatureFastScalarShiftMasks, FeatureSlowSHLD, FeatureSlowUAMem16,
|
|
FeatureInsertVZEROUPPER]>;
|
|
}
|
|
|
|
foreach P = ["k8-sse3", "opteron-sse3", "athlon64-sse3"] in {
|
|
def : Proc<P, [FeatureX87, FeatureCMPXCHG8B, FeatureSSE3, Feature3DNowA,
|
|
FeatureFXSR, FeatureNOPL, FeatureCMPXCHG16B, FeatureCMOV,
|
|
Feature64Bit],
|
|
[FeatureFastScalarShiftMasks, FeatureSlowSHLD, FeatureSlowUAMem16,
|
|
FeatureInsertVZEROUPPER]>;
|
|
}
|
|
|
|
foreach P = ["amdfam10", "barcelona"] in {
|
|
def : Proc<P, ProcessorFeatures.BarcelonaFeatures,
|
|
ProcessorFeatures.BarcelonaTuning>;
|
|
}
|
|
|
|
// Bobcat
|
|
def : Proc<"btver1", ProcessorFeatures.BtVer1Features,
|
|
ProcessorFeatures.BtVer1Tuning>;
|
|
// Jaguar
|
|
def : ProcModel<"btver2", BtVer2Model, ProcessorFeatures.BtVer2Features,
|
|
ProcessorFeatures.BtVer2Tuning>;
|
|
|
|
// Bulldozer
|
|
def : ProcModel<"bdver1", BdVer2Model, ProcessorFeatures.BdVer1Features,
|
|
ProcessorFeatures.BdVer1Tuning>;
|
|
// Piledriver
|
|
def : ProcModel<"bdver2", BdVer2Model, ProcessorFeatures.BdVer2Features,
|
|
ProcessorFeatures.BdVer2Tuning>;
|
|
// Steamroller
|
|
def : Proc<"bdver3", ProcessorFeatures.BdVer3Features,
|
|
ProcessorFeatures.BdVer3Tuning>;
|
|
// Excavator
|
|
def : Proc<"bdver4", ProcessorFeatures.BdVer4Features,
|
|
ProcessorFeatures.BdVer4Tuning>;
|
|
|
|
def : ProcModel<"znver1", Znver1Model, ProcessorFeatures.ZNFeatures,
|
|
ProcessorFeatures.ZNTuning>;
|
|
def : ProcModel<"znver2", Znver2Model, ProcessorFeatures.ZN2Features,
|
|
ProcessorFeatures.ZN2Tuning>;
|
|
def : ProcModel<"znver3", Znver2Model, ProcessorFeatures.ZN3Features,
|
|
ProcessorFeatures.ZN3Tuning>;
|
|
|
|
def : Proc<"geode", [FeatureX87, FeatureCMPXCHG8B, Feature3DNowA],
|
|
[FeatureSlowUAMem16, FeatureInsertVZEROUPPER]>;
|
|
|
|
def : Proc<"winchip-c6", [FeatureX87, FeatureMMX],
|
|
[FeatureSlowUAMem16, FeatureInsertVZEROUPPER]>;
|
|
def : Proc<"winchip2", [FeatureX87, Feature3DNow],
|
|
[FeatureSlowUAMem16, FeatureInsertVZEROUPPER]>;
|
|
def : Proc<"c3", [FeatureX87, Feature3DNow],
|
|
[FeatureSlowUAMem16, FeatureInsertVZEROUPPER]>;
|
|
def : Proc<"c3-2", [FeatureX87, FeatureCMPXCHG8B, FeatureMMX,
|
|
FeatureSSE1, FeatureFXSR, FeatureCMOV],
|
|
[FeatureSlowUAMem16, FeatureInsertVZEROUPPER]>;
|
|
|
|
// We also provide a generic 64-bit specific x86 processor model which tries to
|
|
// be good for modern chips without enabling instruction set encodings past the
|
|
// basic SSE2 and 64-bit ones. It disables slow things from any mainstream and
|
|
// modern 64-bit x86 chip, and enables features that are generally beneficial.
|
|
//
|
|
// We currently use the Sandy Bridge model as the default scheduling model as
|
|
// we use it across Nehalem, Westmere, Sandy Bridge, and Ivy Bridge which
|
|
// covers a huge swath of x86 processors. If there are specific scheduling
|
|
// knobs which need to be tuned differently for AMD chips, we might consider
|
|
// forming a common base for them.
|
|
def : ProcModel<"x86-64", SandyBridgeModel, ProcessorFeatures.X86_64V1Features,
|
|
[
|
|
FeatureSlow3OpsLEA,
|
|
FeatureSlowDivide64,
|
|
FeatureSlowIncDec,
|
|
FeatureMacroFusion,
|
|
FeatureInsertVZEROUPPER
|
|
]>;
|
|
|
|
// x86-64 micro-architecture levels.
|
|
def : ProcModel<"x86-64-v2", SandyBridgeModel, ProcessorFeatures.X86_64V2Features,
|
|
ProcessorFeatures.SNBTuning>;
|
|
// Close to Haswell.
|
|
def : ProcModel<"x86-64-v3", HaswellModel, ProcessorFeatures.X86_64V3Features,
|
|
ProcessorFeatures.HSWTuning>;
|
|
// Close to the AVX-512 level implemented by Xeon Scalable Processors.
|
|
def : ProcModel<"x86-64-v4", HaswellModel, ProcessorFeatures.X86_64V4Features,
|
|
ProcessorFeatures.SKXTuning>;
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Calling Conventions
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
include "X86CallingConv.td"
|
|
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Assembly Parser
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
def ATTAsmParserVariant : AsmParserVariant {
|
|
int Variant = 0;
|
|
|
|
// Variant name.
|
|
string Name = "att";
|
|
|
|
// Discard comments in assembly strings.
|
|
string CommentDelimiter = "#";
|
|
|
|
// Recognize hard coded registers.
|
|
string RegisterPrefix = "%";
|
|
}
|
|
|
|
def IntelAsmParserVariant : AsmParserVariant {
|
|
int Variant = 1;
|
|
|
|
// Variant name.
|
|
string Name = "intel";
|
|
|
|
// Discard comments in assembly strings.
|
|
string CommentDelimiter = ";";
|
|
|
|
// Recognize hard coded registers.
|
|
string RegisterPrefix = "";
|
|
}
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Assembly Printers
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
// The X86 target supports two different syntaxes for emitting machine code.
|
|
// This is controlled by the -x86-asm-syntax={att|intel}
|
|
def ATTAsmWriter : AsmWriter {
|
|
string AsmWriterClassName = "ATTInstPrinter";
|
|
int Variant = 0;
|
|
}
|
|
def IntelAsmWriter : AsmWriter {
|
|
string AsmWriterClassName = "IntelInstPrinter";
|
|
int Variant = 1;
|
|
}
|
|
|
|
def X86 : Target {
|
|
// Information about the instructions...
|
|
let InstructionSet = X86InstrInfo;
|
|
let AssemblyParserVariants = [ATTAsmParserVariant, IntelAsmParserVariant];
|
|
let AssemblyWriters = [ATTAsmWriter, IntelAsmWriter];
|
|
let AllowRegisterRenaming = 1;
|
|
}
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
// Pfm Counters
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
include "X86PfmCounters.td"
|