Merging r326393:

------------------------------------------------------------------------
r326393 | ctopper | 2018-03-01 01:08:38 +0100 (Thu, 01 Mar 2018) | 5 lines

[X86] Make sure we don't combine (fneg (fma X, Y, Z)) to a target specific node when there are no FMA instructions.

This would cause a 'cannot select' error at isel when we should have emitted a lib call and an xor.

Fixes PR36553.
------------------------------------------------------------------------

git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_60@326423 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/X86/X86ISelLowering.cpp b/lib/Target/X86/X86ISelLowering.cpp
index 9237833a2cd04793af18121b7f0fe4b2b0dc188b..10e19f92b4a6349312ec0714ac0ecdfb0c4eae89 100644 (file)
--- a/lib/Target/X86/X86ISelLowering.cpp
+++ b/lib/Target/X86/X86ISelLowering.cpp
@@ -35520,7 +35520,7 @@ static SDValue combineFneg(SDNode *N, SelectionDAG &DAG,
   // If we're negating an FMA node, then we can adjust the
   // instruction to include the extra negation.
   unsigned NewOpcode = 0;
-  if (Arg.hasOneUse()) {
+  if (Arg.hasOneUse() && Subtarget.hasAnyFMA()) {
     switch (Arg.getOpcode()) {
     case ISD::FMA:             NewOpcode = X86ISD::FNMSUB;       break;
     case X86ISD::FMSUB:        NewOpcode = X86ISD::FNMADD;       break;

diff --git a/test/CodeGen/X86/pr36553.ll b/test/CodeGen/X86/pr36553.ll
new file mode 100644 (file)
index 0000000..827f80a
--- /dev/null
+++ b/test/CodeGen/X86/pr36553.ll
@@ -0,0 +1,20 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc < %s -mtriple=x86_64-apple-darwin10 | FileCheck %s
+
+; Make sure we don't crash because we negated an fma when we didn't have any fma instructions.
+
+define float @pr36553(float %a, float %b, float %c) nounwind {
+; CHECK-LABEL: pr36553:
+; CHECK:       ## %bb.0: ## %entry
+; CHECK-NEXT:    pushq %rax
+; CHECK-NEXT:    callq _fmaf
+; CHECK-NEXT:    xorps {{.*}}(%rip), %xmm0
+; CHECK-NEXT:    popq %rax
+; CHECK-NEXT:    retq
+entry:
+  %0 = tail call float @llvm.fma.f32(float %a, float %b, float %c)
+  %sub = fsub float -0.000000e+00, %0
+  ret float %sub
+}
+
+declare float @llvm.fma.f32(float, float, float)