Teach DAGCombine the same multiply-by-1.0 folding trick when doing FM…

…As, just like it now knows for FMULs. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@156029 91177308-0d34-0410-b5e6-96231b3b80d8
hzou35 · May 2, 2012 · 062c0a5 · 062c0a5
1 parent c0f0a93
commit 062c0a5
Show file tree

Hide file tree

Showing 2 changed files with 27 additions and 0 deletions.
diff --git a/lib/CodeGen/SelectionDAG/DAGCombiner.cpp b/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -215,6 +215,7 @@ namespace {
     SDValue visitFADD(SDNode *N);
     SDValue visitFSUB(SDNode *N);
     SDValue visitFMUL(SDNode *N);
+    SDValue visitFMA(SDNode *N);
     SDValue visitFDIV(SDNode *N);
     SDValue visitFREM(SDNode *N);
     SDValue visitFCOPYSIGN(SDNode *N);
@@ -1126,6 +1127,7 @@ SDValue DAGCombiner::visit(SDNode *N) {
   case ISD::FADD:               return visitFADD(N);
   case ISD::FSUB:               return visitFSUB(N);
   case ISD::FMUL:               return visitFMUL(N);
+  case ISD::FMA:                return visitFMA(N);
   case ISD::FDIV:               return visitFDIV(N);
   case ISD::FREM:               return visitFREM(N);
   case ISD::FCOPYSIGN:          return visitFCOPYSIGN(N);
@@ -5751,6 +5753,22 @@ SDValue DAGCombiner::visitFMUL(SDNode *N) {
   return SDValue();
 }
 
+SDValue DAGCombiner::visitFMA(SDNode *N) {
+  SDValue N0 = N->getOperand(0);
+  SDValue N1 = N->getOperand(1);
+  SDValue N2 = N->getOperand(2);
+  ConstantFPSDNode *N0CFP = dyn_cast<ConstantFPSDNode>(N0);
+  ConstantFPSDNode *N1CFP = dyn_cast<ConstantFPSDNode>(N1);
+  EVT VT = N->getValueType(0);
+
+  if (N0CFP && N0CFP->isExactlyValue(1.0))
+    return DAG.getNode(ISD::FADD, N->getDebugLoc(), VT, N1, N2);
+  if (N1CFP && N1CFP->isExactlyValue(1.0))
+    return DAG.getNode(ISD::FADD, N->getDebugLoc(), VT, N0, N2);
+
+  return SDValue();
+}
+
 SDValue DAGCombiner::visitFDIV(SDNode *N) {
   SDValue N0 = N->getOperand(0);
   SDValue N1 = N->getOperand(1);

diff --git a/test/CodeGen/ARM/fusedMAC.ll b/test/CodeGen/ARM/fusedMAC.ll
@@ -180,6 +180,15 @@ entry:
   ret double %tmp3
 }
 
+define float @test_fma_const_fold(float %a, float %b) nounwind {
+; CHECK: test_fma_const_fold
+; CHECK-NOT: vfma
+; CHECK-NOT: vmul
+; CHECK: vadd
+  %ret = call float @llvm.fma.f32(float %a, float 1.0, float %b)
+  ret float %ret
+}
+
 declare float @llvm.fma.f32(float, float, float) nounwind readnone
 declare double @llvm.fma.f64(double, double, double) nounwind readnone
 declare <2 x float> @llvm.fma.v2f32(<2 x float>, <2 x float>, <2 x float>) nounwind readnone