maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

AMDGPU/GlobalISel: Rework legalization for extract/insert vector elt 

Use G_MERGE_VALUES and G_UNMERGE_VALUES on vector elements instead of
G_EXTRACT and G_INSERT when doing custom legalization for
G_EXTRACT_VECTOR_ELT and G_INSERT_VECTOR_ELT.
With this approach legalization artifact combiner gets direct access
to all vector elements.

Differential Revision: https://reviews.llvm.org/D116115
This commit is contained in:
Petar Avramovic 2022-01-10 13:14:28 +01:00
parent 003ac239d8
commit d9d2516aaf
1 changed files with 16 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp
View File

@ -2213,10 +2213,12 @@ bool AMDGPULegalizerInfo::legalizeExtractVectorElt(
LLT EltTy = VecTy.getElementType();
assert(EltTy == MRI.getType(Dst));
if (IdxVal < VecTy.getNumElements())
B.buildExtract(Dst, Vec, IdxVal * EltTy.getSizeInBits());
else
if (IdxVal < VecTy.getNumElements()) {
auto Unmerge = B.buildUnmerge(EltTy, Vec);
B.buildCopy(Dst, Unmerge.getReg(IdxVal));
} else {
B.buildUndef(Dst);
}
MI.eraseFromParent();
return true;
@ -2246,10 +2248,18 @@ bool AMDGPULegalizerInfo::legalizeInsertVectorElt(
LLT EltTy = VecTy.getElementType();
assert(EltTy == MRI.getType(Ins));
if (IdxVal < VecTy.getNumElements())
B.buildInsert(Dst, Vec, Ins, IdxVal * EltTy.getSizeInBits());
else
unsigned NumElts = VecTy.getNumElements();
if (IdxVal < NumElts) {
SmallVector<Register, 8> SrcRegs;
for (unsigned i = 0; i < NumElts; ++i)
SrcRegs.push_back(MRI.createGenericVirtualRegister(EltTy));
B.buildUnmerge(SrcRegs, Vec);
SrcRegs[IdxVal] = MI.getOperand(2).getReg();
B.buildMerge(Dst, SrcRegs);
} else {
B.buildUndef(Dst);
}
MI.eraseFromParent();
return true;