[llvm] r183802 - [mips] Add an IR transformation pass that optimizes calls to sqrt.

Tue Jun 11 16:13:47 PDT 2013

----- Original Message -----
> 
> 
> I was simply copying what gcc was doing. As you've pointed out, you
> can check if the input is negative first. The difference is that
> you'll have to emit one more branch (not sure how much difference
> this will make to performance):

I think this is worth testing. I'd guess that, assuming you arrange the branches so that it defaults to calling the native instruction, the cost of the extra branch will be small, and you won't have the >2x runtime increase on negative inputs.

 -Hal

> 
> 
> if (input is negative)
> 
> libcall
> else
> native instruction
> 
> 
> 
> 
> (transformation in this patch):
> 
> 
> native_instruction
> 
> 
> 
> 
> if (result is nan)
> libcall
> 
> 
> I made this pass mips-specific because I was planning to commit
> another patch which does a mips-specific optimization to calls to
> other math library calls (ceil, trunc and trunc), but there isn't
> any reason the transformation in this patch can't be target
> independent.
> 
> 
> 
> 
> 
> On Tue, Jun 11, 2013 at 3:45 PM, Hal Finkel < hfinkel at anl.gov >
> wrote:
> 
> 
> 
> ----- Original Message -----
> > Author: ahatanak
> > Date: Tue Jun 11 17:21:44 2013
> > New Revision: 183802
> > 
> > URL: http://llvm.org/viewvc/llvm-project?rev=183802&view=rev
> > Log:
> > [mips] Add an IR transformation pass that optimizes calls to sqrt.
> > 
> > The pass emits a call to sqrt that has attribute "read-none". This
> > call will be
> > converted to an ISD::FSQRT node during DAG construction, which will
> > turn into
> > a mips native sqrt instruction.
> 
> This seems almost completely target independent, is there a reason to
> make this MIPS-specific? Also, is it really better to test the
> result for NaN as opposed to checking whether the input is negative?
> 
> -Hal
> 
> 
> 
> > 
> > 
> > Added:
> > llvm/trunk/lib/Target/Mips/MipsOptimizeMathLibCalls.cpp
> > llvm/trunk/test/CodeGen/Mips/optimize-fp-math.ll
> > Modified:
> > llvm/trunk/lib/Target/Mips/Mips.h
> > llvm/trunk/lib/Target/Mips/MipsTargetMachine.cpp
> > 
> > Modified: llvm/trunk/lib/Target/Mips/Mips.h
> > URL:
> > http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/Mips/Mips.h?rev=183802&r1=183801&r2=183802&view=diff
> > ==============================================================================
> > --- llvm/trunk/lib/Target/Mips/Mips.h (original)
> > +++ llvm/trunk/lib/Target/Mips/Mips.h Tue Jun 11 17:21:44 2013
> > @@ -28,7 +28,7 @@ namespace llvm {
> > FunctionPass *createMipsJITCodeEmitterPass(MipsTargetMachine &TM,
> > JITCodeEmitter &JCE);
> > FunctionPass *createMipsConstantIslandPass(MipsTargetMachine &tm);
> > -
> > + FunctionPass *createMipsOptimizeMathLibCalls(MipsTargetMachine
> > &TM);
> > } // end namespace llvm;
> > 
> > #endif
> > 
> > Added: llvm/trunk/lib/Target/Mips/MipsOptimizeMathLibCalls.cpp
> > URL:
> > http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/Mips/MipsOptimizeMathLibCalls.cpp?rev=183802&view=auto
> > ==============================================================================
> > --- llvm/trunk/lib/Target/Mips/MipsOptimizeMathLibCalls.cpp (added)
> > +++ llvm/trunk/lib/Target/Mips/MipsOptimizeMathLibCalls.cpp Tue Jun
> > 11 17:21:44 2013
> > @@ -0,0 +1,175 @@
> > +//===---- MipsOptimizeMathLibCalls.cpp - Optimize math lib calls.
> > ----===//
> > +//
> > +// The LLVM Compiler Infrastructure
> > +//
> > +// This file is distributed under the University of Illinois Open
> > Source
> > +// License. See LICENSE.TXT for details.
> > +//
> > +//===----------------------------------------------------------------------===//
> > +//
> > +// This pass does an IR transformation which enables the backend
> > to
> > emit native
> > +// math instructions.
> > +//
> > +//===----------------------------------------------------------------------===//
> > +
> > +#include "MipsTargetMachine.h"
> > +#include "llvm/IR/IRBuilder.h"
> > +#include "llvm/IR/Intrinsics.h"
> > +#include "llvm/Pass.h"
> > +#include "llvm/Support/CommandLine.h"
> > +#include "llvm/Target/TargetLibraryInfo.h"
> > +#include "llvm/Transforms/Utils/BasicBlockUtils.h"
> > +
> > +using namespace llvm;
> > +
> > +static cl::opt<bool> DisableOpt("disable-mips-math-optimization",
> > + cl::init(false),
> > + cl::desc("MIPS: Disable math lib
> > call "
> > + "optimization."),
> > cl::Hidden);
> > +
> > +namespace {
> > + class MipsOptimizeMathLibCalls : public FunctionPass {
> > + public:
> > + static char ID;
> > +
> > + MipsOptimizeMathLibCalls(MipsTargetMachine &TM_) :
> > + FunctionPass(ID), TM(TM_) {}
> > +
> > + virtual const char *getPassName() const {
> > + return "MIPS: Optimize calls to math library functions.";
> > + }
> > +
> > + virtual void getAnalysisUsage(AnalysisUsage &AU) const;
> > +
> > + virtual bool runOnFunction(Function &F);
> > +
> > + private:
> > + /// Optimize calls to sqrt.
> > + bool optimizeSQRT(CallInst *Call, Function *CalledFunc,
> > + BasicBlock &CurrBB,
> > + Function::iterator &BB);
> > +
> > + const TargetMachine &TM;
> > + };
> > +
> > + char MipsOptimizeMathLibCalls::ID = 0;
> > +}
> > +
> > +FunctionPass
> > *llvm::createMipsOptimizeMathLibCalls(MipsTargetMachine
> > &TM) {
> > + return new MipsOptimizeMathLibCalls(TM);
> > +}
> > +
> > +void MipsOptimizeMathLibCalls::getAnalysisUsage(AnalysisUsage &AU)
> > const {
> > + AU.addRequired<TargetLibraryInfo>();
> > + FunctionPass::getAnalysisUsage(AU);
> > +}
> > +
> > +bool MipsOptimizeMathLibCalls::runOnFunction(Function &F) {
> > + if (DisableOpt)
> > + return false;
> > +
> > + const MipsSubtarget &Subtarget =
> > TM.getSubtarget<MipsSubtarget>();
> > +
> > + if (Subtarget.inMips16Mode())
> > + return false;
> > +
> > + bool Changed = false;
> > + Function::iterator CurrBB;
> > + const TargetLibraryInfo *LibInfo =
> > &getAnalysis<TargetLibraryInfo>();
> > +
> > + for (Function::iterator BB = F.begin(), BE = F.end(); BB != BE;)
> > {
> > + CurrBB = BB++;
> > +
> > + for (BasicBlock::iterator II = CurrBB->begin(), IE =
> > CurrBB->end();
> > + II != IE; ++II) {
> > + CallInst *Call = dyn_cast<CallInst>(&*II);
> > + Function *CalledFunc;
> > +
> > + if (!Call || !(CalledFunc = Call->getCalledFunction()))
> > + continue;
> > +
> > + LibFunc::Func LibFunc;
> > + Attribute A = CalledFunc->getAttributes()
> > + .getAttribute(AttributeSet::FunctionIndex,
> > "use-soft-float");
> > +
> > + // Skip if function has "use-soft-float" attribute.
> > + if ((A.isStringAttribute() && (A.getValueAsString() ==
> > "true")) ||
> > + TM.Options.UseSoftFloat)
> > + continue;
> > +
> > + // Skip if function either has local linkage or is not a known
> > library
> > + // function.
> > + if (CalledFunc->hasLocalLinkage() || !CalledFunc->hasName() ||
> > + !LibInfo->getLibFunc(CalledFunc->getName(), LibFunc))
> > + continue;
> > +
> > + switch (LibFunc) {
> > + case LibFunc::sqrtf:
> > + case LibFunc::sqrt:
> > + if (optimizeSQRT(Call, CalledFunc, *CurrBB, BB))
> > + break;
> > + continue;
> > + default:
> > + continue;
> > + }
> > +
> > + Changed = true;
> > + break;
> > + }
> > + }
> > +
> > + return Changed;
> > +}
> > +
> > +bool MipsOptimizeMathLibCalls::optimizeSQRT(CallInst *Call,
> > + Function *CalledFunc,
> > + BasicBlock &CurrBB,
> > + Function::iterator &BB)
> > {
> > + // There is no need to change the IR, since backend will emit
> > sqrt
> > + // instruction if the call has already been marked read-only.
> > + if (Call->onlyReadsMemory())
> > + return false;
> > +
> > + // Do the following transformation:
> > + //
> > + // (before)
> > + // dst = sqrt(src)
> > + //
> > + // (after)
> > + // v0 = sqrt_noreadmem(src) # native sqrt instruction.
> > + // if (v0 is a NaN)
> > + // v1 = sqrt(src) # library call.
> > + // dst = phi(v0, v1)
> > + //
> > +
> > + // Move all instructions following Call to newly created block
> > JoinBB.
> > + // Create phi and replace all uses.
> > + BasicBlock *JoinBB = llvm::SplitBlock(&CurrBB,
> > Call->getNextNode(), this);
> > + IRBuilder<> Builder(JoinBB, JoinBB->begin());
> > + PHINode *Phi = Builder.CreatePHI(Call->getType(), 2);
> > + Call->replaceAllUsesWith(Phi);
> > +
> > + // Create basic block LibCallBB and insert a call to library
> > function sqrt.
> > + BasicBlock *LibCallBB = BasicBlock::Create(CurrBB.getContext(),
> > "call.sqrt",
> > + CurrBB.getParent(),
> > JoinBB);
> > + Builder.SetInsertPoint(LibCallBB);
> > + Instruction *LibCall = Call->clone();
> > + Builder.Insert(LibCall);
> > + Builder.CreateBr(JoinBB);
> > +
> > + // Add attribute "readnone" so that backend can use a native sqrt
> > instruction
> > + // for this call. Insert a FP compare instruction and a
> > conditional branch
> > + // at the end of CurrBB.
> > + Call->addAttribute(AttributeSet::FunctionIndex,
> > Attribute::ReadNone);
> > + CurrBB.getTerminator()->eraseFromParent();
> > + Builder.SetInsertPoint(&CurrBB);
> > + Value *FCmp = Builder.CreateFCmpOEQ(Call, Call);
> > + Builder.CreateCondBr(FCmp, JoinBB, LibCallBB);
> > +
> > + // Add phi operands.
> > + Phi->addIncoming(Call, &CurrBB);
> > + Phi->addIncoming(LibCall, LibCallBB);
> > +
> > + BB = JoinBB;
> > + return true;
> > +}
> > 
> > Modified: llvm/trunk/lib/Target/Mips/MipsTargetMachine.cpp
> > URL:
> > http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/Mips/MipsTargetMachine.cpp?rev=183802&r1=183801&r2=183802&view=diff
> > ==============================================================================
> > --- llvm/trunk/lib/Target/Mips/MipsTargetMachine.cpp (original)
> > +++ llvm/trunk/lib/Target/Mips/MipsTargetMachine.cpp Tue Jun 11
> > 17:21:44 2013
> > @@ -160,6 +160,7 @@ void MipsPassConfig::addIRPasses() {
> > addPass(createMipsOs16(getMipsTargetMachine()));
> > if (getMipsSubtarget().inMips16HardFloat())
> > addPass(createMips16HardFloat(getMipsTargetMachine()));
> > + addPass(createMipsOptimizeMathLibCalls(getMipsTargetMachine()));
> > }
> > // Install an instruction selector pass using
> > // the ISelDag to gen Mips code.
> > 
> > Added: llvm/trunk/test/CodeGen/Mips/optimize-fp-math.ll
> > URL:
> > http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/Mips/optimize-fp-math.ll?rev=183802&view=auto
> > ==============================================================================
> > --- llvm/trunk/test/CodeGen/Mips/optimize-fp-math.ll (added)
> > +++ llvm/trunk/test/CodeGen/Mips/optimize-fp-math.ll Tue Jun 11
> > 17:21:44 2013
> > @@ -0,0 +1,32 @@
> > +; RUN: llc -march=mipsel < %s | FileCheck %s -check-prefix=32
> > +; RUN: llc -march=mips64el -mcpu=mips64 < %s | FileCheck %s
> > -check-prefix=64
> > +
> > +; 32: test_sqrtf_float_:
> > +; 32: sqrt.s $f[[R0:[0-9]+]], $f{{[0-9]+}}
> > +; 32: c.un.s $f[[R0]], $f[[R0]]
> > +; 64: test_sqrtf_float_:
> > +; 64: sqrt.s $f[[R0:[0-9]+]], $f{{[0-9]+}}
> > +; 64: c.un.s $f[[R0]], $f[[R0]]
> > +
> > +define float @test_sqrtf_float_(float %a) {
> > +entry:
> > + %call = tail call float @sqrtf(float %a)
> > + ret float %call
> > +}
> > +
> > +declare float @sqrtf(float)
> > +
> > +; 32: test_sqrt_double_:
> > +; 32: sqrt.d $f[[R0:[0-9]+]], $f{{[0-9]+}}
> > +; 32: c.un.d $f[[R0]], $f[[R0]]
> > +; 64: test_sqrt_double_:
> > +; 64: sqrt.d $f[[R0:[0-9]+]], $f{{[0-9]+}}
> > +; 64: c.un.d $f[[R0]], $f[[R0]]
> > +
> > +define double @test_sqrt_double_(double %a) {
> > +entry:
> > + %call = tail call double @sqrt(double %a)
> > + ret double %call
> > +}
> > +
> > +declare double @sqrt(double)
> > 
> > 
> > _______________________________________________
> > llvm-commits mailing list
> > llvm-commits at cs.uiuc.edu
> > http://lists.cs.uiuc.edu/mailman/listinfo/llvm-commits
> > 
> _______________________________________________
> llvm-commits mailing list
> llvm-commits at cs.uiuc.edu
> http://lists.cs.uiuc.edu/mailman/listinfo/llvm-commits
> 
> 