From: Sanjay Patel Date: Fri, 21 Aug 2015 20:17:26 +0000 (+0000) Subject: [x86] invert logic for attribute 'FeatureFastUAMem' X-Git-Url: http://plrg.eecs.uci.edu/git/?p=oota-llvm.git;a=commitdiff_plain;h=2071d7abd9616227d6a1c1aacb7e44b3797d6902 [x86] invert logic for attribute 'FeatureFastUAMem' This is a 'no functional change intended' patch. It removes one FIXME, but adds several more. Motivation: the FeatureFastUAMem attribute may be too general. It is used to determine if any sized misaligned memory access under 32-bytes is 'fast'. From the added FIXME comments, however, you can see that we're not consistent about this. Changing the name of the attribute makes it clearer to see the logic holes. Changing this to a 'slow' attribute also means we don't have to add an explicit 'fast' attribute to new chips; fast unaligned accesses have been standard for several generations of CPUs now. Differential Revision: http://reviews.llvm.org/D12154 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@245729 91177308-0d34-0410-b5e6-96231b3b80d8 --- diff --git a/lib/Target/X86/X86.td b/lib/Target/X86/X86.td index 7c2a0c06f30..d081614a821 100644 --- a/lib/Target/X86/X86.td +++ b/lib/Target/X86/X86.td @@ -79,16 +79,12 @@ 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">; -// FIXME: This is a 16-byte (SSE/AVX) feature; we should rename it to make that -// explicit. Also, it seems this would be the default state for most chips -// going forward, so it would probably be better to negate the logic and -// match the 32-byte "slow mem" feature below. -def FeatureFastUAMem : SubtargetFeature<"fast-unaligned-mem", - "IsUAMemFast", "true", - "Fast unaligned memory access">; +def FeatureSlowUAMem : SubtargetFeature<"slow-unaligned-mem-under-32", + "IsUAMemUnder32Slow", "true", + "Slow unaligned 16-byte-or-less memory access">; def FeatureSlowUAMem32 : SubtargetFeature<"slow-unaligned-mem-32", - "IsUAMem32Slow", "true", - "Slow unaligned 32-byte memory access">; + "IsUAMem32Slow", "true", + "Slow unaligned 32-byte memory access">; def FeatureSSE4A : SubtargetFeature<"sse4a", "HasSSE4A", "true", "Support SSE 4a instructions", [FeatureSSE3]>; @@ -213,38 +209,42 @@ def ProcIntelSLM : SubtargetFeature<"slm", "X86ProcFamily", "IntelSLM", class Proc Features> : ProcessorModel; -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<"generic", [FeatureSlowUAMem]>; +def : Proc<"i386", [FeatureSlowUAMem]>; +def : Proc<"i486", [FeatureSlowUAMem]>; +def : Proc<"i586", [FeatureSlowUAMem]>; +def : Proc<"pentium", [FeatureSlowUAMem]>; +def : Proc<"pentium-mmx", [FeatureSlowUAMem, FeatureMMX]>; +def : Proc<"i686", [FeatureSlowUAMem]>; +def : Proc<"pentiumpro", [FeatureSlowUAMem, FeatureCMOV]>; +def : Proc<"pentium2", [FeatureSlowUAMem, FeatureMMX, FeatureCMOV]>; +def : Proc<"pentium3", [FeatureSlowUAMem, FeatureSSE1]>; +def : Proc<"pentium3m", [FeatureSlowUAMem, FeatureSSE1, FeatureSlowBTMem]>; +def : Proc<"pentium-m", [FeatureSlowUAMem, FeatureSSE2, FeatureSlowBTMem]>; +def : Proc<"pentium4", [FeatureSlowUAMem, FeatureSSE2]>; +def : Proc<"pentium4m", [FeatureSlowUAMem, FeatureSSE2, FeatureSlowBTMem]>; // Intel Core Duo. def : ProcessorModel<"yonah", SandyBridgeModel, - [FeatureSSE3, FeatureSlowBTMem]>; + [FeatureSlowUAMem, FeatureSSE3, FeatureSlowBTMem]>; // NetBurst. -def : Proc<"prescott", [FeatureSSE3, FeatureSlowBTMem]>; -def : Proc<"nocona", [FeatureSSE3, FeatureCMPXCHG16B, FeatureSlowBTMem]>; +def : Proc<"prescott", [FeatureSlowUAMem, FeatureSSE3, FeatureSlowBTMem]>; +def : Proc<"nocona", [FeatureSlowUAMem, FeatureSSE3, FeatureCMPXCHG16B, + FeatureSlowBTMem]>; // Intel Core 2 Solo/Duo. def : ProcessorModel<"core2", SandyBridgeModel, - [FeatureSSSE3, FeatureCMPXCHG16B, FeatureSlowBTMem]>; + [FeatureSlowUAMem, FeatureSSSE3, FeatureCMPXCHG16B, + FeatureSlowBTMem]>; def : ProcessorModel<"penryn", SandyBridgeModel, - [FeatureSSE41, FeatureCMPXCHG16B, FeatureSlowBTMem]>; + [FeatureSlowUAMem, FeatureSSE41, FeatureCMPXCHG16B, + FeatureSlowBTMem]>; // Atom CPUs. class BonnellProc : ProcessorModel : ProcessorModel; def : SilvermontProc<"silvermont">; def : SilvermontProc<"slm">; // Legacy alias. @@ -283,7 +282,6 @@ class NehalemProc : ProcessorModel; def : NehalemProc<"nehalem">; @@ -295,7 +293,6 @@ class WestmereProc : ProcessorModel : ProcessorModel : ProcessorModel : ProcessorModel : ProcessorModel; // FIXME: define KNL model class KnightsLandingProc : ProcessorModel; class SkylakeProc : ProcessorModel; // Legacy alias. // AMD CPUs. -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, +def : Proc<"k6", [FeatureSlowUAMem, FeatureMMX]>; +def : Proc<"k6-2", [FeatureSlowUAMem, Feature3DNow]>; +def : Proc<"k6-3", [FeatureSlowUAMem, Feature3DNow]>; +def : Proc<"athlon", [FeatureSlowUAMem, Feature3DNowA, FeatureSlowBTMem, FeatureSlowSHLD]>; -def : Proc<"opteron", [FeatureSSE2, Feature3DNowA, Feature64Bit, +def : Proc<"athlon-tbird", [FeatureSlowUAMem, Feature3DNowA, FeatureSlowBTMem, FeatureSlowSHLD]>; -def : Proc<"athlon64", [FeatureSSE2, Feature3DNowA, Feature64Bit, +def : Proc<"athlon-4", [FeatureSlowUAMem, FeatureSSE1, Feature3DNowA, FeatureSlowBTMem, FeatureSlowSHLD]>; -def : Proc<"athlon-fx", [FeatureSSE2, Feature3DNowA, Feature64Bit, +def : Proc<"athlon-xp", [FeatureSlowUAMem, FeatureSSE1, Feature3DNowA, FeatureSlowBTMem, FeatureSlowSHLD]>; -def : Proc<"k8-sse3", [FeatureSSE3, Feature3DNowA, FeatureCMPXCHG16B, +def : Proc<"athlon-mp", [FeatureSlowUAMem, FeatureSSE1, Feature3DNowA, FeatureSlowBTMem, FeatureSlowSHLD]>; -def : Proc<"opteron-sse3", [FeatureSSE3, Feature3DNowA, FeatureCMPXCHG16B, - FeatureSlowBTMem, FeatureSlowSHLD]>; -def : Proc<"athlon64-sse3", [FeatureSSE3, Feature3DNowA, FeatureCMPXCHG16B, - FeatureSlowBTMem, FeatureSlowSHLD]>; -def : Proc<"amdfam10", [FeatureSSE4A, +def : Proc<"k8", [FeatureSlowUAMem, FeatureSSE2, Feature3DNowA, + Feature64Bit, FeatureSlowBTMem, + FeatureSlowSHLD]>; +def : Proc<"opteron", [FeatureSlowUAMem, FeatureSSE2, Feature3DNowA, + Feature64Bit, FeatureSlowBTMem, + FeatureSlowSHLD]>; +def : Proc<"athlon64", [FeatureSlowUAMem, FeatureSSE2, Feature3DNowA, + Feature64Bit, FeatureSlowBTMem, + FeatureSlowSHLD]>; +def : Proc<"athlon-fx", [FeatureSlowUAMem, FeatureSSE2, Feature3DNowA, + Feature64Bit, FeatureSlowBTMem, + FeatureSlowSHLD]>; +def : Proc<"k8-sse3", [FeatureSlowUAMem, FeatureSSE3, Feature3DNowA, + FeatureCMPXCHG16B, FeatureSlowBTMem, + FeatureSlowSHLD]>; +def : Proc<"opteron-sse3", [FeatureSlowUAMem, FeatureSSE3, Feature3DNowA, + FeatureCMPXCHG16B, FeatureSlowBTMem, + FeatureSlowSHLD]>; +def : Proc<"athlon64-sse3", [FeatureSlowUAMem, FeatureSSE3, Feature3DNowA, + FeatureCMPXCHG16B, FeatureSlowBTMem, + FeatureSlowSHLD]>; +def : Proc<"amdfam10", [FeatureSlowUAMem, FeatureSSE4A, Feature3DNowA, FeatureCMPXCHG16B, FeatureLZCNT, FeaturePOPCNT, FeatureSlowBTMem, FeatureSlowSHLD]>; -def : Proc<"barcelona", [FeatureSSE4A, +def : Proc<"barcelona", [FeatureSlowUAMem, FeatureSSE4A, Feature3DNowA, FeatureCMPXCHG16B, FeatureLZCNT, FeaturePOPCNT, FeatureSlowBTMem, FeatureSlowSHLD]>; + +// FIXME: We should remove 'FeatureSlowUAMem' from AMD chips under here. + // Bobcat def : Proc<"btver1", [FeatureSSSE3, FeatureSSE4A, FeatureCMPXCHG16B, FeaturePRFCHW, FeatureLZCNT, FeaturePOPCNT, - FeatureSlowSHLD]>; + FeatureSlowSHLD, FeatureSlowUAMem]>; // Jaguar def : ProcessorModel<"btver2", BtVer2Model, [FeatureAVX, FeatureSSE4A, FeatureCMPXCHG16B, FeaturePRFCHW, FeatureAES, FeaturePCLMUL, FeatureBMI, FeatureF16C, FeatureMOVBE, - FeatureLZCNT, FeaturePOPCNT, FeatureFastUAMem, + FeatureLZCNT, FeaturePOPCNT, FeatureSlowSHLD]>; -// TODO: We should probably add 'FeatureFastUAMem' to all of the AMD chips. - // Bulldozer def : Proc<"bdver1", [FeatureXOP, FeatureFMA4, FeatureCMPXCHG16B, FeatureAES, FeaturePRFCHW, FeaturePCLMUL, FeatureAVX, FeatureSSE4A, FeatureLZCNT, - FeaturePOPCNT, FeatureSlowSHLD]>; + FeaturePOPCNT, FeatureSlowSHLD, + FeatureSlowUAMem]>; // Piledriver def : Proc<"bdver2", [FeatureXOP, FeatureFMA4, FeatureCMPXCHG16B, FeatureAES, FeaturePRFCHW, FeaturePCLMUL, FeatureAVX, FeatureSSE4A, FeatureF16C, FeatureLZCNT, FeaturePOPCNT, FeatureBMI, - FeatureTBM, FeatureFMA, FeatureSlowSHLD]>; + FeatureTBM, FeatureFMA, FeatureSlowSHLD, + FeatureSlowUAMem]>; // Steamroller def : Proc<"bdver3", [FeatureXOP, FeatureFMA4, FeatureCMPXCHG16B, @@ -474,7 +477,7 @@ def : Proc<"bdver3", [FeatureXOP, FeatureFMA4, FeatureCMPXCHG16B, FeatureAVX, FeatureSSE4A, FeatureF16C, FeatureLZCNT, FeaturePOPCNT, FeatureBMI, FeatureTBM, FeatureFMA, FeatureSlowSHLD, - FeatureFSGSBase]>; + FeatureFSGSBase, FeatureSlowUAMem]>; // Excavator def : Proc<"bdver4", [FeatureAVX2, FeatureXOP, FeatureFMA4, @@ -482,14 +485,14 @@ def : Proc<"bdver4", [FeatureAVX2, FeatureXOP, FeatureFMA4, FeaturePCLMUL, FeatureF16C, FeatureLZCNT, FeaturePOPCNT, FeatureBMI, FeatureBMI2, FeatureTBM, FeatureFMA, FeatureSSE4A, - FeatureFSGSBase]>; + FeatureFSGSBase, FeatureSlowUAMem]>; -def : Proc<"geode", [Feature3DNowA]>; +def : Proc<"geode", [FeatureSlowUAMem, Feature3DNowA]>; -def : Proc<"winchip-c6", [FeatureMMX]>; -def : Proc<"winchip2", [Feature3DNow]>; -def : Proc<"c3", [Feature3DNow]>; -def : Proc<"c3-2", [FeatureSSE1]>; +def : Proc<"winchip-c6", [FeatureSlowUAMem, FeatureMMX]>; +def : Proc<"winchip2", [FeatureSlowUAMem, Feature3DNow]>; +def : Proc<"c3", [FeatureSlowUAMem, Feature3DNow]>; +def : Proc<"c3-2", [FeatureSlowUAMem, 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 @@ -502,8 +505,7 @@ def : Proc<"c3-2", [FeatureSSE1]>; // 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]>; + [FeatureSSE2, Feature64Bit, FeatureSlowBTMem]>; //===----------------------------------------------------------------------===// // Register File Description diff --git a/lib/Target/X86/X86ISelLowering.cpp b/lib/Target/X86/X86ISelLowering.cpp index 9f1bf6ddeb0..430ee22916c 100644 --- a/lib/Target/X86/X86ISelLowering.cpp +++ b/lib/Target/X86/X86ISelLowering.cpp @@ -1876,10 +1876,11 @@ X86TargetLowering::getOptimalMemOpType(uint64_t Size, if ((!IsMemset || ZeroMemset) && !F->hasFnAttribute(Attribute::NoImplicitFloat)) { if (Size >= 16 && - (Subtarget->isUnalignedMemAccessFast() || + (!Subtarget->isUnalignedMemUnder32Slow() || ((DstAlign == 0 || DstAlign >= 16) && (SrcAlign == 0 || SrcAlign >= 16)))) { if (Size >= 32) { + // FIXME: Check if unaligned 32-byte accesses are slow. if (Subtarget->hasInt256()) return MVT::v8i32; if (Subtarget->hasFp256()) @@ -1897,6 +1898,9 @@ X86TargetLowering::getOptimalMemOpType(uint64_t Size, return MVT::f64; } } + // This is a compromise. If we reach here, unaligned accesses may be slow on + // this target. However, creating smaller, aligned accesses could be even + // slower and would certainly be a lot more code. if (Subtarget->is64Bit() && Size >= 8) return MVT::i64; return MVT::i32; @@ -1916,12 +1920,10 @@ X86TargetLowering::allowsMisalignedMemoryAccesses(EVT VT, unsigned, bool *Fast) const { if (Fast) { - // FIXME: We should be checking 128-bit accesses separately from smaller - // accesses. if (VT.getSizeInBits() == 256) *Fast = !Subtarget->isUnalignedMem32Slow(); else - *Fast = Subtarget->isUnalignedMemAccessFast(); + *Fast = !Subtarget->isUnalignedMemUnder32Slow(); } return true; } diff --git a/lib/Target/X86/X86InstrInfo.cpp b/lib/Target/X86/X86InstrInfo.cpp index d964bf17a0f..9d799d8e780 100644 --- a/lib/Target/X86/X86InstrInfo.cpp +++ b/lib/Target/X86/X86InstrInfo.cpp @@ -5508,9 +5508,10 @@ bool X86InstrInfo::unfoldMemoryOperand(MachineFunction &MF, MachineInstr *MI, const MCInstrDesc &MCID = get(Opc); const TargetRegisterClass *RC = getRegClass(MCID, Index, &RI, MF); + // TODO: Check if 32-byte or greater accesses are slow too? if (!MI->hasOneMemOperand() && RC == &X86::VR128RegClass && - !Subtarget.isUnalignedMemAccessFast()) + Subtarget.isUnalignedMemUnder32Slow()) // Without memoperands, loadRegFromAddr and storeRegToStackSlot will // conservatively assume the address is unaligned. That's bad for // performance. @@ -5658,9 +5659,11 @@ X86InstrInfo::unfoldMemoryOperand(SelectionDAG &DAG, SDNode *N, cast(N)->memoperands_end()); if (!(*MMOs.first) && RC == &X86::VR128RegClass && - !Subtarget.isUnalignedMemAccessFast()) + Subtarget.isUnalignedMemUnder32Slow()) // Do not introduce a slow unaligned load. return false; + // FIXME: If a VR128 can have size 32, we should be checking if a 32-byte + // memory access is slow above. unsigned Alignment = RC->getSize() == 32 ? 32 : 16; bool isAligned = (*MMOs.first) && (*MMOs.first)->getAlignment() >= Alignment; @@ -5701,9 +5704,11 @@ X86InstrInfo::unfoldMemoryOperand(SelectionDAG &DAG, SDNode *N, cast(N)->memoperands_end()); if (!(*MMOs.first) && RC == &X86::VR128RegClass && - !Subtarget.isUnalignedMemAccessFast()) + Subtarget.isUnalignedMemUnder32Slow()) // Do not introduce a slow unaligned store. return false; + // FIXME: If a VR128 can have size 32, we should be checking if a 32-byte + // memory access is slow above. unsigned Alignment = RC->getSize() == 32 ? 32 : 16; bool isAligned = (*MMOs.first) && (*MMOs.first)->getAlignment() >= Alignment; diff --git a/lib/Target/X86/X86Subtarget.cpp b/lib/Target/X86/X86Subtarget.cpp index c3f686dd58f..565ba1ded7e 100644 --- a/lib/Target/X86/X86Subtarget.cpp +++ b/lib/Target/X86/X86Subtarget.cpp @@ -255,7 +255,7 @@ void X86Subtarget::initializeEnvironment() { HasMPX = false; IsBTMemSlow = false; IsSHLDSlow = false; - IsUAMemFast = false; + IsUAMemUnder32Slow = false; IsUAMem32Slow = false; HasSSEUnalignedMem = false; HasCmpxchg16b = false; diff --git a/lib/Target/X86/X86Subtarget.h b/lib/Target/X86/X86Subtarget.h index 14e0088bc9b..d5d00277e5b 100644 --- a/lib/Target/X86/X86Subtarget.h +++ b/lib/Target/X86/X86Subtarget.h @@ -146,10 +146,10 @@ protected: /// True if SHLD instructions are slow. bool IsSHLDSlow; - /// True if unaligned memory access is fast. - bool IsUAMemFast; + /// True if unaligned memory accesses of 16-bytes or smaller are slow. + bool IsUAMemUnder32Slow; - /// True if unaligned 32-byte memory accesses are slow. + /// True if unaligned memory accesses of 32-bytes are slow. bool IsUAMem32Slow; /// True if SSE operations can have unaligned memory operands. @@ -357,7 +357,7 @@ public: bool hasRDSEED() const { return HasRDSEED; } bool isBTMemSlow() const { return IsBTMemSlow; } bool isSHLDSlow() const { return IsSHLDSlow; } - bool isUnalignedMemAccessFast() const { return IsUAMemFast; } + bool isUnalignedMemUnder32Slow() const { return IsUAMemUnder32Slow; } bool isUnalignedMem32Slow() const { return IsUAMem32Slow; } bool hasSSEUnalignedMem() const { return HasSSEUnalignedMem; } bool hasCmpxchg16b() const { return HasCmpxchg16b; }