From 19f9f374d9afe3efd33dc1943d3d7fd2c54fba76 Mon Sep 17 00:00:00 2001 From: Sanjay Patel Date: Fri, 20 Dec 2019 17:24:53 -0500 Subject: [SimplifyLibCalls] require fast-math-flags for pow(X, -0.5) transforms As discussed in PR44330: https://bugs.llvm.org/show_bug.cgi?id=44330 ...the transform from pow(X, -0.5) libcall/intrinsic to reciprocal square root can result in small deviations from the expected result due to differences in the pow() implementation and/or the extra rounding step from the division. This patch proposes to allow that difference with either the 'approximate functions' or 'reassociate' FMF: http://llvm.org/docs/LangRef.html#fast-math-flags In practice, this likely means that the code is compiled with all of 'fast' (-ffast-math), but I have preserved the existing specializations for -0.0/-INF that enable generating safe code if those special values are allowed simultaneously with allowing approximation/reassociation. The question about whether a similar restriction is needed for the non-reciprocal case -- pow(X, 0.5) -- is deferred. That transform is allowed without FMF currently, and this patch does not change that behavior. Differential Revision: https://reviews.llvm.org/D71706 --- llvm/lib/Transforms/Utils/SimplifyLibCalls.cpp | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'llvm/lib/Transforms/Utils/SimplifyLibCalls.cpp') diff --git a/llvm/lib/Transforms/Utils/SimplifyLibCalls.cpp b/llvm/lib/Transforms/Utils/SimplifyLibCalls.cpp index 6c09600..fa3a9d2 100644 --- a/llvm/lib/Transforms/Utils/SimplifyLibCalls.cpp +++ b/llvm/lib/Transforms/Utils/SimplifyLibCalls.cpp @@ -1644,6 +1644,11 @@ Value *LibCallSimplifier::replacePowWithSqrt(CallInst *Pow, IRBuilder<> &B) { (!ExpoF->isExactlyValue(0.5) && !ExpoF->isExactlyValue(-0.5))) return nullptr; + // Converting pow(X, -0.5) to 1/sqrt(X) may introduce an extra rounding step, + // so that requires fast-math-flags (afn or reassoc). + if (ExpoF->isNegative() && (!Pow->hasApproxFunc() && !Pow->hasAllowReassoc())) + return nullptr; + Sqrt = getSqrtCall(Base, Attrs, Pow->doesNotAccessMemory(), Mod, B, TLI); if (!Sqrt) return nullptr; -- cgit v1.1