RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2025-01-31 20:51:52 +01:00
Code Issues Projects Releases Wiki Activity

DAG: Fix extract_subvector combine for a single element

Browse Source 
This would fail before because 1x vectors aren't legal,
so instead just use the scalar type.

Avoids regressions in a future AMDGPU commit to add
v4i16/v4f16 as legal types.

Test update is just the one test that this triggers
on in tree now. It wasn't checking anything before.
The result is completely  changed since the selects
are eliminated. Not sure if it's considered better
or not.

llvm-svn: 334440
This commit is contained in:
Matt Arsenault 2018-06-11 21:27:41 +00:00
parent 799395800d
commit a27dc5bdab
2 changed files with 27 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
lib/CodeGen/SelectionDAG/DAGCombiner.cpp
View File

@ -15968,13 +15968,22 @@ SDValue DAGCombiner::visitEXTRACT_SUBVECTOR(SDNode* N) {
// Only do this if we won't split any elements.
if (ExtractSize % EltSize == 0) {
unsigned NumElems = ExtractSize / EltSize;
EVT ExtractVT = EVT::getVectorVT(*DAG.getContext(),
InVT.getVectorElementType(), NumElems);
EVT EltVT = InVT.getVectorElementType();
EVT ExtractVT = NumElems == 1 ? EltVT :
EVT::getVectorVT(*DAG.getContext(), EltVT, NumElems);
if ((Level < AfterLegalizeDAG ||
TLI.isOperationLegal(ISD::BUILD_VECTOR, ExtractVT)) &&
(NumElems == 1 ||
TLI.isOperationLegal(ISD::BUILD_VECTOR, ExtractVT))) &&
(!LegalTypes || TLI.isTypeLegal(ExtractVT))) {
unsigned IdxVal = (Idx->getZExtValue() * NVT.getScalarSizeInBits()) /
EltSize;
if (NumElems == 1) {
SDValue Src = V->getOperand(IdxVal);
if (EltVT != Src.getValueType())
Src = DAG.getNode(ISD::TRUNCATE, SDLoc(N), InVT, Src);
return DAG.getBitcast(NVT, Src);
}
// Extract the pieces from the original build_vector.
SDValue BuildVec = DAG.getBuildVector(ExtractVT, SDLoc(N),

17
test/CodeGen/ARM/2013-05-13-DAGCombiner-undef-mask.ll
View File

@ -1,7 +1,20 @@
; RUN: llc < %s
target triple = "armv7-none-linux-gnueabi"
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=armv7-none-linux-gnueabi < %s | FileCheck %s
define <3 x i64> @shuffle(i1 %dec1, i1 %dec0, <3 x i64> %b) {
; CHECK-LABEL: shuffle:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: tst r1, #1
; CHECK-NEXT: moveq r1, #0
; CHECK-NEXT: vmoveq d16, r1, r1
; CHECK-NEXT: vldrne d16, [sp]
; CHECK-NEXT: tst r2, #1
; CHECK-NEXT: moveq r1, #0
; CHECK-NEXT: vmoveq d18, r1, r1
; CHECK-NEXT: vldrne d18, [sp, #8]
; CHECK-NEXT: vorr d17, d18, d18
; CHECK-NEXT: vst1.64 {d16, d17}, [r0:128]
; CHECK-NEXT: bx lr
entry:
%.sink = select i1 %dec1, <3 x i64> %b, <3 x i64> zeroinitializer
%.sink15 = select i1 %dec0, <3 x i64> %b, <3 x i64> zeroinitializer