X-Git-Url: http://plrg.eecs.uci.edu/git/?a=blobdiff_plain;f=lib%2FTarget%2FX86%2FX86.td;h=5c88b5df443a070cf51d4702a125dfb8b7d2a84f;hb=a46f06efe217b3c3328d9ececf8de0c8c7dee446;hp=0216252c19b38a73978de8f6dfd4ae9a76fd7641;hpb=7b672ed380cf44894f8b96c52558dcfc136af383;p=oota-llvm.git diff --git a/lib/Target/X86/X86.td b/lib/Target/X86/X86.td index 0216252c19b..5c88b5df443 100644 --- a/lib/Target/X86/X86.td +++ b/lib/Target/X86/X86.td @@ -22,6 +22,10 @@ include "llvm/Target/Target.td" 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 @@ -50,10 +54,10 @@ def FeatureSSE3 : SubtargetFeature<"sse3", "X86SSELevel", "SSE3", def FeatureSSSE3 : SubtargetFeature<"ssse3", "X86SSELevel", "SSSE3", "Enable SSSE3 instructions", [FeatureSSE3]>; -def FeatureSSE41 : SubtargetFeature<"sse41", "X86SSELevel", "SSE41", +def FeatureSSE41 : SubtargetFeature<"sse4.1", "X86SSELevel", "SSE41", "Enable SSE 4.1 instructions", [FeatureSSSE3]>; -def FeatureSSE42 : SubtargetFeature<"sse42", "X86SSELevel", "SSE42", +def FeatureSSE42 : SubtargetFeature<"sse4.2", "X86SSELevel", "SSE42", "Enable SSE 4.2 instructions", [FeatureSSE41]>; def Feature3DNow : SubtargetFeature<"3dnow", "X863DNowLevel", "ThreeDNow", @@ -68,11 +72,13 @@ def Feature3DNowA : SubtargetFeature<"3dnowa", "X863DNowLevel", "ThreeDNowA", def Feature64Bit : SubtargetFeature<"64bit", "HasX86_64", "true", "Support 64-bit instructions", [FeatureCMOV]>; -def FeatureCMPXCHG16B : SubtargetFeature<"cmpxchg16b", "HasCmpxchg16b", "true", +def FeatureCMPXCHG16B : SubtargetFeature<"cx16", "HasCmpxchg16b", "true", "64-bit with cmpxchg16b", [Feature64Bit]>; def FeatureSlowBTMem : SubtargetFeature<"slow-bt-mem", "IsBTMemSlow", "true", "Bit testing of memory is slow">; +def FeatureSlowSHLD : SubtargetFeature<"slow-shld", "IsSHLDSlow", "true", + "SHLD instruction is slow">; def FeatureFastUAMem : SubtargetFeature<"fast-unaligned-mem", "IsUAMemFast", "true", "Fast unaligned memory access">; @@ -86,6 +92,27 @@ def FeatureAVX : SubtargetFeature<"avx", "X86SSELevel", "AVX", def FeatureAVX2 : SubtargetFeature<"avx2", "X86SSELevel", "AVX2", "Enable AVX2 instructions", [FeatureAVX]>; +def FeatureAVX512 : SubtargetFeature<"avx512f", "X86SSELevel", "AVX512F", + "Enable AVX-512 instructions", + [FeatureAVX2]>; +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 FeaturePFI : SubtargetFeature<"avx512pf", "HasPFI", "true", + "Enable AVX-512 PreFetch Instructions", + [FeatureAVX512]>; +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 FeaturePCLMUL : SubtargetFeature<"pclmul", "HasPCLMUL", "true", "Enable packed carry-less multiplication instructions", [FeatureSSE2]>; @@ -104,12 +131,15 @@ def FeatureVectorUAMem : SubtargetFeature<"vector-unaligned-mem", def FeatureAES : SubtargetFeature<"aes", "HasAES", "true", "Enable AES instructions", [FeatureSSE2]>; +def FeatureTBM : SubtargetFeature<"tbm", "HasTBM", "true", + "Enable TBM instructions">; def FeatureMOVBE : SubtargetFeature<"movbe", "HasMOVBE", "true", "Support MOVBE instruction">; -def FeatureRDRAND : SubtargetFeature<"rdrand", "HasRDRAND", "true", +def FeatureRDRAND : SubtargetFeature<"rdrnd", "HasRDRAND", "true", "Support RDRAND instruction">; def FeatureF16C : SubtargetFeature<"f16c", "HasF16C", "true", - "Support 16-bit floating point conversion instructions">; + "Support 16-bit floating point conversion instructions", + [FeatureAVX]>; def FeatureFSGSBase : SubtargetFeature<"fsgsbase", "HasFSGSBase", "true", "Support FS/GS Base instructions">; def FeatureLZCNT : SubtargetFeature<"lzcnt", "HasLZCNT", "true", @@ -120,8 +150,21 @@ def FeatureBMI2 : SubtargetFeature<"bmi2", "HasBMI2", "true", "Support BMI2 instructions">; def FeatureRTM : SubtargetFeature<"rtm", "HasRTM", "true", "Support RTM instructions">; +def FeatureHLE : SubtargetFeature<"hle", "HasHLE", "true", + "Support HLE">; def FeatureADX : SubtargetFeature<"adx", "HasADX", "true", "Support ADX instructions">; +def FeatureSHA : SubtargetFeature<"sha", "HasSHA", "true", + "Enable SHA instructions", + [FeatureSSE2]>; +def FeatureSGX : SubtargetFeature<"sgx", "HasSGX", "true", + "Support SGX instructions">; +def FeaturePRFCHW : SubtargetFeature<"prfchw", "HasPRFCHW", "true", + "Support PRFCHW instructions">; +def FeatureRDSEED : SubtargetFeature<"rdseed", "HasRDSEED", "true", + "Support RDSEED instruction">; +def FeatureSMAP : SubtargetFeature<"smap", "HasSMAP", "true", + "Support SMAP instructions">; def FeatureLeaForSP : SubtargetFeature<"lea-sp", "UseLeaForSP", "true", "Use LEA for adjusting the stack pointer">; def FeatureSlowDivide : SubtargetFeature<"idiv-to-divb", @@ -130,6 +173,17 @@ def FeatureSlowDivide : SubtargetFeature<"idiv-to-divb", def FeaturePadShortFunctions : SubtargetFeature<"pad-short-functions", "PadShortFunctions", "true", "Pad short functions">; +def FeatureCallRegIndirect : SubtargetFeature<"call-reg-indirect", + "CallRegIndirect", "true", + "Call register indirect">; +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 FeatureSlowIncDec : SubtargetFeature<"slow-incdec", "SlowIncDec", "true", + "INC and DEC instructions are slower than ADD and SUB">; +def FeatureUseSqrtEst : SubtargetFeature<"use-sqrt-est", "UseSqrtEst", "true", + "Use RSQRT* to optimize square root calculations">; //===----------------------------------------------------------------------===// // X86 processors supported. @@ -139,13 +193,12 @@ include "X86Schedule.td" def ProcIntelAtom : SubtargetFeature<"atom", "X86ProcFamily", "IntelAtom", "Intel Atom processors">; +def ProcIntelSLM : SubtargetFeature<"slm", "X86ProcFamily", "IntelSLM", + "Intel Silvermont processors">; class Proc Features> : ProcessorModel; -class AtomProc Features> - : ProcessorModel; - def : Proc<"generic", []>; def : Proc<"i386", []>; def : Proc<"i486", []>; @@ -160,86 +213,170 @@ def : Proc<"pentium3m", [FeatureSSE1, FeatureSlowBTMem]>; def : Proc<"pentium-m", [FeatureSSE2, FeatureSlowBTMem]>; def : Proc<"pentium4", [FeatureSSE2]>; def : Proc<"pentium4m", [FeatureSSE2, FeatureSlowBTMem]>; -def : Proc<"x86-64", [FeatureSSE2, Feature64Bit, FeatureSlowBTMem, - FeatureFastUAMem]>; -def : Proc<"yonah", [FeatureSSE3, FeatureSlowBTMem]>; -def : Proc<"prescott", [FeatureSSE3, FeatureSlowBTMem]>; -def : Proc<"nocona", [FeatureSSE3, FeatureCMPXCHG16B, - FeatureSlowBTMem]>; -def : Proc<"core2", [FeatureSSSE3, FeatureCMPXCHG16B, - FeatureSlowBTMem]>; -def : Proc<"penryn", [FeatureSSE41, FeatureCMPXCHG16B, - FeatureSlowBTMem]>; -def : AtomProc<"atom", [ProcIntelAtom, FeatureSSSE3, FeatureCMPXCHG16B, - FeatureMOVBE, FeatureSlowBTMem, FeatureLeaForSP, - FeatureSlowDivide, FeaturePadShortFunctions]>; + +// Intel Core Duo. +def : ProcessorModel<"yonah", SandyBridgeModel, + [FeatureSSE3, FeatureSlowBTMem]>; + +// NetBurst. +def : Proc<"prescott", [FeatureSSE3, FeatureSlowBTMem]>; +def : Proc<"nocona", [FeatureSSE3, FeatureCMPXCHG16B, FeatureSlowBTMem]>; + +// Intel Core 2 Solo/Duo. +def : ProcessorModel<"core2", SandyBridgeModel, + [FeatureSSSE3, FeatureCMPXCHG16B, FeatureSlowBTMem]>; +def : ProcessorModel<"penryn", SandyBridgeModel, + [FeatureSSE41, FeatureCMPXCHG16B, FeatureSlowBTMem]>; + +// Atom. +def : ProcessorModel<"atom", AtomModel, + [ProcIntelAtom, FeatureSSSE3, FeatureCMPXCHG16B, + FeatureMOVBE, FeatureSlowBTMem, FeatureLeaForSP, + FeatureSlowDivide, + FeatureCallRegIndirect, + FeatureLEAUsesAG, + FeaturePadShortFunctions]>; + +// Atom Silvermont. +def : ProcessorModel<"slm", SLMModel, [ProcIntelSLM, + FeatureSSE42, FeatureCMPXCHG16B, + FeatureMOVBE, FeaturePOPCNT, + FeaturePCLMUL, FeatureAES, + FeatureCallRegIndirect, + FeaturePRFCHW, + FeatureSlowLEA, FeatureSlowIncDec, + FeatureSlowBTMem, FeatureFastUAMem]>; // "Arrandale" along with corei3 and corei5 -def : Proc<"corei7", [FeatureSSE42, FeatureCMPXCHG16B, - FeatureSlowBTMem, FeatureFastUAMem, - FeaturePOPCNT, FeatureAES]>; -def : Proc<"nehalem", [FeatureSSE42, FeatureCMPXCHG16B, - FeatureSlowBTMem, FeatureFastUAMem, - FeaturePOPCNT]>; +def : ProcessorModel<"corei7", SandyBridgeModel, + [FeatureSSE42, FeatureCMPXCHG16B, FeatureSlowBTMem, + FeatureFastUAMem, FeaturePOPCNT, FeatureAES]>; + +def : ProcessorModel<"nehalem", SandyBridgeModel, + [FeatureSSE42, FeatureCMPXCHG16B, FeatureSlowBTMem, + FeatureFastUAMem, FeaturePOPCNT]>; // Westmere is a similar machine to nehalem with some additional features. // Westmere is the corei3/i5/i7 path from nehalem to sandybridge -def : Proc<"westmere", [FeatureSSE42, FeatureCMPXCHG16B, - FeatureSlowBTMem, FeatureFastUAMem, - FeaturePOPCNT, FeatureAES, FeaturePCLMUL]>; +def : ProcessorModel<"westmere", SandyBridgeModel, + [FeatureSSE42, FeatureCMPXCHG16B, FeatureSlowBTMem, + FeatureFastUAMem, FeaturePOPCNT, FeatureAES, + FeaturePCLMUL]>; // Sandy Bridge // SSE is not listed here since llvm treats AVX as a reimplementation of SSE, // rather than a superset. -def : Proc<"corei7-avx", [FeatureAVX, FeatureCMPXCHG16B, FeatureFastUAMem, - FeaturePOPCNT, FeatureAES, FeaturePCLMUL]>; +def : ProcessorModel<"corei7-avx", SandyBridgeModel, + [FeatureAVX, FeatureCMPXCHG16B, FeatureFastUAMem, + FeaturePOPCNT, FeatureAES, FeaturePCLMUL]>; // Ivy Bridge -def : Proc<"core-avx-i", [FeatureAVX, FeatureCMPXCHG16B, FeatureFastUAMem, - FeaturePOPCNT, FeatureAES, FeaturePCLMUL, - FeatureRDRAND, FeatureF16C, FeatureFSGSBase]>; +def : ProcessorModel<"core-avx-i", SandyBridgeModel, + [FeatureAVX, FeatureCMPXCHG16B, FeatureFastUAMem, + FeaturePOPCNT, FeatureAES, FeaturePCLMUL, FeatureRDRAND, + FeatureF16C, FeatureFSGSBase]>; // Haswell -def : Proc<"core-avx2", [FeatureAVX2, FeatureCMPXCHG16B, FeatureFastUAMem, - FeaturePOPCNT, FeatureAES, FeaturePCLMUL, - FeatureRDRAND, FeatureF16C, FeatureFSGSBase, - FeatureMOVBE, FeatureLZCNT, FeatureBMI, - FeatureBMI2, FeatureFMA, - FeatureRTM]>; +def : ProcessorModel<"core-avx2", HaswellModel, + [FeatureAVX2, FeatureCMPXCHG16B, FeatureFastUAMem, + FeaturePOPCNT, FeatureAES, FeaturePCLMUL, FeatureRDRAND, + FeatureF16C, FeatureFSGSBase, FeatureMOVBE, FeatureLZCNT, + FeatureBMI, FeatureBMI2, FeatureFMA, FeatureRTM, + FeatureHLE]>; + +// Broadwell +def : ProcessorModel<"broadwell", HaswellModel, + [FeatureAVX2, FeatureCMPXCHG16B, FeatureFastUAMem, + FeaturePOPCNT, FeatureAES, FeaturePCLMUL, FeatureRDRAND, + FeatureF16C, FeatureFSGSBase, FeatureMOVBE, FeatureLZCNT, + FeatureBMI, FeatureBMI2, FeatureFMA, FeatureRTM, + FeatureHLE, FeatureADX, FeatureRDSEED, FeatureSMAP]>; +// KNL +// FIXME: define KNL model +def : ProcessorModel<"knl", HaswellModel, + [FeatureAVX512, FeatureERI, FeatureCDI, FeaturePFI, + FeatureCMPXCHG16B, FeatureFastUAMem, FeaturePOPCNT, + FeatureAES, FeaturePCLMUL, FeatureRDRAND, FeatureF16C, + FeatureFSGSBase, FeatureMOVBE, FeatureLZCNT, FeatureBMI, + FeatureBMI2, FeatureFMA, FeatureRTM, FeatureHLE, + FeatureSlowIncDec]>; + +// SKX +// FIXME: define SKX model +def : ProcessorModel<"skx", HaswellModel, + [FeatureAVX512, FeatureCDI, + FeatureDQI, FeatureBWI, FeatureVLX, + FeatureCMPXCHG16B, FeatureFastUAMem, FeaturePOPCNT, + FeatureAES, FeaturePCLMUL, FeatureRDRAND, FeatureF16C, + FeatureFSGSBase, FeatureMOVBE, FeatureLZCNT, FeatureBMI, + FeatureBMI2, FeatureFMA, FeatureRTM, FeatureHLE, + FeatureSlowIncDec, FeatureSGX]>; def : Proc<"k6", [FeatureMMX]>; def : Proc<"k6-2", [Feature3DNow]>; def : Proc<"k6-3", [Feature3DNow]>; -def : Proc<"athlon", [Feature3DNowA, FeatureSlowBTMem]>; -def : Proc<"athlon-tbird", [Feature3DNowA, FeatureSlowBTMem]>; -def : Proc<"athlon-4", [FeatureSSE1, Feature3DNowA, FeatureSlowBTMem]>; -def : Proc<"athlon-xp", [FeatureSSE1, Feature3DNowA, FeatureSlowBTMem]>; -def : Proc<"athlon-mp", [FeatureSSE1, Feature3DNowA, FeatureSlowBTMem]>; +def : Proc<"athlon", [Feature3DNowA, FeatureSlowBTMem, + FeatureSlowSHLD]>; +def : Proc<"athlon-tbird", [Feature3DNowA, FeatureSlowBTMem, + FeatureSlowSHLD]>; +def : Proc<"athlon-4", [FeatureSSE1, Feature3DNowA, FeatureSlowBTMem, + FeatureSlowSHLD]>; +def : Proc<"athlon-xp", [FeatureSSE1, Feature3DNowA, FeatureSlowBTMem, + FeatureSlowSHLD]>; +def : Proc<"athlon-mp", [FeatureSSE1, Feature3DNowA, FeatureSlowBTMem, + FeatureSlowSHLD]>; def : Proc<"k8", [FeatureSSE2, Feature3DNowA, Feature64Bit, - FeatureSlowBTMem]>; + FeatureSlowBTMem, FeatureSlowSHLD]>; def : Proc<"opteron", [FeatureSSE2, Feature3DNowA, Feature64Bit, - FeatureSlowBTMem]>; + FeatureSlowBTMem, FeatureSlowSHLD]>; def : Proc<"athlon64", [FeatureSSE2, Feature3DNowA, Feature64Bit, - FeatureSlowBTMem]>; + FeatureSlowBTMem, FeatureSlowSHLD]>; def : Proc<"athlon-fx", [FeatureSSE2, Feature3DNowA, Feature64Bit, - FeatureSlowBTMem]>; + FeatureSlowBTMem, FeatureSlowSHLD]>; def : Proc<"k8-sse3", [FeatureSSE3, Feature3DNowA, FeatureCMPXCHG16B, - FeatureSlowBTMem]>; + FeatureSlowBTMem, FeatureSlowSHLD]>; def : Proc<"opteron-sse3", [FeatureSSE3, Feature3DNowA, FeatureCMPXCHG16B, - FeatureSlowBTMem]>; + FeatureSlowBTMem, FeatureSlowSHLD]>; def : Proc<"athlon64-sse3", [FeatureSSE3, Feature3DNowA, FeatureCMPXCHG16B, - FeatureSlowBTMem]>; + FeatureSlowBTMem, FeatureSlowSHLD]>; def : Proc<"amdfam10", [FeatureSSE4A, Feature3DNowA, FeatureCMPXCHG16B, FeatureLZCNT, - FeaturePOPCNT, FeatureSlowBTMem]>; + FeaturePOPCNT, FeatureSlowBTMem, + FeatureSlowSHLD]>; // Bobcat def : Proc<"btver1", [FeatureSSSE3, FeatureSSE4A, FeatureCMPXCHG16B, - FeatureLZCNT, FeaturePOPCNT]>; + FeaturePRFCHW, FeatureLZCNT, FeaturePOPCNT, + FeatureSlowSHLD]>; + +// Jaguar +def : ProcessorModel<"btver2", BtVer2Model, + [FeatureAVX, FeatureSSE4A, FeatureCMPXCHG16B, + FeaturePRFCHW, FeatureAES, FeaturePCLMUL, + FeatureBMI, FeatureF16C, FeatureMOVBE, + FeatureLZCNT, FeaturePOPCNT, FeatureSlowSHLD, + FeatureUseSqrtEst]>; + // Bulldozer def : Proc<"bdver1", [FeatureXOP, FeatureFMA4, FeatureCMPXCHG16B, - FeatureAES, FeaturePCLMUL, - FeatureLZCNT, FeaturePOPCNT]>; -// Enhanced Bulldozer + FeatureAES, FeaturePRFCHW, FeaturePCLMUL, + FeatureLZCNT, FeaturePOPCNT, FeatureSlowSHLD]>; +// Piledriver def : Proc<"bdver2", [FeatureXOP, FeatureFMA4, FeatureCMPXCHG16B, - FeatureAES, FeaturePCLMUL, + FeatureAES, FeaturePRFCHW, FeaturePCLMUL, FeatureF16C, FeatureLZCNT, - FeaturePOPCNT, FeatureBMI, FeatureFMA]>; + FeaturePOPCNT, FeatureBMI, FeatureTBM, + FeatureFMA, FeatureSlowSHLD]>; + +// Steamroller +def : Proc<"bdver3", [FeatureXOP, FeatureFMA4, FeatureCMPXCHG16B, + FeatureAES, FeaturePRFCHW, FeaturePCLMUL, + FeatureF16C, FeatureLZCNT, + FeaturePOPCNT, FeatureBMI, FeatureTBM, + FeatureFMA, FeatureFSGSBase]>; + +// Excavator +def : Proc<"bdver4", [FeatureAVX2, FeatureXOP, FeatureFMA4, + FeatureCMPXCHG16B, FeatureAES, FeaturePRFCHW, + FeaturePCLMUL, FeatureF16C, FeatureLZCNT, + FeaturePOPCNT, FeatureBMI, FeatureBMI2, + FeatureTBM, FeatureFMA, FeatureFSGSBase]>; + def : Proc<"geode", [Feature3DNowA]>; def : Proc<"winchip-c6", [FeatureMMX]>; @@ -247,6 +384,20 @@ def : Proc<"winchip2", [Feature3DNow]>; def : Proc<"c3", [Feature3DNow]>; def : Proc<"c3-2", [FeatureSSE1]>; +// 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 : ProcessorModel<"x86-64", SandyBridgeModel, + [FeatureSSE2, Feature64Bit, FeatureSlowBTMem, + FeatureFastUAMem]>; + //===----------------------------------------------------------------------===// // Register File Description //===----------------------------------------------------------------------===// @@ -279,6 +430,9 @@ def ATTAsmParser : AsmParser { def ATTAsmParserVariant : AsmParserVariant { int Variant = 0; + // Variant name. + string Name = "att"; + // Discard comments in assembly strings. string CommentDelimiter = "#"; @@ -289,6 +443,9 @@ def ATTAsmParserVariant : AsmParserVariant { def IntelAsmParserVariant : AsmParserVariant { int Variant = 1; + // Variant name. + string Name = "intel"; + // Discard comments in assembly strings. string CommentDelimiter = ";"; @@ -305,12 +462,10 @@ def IntelAsmParserVariant : AsmParserVariant { def ATTAsmWriter : AsmWriter { string AsmWriterClassName = "ATTInstPrinter"; int Variant = 0; - bit isMCAsmWriter = 1; } def IntelAsmWriter : AsmWriter { string AsmWriterClassName = "IntelInstPrinter"; int Variant = 1; - bit isMCAsmWriter = 1; } def X86 : Target {