AMDGPU: Fold rcp/rsq of undef to undef

llvm-svn: 298725

1 files changed, 15 insertions, 2 deletions

diff --git a/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp b/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp
index c259e7e9a93..845cf109897 100644
--- a/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp
@@ -3065,9 +3065,14 @@ Instruction *InstCombiner::visitCallInst(CallInst &CI) {
 
     break;
   }
-
   case Intrinsic::amdgcn_rcp: {
-    if (const ConstantFP *C = dyn_cast<ConstantFP>(II->getArgOperand(0))) {
+    Value *Src = II->getArgOperand(0);
+
+    // TODO: Move to ConstantFolding/InstSimplify?
+    if (isa<UndefValue>(Src))
+      return replaceInstUsesWith(CI, Src);
+
+    if (const ConstantFP *C = dyn_cast<ConstantFP>(Src)) {
       const APFloat &ArgVal = C->getValueAPF();
       APFloat Val(ArgVal.getSemantics(), 1.0);
       APFloat::opStatus Status = Val.divide(ArgVal,
@@ -3080,6 +3085,14 @@ Instruction *InstCombiner::visitCallInst(CallInst &CI) {
 
     break;
   }
+  case Intrinsic::amdgcn_rsq: {
+    Value *Src = II->getArgOperand(0);
+
+    // TODO: Move to ConstantFolding/InstSimplify?
+    if (isa<UndefValue>(Src))
+      return replaceInstUsesWith(CI, Src);
+    break;
+  }
   case Intrinsic::amdgcn_frexp_mant:
   case Intrinsic::amdgcn_frexp_exp: {
     Value *Src = II->getArgOperand(0);