[llvm] [IA]: Construct (de)interleave4 out of (de)interleave2 (PR #89276)
Paul Walker via llvm-commits
llvm-commits at lists.llvm.org
Fri Jun 21 06:47:17 PDT 2024
================
@@ -16637,40 +16704,78 @@ bool AArch64TargetLowering::lowerDeinterleaveIntrinsicToLoad(
LdN = Builder.CreateCall(LdNFunc, {Pred, Address}, "ldN");
else
LdN = Builder.CreateCall(LdNFunc, Address, "ldN");
-
Value *Idx =
Builder.getInt64(I * LdTy->getElementCount().getKnownMinValue());
- Left = Builder.CreateInsertVector(
- VTy, Left, Builder.CreateExtractValue(LdN, 0), Idx);
- Right = Builder.CreateInsertVector(
- VTy, Right, Builder.CreateExtractValue(LdN, 1), Idx);
+ for (unsigned J = 0; J < Factor; ++J) {
+ WideValues[J] = Builder.CreateInsertVector(
+ VTy, WideValues[J], Builder.CreateExtractValue(LdN, J), Idx);
+ }
+ }
+ if (Factor == 2)
+ Result = PoisonValue::get(StructType::get(VTy, VTy));
+ else
+ Result = PoisonValue::get(StructType::get(VTy, VTy, VTy, VTy));
+ // Construct the wide result out of the small results.
+ for (unsigned J = 0; J < Factor; ++J) {
+ Result = Builder.CreateInsertValue(Result, WideValues[J], J);
}
-
- Result = PoisonValue::get(DI->getType());
- Result = Builder.CreateInsertValue(Result, Left, 0);
- Result = Builder.CreateInsertValue(Result, Right, 1);
} else {
if (UseScalable)
Result = Builder.CreateCall(LdNFunc, {Pred, BaseAddr}, "ldN");
else
Result = Builder.CreateCall(LdNFunc, BaseAddr, "ldN");
}
-
+ if (Factor > 2) {
+ // Itereate over old deinterleaved values to replace it by
+ // the new deinterleaved values.
+ for (unsigned I = 0; I < DeinterleavedValues.size(); I++) {
+ Value *NewExtract = Builder.CreateExtractValue(Result, I);
+ DeinterleavedValues[I]->replaceAllUsesWith(NewExtract);
+ }
+ for (unsigned I = 0; I < DeinterleavedValues.size(); I++)
+ deleteDeadDeinterleaveInstructions(DeinterleavedValues[I]);
+ return true;
+ }
DI->replaceAllUsesWith(Result);
----------------
paulwalker-arm wrote:
With my `getDeinterleavedValues ` suggestion above I think this can be unified as well and would fix the existing issue whereby the Factor==2 code is assuming the wording of the extracts.
https://github.com/llvm/llvm-project/pull/89276
More information about the llvm-commits
mailing list