Skip to content

[X86] combineConcatVectorOps - convert X86ISD::PALIGNR concatenation to use combineConcatVectorOps recursion #130572

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Mar 10, 2025
Merged

[X86] combineConcatVectorOps - convert X86ISD::PALIGNR concatenation to use combineConcatVectorOps recursion #130572

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 7 additions & 3 deletions llvm/lib/Target/X86/X86ISelLowering.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -58443,9 +58443,13 @@ static SDValue combineConcatVectorOps(const SDLoc &DL, MVT VT,
llvm::all_of(Ops, [Op0](SDValue Op) {
return Op0.getOperand(2) == Op.getOperand(2);
})) {
return DAG.getNode(Op0.getOpcode(), DL, VT,
ConcatSubOperand(VT, Ops, 0),
ConcatSubOperand(VT, Ops, 1), Op0.getOperand(2));
SDValue Concat0 = CombineSubOperand(VT, Ops, 0);
SDValue Concat1 = CombineSubOperand(VT, Ops, 1);
if (Concat0 || Concat1)
return DAG.getNode(Op0.getOpcode(), DL, VT,
Concat0 ? Concat0 : ConcatSubOperand(VT, Ops, 0),
Concat1 ? Concat1 : ConcatSubOperand(VT, Ops, 1),
Op0.getOperand(2));
}
break;
case X86ISD::BLENDI:
Expand Down
10 changes: 4 additions & 6 deletions llvm/test/CodeGen/X86/vector-shuffle-combining-avx2.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -775,15 +775,13 @@ define <32 x i8> @combine_pshufb_pshufb_or_pshufb(<32 x i8> %a0) {
ret <32 x i8> %4
}

; TODO: Not beneficial to concatenate both inputs just to create a 256-bit palignr
; Not beneficial to concatenate both inputs just to create a 256-bit palignr
define <32 x i8> @concat_alignr_unnecessary(<16 x i8> %a0, <16 x i8> noundef %a1, <16 x i8> %a2) nounwind {
; CHECK-LABEL: concat_alignr_unnecessary:
; CHECK: # %bb.0:
; CHECK-NEXT: # kill: def $xmm1 killed $xmm1 def $ymm1
; CHECK-NEXT: # kill: def $xmm0 killed $xmm0 def $ymm0
; CHECK-NEXT: vinserti128 $1, %xmm2, %ymm1, %ymm1
; CHECK-NEXT: vinserti128 $1, %xmm0, %ymm0, %ymm0
; CHECK-NEXT: vpalignr {{.*#+}} ymm0 = ymm1[3,4,5,6,7,8,9,10,11,12,13,14,15],ymm0[0,1,2],ymm1[19,20,21,22,23,24,25,26,27,28,29,30,31],ymm0[16,17,18]
; CHECK-NEXT: vpalignr {{.*#+}} xmm1 = xmm1[3,4,5,6,7,8,9,10,11,12,13,14,15],xmm0[0,1,2]
; CHECK-NEXT: vpalignr {{.*#+}} xmm0 = xmm2[3,4,5,6,7,8,9,10,11,12,13,14,15],xmm0[0,1,2]
; CHECK-NEXT: vinserti128 $1, %xmm0, %ymm1, %ymm0
; CHECK-NEXT: ret{{[l|q]}}
%lo = shufflevector <16 x i8> %a1, <16 x i8> %a0, <16 x i32> <i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18>
%hi = shufflevector <16 x i8> %a2, <16 x i8> %a0, <16 x i32> <i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18>
Expand Down