6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2025-01-09 10:31:14 +00:00
Code Issues Projects Releases Wiki Activity

Improve sqrt estimate algorithm (fast-math)

Browse Source 
This patch changes the fast-math implementation for calculating sqrt(x) from:
y = 1 / (1 / sqrt(x))
to:
y = x * (1 / sqrt(x))

This has 2 benefits: less code / faster code and one less estimate instruction 
that may lose precision.

The only target that will be affected (until http://reviews.llvm.org/D5658 is approved)
is PPC. The difference in codegen for PPC is 2 less flops for a single-precision sqrtf
or vector sqrtf and 4 less flops for a double-precision sqrt. 
We also eliminate a constant load and extra register usage.

Differential Revision: http://reviews.llvm.org/D5682



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@219445 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Sanjay Patel 2014-10-09 21:26:35 +00:00
parent c3d3f63e74
commit a4554c2897
2 changed files with 18 additions and 26 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

33
lib/CodeGen/SelectionDAG/DAGCombiner.cpp
View File

@ -7088,26 +7088,25 @@ SDValue DAGCombiner::visitFREM(SDNode *N) {
SDValue DAGCombiner::visitFSQRT(SDNode *N) {
if (DAG.getTarget().Options.UnsafeFPMath) {
// Compute this as 1/(1/sqrt(X)): the reciprocal of the reciprocal sqrt.
// Compute this as X * (1/sqrt(X)) = X * (X ** -0.5)
if (SDValue RV = BuildRsqrtEstimate(N->getOperand(0))) {
AddToWorklist(RV.getNode());
RV = BuildReciprocalEstimate(RV);
if (RV.getNode()) {
// Unfortunately, RV is now NaN if the input was exactly 0.
// Select out this case and force the answer to 0.
EVT VT = RV.getValueType();
SDValue Zero = DAG.getConstantFP(0.0, VT);
SDValue ZeroCmp =
DAG.getSetCC(SDLoc(N), TLI.getSetCCResultType(*DAG.getContext(), VT),
N->getOperand(0), Zero, ISD::SETEQ);
AddToWorklist(ZeroCmp.getNode());
AddToWorklist(RV.getNode());
EVT VT = RV.getValueType();
RV = DAG.getNode(ISD::FMUL, SDLoc(N), VT, N->getOperand(0), RV);
AddToWorklist(RV.getNode());
RV = DAG.getNode(VT.isVector() ? ISD::VSELECT : ISD::SELECT,
SDLoc(N), VT, ZeroCmp, Zero, RV);
return RV;
}
// Unfortunately, RV is now NaN if the input was exactly 0.
// Select out this case and force the answer to 0.
SDValue Zero = DAG.getConstantFP(0.0, VT);
SDValue ZeroCmp =
DAG.getSetCC(SDLoc(N), TLI.getSetCCResultType(*DAG.getContext(), VT),
N->getOperand(0), Zero, ISD::SETEQ);
AddToWorklist(ZeroCmp.getNode());
AddToWorklist(RV.getNode());
RV = DAG.getNode(VT.isVector() ? ISD::VSELECT : ISD::SELECT,
SDLoc(N), VT, ZeroCmp, Zero, RV);
return RV;
}
}
return SDValue();

11
test/CodeGen/PowerPC/recipest.ll
View File

@ -197,11 +197,7 @@ define double @foo3(double %a) nounwind {
; CHECK-NEXT: fmul
; CHECK-NEXT: fmadd
; CHECK-NEXT: fmul
; CHECK-NEXT: fre
; CHECK-NEXT: fnmsub
; CHECK-NEXT: fmadd
; CHECK-NEXT: fnmsub
; CHECK-NEXT: fmadd
; CHECK-NEXT: fmul
; CHECK: blr
; CHECK-SAFE: @foo3
@ -220,9 +216,7 @@ define float @goo3(float %a) nounwind {
; CHECK: fmuls
; CHECK-NEXT: fmadds
; CHECK-NEXT: fmuls
; CHECK-NEXT: fres
; CHECK-NEXT: fnmsubs
; CHECK-NEXT: fmadds
; CHECK-NEXT: fmuls
; CHECK: blr
; CHECK-SAFE: @goo3
@ -236,7 +230,6 @@ define <4 x float> @hoo3(<4 x float> %a) nounwind {
; CHECK: @hoo3
; CHECK: vrsqrtefp
; CHECK-DAG: vrefp
; CHECK-DAG: vcmpeqfp
; CHECK-SAFE: @hoo3