maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[X86] Use ADD/SUB instead of INC/DEC for Silvermont 

According to Intel Software Optimization Manual 
on Silvermont INC or DEC instructions require 
an additional uop to merge the flags.
As a result, a branch instruction depending 
on an INC or a DEC instruction incurs a 1 cycle penalty.

Differential Revision: http://reviews.llvm.org/D3990

llvm-svn: 210466
This commit is contained in:
Alexey Volkov 2014-06-09 11:40:41 +00:00
parent b22b963669
commit 5260dba323
6 changed files with 37 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
llvm/lib/Target/X86/X86.td
View File

@ -168,6 +168,8 @@ 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.
@ -228,7 +230,7 @@ def : ProcessorModel<"slm", SLMModel, [ProcIntelSLM,
FeaturePCLMUL, FeatureAES,
FeatureCallRegIndirect,
FeaturePRFCHW,
FeatureSlowLEA,
FeatureSlowLEA, FeatureSlowIncDec,
FeatureSlowBTMem, FeatureFastUAMem]>;
// "Arrandale" along with corei3 and corei5
def : ProcessorModel<"corei7", SandyBridgeModel,

4
llvm/lib/Target/X86/X86ISelLowering.cpp
View File

@ -10139,14 +10139,14 @@ SDValue X86TargetLowering::EmitTest(SDValue Op, unsigned X86CC, SDLoc dl,
if (ConstantSDNode *C =
dyn_cast<ConstantSDNode>(ArithOp.getNode()->getOperand(1))) {
// An add of one will be selected as an INC.
if (C->getAPIntValue() == 1) {
if (C->getAPIntValue() == 1 && !Subtarget->slowIncDec()) {
Opcode = X86ISD::INC;
NumOperands = 1;
break;
}
// An add of negative one (subtract of one) will be selected as a DEC.
if (C->getAPIntValue().isAllOnesValue()) {
if (C->getAPIntValue().isAllOnesValue() && !Subtarget->slowIncDec()) {
Opcode = X86ISD::DEC;
NumOperands = 1;
break;

38
llvm/lib/Target/X86/X86InstrCompiler.td
View File

@ -1696,20 +1696,34 @@ def : Pat<(mul (loadi64 addr:$src1), i64immSExt32:$src2),
(IMUL64rmi32 addr:$src1, i64immSExt32:$src2)>;
// Increment reg.
def : Pat<(add GR8 :$src, 1), (INC8r GR8 :$src)>;
def : Pat<(add GR16:$src, 1), (INC16r GR16:$src)>, Requires<[Not64BitMode]>;
def : Pat<(add GR16:$src, 1), (INC64_16r GR16:$src)>, Requires<[In64BitMode]>;
def : Pat<(add GR32:$src, 1), (INC32r GR32:$src)>, Requires<[Not64BitMode]>;
def : Pat<(add GR32:$src, 1), (INC64_32r GR32:$src)>, Requires<[In64BitMode]>;
def : Pat<(add GR64:$src, 1), (INC64r GR64:$src)>;
// Do not make INC if it is slow
def : Pat<(add GR8:$src, 1),
(INC8r GR8:$src)>, Requires<[NotSlowIncDec]>;
def : Pat<(add GR16:$src, 1),
(INC16r GR16:$src)>, Requires<[NotSlowIncDec, Not64BitMode]>;
def : Pat<(add GR16:$src, 1),
(INC64_16r GR16:$src)>, Requires<[NotSlowIncDec, In64BitMode]>;
def : Pat<(add GR32:$src, 1),
(INC32r GR32:$src)>, Requires<[NotSlowIncDec, Not64BitMode]>;
def : Pat<(add GR32:$src, 1),
(INC64_32r GR32:$src)>, Requires<[NotSlowIncDec, In64BitMode]>;
def : Pat<(add GR64:$src, 1),
(INC64r GR64:$src)>, Requires<[NotSlowIncDec]>;
// Decrement reg.
def : Pat<(add GR8 :$src, -1), (DEC8r GR8 :$src)>;
def : Pat<(add GR16:$src, -1), (DEC16r GR16:$src)>, Requires<[Not64BitMode]>;
def : Pat<(add GR16:$src, -1), (DEC64_16r GR16:$src)>, Requires<[In64BitMode]>;
def : Pat<(add GR32:$src, -1), (DEC32r GR32:$src)>, Requires<[Not64BitMode]>;
def : Pat<(add GR32:$src, -1), (DEC64_32r GR32:$src)>, Requires<[In64BitMode]>;
def : Pat<(add GR64:$src, -1), (DEC64r GR64:$src)>;
// Do not make DEC if it is slow
def : Pat<(add GR8:$src, -1),
(DEC8r GR8:$src)>, Requires<[NotSlowIncDec]>;
def : Pat<(add GR16:$src, -1),
(DEC16r GR16:$src)>, Requires<[NotSlowIncDec, Not64BitMode]>;
def : Pat<(add GR16:$src, -1),
(DEC64_16r GR16:$src)>, Requires<[NotSlowIncDec, In64BitMode]>;
def : Pat<(add GR32:$src, -1),
(DEC32r GR32:$src)>, Requires<[NotSlowIncDec, Not64BitMode]>;
def : Pat<(add GR32:$src, -1),
(DEC64_32r GR32:$src)>, Requires<[NotSlowIncDec, In64BitMode]>;
def : Pat<(add GR64:$src, -1),
(DEC64r GR64:$src)>, Requires<[NotSlowIncDec]>;
// or reg/reg.
def : Pat<(or GR8 :$src1, GR8 :$src2), (OR8rr GR8 :$src1, GR8 :$src2)>;

1
llvm/lib/Target/X86/X86InstrInfo.td
View File

@ -795,6 +795,7 @@ def OptForSpeed : Predicate<"!OptForSize">;
def FastBTMem : Predicate<"!Subtarget->isBTMemSlow()">;
def CallImmAddr : Predicate<"Subtarget->IsLegalToCallImmediateAddr(TM)">;
def FavorMemIndirectCall : Predicate<"!Subtarget->callRegIndirect()">;
def NotSlowIncDec : Predicate<"!Subtarget->slowIncDec()">;
//===----------------------------------------------------------------------===//
// X86 Instruction Format Definitions.

1
llvm/lib/Target/X86/X86Subtarget.cpp
View File

@ -291,6 +291,7 @@ void X86Subtarget::initializeEnvironment() {
CallRegIndirect = false;
LEAUsesAG = false;
SlowLEA = false;
SlowIncDec = false;
stackAlignment = 4;
// FIXME: this is a known good value for Yonah. How about others?
MaxInlineSizeThreshold = 128;

4
llvm/lib/Target/X86/X86Subtarget.h
View File

@ -181,6 +181,9 @@ protected:
/// SlowLEA - True if the LEA instruction with certain arguments is slow
bool SlowLEA;
/// SlowIncDec - True if INC and DEC instructions are slow when writing to flags
bool SlowIncDec;
/// Processor has AVX-512 PreFetch Instructions
bool HasPFI;
@ -319,6 +322,7 @@ public:
bool callRegIndirect() const { return CallRegIndirect; }
bool LEAusesAG() const { return LEAUsesAG; }
bool slowLEA() const { return SlowLEA; }
bool slowIncDec() const { return SlowIncDec; }
bool hasCDI() const { return HasCDI; }
bool hasPFI() const { return HasPFI; }
bool hasERI() const { return HasERI; }