[ComplexDeinterleaving] Propagate fast math flags to symmetric operations.

[dmgreen]

Summary

This is a simple patch to make sure fast math flags are propagated through to the newly created symmetric operations, which can help with later simplifications.

llvm/lib/CodeGen/ComplexDeinterleavingPass.cpp

static Value *replaceSymmetricNode(ComplexDeinterleavingGraph::RawNodePtr Node,
   else if (I->isBinaryOp())
     assert(InputB && "Binary symmetric operations need two inputs, only one "
                      "was provided.");
 
   IRBuilder<> B(I);
 
   switch (I->getOpcode()) {
   case Instruction::FNeg:
-    return B.CreateFNeg(InputA);
+    return B.CreateFNegFMF(InputA, I);
   case Instruction::FAdd:
-    return B.CreateFAdd(InputA, InputB);
+    return B.CreateFAddFMF(InputA, InputB, I);
   case Instruction::FSub:
-    return B.CreateFSub(InputA, InputB);
+    return B.CreateFSubFMF(InputA, InputB, I);
   case Instruction::FMul:
-    return B.CreateFMul(InputA, InputB);
+    return B.CreateFMulFMF(InputA, InputB, I);
   }
 
   return nullptr;
 }
 
 Value *ComplexDeinterleavingGraph::replaceNode(
     ComplexDeinterleavingGraph::RawNodePtr Node) {
   if (Node->ReplacementNode)

llvm/test/CodeGen/AArch64/complex-deinterleaving-mixed-cases.ll

entry:
   %interleaved.vec = shufflevector <2 x float> %11, <2 x float> %8, <4 x i32> <i32 0, i32 2, i32 1, i32 3>
   ret <4 x float> %interleaved.vec
 }
 
 ; Expected to transform
 define <4 x float> @mul_addequal(<4 x float> %a, <4 x float> %b, <4 x float> %c) {
 ; CHECK-LABEL: mul_addequal:
 ; CHECK:       // %bb.0: // %entry
-; CHECK-NEXT:    movi v3.2d, #0000000000000000
-; CHECK-NEXT:    fcmla v3.4s, v0.4s, v1.4s, #0
-; CHECK-NEXT:    fcmla v3.4s, v0.4s, v1.4s, #90
-; CHECK-NEXT:    fadd v0.4s, v3.4s, v2.4s
+; CHECK-NEXT:    fcmla v2.4s, v0.4s, v1.4s, #0
+; CHECK-NEXT:    fcmla v2.4s, v0.4s, v1.4s, #90
+; CHECK-NEXT:    mov v0.16b, v2.16b
 ; CHECK-NEXT:    ret
 entry:
   %strided.vec = shufflevector <4 x float> %a, <4 x float> poison, <2 x i32> <i32 0, i32 2>
   %a.imag = shufflevector <4 x float> %a, <4 x float> poison, <2 x i32> <i32 1, i32 3>
   %b.real = shufflevector <4 x float> %b, <4 x float> poison, <2 x i32> <i32 0, i32 2>
   %b.imag = shufflevector <4 x float> %b, <4 x float> poison, <2 x i32> <i32 1, i32 3>
   %0 = fmul fast <2 x float> %b.imag, %strided.vec
   %1 = fmul fast <2 x float> %b.real, %a.imag