[SimplifyLibCalls] pow(x, -0.5) -> 1.0 / sqrt(x).

Differential Revision: https://reviews.llvm.org/D28479 llvm-svn: 291486
llvm · Jan 9, 2017 · 472684e · 472684e
1 parent d4b24ed
commit 472684e
Show file tree

Hide file tree

Showing 2 changed files with 28 additions and 1 deletion.
diff --git a/llvm/lib/Transforms/Utils/SimplifyLibCalls.cpp b/llvm/lib/Transforms/Utils/SimplifyLibCalls.cpp
@@ -1074,6 +1074,24 @@ Value *LibCallSimplifier::optimizePow(CallInst *CI, IRBuilder<> &B) {
   if (Op2C->getValueAPF().isZero()) // pow(x, 0.0) -> 1.0
     return ConstantFP::get(CI->getType(), 1.0);
 
+  if (Op2C->isExactlyValue(-0.5) &&
+      hasUnaryFloatFn(TLI, Op2->getType(), LibFunc::sqrt, LibFunc::sqrtf,
+                      LibFunc::sqrtl)) {
+    // If -ffast-math:
+    // pow(x, -0.5) -> 1.0 / sqrt(x)
+    if (CI->hasUnsafeAlgebra()) {
+      IRBuilder<>::FastMathFlagGuard Guard(B);
+      B.setFastMathFlags(CI->getFastMathFlags());
+
+      // Here we cannot lower to an intrinsic because C99 sqrt() and llvm.sqrt
+      // are not guaranteed to have the same semantics.
+      Value *Sqrt = emitUnaryFloatFnCall(Op1, TLI->getName(LibFunc::sqrt), B,
+                                         Callee->getAttributes());
+
+      return B.CreateFDiv(ConstantFP::get(CI->getType(), 1.0), Sqrt, "sqrtrecip");
+    }
+  }
+
   if (Op2C->isExactlyValue(0.5) &&
       hasUnaryFloatFn(TLI, Op2->getType(), LibFunc::sqrt, LibFunc::sqrtf,
                       LibFunc::sqrtl) &&

diff --git a/llvm/test/Transforms/InstCombine/pow-sqrt.ll b/llvm/test/Transforms/InstCombine/pow-sqrt.ll
@@ -9,5 +9,14 @@ define double @pow_half(double %x) {
 ; CHECK-NEXT:  %sqrt = call fast double @sqrt(double %x)
 ; CHECK-NEXT:  ret double %sqrt
 
-declare double @llvm.pow.f64(double, double)
+define double @pow_neghalf(double %x) {
+  %pow = call fast double @llvm.pow.f64(double %x, double -5.000000e-01)
+  ret double %pow
+}
 
+; CHECK-LABEL: define double @pow_neghalf(
+; CHECK-NEXT: %sqrt = call fast double @sqrt(double %x) #0
+; CHECK-NEXT: %sqrtrecip = fdiv fast double 1.000000e+00, %sqrt
+; CHECK-NEXT: ret double %sqrtrecip
+
+declare double @llvm.pow.f64(double, double)