RPCSX/llvm
1
0
Fork 0
mirror of https://github.com/RPCSX/llvm.git synced 2024-12-15 16:09:02 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Teach DAGCombine the same multiply-by-1.0 folding trick when doing FMAs, just like it now knows for FMULs.

Browse Source 
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@156029 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Owen Anderson 2012-05-02 22:17:40 +00:00
parent c0f0a93936
commit 062c0a5b58
2 changed files with 27 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
lib/CodeGen/SelectionDAG/DAGCombiner.cpp
View File

@ -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);

9
test/CodeGen/ARM/fusedMAC.ll
View File

@ -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