RPCSX/llvm
1
0
Fork 0
mirror of https://github.com/RPCSX/llvm.git synced 2024-12-03 17:31:50 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

[PPCMIPeephole] Fix splat elimination

Browse Source 
Summary:
In PPCMIPeephole, when we see two splat instructions, we can't simply do the following transformation:
  B = Splat A
  C = Splat B
=>
  C = Splat A
because B may still be used between these two instructions. Instead, we should make the second Splat a PPC::COPY and let later passes decide whether to remove it or not:
  B = Splat A
  C = Splat B
=>
  B = Splat A
  C = COPY B

Fixes PR30663.

Reviewers: echristo, iteratee, kbarton, nemanjai

Subscribers: mehdi_amini, llvm-commits

Differential Revision: https://reviews.llvm.org/D25493


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@283961 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Tim Shen 2016-10-12 00:48:25 +00:00
parent 47b7d1a540
commit 13774eea42
2 changed files with 29 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
lib/Target/PowerPC/PPCMIPeephole.cpp
View File

@ -201,11 +201,13 @@ bool PPCMIPeephole::simplifyCode(void) {
// Splat fed by another splat - switch the output of the first
// and remove the second.
if (SameOpcode) {
DefMI->getOperand(0).setReg(MI.getOperand(0).getReg());
DEBUG(dbgs() << "Changing redundant splat to a copy: ");
DEBUG(MI.dump());
BuildMI(MBB, &MI, MI.getDebugLoc(), TII->get(PPC::COPY),
MI.getOperand(0).getReg())
.addOperand(MI.getOperand(OpNo));
ToErase = &MI;
Simplified = true;
DEBUG(dbgs() << "Removing redundant splat: ");
DEBUG(MI.dump());
}
// Splat fed by a shift. Usually when we align value to splat into
// vector element zero.

24
test/CodeGen/PowerPC/pr30663.ll Normal file
View File

@ -0,0 +1,24 @@
; RUN: llc -O1 < %s | FileCheck %s
target triple = "powerpc64le-linux-gnu"
; The second xxspltw should be eliminated.
; CHECK: xxspltw
; CHECK-NOT: xxspltw
define void @Test() {
bb4:
%tmp = load <4 x i8>, <4 x i8>* undef
%tmp8 = bitcast <4 x i8> %tmp to float
%tmp18 = fmul float %tmp8, undef
%tmp19 = fsub float 0.000000e+00, %tmp18
store float %tmp19, float* undef
%tmp22 = shufflevector <4 x i8> %tmp, <4 x i8> undef, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3>
%tmp23 = bitcast <16 x i8> %tmp22 to <4 x float>
%tmp25 = tail call <4 x float> @llvm.fma.v4f32(<4 x float> undef, <4 x float> %tmp23, <4 x float> undef)
%tmp26 = fsub <4 x float> zeroinitializer, %tmp25
%tmp27 = bitcast <4 x float> %tmp26 to <4 x i32>
tail call void @llvm.ppc.altivec.stvx(<4 x i32> %tmp27, i8* undef)
ret void
}
declare void @llvm.ppc.altivec.stvx(<4 x i32>, i8*)
declare <4 x float> @llvm.fma.v4f32(<4 x float>, <4 x float>, <4 x float>)