[llvm] [WIP][X86] combineShiftRightLogical - fold srl(vecreduce_umax(x),bw-1) as MOVMSK signbit reduction (PR #210281)
via llvm-commits
llvm-commits at lists.llvm.org
Fri Jul 17 03:09:04 PDT 2026
llvmorg-github-actions[bot] wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-x86
Author: Simon Pilgrim (RKSimon)
<details>
<summary>Changes</summary>
VectorCombine may have folded: icmp_eq(vecreduce_or(splatsign(x)),0) --> icmp_sgt(vecreduce_umax(x),-1) which DAG folds to: srl(vecreduce_umax(x),bw-1).
This match attempts to lower:
srl(vecreduce_umax(x),bw-1) -> icmp_ne(movmsk(x),0) "any_of negative"
srl(not(vecreduce_umax(x)),bw-1) -> icmp_eq(movmsk(x),0) "none_of negative"
The correct fix would be to improve vecreduce_or costs to prevent VectorCombine doing this, but that change is far too big to be merged into 23.x - so I've created the narrow vXi32 backend fix.
Fixes #<!-- -->209714
---
Full diff: https://github.com/llvm/llvm-project/pull/210281.diff
2 Files Affected:
- (modified) llvm/lib/Target/X86/X86ISelLowering.cpp (+20)
- (modified) llvm/test/CodeGen/X86/vector-reduce-umax.ll (+138-10)
``````````diff
diff --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp
index 97e783c09f0f2..c2278183fa133 100644
--- a/llvm/lib/Target/X86/X86ISelLowering.cpp
+++ b/llvm/lib/Target/X86/X86ISelLowering.cpp
@@ -50910,6 +50910,26 @@ static SDValue combineShiftRightLogical(SDNode *N, SelectionDAG &DAG,
}
}
+ // VectorCombine may have folded:
+ // icmp_eq(vecreduce_or(splatsign(x)),0) --> icmp_sgt(vecreduce_umax(x),-1)
+ // which DAG folds to: srl(vecreduce_umax(x),bw-1).
+ // This attempts to reconstruct the signbit reduction.
+ if (sd_match(N1, m_SpecificInt(EltSizeInBits - 1))) {
+ SDValue X = N0;
+ ISD::CondCode CC = ISD::SETNE;
+ if (sd_match(N0, m_Not(m_Value(X))))
+ CC = ISD::SETEQ;
+ if (X.getOpcode() == ISD::VECREDUCE_UMAX) {
+ SDValue V = X.getOperand(0);
+ if (DAG.getTargetLoweringInfo().isTypeLegal(V.getValueType()) &&
+ (V.getValueType() == MVT::v4i32 || V.getValueType() == MVT::v8i32)) {
+ V = DAG.getNode(X86ISD::MOVMSK, DL, MVT::i32, V);
+ V = DAG.getSetCC(DL, MVT::i8, V, DAG.getConstant(0, DL, MVT::i32), CC);
+ return DAG.getZExtOrTrunc(V, DL, VT);
+ }
+ }
+ }
+
// Only do this on the last DAG combine as it can interfere with other
// combines.
if (!DCI.isAfterLegalizeDAG())
diff --git a/llvm/test/CodeGen/X86/vector-reduce-umax.ll b/llvm/test/CodeGen/X86/vector-reduce-umax.ll
index b45c2914bdccd..ca252968b4898 100644
--- a/llvm/test/CodeGen/X86/vector-reduce-umax.ll
+++ b/llvm/test/CodeGen/X86/vector-reduce-umax.ll
@@ -1,14 +1,14 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc < %s -mtriple=i686-- -mattr=+sse2 | FileCheck %s --check-prefixes=SSE,SSE2,X86-SSE2
-; RUN: llc < %s -mtriple=x86_64-- -mattr=+sse2 | FileCheck %s --check-prefixes=SSE,SSE2,X64-SSE2
-; RUN: llc < %s -mtriple=i686-- -mattr=+sse4.1 | FileCheck %s --check-prefixes=SSE,SSE4,X86-SSE4,X86-SSE41
-; RUN: llc < %s -mtriple=x86_64-- -mattr=+sse4.1 | FileCheck %s --check-prefixes=SSE,SSE4,X64-SSE4,X64-SSE41
-; RUN: llc < %s -mtriple=i686-- -mattr=+sse4.2 | FileCheck %s --check-prefixes=SSE,SSE4,X86-SSE4,X86-SSE42
-; RUN: llc < %s -mtriple=x86_64-- -mattr=+sse4.2 | FileCheck %s --check-prefixes=SSE,SSE4,X64-SSE4,X64-SSE42
-; RUN: llc < %s -mtriple=i686-- -mattr=+avx | FileCheck %s --check-prefixes=AVX,AVX1,X86-AVX1
-; RUN: llc < %s -mtriple=x86_64-- -mattr=+avx | FileCheck %s --check-prefixes=AVX,AVX1,X64-AVX1
-; RUN: llc < %s -mtriple=i686-- -mattr=+avx2 | FileCheck %s --check-prefixes=AVX,AVX2,X86-AVX2
-; RUN: llc < %s -mtriple=x86_64-- -mattr=+avx2 | FileCheck %s --check-prefixes=AVX,AVX2,X64-AVX2
+; RUN: llc < %s -mtriple=i686-- -mattr=+sse2 | FileCheck %s --check-prefixes=SSE,SSE2,X86-SSE,X86-SSE2
+; RUN: llc < %s -mtriple=x86_64-- -mattr=+sse2 | FileCheck %s --check-prefixes=SSE,SSE2,X64-SSE,X64-SSE2
+; RUN: llc < %s -mtriple=i686-- -mattr=+sse4.1 | FileCheck %s --check-prefixes=SSE,SSE4,X86-SSE,X86-SSE4,X86-SSE41
+; RUN: llc < %s -mtriple=x86_64-- -mattr=+sse4.1 | FileCheck %s --check-prefixes=SSE,SSE4,X64-SSE,X64-SSE4,X64-SSE41
+; RUN: llc < %s -mtriple=i686-- -mattr=+sse4.2 | FileCheck %s --check-prefixes=SSE,SSE4,X86-SSE,X86-SSE4,X86-SSE42
+; RUN: llc < %s -mtriple=x86_64-- -mattr=+sse4.2 | FileCheck %s --check-prefixes=SSE,SSE4,X64-SSE,X64-SSE4,X64-SSE42
+; RUN: llc < %s -mtriple=i686-- -mattr=+avx | FileCheck %s --check-prefixes=AVX,AVX1,X86-AVX,X86-AVX1
+; RUN: llc < %s -mtriple=x86_64-- -mattr=+avx | FileCheck %s --check-prefixes=AVX,AVX1,X64-AVX,X64-AVX1
+; RUN: llc < %s -mtriple=i686-- -mattr=+avx2 | FileCheck %s --check-prefixes=AVX,AVX2,X86-AVX,X86-AVX2
+; RUN: llc < %s -mtriple=x86_64-- -mattr=+avx2 | FileCheck %s --check-prefixes=AVX,AVX2,X64-AVX,X64-AVX2
; RUN: llc < %s -mtriple=x86_64-- -mattr=+avx512f,+avx512bw | FileCheck %s --check-prefixes=AVX,AVX512,AVX512BW
; RUN: llc < %s -mtriple=x86_64-- -mattr=+avx512f,+avx512bw,+avx512dq,+avx512vl | FileCheck %s --check-prefixes=AVX,AVX512,AVX512VL
@@ -3504,6 +3504,134 @@ define i8 @test_v128i8(<128 x i8> %a0) nounwind {
ret i8 %1
}
+; PR209714
+define i32 @reduce_umax_v4i32_signbit(ptr %pa, ptr %pb) {
+; X86-SSE-LABEL: reduce_umax_v4i32_signbit:
+; X86-SSE: # %bb.0:
+; X86-SSE-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X86-SSE-NEXT: movl {{[0-9]+}}(%esp), %ecx
+; X86-SSE-NEXT: movaps (%ecx), %xmm0
+; X86-SSE-NEXT: andps (%eax), %xmm0
+; X86-SSE-NEXT: movmskps %xmm0, %ecx
+; X86-SSE-NEXT: xorl %eax, %eax
+; X86-SSE-NEXT: testl %ecx, %ecx
+; X86-SSE-NEXT: sete %al
+; X86-SSE-NEXT: retl
+;
+; X64-SSE-LABEL: reduce_umax_v4i32_signbit:
+; X64-SSE: # %bb.0:
+; X64-SSE-NEXT: movaps (%rsi), %xmm0
+; X64-SSE-NEXT: andps (%rdi), %xmm0
+; X64-SSE-NEXT: movmskps %xmm0, %ecx
+; X64-SSE-NEXT: xorl %eax, %eax
+; X64-SSE-NEXT: testl %ecx, %ecx
+; X64-SSE-NEXT: sete %al
+; X64-SSE-NEXT: retq
+;
+; X86-AVX-LABEL: reduce_umax_v4i32_signbit:
+; X86-AVX: # %bb.0:
+; X86-AVX-NEXT: movl {{[0-9]+}}(%esp), %ecx
+; X86-AVX-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X86-AVX-NEXT: vmovaps (%eax), %xmm0
+; X86-AVX-NEXT: xorl %eax, %eax
+; X86-AVX-NEXT: vtestps (%ecx), %xmm0
+; X86-AVX-NEXT: sete %al
+; X86-AVX-NEXT: retl
+;
+; X64-AVX-LABEL: reduce_umax_v4i32_signbit:
+; X64-AVX: # %bb.0:
+; X64-AVX-NEXT: vmovaps (%rdi), %xmm0
+; X64-AVX-NEXT: xorl %eax, %eax
+; X64-AVX-NEXT: vtestps (%rsi), %xmm0
+; X64-AVX-NEXT: sete %al
+; X64-AVX-NEXT: retq
+;
+; AVX512-LABEL: reduce_umax_v4i32_signbit:
+; AVX512: # %bb.0:
+; AVX512-NEXT: vmovaps (%rdi), %xmm0
+; AVX512-NEXT: xorl %eax, %eax
+; AVX512-NEXT: vtestps (%rsi), %xmm0
+; AVX512-NEXT: sete %al
+; AVX512-NEXT: retq
+ %a = load <4 x i32>, ptr %pa
+ %b = load <4 x i32>, ptr %pb
+ %a.not = xor <4 x i32> %a, splat (i32 -1)
+ %and = and <4 x i32> %b, %a
+ %rdx = call i32 @llvm.vector.reduce.umax.v4i32(<4 x i32> %and)
+ %cmp = icmp sgt i32 %rdx, -1
+ %res = zext i1 %cmp to i32
+ ret i32 %res
+}
+
+
+; PR209714
+define i32 @reduce_umax_v8i32_signbit_not(ptr %pa, ptr %pb) {
+; X86-SSE-LABEL: reduce_umax_v8i32_signbit_not:
+; X86-SSE: # %bb.0:
+; X86-SSE-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X86-SSE-NEXT: movl {{[0-9]+}}(%esp), %ecx
+; X86-SSE-NEXT: movaps (%ecx), %xmm0
+; X86-SSE-NEXT: movaps 16(%ecx), %xmm1
+; X86-SSE-NEXT: andnps 16(%eax), %xmm1
+; X86-SSE-NEXT: andnps (%eax), %xmm0
+; X86-SSE-NEXT: orps %xmm1, %xmm0
+; X86-SSE-NEXT: movmskps %xmm0, %ecx
+; X86-SSE-NEXT: xorl %eax, %eax
+; X86-SSE-NEXT: testl %ecx, %ecx
+; X86-SSE-NEXT: sete %al
+; X86-SSE-NEXT: retl
+;
+; X64-SSE-LABEL: reduce_umax_v8i32_signbit_not:
+; X64-SSE: # %bb.0:
+; X64-SSE-NEXT: movaps (%rdi), %xmm0
+; X64-SSE-NEXT: movaps 16(%rdi), %xmm1
+; X64-SSE-NEXT: andnps 16(%rsi), %xmm1
+; X64-SSE-NEXT: andnps (%rsi), %xmm0
+; X64-SSE-NEXT: orps %xmm1, %xmm0
+; X64-SSE-NEXT: movmskps %xmm0, %ecx
+; X64-SSE-NEXT: xorl %eax, %eax
+; X64-SSE-NEXT: testl %ecx, %ecx
+; X64-SSE-NEXT: sete %al
+; X64-SSE-NEXT: retq
+;
+; X86-AVX-LABEL: reduce_umax_v8i32_signbit_not:
+; X86-AVX: # %bb.0:
+; X86-AVX-NEXT: movl {{[0-9]+}}(%esp), %ecx
+; X86-AVX-NEXT: movl {{[0-9]+}}(%esp), %eax
+; X86-AVX-NEXT: vmovaps (%eax), %ymm0
+; X86-AVX-NEXT: xorl %eax, %eax
+; X86-AVX-NEXT: vtestps (%ecx), %ymm0
+; X86-AVX-NEXT: setb %al
+; X86-AVX-NEXT: vzeroupper
+; X86-AVX-NEXT: retl
+;
+; X64-AVX-LABEL: reduce_umax_v8i32_signbit_not:
+; X64-AVX: # %bb.0:
+; X64-AVX-NEXT: vmovaps (%rdi), %ymm0
+; X64-AVX-NEXT: xorl %eax, %eax
+; X64-AVX-NEXT: vtestps (%rsi), %ymm0
+; X64-AVX-NEXT: setb %al
+; X64-AVX-NEXT: vzeroupper
+; X64-AVX-NEXT: retq
+;
+; AVX512-LABEL: reduce_umax_v8i32_signbit_not:
+; AVX512: # %bb.0:
+; AVX512-NEXT: vmovaps (%rdi), %ymm0
+; AVX512-NEXT: xorl %eax, %eax
+; AVX512-NEXT: vtestps (%rsi), %ymm0
+; AVX512-NEXT: setb %al
+; AVX512-NEXT: vzeroupper
+; AVX512-NEXT: retq
+ %a = load <8 x i32>, ptr %pa
+ %b = load <8 x i32>, ptr %pb
+ %a.not = xor <8 x i32> %a, splat (i32 -1)
+ %and = and <8 x i32> %b, %a.not
+ %rdx = call i32 @llvm.vector.reduce.umax.v8i32(<8 x i32> %and)
+ %cmp = icmp sgt i32 %rdx, -1
+ %res = zext i1 %cmp to i32
+ ret i32 %res
+}
+
declare i64 @llvm.vector.reduce.umax.v2i64(<2 x i64>)
declare i64 @llvm.vector.reduce.umax.v4i64(<4 x i64>)
declare i64 @llvm.vector.reduce.umax.v8i64(<8 x i64>)
``````````
</details>
https://github.com/llvm/llvm-project/pull/210281
More information about the llvm-commits
mailing list