def FeaturePOPCNT : SubtargetFeature<"popcnt", "HasPOPCNT", "true",
"Support POPCNT instruction">;
+def FeatureXSAVE : SubtargetFeature<"xsave", "HasXSAVE", "true",
+ "Support xsave instructions">;
-def FeatureMMX : SubtargetFeature<"mmx","X86SSELevel", "MMX",
+def FeatureXSAVEOPT: SubtargetFeature<"xsaveopt", "HasXSAVEOPT", "true",
+ "Support xsaveopt instructions">;
+
+def FeatureXSAVEC : SubtargetFeature<"xsavec", "HasXSAVEC", "true",
+ "Support xsavec instructions">;
+
+def FeatureXSAVES : SubtargetFeature<"xsaves", "HasXSAVES", "true",
+ "Support xsaves instructions">;
+
+// 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","HasMMX", "true",
"Enable MMX instructions">;
+
def FeatureSSE1 : SubtargetFeature<"sse", "X86SSELevel", "SSE1",
"Enable SSE instructions",
// SSE codegen depends on cmovs, and all
// SSE1+ processors support them.
- [FeatureMMX, FeatureCMOV]>;
+ [FeatureCMOV]>;
def FeatureSSE2 : SubtargetFeature<"sse2", "X86SSELevel", "SSE2",
"Enable SSE2 instructions",
[FeatureSSE1]>;
"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">;
+// 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 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]>;
def FeatureXOP : SubtargetFeature<"xop", "HasXOP", "true",
"Enable XOP instructions",
[FeatureFMA4]>;
-def FeatureVectorUAMem : SubtargetFeature<"vector-unaligned-mem",
- "HasVectorUAMem", "true",
- "Allow unaligned memory operands on vector/SIMD instructions">;
+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]>;
"Support PRFCHW instructions">;
def FeatureRDSEED : SubtargetFeature<"rdseed", "HasRDSEED", "true",
"Support RDSEED instruction">;
+def FeatureMPX : SubtargetFeature<"mpx", "HasMPX", "true",
+ "Support MPX instructions">;
def FeatureLeaForSP : SubtargetFeature<"lea-sp", "UseLeaForSP", "true",
"Use LEA for adjusting the stack pointer">;
-def FeatureSlowDivide : SubtargetFeature<"idiv-to-divb",
- "HasSlowDivide", "true",
- "Use small divide for positive values less than 256">;
+def FeatureSlowDivide32 : SubtargetFeature<"idivl-to-divb",
+ "HasSlowDivide32", "true",
+ "Use 8-bit divide for positive values less than 256">;
+def FeatureSlowDivide64 : SubtargetFeature<"idivq-to-divw",
+ "HasSlowDivide64", "true",
+ "Use 16-bit divide for positive values less than 65536">;
def FeaturePadShortFunctions : SubtargetFeature<"pad-short-functions",
"PadShortFunctions", "true",
"Pad short functions">;
+// TODO: This feature ought to be renamed.
+// What it really refers to are CPUs for which certain instructions
+// (which ones besides the example below?) are microcoded.
+// The best examples of this are the memory forms of CALL and PUSH
+// instructions, which should be avoided in favor of a MOV + register CALL/PUSH.
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 FeatureSoftFloat
+ : SubtargetFeature<"soft-float", "UseSoftFloat", "true",
+ "Use software floating point features.">;
//===----------------------------------------------------------------------===//
// X86 processors supported.
class Proc<string Name, list<SubtargetFeature> Features>
: ProcessorModel<Name, GenericModel, Features>;
-def : Proc<"generic", []>;
-def : Proc<"i386", []>;
-def : Proc<"i486", []>;
-def : Proc<"i586", []>;
-def : Proc<"pentium", []>;
-def : Proc<"pentium-mmx", [FeatureMMX]>;
-def : Proc<"i686", []>;
-def : Proc<"pentiumpro", [FeatureCMOV]>;
-def : Proc<"pentium2", [FeatureMMX, FeatureCMOV]>;
-def : Proc<"pentium3", [FeatureSSE1]>;
-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<"generic", [FeatureSlowUAMem16]>;
+def : Proc<"i386", [FeatureSlowUAMem16]>;
+def : Proc<"i486", [FeatureSlowUAMem16]>;
+def : Proc<"i586", [FeatureSlowUAMem16]>;
+def : Proc<"pentium", [FeatureSlowUAMem16]>;
+def : Proc<"pentium-mmx", [FeatureSlowUAMem16, FeatureMMX]>;
+def : Proc<"i686", [FeatureSlowUAMem16]>;
+def : Proc<"pentiumpro", [FeatureSlowUAMem16, FeatureCMOV]>;
+def : Proc<"pentium2", [FeatureSlowUAMem16, FeatureMMX, FeatureCMOV]>;
+def : Proc<"pentium3", [FeatureSlowUAMem16, FeatureMMX, FeatureSSE1]>;
+def : Proc<"pentium3m", [FeatureSlowUAMem16, FeatureMMX, FeatureSSE1,
+ FeatureSlowBTMem]>;
+def : Proc<"pentium-m", [FeatureSlowUAMem16, FeatureMMX, FeatureSSE2,
+ FeatureSlowBTMem]>;
+def : Proc<"pentium4", [FeatureSlowUAMem16, FeatureMMX, FeatureSSE2]>;
+def : Proc<"pentium4m", [FeatureSlowUAMem16, FeatureMMX, FeatureSSE2,
+ FeatureSlowBTMem]>;
+
// Intel Core Duo.
-def : ProcessorModel<"yonah", SandyBridgeModel,
- [FeatureSSE3, FeatureSlowBTMem]>;
+def : ProcessorModel<
+ "yonah", SandyBridgeModel,
+ [ FeatureSlowUAMem16, FeatureMMX, FeatureSSE3, FeatureSlowBTMem ]>;
// NetBurst.
-def : Proc<"prescott", [FeatureSSE3, FeatureSlowBTMem]>;
-def : Proc<"nocona", [FeatureSSE3, FeatureCMPXCHG16B, FeatureSlowBTMem]>;
+def : Proc<"prescott",
+ [ FeatureSlowUAMem16, FeatureMMX, FeatureSSE3, FeatureSlowBTMem ]>;
+def : Proc<"nocona", [
+ FeatureSlowUAMem16,
+ FeatureMMX,
+ 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,
- FeatureSlowBTMem, FeatureFastUAMem]>;
+def : ProcessorModel<"core2", SandyBridgeModel, [
+ FeatureSlowUAMem16,
+ FeatureMMX,
+ FeatureSSSE3,
+ FeatureCMPXCHG16B,
+ FeatureSlowBTMem
+]>;
+def : ProcessorModel<"penryn", SandyBridgeModel, [
+ FeatureSlowUAMem16,
+ FeatureMMX,
+ FeatureSSE41,
+ FeatureCMPXCHG16B,
+ FeatureSlowBTMem
+]>;
+
+// Atom CPUs.
+class BonnellProc<string Name> : ProcessorModel<Name, AtomModel, [
+ ProcIntelAtom,
+ FeatureSlowUAMem16,
+ FeatureMMX,
+ FeatureSSSE3,
+ FeatureCMPXCHG16B,
+ FeatureMOVBE,
+ FeatureSlowBTMem,
+ FeatureLeaForSP,
+ FeatureSlowDivide32,
+ FeatureSlowDivide64,
+ FeatureCallRegIndirect,
+ FeatureLEAUsesAG,
+ FeaturePadShortFunctions
+]>;
+def : BonnellProc<"bonnell">;
+def : BonnellProc<"atom">; // Pin the generic name to the baseline.
+
+class SilvermontProc<string Name> : ProcessorModel<Name, SLMModel, [
+ ProcIntelSLM,
+ FeatureMMX,
+ FeatureSSE42,
+ FeatureCMPXCHG16B,
+ FeatureMOVBE,
+ FeaturePOPCNT,
+ FeaturePCLMUL,
+ FeatureAES,
+ FeatureSlowDivide64,
+ FeatureCallRegIndirect,
+ FeaturePRFCHW,
+ FeatureSlowLEA,
+ FeatureSlowIncDec,
+ FeatureSlowBTMem
+]>;
+def : SilvermontProc<"silvermont">;
+def : SilvermontProc<"slm">; // Legacy alias.
+
// "Arrandale" along with corei3 and corei5
-def : ProcessorModel<"corei7", SandyBridgeModel,
- [FeatureSSE42, FeatureCMPXCHG16B, FeatureSlowBTMem,
- FeatureFastUAMem, FeaturePOPCNT, FeatureAES]>;
+class NehalemProc<string Name> : ProcessorModel<Name, SandyBridgeModel, [
+ FeatureMMX,
+ FeatureSSE42,
+ FeatureCMPXCHG16B,
+ FeatureSlowBTMem,
+ FeaturePOPCNT
+]>;
+def : NehalemProc<"nehalem">;
+def : NehalemProc<"corei7">;
-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 : ProcessorModel<"westmere", SandyBridgeModel,
- [FeatureSSE42, FeatureCMPXCHG16B, FeatureSlowBTMem,
- FeatureFastUAMem, FeaturePOPCNT, FeatureAES,
- FeaturePCLMUL]>;
-// Sandy Bridge
+class WestmereProc<string Name> : ProcessorModel<Name, SandyBridgeModel, [
+ FeatureMMX,
+ FeatureSSE42,
+ FeatureCMPXCHG16B,
+ FeatureSlowBTMem,
+ FeaturePOPCNT,
+ FeatureAES,
+ FeaturePCLMUL
+]>;
+def : WestmereProc<"westmere">;
+
// SSE is not listed here since llvm treats AVX as a reimplementation of SSE,
// rather than a superset.
-def : ProcessorModel<"corei7-avx", SandyBridgeModel,
- [FeatureAVX, FeatureCMPXCHG16B, FeatureFastUAMem,
- FeaturePOPCNT, FeatureAES, FeaturePCLMUL]>;
-// Ivy Bridge
-def : ProcessorModel<"core-avx-i", SandyBridgeModel,
- [FeatureAVX, FeatureCMPXCHG16B, FeatureFastUAMem,
- FeaturePOPCNT, FeatureAES, FeaturePCLMUL, FeatureRDRAND,
- FeatureF16C, FeatureFSGSBase]>;
-
-// Haswell
-def : ProcessorModel<"core-avx2", HaswellModel,
- [FeatureAVX2, FeatureCMPXCHG16B, FeatureFastUAMem,
- FeaturePOPCNT, FeatureAES, FeaturePCLMUL, FeatureRDRAND,
- FeatureF16C, FeatureFSGSBase, FeatureMOVBE, FeatureLZCNT,
- FeatureBMI, FeatureBMI2, FeatureFMA, FeatureRTM,
- FeatureHLE]>;
-
-// KNL
+class SandyBridgeProc<string Name> : ProcessorModel<Name, SandyBridgeModel, [
+ FeatureMMX,
+ FeatureAVX,
+ FeatureCMPXCHG16B,
+ FeatureSlowBTMem,
+ FeatureSlowUAMem32,
+ FeaturePOPCNT,
+ FeatureAES,
+ FeaturePCLMUL
+]>;
+def : SandyBridgeProc<"sandybridge">;
+def : SandyBridgeProc<"corei7-avx">; // Legacy alias.
+
+class IvyBridgeProc<string Name> : ProcessorModel<Name, SandyBridgeModel, [
+ FeatureMMX,
+ FeatureAVX,
+ FeatureCMPXCHG16B,
+ FeatureSlowBTMem,
+ FeatureSlowUAMem32,
+ FeaturePOPCNT,
+ FeatureAES,
+ FeaturePCLMUL,
+ FeatureRDRAND,
+ FeatureF16C,
+ FeatureFSGSBase
+]>;
+def : IvyBridgeProc<"ivybridge">;
+def : IvyBridgeProc<"core-avx-i">; // Legacy alias.
+
+class HaswellProc<string Name> : ProcessorModel<Name, HaswellModel, [
+ FeatureMMX,
+ FeatureAVX2,
+ FeatureCMPXCHG16B,
+ FeatureSlowBTMem,
+ FeaturePOPCNT,
+ FeatureAES,
+ FeaturePCLMUL,
+ FeatureRDRAND,
+ FeatureF16C,
+ FeatureFSGSBase,
+ FeatureMOVBE,
+ FeatureLZCNT,
+ FeatureBMI,
+ FeatureBMI2,
+ FeatureFMA,
+ FeatureRTM,
+ FeatureHLE,
+ FeatureSlowIncDec
+]>;
+def : HaswellProc<"haswell">;
+def : HaswellProc<"core-avx2">; // Legacy alias.
+
+class BroadwellProc<string Name> : ProcessorModel<Name, HaswellModel, [
+ FeatureMMX,
+ FeatureAVX2,
+ FeatureCMPXCHG16B,
+ FeatureSlowBTMem,
+ FeaturePOPCNT,
+ FeatureAES,
+ FeaturePCLMUL,
+ FeatureRDRAND,
+ FeatureF16C,
+ FeatureFSGSBase,
+ FeatureMOVBE,
+ FeatureLZCNT,
+ FeatureBMI,
+ FeatureBMI2,
+ FeatureFMA,
+ FeatureRTM,
+ FeatureHLE,
+ FeatureADX,
+ FeatureRDSEED,
+ FeatureSlowIncDec
+]>;
+def : BroadwellProc<"broadwell">;
+
// 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]>;
-
-def : Proc<"k6", [FeatureMMX]>;
-def : Proc<"k6-2", [Feature3DNow]>;
-def : Proc<"k6-3", [Feature3DNow]>;
-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,
+class KnightsLandingProc<string Name> : ProcessorModel<Name, HaswellModel, [
+ FeatureMMX,
+ FeatureAVX512,
+ FeatureERI,
+ FeatureCDI,
+ FeaturePFI,
+ FeatureCMPXCHG16B,
+ FeaturePOPCNT,
+ FeatureAES,
+ FeaturePCLMUL,
+ FeatureRDRAND,
+ FeatureF16C,
+ FeatureFSGSBase,
+ FeatureMOVBE,
+ FeatureLZCNT,
+ FeatureBMI,
+ FeatureBMI2,
+ FeatureFMA,
+ FeatureRTM,
+ FeatureHLE,
+ FeatureSlowIncDec,
+ FeatureMPX
+]>;
+def : KnightsLandingProc<"knl">;
+
+// FIXME: define SKX model
+class SkylakeProc<string Name> : ProcessorModel<Name, HaswellModel, [
+ FeatureMMX,
+ FeatureAVX512,
+ FeatureCDI,
+ FeatureDQI,
+ FeatureBWI,
+ FeatureVLX,
+ FeatureCMPXCHG16B,
+ FeatureSlowBTMem,
+ FeaturePOPCNT,
+ FeatureAES,
+ FeaturePCLMUL,
+ FeatureRDRAND,
+ FeatureF16C,
+ FeatureFSGSBase,
+ FeatureMOVBE,
+ FeatureLZCNT,
+ FeatureBMI,
+ FeatureBMI2,
+ FeatureFMA,
+ FeatureRTM,
+ FeatureHLE,
+ FeatureADX,
+ FeatureRDSEED,
+ FeatureSlowIncDec,
+ FeatureMPX
+]>;
+def : SkylakeProc<"skylake">;
+def : SkylakeProc<"skx">; // Legacy alias.
+
+
+// AMD CPUs.
+
+def : Proc<"k6", [FeatureSlowUAMem16, FeatureMMX]>;
+def : Proc<"k6-2", [FeatureSlowUAMem16, Feature3DNow]>;
+def : Proc<"k6-3", [FeatureSlowUAMem16, Feature3DNow]>;
+def : Proc<"athlon", [FeatureSlowUAMem16, Feature3DNowA,
FeatureSlowBTMem, FeatureSlowSHLD]>;
-def : Proc<"opteron", [FeatureSSE2, Feature3DNowA, Feature64Bit,
+def : Proc<"athlon-tbird", [FeatureSlowUAMem16, Feature3DNowA,
FeatureSlowBTMem, FeatureSlowSHLD]>;
-def : Proc<"athlon64", [FeatureSSE2, Feature3DNowA, Feature64Bit,
+def : Proc<"athlon-4", [FeatureSlowUAMem16, FeatureSSE1, Feature3DNowA,
FeatureSlowBTMem, FeatureSlowSHLD]>;
-def : Proc<"athlon-fx", [FeatureSSE2, Feature3DNowA, Feature64Bit,
+def : Proc<"athlon-xp", [FeatureSlowUAMem16, FeatureSSE1, Feature3DNowA,
FeatureSlowBTMem, FeatureSlowSHLD]>;
-def : Proc<"k8-sse3", [FeatureSSE3, Feature3DNowA, FeatureCMPXCHG16B,
- FeatureSlowBTMem, FeatureSlowSHLD]>;
-def : Proc<"opteron-sse3", [FeatureSSE3, Feature3DNowA, FeatureCMPXCHG16B,
- FeatureSlowBTMem, FeatureSlowSHLD]>;
-def : Proc<"athlon64-sse3", [FeatureSSE3, Feature3DNowA, FeatureCMPXCHG16B,
+def : Proc<"athlon-mp", [FeatureSlowUAMem16, FeatureSSE1, Feature3DNowA,
FeatureSlowBTMem, FeatureSlowSHLD]>;
+def : Proc<"k8", [FeatureSlowUAMem16, FeatureSSE2, Feature3DNowA,
+ Feature64Bit, FeatureSlowBTMem,
+ FeatureSlowSHLD]>;
+def : Proc<"opteron", [FeatureSlowUAMem16, FeatureSSE2, Feature3DNowA,
+ Feature64Bit, FeatureSlowBTMem,
+ FeatureSlowSHLD]>;
+def : Proc<"athlon64", [FeatureSlowUAMem16, FeatureSSE2, Feature3DNowA,
+ Feature64Bit, FeatureSlowBTMem,
+ FeatureSlowSHLD]>;
+def : Proc<"athlon-fx", [FeatureSlowUAMem16, FeatureSSE2, Feature3DNowA,
+ Feature64Bit, FeatureSlowBTMem,
+ FeatureSlowSHLD]>;
+def : Proc<"k8-sse3", [FeatureSlowUAMem16, FeatureSSE3, Feature3DNowA,
+ FeatureCMPXCHG16B, FeatureSlowBTMem,
+ FeatureSlowSHLD]>;
+def : Proc<"opteron-sse3", [FeatureSlowUAMem16, FeatureSSE3, Feature3DNowA,
+ FeatureCMPXCHG16B, FeatureSlowBTMem,
+ FeatureSlowSHLD]>;
+def : Proc<"athlon64-sse3", [FeatureSlowUAMem16, FeatureSSE3, Feature3DNowA,
+ FeatureCMPXCHG16B, FeatureSlowBTMem,
+ FeatureSlowSHLD]>;
def : Proc<"amdfam10", [FeatureSSE4A,
Feature3DNowA, FeatureCMPXCHG16B, FeatureLZCNT,
FeaturePOPCNT, FeatureSlowBTMem,
FeatureSlowSHLD]>;
-// Bobcat
-def : Proc<"btver1", [FeatureSSSE3, FeatureSSE4A, FeatureCMPXCHG16B,
- FeaturePRFCHW, FeatureLZCNT, FeaturePOPCNT,
+def : Proc<"barcelona", [FeatureSSE4A,
+ Feature3DNowA, FeatureCMPXCHG16B, FeatureLZCNT,
+ FeaturePOPCNT, FeatureSlowBTMem,
FeatureSlowSHLD]>;
+
+// Bobcat
+def : Proc<"btver1", [
+ FeatureMMX,
+ FeatureSSSE3,
+ FeatureSSE4A,
+ FeatureCMPXCHG16B,
+ FeaturePRFCHW,
+ FeatureLZCNT,
+ FeaturePOPCNT,
+ FeatureSlowSHLD
+]>;
+
// Jaguar
-def : Proc<"btver2", [FeatureAVX, FeatureSSE4A, FeatureCMPXCHG16B,
- FeaturePRFCHW, FeatureAES, FeaturePCLMUL,
- FeatureBMI, FeatureF16C, FeatureMOVBE,
- FeatureLZCNT, FeaturePOPCNT, FeatureSlowSHLD]>;
+def : ProcessorModel<"btver2", BtVer2Model, [
+ FeatureMMX,
+ FeatureAVX,
+ FeatureSSE4A,
+ FeatureCMPXCHG16B,
+ FeaturePRFCHW,
+ FeatureAES,
+ FeaturePCLMUL,
+ FeatureBMI,
+ FeatureF16C,
+ FeatureMOVBE,
+ FeatureLZCNT,
+ FeaturePOPCNT,
+ FeatureSlowSHLD
+]>;
+
// Bulldozer
-def : Proc<"bdver1", [FeatureXOP, FeatureFMA4, FeatureCMPXCHG16B,
- FeatureAES, FeaturePRFCHW, FeaturePCLMUL,
- FeatureLZCNT, FeaturePOPCNT, FeatureSlowSHLD]>;
+def : Proc<"bdver1", [
+ FeatureXOP,
+ FeatureFMA4,
+ FeatureCMPXCHG16B,
+ FeatureAES,
+ FeaturePRFCHW,
+ FeaturePCLMUL,
+ FeatureMMX,
+ FeatureAVX,
+ FeatureSSE4A,
+ FeatureLZCNT,
+ FeaturePOPCNT,
+ FeatureSlowSHLD
+]>;
// Piledriver
-def : Proc<"bdver2", [FeatureXOP, FeatureFMA4, FeatureCMPXCHG16B,
- FeatureAES, FeaturePRFCHW, FeaturePCLMUL,
- FeatureF16C, FeatureLZCNT,
- FeaturePOPCNT, FeatureBMI, FeatureTBM,
- FeatureFMA, FeatureSlowSHLD]>;
+def : Proc<"bdver2", [
+ FeatureXOP,
+ FeatureFMA4,
+ FeatureCMPXCHG16B,
+ FeatureAES,
+ FeaturePRFCHW,
+ FeaturePCLMUL,
+ FeatureMMX,
+ FeatureAVX,
+ FeatureSSE4A,
+ FeatureF16C,
+ FeatureLZCNT,
+ FeaturePOPCNT,
+ FeatureBMI,
+ FeatureTBM,
+ FeatureFMA,
+ FeatureSlowSHLD
+]>;
// Steamroller
-def : Proc<"bdver3", [FeatureXOP, FeatureFMA4, FeatureCMPXCHG16B,
- FeatureAES, FeaturePRFCHW, FeaturePCLMUL,
- FeatureF16C, FeatureLZCNT,
- FeaturePOPCNT, FeatureBMI, FeatureTBM,
- FeatureFMA, FeatureFSGSBase]>;
-
-def : Proc<"geode", [Feature3DNowA]>;
-
-def : Proc<"winchip-c6", [FeatureMMX]>;
-def : Proc<"winchip2", [Feature3DNow]>;
-def : Proc<"c3", [Feature3DNow]>;
-def : Proc<"c3-2", [FeatureSSE1]>;
+def : Proc<"bdver3", [
+ FeatureXOP,
+ FeatureFMA4,
+ FeatureCMPXCHG16B,
+ FeatureAES,
+ FeaturePRFCHW,
+ FeaturePCLMUL,
+ FeatureMMX,
+ FeatureAVX,
+ FeatureSSE4A,
+ FeatureF16C,
+ FeatureLZCNT,
+ FeaturePOPCNT,
+ FeatureBMI,
+ FeatureTBM,
+ FeatureFMA,
+ FeatureSlowSHLD,
+ FeatureFSGSBase
+]>;
+
+// Excavator
+def : Proc<"bdver4", [
+ FeatureMMX,
+ FeatureAVX2,
+ FeatureXOP,
+ FeatureFMA4,
+ FeatureCMPXCHG16B,
+ FeatureAES,
+ FeaturePRFCHW,
+ FeaturePCLMUL,
+ FeatureF16C,
+ FeatureLZCNT,
+ FeaturePOPCNT,
+ FeatureBMI,
+ FeatureBMI2,
+ FeatureTBM,
+ FeatureFMA,
+ FeatureSSE4A,
+ FeatureFSGSBase
+]>;
+
+def : Proc<"geode", [FeatureSlowUAMem16, Feature3DNowA]>;
+
+def : Proc<"winchip-c6", [FeatureSlowUAMem16, FeatureMMX]>;
+def : Proc<"winchip2", [FeatureSlowUAMem16, Feature3DNow]>;
+def : Proc<"c3", [FeatureSlowUAMem16, Feature3DNow]>;
+def : Proc<"c3-2", [ FeatureSlowUAMem16, FeatureMMX, 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,
+ [ FeatureMMX, FeatureSSE2, Feature64Bit, FeatureSlowBTMem ]>;
//===----------------------------------------------------------------------===//
// Register File Description
projects / oota-llvm.git / blobdiff