diff options
Diffstat (limited to 'contrib/llvm/lib/Target/X86/X86.td')
| -rw-r--r-- | contrib/llvm/lib/Target/X86/X86.td | 106 |
1 files changed, 81 insertions, 25 deletions
diff --git a/contrib/llvm/lib/Target/X86/X86.td b/contrib/llvm/lib/Target/X86/X86.td index 65c5552..cd32a0f 100644 --- a/contrib/llvm/lib/Target/X86/X86.td +++ b/contrib/llvm/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 @@ -73,6 +77,8 @@ def FeatureCMPXCHG16B : SubtargetFeature<"cx16", "HasCmpxchg16b", "true", [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">; @@ -98,7 +104,15 @@ def FeatureCDI : SubtargetFeature<"avx512cd", "HasCDI", "true", 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]>; @@ -160,6 +174,10 @@ def FeatureCallRegIndirect : SubtargetFeature<"call-reg-indirect", "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">; //===----------------------------------------------------------------------===// // X86 processors supported. @@ -189,8 +207,7 @@ 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]>; + // Intel Core Duo. def : ProcessorModel<"yonah", SandyBridgeModel, [FeatureSSE3, FeatureSlowBTMem]>; @@ -221,7 +238,8 @@ def : ProcessorModel<"slm", SLMModel, [ProcIntelSLM, FeaturePCLMUL, FeatureAES, FeatureCallRegIndirect, FeaturePRFCHW, - FeatureSlowBTMem]>; + FeatureSlowLEA, FeatureSlowIncDec, + FeatureSlowBTMem, FeatureFastUAMem]>; // "Arrandale" along with corei3 and corei5 def : ProcessorModel<"corei7", SandyBridgeModel, [FeatureSSE42, FeatureCMPXCHG16B, FeatureSlowBTMem, @@ -263,51 +281,70 @@ def : ProcessorModel<"knl", HaswellModel, FeatureCMPXCHG16B, FeatureFastUAMem, FeaturePOPCNT, FeatureAES, FeaturePCLMUL, FeatureRDRAND, FeatureF16C, FeatureFSGSBase, FeatureMOVBE, FeatureLZCNT, FeatureBMI, - FeatureBMI2, FeatureFMA, FeatureRTM, FeatureHLE]>; + 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]>; 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, - FeaturePRFCHW, FeatureLZCNT, FeaturePOPCNT]>; + FeaturePRFCHW, FeatureLZCNT, FeaturePOPCNT, + FeatureSlowSHLD]>; // Jaguar def : Proc<"btver2", [FeatureAVX, FeatureSSE4A, FeatureCMPXCHG16B, FeaturePRFCHW, FeatureAES, FeaturePCLMUL, FeatureBMI, FeatureF16C, FeatureMOVBE, - FeatureLZCNT, FeaturePOPCNT]>; + FeatureLZCNT, FeaturePOPCNT, FeatureSlowSHLD]>; // Bulldozer def : Proc<"bdver1", [FeatureXOP, FeatureFMA4, FeatureCMPXCHG16B, FeatureAES, FeaturePRFCHW, FeaturePCLMUL, - FeatureLZCNT, FeaturePOPCNT]>; + FeatureLZCNT, FeaturePOPCNT, FeatureSlowSHLD]>; // Piledriver def : Proc<"bdver2", [FeatureXOP, FeatureFMA4, FeatureCMPXCHG16B, FeatureAES, FeaturePRFCHW, FeaturePCLMUL, FeatureF16C, FeatureLZCNT, - FeaturePOPCNT, FeatureBMI, FeatureTBM, - FeatureFMA]>; + FeaturePOPCNT, FeatureBMI, FeatureTBM, + FeatureFMA, FeatureSlowSHLD]>; // Steamroller def : Proc<"bdver3", [FeatureXOP, FeatureFMA4, FeatureCMPXCHG16B, @@ -316,6 +353,13 @@ def : Proc<"bdver3", [FeatureXOP, FeatureFMA4, FeatureCMPXCHG16B, 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]>; @@ -323,6 +367,20 @@ 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 //===----------------------------------------------------------------------===// @@ -387,12 +445,10 @@ 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 { |
