[llvm-branch-commits] [llvm] e5507c4 - Revert "[SelDag] Use use BoolVT size when expanding find-last-active, if larg…"
via llvm-branch-commits
llvm-branch-commits at lists.llvm.org
Wed Jan 14 12:46:23 PST 2026
Author: Florian Hahn
Date: 2026-01-14T20:46:19Z
New Revision: e5507c49f7fd184f598e8b62d6afe76365c530ad
URL: https://github.com/llvm/llvm-project/commit/e5507c49f7fd184f598e8b62d6afe76365c530ad
DIFF: https://github.com/llvm/llvm-project/commit/e5507c49f7fd184f598e8b62d6afe76365c530ad.diff
LOG: Revert "[SelDag] Use use BoolVT size when expanding find-last-active, if larg…"
This reverts commit 68a04c1adae8dc2a031a1d483d2b73dbbe92f060.
Added:
Modified:
llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp
llvm/test/CodeGen/X86/vector-extract-last-active.ll
Removed:
################################################################################
diff --git a/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp b/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp
index b71059a6ce354..64f73a4b5d699 100644
--- a/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp
@@ -9729,12 +9729,9 @@ SDValue TargetLowering::expandVectorFindLastActive(SDNode *N,
if (MaskVT.isScalableVector())
VScaleRange = getVScaleRange(&DAG.getMachineFunction().getFunction(), 64);
const TargetLowering &TLI = DAG.getTargetLoweringInfo();
- uint64_t EltWidth = TLI.getBitWidthForCttzElements(
+ unsigned EltWidth = TLI.getBitWidthForCttzElements(
BoolVT.getTypeForEVT(*DAG.getContext()), MaskVT.getVectorElementCount(),
/*ZeroIsPoison=*/true, &VScaleRange);
- // If the step vector element type is smaller than the mask element type,
- // use the mask type directly to avoid widening issues.
- EltWidth = std::max(EltWidth, BoolVT.getFixedSizeInBits());
EVT StepVT = MVT::getIntegerVT(EltWidth);
EVT StepVecVT = MaskVT.changeVectorElementType(*DAG.getContext(), StepVT);
diff --git a/llvm/test/CodeGen/X86/vector-extract-last-active.ll b/llvm/test/CodeGen/X86/vector-extract-last-active.ll
index e891b27de2756..09d305eaaeb77 100644
--- a/llvm/test/CodeGen/X86/vector-extract-last-active.ll
+++ b/llvm/test/CodeGen/X86/vector-extract-last-active.ll
@@ -8,28 +8,32 @@
define i32 @extract_last_active_v4i32(<4 x i32> %a, <4 x i1> %c) {
; CHECK-LABEL: extract_last_active_v4i32:
; CHECK: # %bb.0:
-; CHECK-NEXT: pshufd {{.*#+}} xmm2 = xmm1[3,3,3,3]
-; CHECK-NEXT: movd %xmm2, %eax
+; CHECK-NEXT: movd %xmm1, %eax
; CHECK-NEXT: pshufd {{.*#+}} xmm2 = xmm1[2,3,2,3]
; CHECK-NEXT: movd %xmm2, %ecx
-; CHECK-NEXT: movd %xmm1, %edx
; CHECK-NEXT: pshufd {{.*#+}} xmm2 = xmm1[1,1,1,1]
-; CHECK-NEXT: movd %xmm2, %esi
+; CHECK-NEXT: movd %xmm2, %edx
+; CHECK-NEXT: pshufd {{.*#+}} xmm1 = xmm1[3,3,3,3]
+; CHECK-NEXT: movd %xmm1, %esi
; CHECK-NEXT: movaps %xmm0, -{{[0-9]+}}(%rsp)
-; CHECK-NEXT: pand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1
-; CHECK-NEXT: pshufd {{.*#+}} xmm0 = xmm1[2,3,2,3]
-; CHECK-NEXT: movd %xmm0, %edi
-; CHECK-NEXT: pshufd {{.*#+}} xmm0 = xmm1[1,1,1,1]
-; CHECK-NEXT: movd %xmm0, %r8d
-; CHECK-NEXT: cmpl %edi, %r8d
-; CHECK-NEXT: cmoval %r8d, %edi
-; CHECK-NEXT: pshufd {{.*#+}} xmm0 = xmm1[3,3,3,3]
-; CHECK-NEXT: movd %xmm0, %r8d
-; CHECK-NEXT: cmpl %r8d, %edi
+; CHECK-NEXT: xorl %edi, %edi
+; CHECK-NEXT: testl %esi, %esi
+; CHECK-NEXT: setne %dil
+; CHECK-NEXT: leal (%rdi,%rdi,2), %r8d
+; CHECK-NEXT: xorl %r9d, %r9d
+; CHECK-NEXT: testl %edx, %edx
+; CHECK-NEXT: setne %r9b
+; CHECK-NEXT: xorl %edi, %edi
+; CHECK-NEXT: testl %ecx, %ecx
+; CHECK-NEXT: setne %dil
+; CHECK-NEXT: addl %edi, %edi
+; CHECK-NEXT: cmpb %dil, %r9b
+; CHECK-NEXT: cmoval %r9d, %edi
+; CHECK-NEXT: cmpb %r8b, %dil
; CHECK-NEXT: cmovbel %r8d, %edi
-; CHECK-NEXT: orl %edx, %esi
-; CHECK-NEXT: orl %eax, %ecx
+; CHECK-NEXT: orl %edx, %eax
; CHECK-NEXT: orl %esi, %ecx
+; CHECK-NEXT: orl %eax, %ecx
; CHECK-NEXT: andb $1, %cl
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: cmpb $1, %cl
@@ -44,18 +48,28 @@ define i32 @extract_last_active_v4i32_no_default(<4 x i32> %a, <4 x i1> %c) {
; CHECK-LABEL: extract_last_active_v4i32_no_default:
; CHECK: # %bb.0:
; CHECK-NEXT: movaps %xmm0, -{{[0-9]+}}(%rsp)
-; CHECK-NEXT: pand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1
-; CHECK-NEXT: pshufd {{.*#+}} xmm0 = xmm1[2,3,2,3]
+; CHECK-NEXT: pshufd {{.*#+}} xmm0 = xmm1[3,3,3,3]
; CHECK-NEXT: movd %xmm0, %eax
+; CHECK-NEXT: xorl %ecx, %ecx
+; CHECK-NEXT: testl %eax, %eax
+; CHECK-NEXT: setne %cl
+; CHECK-NEXT: leal (%rcx,%rcx,2), %eax
; CHECK-NEXT: pshufd {{.*#+}} xmm0 = xmm1[1,1,1,1]
; CHECK-NEXT: movd %xmm0, %ecx
-; CHECK-NEXT: cmpl %eax, %ecx
-; CHECK-NEXT: cmoval %ecx, %eax
-; CHECK-NEXT: pshufd {{.*#+}} xmm0 = xmm1[3,3,3,3]
+; CHECK-NEXT: xorl %edx, %edx
+; CHECK-NEXT: testl %ecx, %ecx
+; CHECK-NEXT: setne %dl
+; CHECK-NEXT: pshufd {{.*#+}} xmm0 = xmm1[2,3,2,3]
; CHECK-NEXT: movd %xmm0, %ecx
-; CHECK-NEXT: cmpl %ecx, %eax
-; CHECK-NEXT: cmovbel %ecx, %eax
-; CHECK-NEXT: movl -24(%rsp,%rax,4), %eax
+; CHECK-NEXT: xorl %esi, %esi
+; CHECK-NEXT: testl %ecx, %ecx
+; CHECK-NEXT: setne %sil
+; CHECK-NEXT: addl %esi, %esi
+; CHECK-NEXT: cmpb %sil, %dl
+; CHECK-NEXT: cmoval %edx, %esi
+; CHECK-NEXT: cmpb %al, %sil
+; CHECK-NEXT: cmovbel %eax, %esi
+; CHECK-NEXT: movl -24(%rsp,%rsi,4), %eax
; CHECK-NEXT: retq
%res = call i32 @llvm.experimental.vector.extract.last.active.v4i32(<4 x i32> %a, <4 x i1> %c, i32 poison)
ret i32 %res
@@ -67,15 +81,18 @@ define i32 @extract_last_active_v2i32(<2 x i32> %a, <2 x i1> %c) {
; CHECK: # %bb.0:
; CHECK-NEXT: pshufd {{.*#+}} xmm2 = xmm1[2,3,2,3]
; CHECK-NEXT: movq %xmm2, %rcx
-; CHECK-NEXT: movq %xmm1, %rdx
+; CHECK-NEXT: movq %xmm1, %rax
; CHECK-NEXT: movaps %xmm0, -{{[0-9]+}}(%rsp)
-; CHECK-NEXT: orl %ecx, %edx
+; CHECK-NEXT: movl %ecx, %edx
+; CHECK-NEXT: orl %eax, %edx
; CHECK-NEXT: andb $1, %dl
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: cmpb $1, %dl
; CHECK-NEXT: sbbl %eax, %eax
-; CHECK-NEXT: andl $1, %ecx
-; CHECK-NEXT: orl -24(%rsp,%rcx,4), %eax
+; CHECK-NEXT: xorl %edx, %edx
+; CHECK-NEXT: testq %rcx, %rcx
+; CHECK-NEXT: setne %dl
+; CHECK-NEXT: orl -24(%rsp,%rdx,4), %eax
; CHECK-NEXT: retq
%res = call i32 @llvm.experimental.vector.extract.last.active.v2i32(<2 x i32> %a, <2 x i1> %c, i32 -1)
ret i32 %res
@@ -86,24 +103,23 @@ define i32 @extract_last_active_v2i32(<2 x i32> %a, <2 x i1> %c) {
define i32 @extract_last_active_v3i32(<3 x i32> %a, <3 x i1> %c) {
; CHECK-LABEL: extract_last_active_v3i32:
; CHECK: # %bb.0:
-; CHECK-NEXT: movd %edx, %xmm1
-; CHECK-NEXT: movd %esi, %xmm2
-; CHECK-NEXT: pshufd {{.*#+}} xmm2 = xmm2[0,0,1,1]
-; CHECK-NEXT: punpcklqdq {{.*#+}} xmm2 = xmm2[0],xmm1[0]
; CHECK-NEXT: movaps %xmm0, -{{[0-9]+}}(%rsp)
-; CHECK-NEXT: pand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm2
-; CHECK-NEXT: pshufd {{.*#+}} xmm0 = xmm2[2,3,2,3]
-; CHECK-NEXT: movd %xmm0, %ecx
-; CHECK-NEXT: pshufd {{.*#+}} xmm0 = xmm2[1,1,1,1]
-; CHECK-NEXT: movd %xmm0, %eax
-; CHECK-NEXT: cmpl %ecx, %eax
-; CHECK-NEXT: cmoval %eax, %ecx
; CHECK-NEXT: orl %esi, %edi
; CHECK-NEXT: orl %edx, %edi
; CHECK-NEXT: andb $1, %dil
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: cmpb $1, %dil
; CHECK-NEXT: sbbl %eax, %eax
+; CHECK-NEXT: xorl %ecx, %ecx
+; CHECK-NEXT: testl %esi, %esi
+; CHECK-NEXT: setne %cl
+; CHECK-NEXT: xorl %esi, %esi
+; CHECK-NEXT: testl %edx, %edx
+; CHECK-NEXT: setne %sil
+; CHECK-NEXT: addl %esi, %esi
+; CHECK-NEXT: cmpb %sil, %cl
+; CHECK-NEXT: cmoval %ecx, %esi
+; CHECK-NEXT: movzbl %sil, %ecx
; CHECK-NEXT: orl -24(%rsp,%rcx,4), %eax
; CHECK-NEXT: retq
%res = call i32 @llvm.experimental.vector.extract.last.active.v3i32(<3 x i32> %a, <3 x i1> %c, i32 -1)
@@ -114,53 +130,75 @@ define i32 @extract_last_active_v3i32(<3 x i32> %a, <3 x i1> %c) {
define i32 @extract_last_active_v8i32(<8 x i32> %a, <8 x i1> %c) {
; CHECK-LABEL: extract_last_active_v8i32:
; CHECK: # %bb.0:
-; CHECK-NEXT: pushq %rbx
+; CHECK-NEXT: pushq %rbp
; CHECK-NEXT: .cfi_def_cfa_offset 16
-; CHECK-NEXT: .cfi_offset %rbx, -16
+; CHECK-NEXT: pushq %rbx
+; CHECK-NEXT: .cfi_def_cfa_offset 24
+; CHECK-NEXT: .cfi_offset %rbx, -24
+; CHECK-NEXT: .cfi_offset %rbp, -16
+; CHECK-NEXT: movd %xmm2, %edi
; CHECK-NEXT: pextrw $7, %xmm2, %eax
-; CHECK-NEXT: pextrw $6, %xmm2, %esi
+; CHECK-NEXT: pextrw $6, %xmm2, %edx
; CHECK-NEXT: pextrw $5, %xmm2, %r8d
; CHECK-NEXT: pextrw $4, %xmm2, %ecx
+; CHECK-NEXT: pextrw $2, %xmm2, %esi
+; CHECK-NEXT: pextrw $1, %xmm2, %r10d
; CHECK-NEXT: pextrw $3, %xmm2, %r9d
-; CHECK-NEXT: pextrw $2, %xmm2, %edi
-; CHECK-NEXT: pextrw $1, %xmm2, %r11d
-; CHECK-NEXT: movd %xmm2, %r10d
; CHECK-NEXT: movaps %xmm1, -{{[0-9]+}}(%rsp)
; CHECK-NEXT: movaps %xmm0, -{{[0-9]+}}(%rsp)
-; CHECK-NEXT: pand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm2
-; CHECK-NEXT: pextrw $2, %xmm2, %edx
-; CHECK-NEXT: pextrw $1, %xmm2, %ebx
-; CHECK-NEXT: cmpw %dx, %bx
-; CHECK-NEXT: cmoval %ebx, %edx
-; CHECK-NEXT: pextrw $3, %xmm2, %ebx
-; CHECK-NEXT: cmpw %bx, %dx
-; CHECK-NEXT: cmovbel %ebx, %edx
-; CHECK-NEXT: pextrw $4, %xmm2, %ebx
-; CHECK-NEXT: cmpw %bx, %dx
-; CHECK-NEXT: cmovbel %ebx, %edx
-; CHECK-NEXT: pextrw $5, %xmm2, %ebx
-; CHECK-NEXT: cmpw %bx, %dx
-; CHECK-NEXT: cmovbel %ebx, %edx
-; CHECK-NEXT: pextrw $6, %xmm2, %ebx
-; CHECK-NEXT: cmpw %bx, %dx
-; CHECK-NEXT: cmovbel %ebx, %edx
-; CHECK-NEXT: pextrw $7, %xmm2, %ebx
-; CHECK-NEXT: cmpw %bx, %dx
-; CHECK-NEXT: cmovbel %ebx, %edx
-; CHECK-NEXT: andl $7, %edx
-; CHECK-NEXT: orl %r11d, %r10d
-; CHECK-NEXT: orl %r9d, %edi
+; CHECK-NEXT: xorl %r11d, %r11d
+; CHECK-NEXT: testl %r9d, %r9d
+; CHECK-NEXT: setne %r11b
+; CHECK-NEXT: leal (%r11,%r11,2), %r11d
+; CHECK-NEXT: xorl %ebx, %ebx
+; CHECK-NEXT: testl %r10d, %r10d
+; CHECK-NEXT: setne %bl
+; CHECK-NEXT: xorl %ebp, %ebp
+; CHECK-NEXT: testl %esi, %esi
+; CHECK-NEXT: setne %bpl
+; CHECK-NEXT: addl %ebp, %ebp
+; CHECK-NEXT: cmpb %bpl, %bl
+; CHECK-NEXT: cmoval %ebx, %ebp
+; CHECK-NEXT: cmpb %r11b, %bpl
+; CHECK-NEXT: cmovbel %r11d, %ebp
+; CHECK-NEXT: xorl %r11d, %r11d
+; CHECK-NEXT: testl %ecx, %ecx
+; CHECK-NEXT: setne %r11b
+; CHECK-NEXT: shll $2, %r11d
+; CHECK-NEXT: cmpb %r11b, %bpl
+; CHECK-NEXT: cmoval %ebp, %r11d
+; CHECK-NEXT: xorl %ebx, %ebx
+; CHECK-NEXT: testl %r8d, %r8d
+; CHECK-NEXT: setne %bl
+; CHECK-NEXT: leal (%rbx,%rbx,4), %ebx
+; CHECK-NEXT: cmpb %bl, %r11b
+; CHECK-NEXT: cmovbel %ebx, %r11d
+; CHECK-NEXT: testl %edx, %edx
+; CHECK-NEXT: movl $6, %ebx
+; CHECK-NEXT: cmovel %edx, %ebx
+; CHECK-NEXT: cmpb %bl, %r11b
+; CHECK-NEXT: cmoval %r11d, %ebx
+; CHECK-NEXT: testl %eax, %eax
+; CHECK-NEXT: movl $7, %r11d
+; CHECK-NEXT: cmovel %eax, %r11d
+; CHECK-NEXT: cmpb %r11b, %bl
+; CHECK-NEXT: cmoval %ebx, %r11d
+; CHECK-NEXT: andl $7, %r11d
; CHECK-NEXT: orl %r10d, %edi
+; CHECK-NEXT: orl %r9d, %esi
+; CHECK-NEXT: orl %edi, %esi
; CHECK-NEXT: orl %r8d, %ecx
+; CHECK-NEXT: orl %edx, %ecx
; CHECK-NEXT: orl %esi, %ecx
-; CHECK-NEXT: orl %edi, %ecx
; CHECK-NEXT: orl %eax, %ecx
; CHECK-NEXT: andb $1, %cl
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: cmpb $1, %cl
; CHECK-NEXT: sbbl %eax, %eax
-; CHECK-NEXT: orl -32(%rsp,%rdx,4), %eax
+; CHECK-NEXT: orl -40(%rsp,%r11,4), %eax
; CHECK-NEXT: popq %rbx
+; CHECK-NEXT: .cfi_def_cfa_offset 16
+; CHECK-NEXT: popq %rbp
; CHECK-NEXT: .cfi_def_cfa_offset 8
; CHECK-NEXT: retq
%res = call i32 @llvm.experimental.vector.extract.last.active.v8i32(<8 x i32> %a, <8 x i1> %c, i32 -1)
@@ -247,27 +285,3 @@ define i32 @extract_last_active_v16i32(<16 x i32> %a, <16 x i1> %c) {
%res = call i32 @llvm.experimental.vector.extract.last.active.v16i32(<16 x i32> %a, <16 x i1> %c, i32 -1)
ret i32 %res
}
-
-; Test for older x86 CPUs (pre-AVX) where the mask type legalization creates
-; larger element types, requiring the step vector type adjustment.
-define i32 @extract_last_active_v4i32_penryn(<4 x i32> %a, <4 x i1> %c) "target-cpu"="penryn" {
-; CHECK-LABEL: extract_last_active_v4i32_penryn:
-; CHECK: # %bb.0:
-; CHECK-NEXT: movaps %xmm0, %xmm2
-; CHECK-NEXT: xorps %xmm3, %xmm3
-; CHECK-NEXT: movaps %xmm1, %xmm0
-; CHECK-NEXT: blendvps %xmm0, {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm3
-; CHECK-NEXT: extractps $2, %xmm3, %eax
-; CHECK-NEXT: extractps $1, %xmm3, %ecx
-; CHECK-NEXT: cmpl %eax, %ecx
-; CHECK-NEXT: cmoval %ecx, %eax
-; CHECK-NEXT: extractps $3, %xmm3, %ecx
-; CHECK-NEXT: cmpl %ecx, %eax
-; CHECK-NEXT: cmovbel %ecx, %eax
-; CHECK-NEXT: movaps %xmm2, -{{[0-9]+}}(%rsp)
-; CHECK-NEXT: shll $2, %eax
-; CHECK-NEXT: movl -24(%rsp,%rax), %eax
-; CHECK-NEXT: retq
- %res = call i32 @llvm.experimental.vector.extract.last.active.v4i32(<4 x i32> %a, <4 x i1> %c, i32 poison)
- ret i32 %res
-}
More information about the llvm-branch-commits
mailing list