diff options
author | Davide Italiano <davide@freebsd.org> | 2015-11-03 20:32:23 +0000 |
---|---|---|
committer | Davide Italiano <davide@freebsd.org> | 2015-11-03 20:32:23 +0000 |
commit | c8a7913f23460112182b5216fa2cde084886cad4 (patch) | |
tree | 185f7290a7891906d1949db19f21cd2105f57683 /llvm/lib | |
parent | e88dc04c4854124c6cf4c2d0fc554029ea190846 (diff) | |
download | bcm5719-llvm-c8a7913f23460112182b5216fa2cde084886cad4.tar.gz bcm5719-llvm-c8a7913f23460112182b5216fa2cde084886cad4.zip |
[SimplifyLibCalls] Add a new transformation: pow(exp(x), y) -> exp(x*y)
This one is enabled only under -ffast-math (due to rounding/overflows)
but allows us to emit shorter code.
Before (on FreeBSD x86-64):
4007f0: 50 push %rax
4007f1: f2 0f 11 0c 24 movsd %xmm1,(%rsp)
4007f6: e8 75 fd ff ff callq 400570 <exp2@plt>
4007fb: f2 0f 10 0c 24 movsd (%rsp),%xmm1
400800: 58 pop %rax
400801: e9 7a fd ff ff jmpq 400580 <pow@plt>
400806: 66 2e 0f 1f 84 00 00 nopw %cs:0x0(%rax,%rax,1)
40080d: 00 00 00
After:
4007b0: f2 0f 59 c1 mulsd %xmm1,%xmm0
4007b4: e9 87 fd ff ff jmpq 400540 <exp2@plt>
4007b9: 0f 1f 80 00 00 00 00 nopl 0x0(%rax)
Differential Revision: http://reviews.llvm.org/D14045
llvm-svn: 251976
Diffstat (limited to 'llvm/lib')
-rw-r--r-- | llvm/lib/Transforms/Utils/SimplifyLibCalls.cpp | 26 |
1 files changed, 26 insertions, 0 deletions
diff --git a/llvm/lib/Transforms/Utils/SimplifyLibCalls.cpp b/llvm/lib/Transforms/Utils/SimplifyLibCalls.cpp index 9fabf5de7f4..14a0a57ce30 100644 --- a/llvm/lib/Transforms/Utils/SimplifyLibCalls.cpp +++ b/llvm/lib/Transforms/Utils/SimplifyLibCalls.cpp @@ -1103,6 +1103,32 @@ Value *LibCallSimplifier::optimizePow(CallInst *CI, IRBuilder<> &B) { Callee->getAttributes()); } + // pow(exp(x), y) -> exp(x*y) + // pow(exp2(x), y) -> exp2(x * y) + // We enable these only under fast-math. Besides rounding + // differences the transformation changes overflow and + // underflow behavior quite dramatically. + // Example: x = 1000, y = 0.001. + // pow(exp(x), y) = pow(inf, 0.001) = inf, whereas exp(x*y) = exp(1). + if (canUseUnsafeFPMath(CI->getParent()->getParent())) { + if (auto *OpC = dyn_cast<CallInst>(Op1)) { + IRBuilder<>::FastMathFlagGuard Guard(B); + FastMathFlags FMF; + FMF.setUnsafeAlgebra(); + B.SetFastMathFlags(FMF); + + LibFunc::Func Func; + Function *Callee = OpC->getCalledFunction(); + StringRef FuncName = Callee->getName(); + + if (TLI->getLibFunc(FuncName, Func) && TLI->has(Func) && + (Func == LibFunc::exp || Func == LibFunc::exp2)) + return EmitUnaryFloatFnCall( + B.CreateFMul(OpC->getArgOperand(0), Op2, "mul"), FuncName, B, + Callee->getAttributes()); + } + } + ConstantFP *Op2C = dyn_cast<ConstantFP>(Op2); if (!Op2C) return Ret; |