[SimplifyLibCalls] New trick: pow(x, 0.5) -> sqrt(x) under -ffast-math.
Differential Revision: http://reviews.llvm.org/D14466
llvm-svn: 253521
diff --git a/llvm/lib/Transforms/Utils/SimplifyLibCalls.cpp b/llvm/lib/Transforms/Utils/SimplifyLibCalls.cpp
index 8e2eeb9..72abd0b 100644
--- a/llvm/lib/Transforms/Utils/SimplifyLibCalls.cpp
+++ b/llvm/lib/Transforms/Utils/SimplifyLibCalls.cpp
@@ -1096,6 +1096,8 @@
Callee->getAttributes());
}
+ bool unsafeFPMath = canUseUnsafeFPMath(CI->getParent()->getParent());
+
// pow(exp(x), y) -> exp(x*y)
// pow(exp2(x), y) -> exp2(x * y)
// We enable these only under fast-math. Besides rounding
@@ -1103,7 +1105,7 @@
// 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 (unsafeFPMath) {
if (auto *OpC = dyn_cast<CallInst>(Op1)) {
IRBuilder<>::FastMathFlagGuard Guard(B);
FastMathFlags FMF;
@@ -1134,10 +1136,15 @@
LibFunc::sqrtl) &&
hasUnaryFloatFn(TLI, Op2->getType(), LibFunc::fabs, LibFunc::fabsf,
LibFunc::fabsl)) {
+
+ // In -ffast-math, pow(x, 0.5) -> sqrt(x).
+ if (unsafeFPMath)
+ return EmitUnaryFloatFnCall(Op1, TLI->getName(LibFunc::sqrt), B,
+ Callee->getAttributes());
+
// Expand pow(x, 0.5) to (x == -infinity ? +infinity : fabs(sqrt(x))).
// This is faster than calling pow, and still handles negative zero
// and negative infinity correctly.
- // TODO: In fast-math mode, this could be just sqrt(x).
// TODO: In finite-only mode, this could be just fabs(sqrt(x)).
Value *Inf = ConstantFP::getInfinity(CI->getType());
Value *NegInf = ConstantFP::getInfinity(CI->getType(), true);