[llvm] [VPlan] Simplify x && false -> false, x | 0 -> x (PR #156345)
Ramkumar Ramachandra via llvm-commits
llvm-commits at lists.llvm.org
Wed Sep 3 04:02:17 PDT 2025
https://github.com/artagnon updated https://github.com/llvm/llvm-project/pull/156345
>From 1665705df63ecbf3ce40316e72c502fbc1b78b21 Mon Sep 17 00:00:00 2001
From: Ramkumar Ramachandra <ramkumar.ramachandra at codasip.com>
Date: Mon, 1 Sep 2025 14:17:02 +0100
Subject: [PATCH 1/2] [VPlan] Simplify commutative logical ops
Introduce m_c_Logical(And|Or), and use it to simplify some identities in
simplifyRecipe.
---
.../Transforms/Vectorize/VPlanTransforms.cpp | 31 ++---
.../LoopVectorize/AArch64/blend-costs.ll | 120 +++++++-----------
.../RISCV/type-info-cache-evl-crash.ll | 3 +-
.../LoopVectorize/X86/constant-fold.ll | 49 +------
4 files changed, 70 insertions(+), 133 deletions(-)
diff --git a/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp b/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp
index c588453091fcc..497f00eaa8963 100644
--- a/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp
+++ b/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp
@@ -1081,21 +1081,6 @@ static void simplifyRecipe(VPRecipeBase &R, VPTypeAnalysis &TypeInfo) {
return;
}
- // OR x, 1 -> 1.
- if (match(Def, m_c_BinaryOr(m_VPValue(X), m_AllOnes()))) {
- Def->replaceAllUsesWith(Def->getOperand(0) == X ? Def->getOperand(1)
- : Def->getOperand(0));
- Def->eraseFromParent();
- return;
- }
-
- // AND x, 0 -> 0
- if (match(&R, m_c_BinaryAnd(m_VPValue(X), m_ZeroInt()))) {
- Def->replaceAllUsesWith(R.getOperand(0) == X ? R.getOperand(1)
- : R.getOperand(0));
- return;
- }
-
// (x && y) || (x && z) -> x && (y || z)
VPBuilder Builder(Def);
if (match(Def, m_c_BinaryOr(m_LogicalAnd(m_VPValue(X), m_VPValue(Y)),
@@ -1107,6 +1092,22 @@ static void simplifyRecipe(VPRecipeBase &R, VPTypeAnalysis &TypeInfo) {
return Def->replaceAllUsesWith(
Builder.createLogicalAnd(X, Builder.createOr(Y, Z)));
+ // x | 1 -> 1
+ if (match(Def, m_c_BinaryOr(m_VPValue(X), m_AllOnes())))
+ return Def->replaceAllUsesWith(Def->getOperand(Def->getOperand(0) == X));
+
+ // x | 0 -> x
+ if (match(Def, m_c_BinaryOr(m_VPValue(X), m_ZeroInt())))
+ return Def->replaceAllUsesWith(X);
+
+ // x & 0 -> 0
+ if (match(Def, m_c_BinaryAnd(m_VPValue(X), m_ZeroInt())))
+ return Def->replaceAllUsesWith(Def->getOperand(Def->getOperand(0) == X));
+
+ // x && false -> false
+ if (match(Def, m_LogicalAnd(m_VPValue(X), m_False())))
+ return Def->replaceAllUsesWith(Def->getOperand(1));
+
if (match(Def, m_Select(m_VPValue(), m_VPValue(X), m_Deferred(X))))
return Def->replaceAllUsesWith(X);
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/blend-costs.ll b/llvm/test/Transforms/LoopVectorize/AArch64/blend-costs.ll
index e44ddbce34fd5..33ec2839a50b2 100644
--- a/llvm/test/Transforms/LoopVectorize/AArch64/blend-costs.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/blend-costs.ll
@@ -16,128 +16,106 @@ define void @test_blend_feeding_replicated_store_1(i64 %N, ptr noalias %src, ptr
; CHECK-NEXT: [[TMP1:%.*]] = icmp eq i64 [[N_MOD_VF]], 0
; CHECK-NEXT: [[TMP2:%.*]] = select i1 [[TMP1]], i64 16, i64 [[N_MOD_VF]]
; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 [[TMP43]], [[TMP2]]
-; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <16 x ptr> poison, ptr [[DST]], i64 0
-; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <16 x ptr> [[BROADCAST_SPLATINSERT]], <16 x ptr> poison, <16 x i32> zeroinitializer
; CHECK-NEXT: br label %[[VECTOR_BODY:.*]]
; CHECK: [[VECTOR_BODY]]:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[PRED_STORE_CONTINUE30:.*]] ]
; CHECK-NEXT: [[TMP4:%.*]] = getelementptr inbounds i32, ptr [[SRC]], i64 [[INDEX]]
; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <16 x i32>, ptr [[TMP4]], align 4
-; CHECK-NEXT: [[TMP6:%.*]] = icmp slt <16 x i32> [[WIDE_LOAD]], zeroinitializer
-; CHECK-NEXT: [[TMP7:%.*]] = select <16 x i1> [[TMP6]], <16 x i1> zeroinitializer, <16 x i1> zeroinitializer
-; CHECK-NEXT: [[TMP8:%.*]] = xor <16 x i1> [[TMP6]], splat (i1 true)
-; CHECK-NEXT: [[TMP9:%.*]] = or <16 x i1> [[TMP7]], [[TMP8]]
-; CHECK-NEXT: [[PREDPHI:%.*]] = select <16 x i1> [[TMP6]], <16 x ptr> [[BROADCAST_SPLAT]], <16 x ptr> zeroinitializer
-; CHECK-NEXT: [[TMP10:%.*]] = extractelement <16 x i1> [[TMP9]], i32 0
-; CHECK-NEXT: br i1 [[TMP10]], label %[[PRED_STORE_IF:.*]], label %[[PRED_STORE_CONTINUE:.*]]
+; CHECK-NEXT: [[TMP5:%.*]] = icmp sge <16 x i32> [[WIDE_LOAD]], zeroinitializer
+; CHECK-NEXT: [[TMP21:%.*]] = extractelement <16 x i1> [[TMP5]], i32 0
+; CHECK-NEXT: br i1 [[TMP21]], label %[[PRED_STORE_IF:.*]], label %[[PRED_STORE_CONTINUE:.*]]
; CHECK: [[PRED_STORE_IF]]:
-; CHECK-NEXT: [[TMP11:%.*]] = extractelement <16 x ptr> [[PREDPHI]], i32 0
-; CHECK-NEXT: store i8 0, ptr [[TMP11]], align 1
+; CHECK-NEXT: store i8 0, ptr null, align 1
; CHECK-NEXT: br label %[[PRED_STORE_CONTINUE]]
; CHECK: [[PRED_STORE_CONTINUE]]:
-; CHECK-NEXT: [[TMP12:%.*]] = extractelement <16 x i1> [[TMP9]], i32 1
-; CHECK-NEXT: br i1 [[TMP12]], label %[[PRED_STORE_IF1:.*]], label %[[PRED_STORE_CONTINUE2:.*]]
+; CHECK-NEXT: [[TMP6:%.*]] = extractelement <16 x i1> [[TMP5]], i32 1
+; CHECK-NEXT: br i1 [[TMP6]], label %[[PRED_STORE_IF1:.*]], label %[[PRED_STORE_CONTINUE2:.*]]
; CHECK: [[PRED_STORE_IF1]]:
-; CHECK-NEXT: [[TMP13:%.*]] = extractelement <16 x ptr> [[PREDPHI]], i32 1
-; CHECK-NEXT: store i8 0, ptr [[TMP13]], align 1
+; CHECK-NEXT: store i8 0, ptr null, align 1
; CHECK-NEXT: br label %[[PRED_STORE_CONTINUE2]]
; CHECK: [[PRED_STORE_CONTINUE2]]:
-; CHECK-NEXT: [[TMP14:%.*]] = extractelement <16 x i1> [[TMP9]], i32 2
-; CHECK-NEXT: br i1 [[TMP14]], label %[[PRED_STORE_IF3:.*]], label %[[PRED_STORE_CONTINUE4:.*]]
+; CHECK-NEXT: [[TMP7:%.*]] = extractelement <16 x i1> [[TMP5]], i32 2
+; CHECK-NEXT: br i1 [[TMP7]], label %[[PRED_STORE_IF3:.*]], label %[[PRED_STORE_CONTINUE4:.*]]
; CHECK: [[PRED_STORE_IF3]]:
-; CHECK-NEXT: [[TMP15:%.*]] = extractelement <16 x ptr> [[PREDPHI]], i32 2
-; CHECK-NEXT: store i8 0, ptr [[TMP15]], align 1
+; CHECK-NEXT: store i8 0, ptr null, align 1
; CHECK-NEXT: br label %[[PRED_STORE_CONTINUE4]]
; CHECK: [[PRED_STORE_CONTINUE4]]:
-; CHECK-NEXT: [[TMP16:%.*]] = extractelement <16 x i1> [[TMP9]], i32 3
-; CHECK-NEXT: br i1 [[TMP16]], label %[[PRED_STORE_IF5:.*]], label %[[PRED_STORE_CONTINUE6:.*]]
+; CHECK-NEXT: [[TMP8:%.*]] = extractelement <16 x i1> [[TMP5]], i32 3
+; CHECK-NEXT: br i1 [[TMP8]], label %[[PRED_STORE_IF5:.*]], label %[[PRED_STORE_CONTINUE6:.*]]
; CHECK: [[PRED_STORE_IF5]]:
-; CHECK-NEXT: [[TMP17:%.*]] = extractelement <16 x ptr> [[PREDPHI]], i32 3
-; CHECK-NEXT: store i8 0, ptr [[TMP17]], align 1
+; CHECK-NEXT: store i8 0, ptr null, align 1
; CHECK-NEXT: br label %[[PRED_STORE_CONTINUE6]]
; CHECK: [[PRED_STORE_CONTINUE6]]:
-; CHECK-NEXT: [[TMP18:%.*]] = extractelement <16 x i1> [[TMP9]], i32 4
-; CHECK-NEXT: br i1 [[TMP18]], label %[[PRED_STORE_IF7:.*]], label %[[PRED_STORE_CONTINUE8:.*]]
+; CHECK-NEXT: [[TMP9:%.*]] = extractelement <16 x i1> [[TMP5]], i32 4
+; CHECK-NEXT: br i1 [[TMP9]], label %[[PRED_STORE_IF7:.*]], label %[[PRED_STORE_CONTINUE8:.*]]
; CHECK: [[PRED_STORE_IF7]]:
-; CHECK-NEXT: [[TMP19:%.*]] = extractelement <16 x ptr> [[PREDPHI]], i32 4
-; CHECK-NEXT: store i8 0, ptr [[TMP19]], align 1
+; CHECK-NEXT: store i8 0, ptr null, align 1
; CHECK-NEXT: br label %[[PRED_STORE_CONTINUE8]]
; CHECK: [[PRED_STORE_CONTINUE8]]:
-; CHECK-NEXT: [[TMP20:%.*]] = extractelement <16 x i1> [[TMP9]], i32 5
-; CHECK-NEXT: br i1 [[TMP20]], label %[[PRED_STORE_IF9:.*]], label %[[PRED_STORE_CONTINUE10:.*]]
+; CHECK-NEXT: [[TMP10:%.*]] = extractelement <16 x i1> [[TMP5]], i32 5
+; CHECK-NEXT: br i1 [[TMP10]], label %[[PRED_STORE_IF9:.*]], label %[[PRED_STORE_CONTINUE10:.*]]
; CHECK: [[PRED_STORE_IF9]]:
-; CHECK-NEXT: [[TMP21:%.*]] = extractelement <16 x ptr> [[PREDPHI]], i32 5
-; CHECK-NEXT: store i8 0, ptr [[TMP21]], align 1
+; CHECK-NEXT: store i8 0, ptr null, align 1
; CHECK-NEXT: br label %[[PRED_STORE_CONTINUE10]]
; CHECK: [[PRED_STORE_CONTINUE10]]:
-; CHECK-NEXT: [[TMP22:%.*]] = extractelement <16 x i1> [[TMP9]], i32 6
-; CHECK-NEXT: br i1 [[TMP22]], label %[[PRED_STORE_IF11:.*]], label %[[PRED_STORE_CONTINUE12:.*]]
+; CHECK-NEXT: [[TMP11:%.*]] = extractelement <16 x i1> [[TMP5]], i32 6
+; CHECK-NEXT: br i1 [[TMP11]], label %[[PRED_STORE_IF11:.*]], label %[[PRED_STORE_CONTINUE12:.*]]
; CHECK: [[PRED_STORE_IF11]]:
-; CHECK-NEXT: [[TMP23:%.*]] = extractelement <16 x ptr> [[PREDPHI]], i32 6
-; CHECK-NEXT: store i8 0, ptr [[TMP23]], align 1
+; CHECK-NEXT: store i8 0, ptr null, align 1
; CHECK-NEXT: br label %[[PRED_STORE_CONTINUE12]]
; CHECK: [[PRED_STORE_CONTINUE12]]:
-; CHECK-NEXT: [[TMP24:%.*]] = extractelement <16 x i1> [[TMP9]], i32 7
-; CHECK-NEXT: br i1 [[TMP24]], label %[[PRED_STORE_IF13:.*]], label %[[PRED_STORE_CONTINUE14:.*]]
+; CHECK-NEXT: [[TMP12:%.*]] = extractelement <16 x i1> [[TMP5]], i32 7
+; CHECK-NEXT: br i1 [[TMP12]], label %[[PRED_STORE_IF13:.*]], label %[[PRED_STORE_CONTINUE14:.*]]
; CHECK: [[PRED_STORE_IF13]]:
-; CHECK-NEXT: [[TMP25:%.*]] = extractelement <16 x ptr> [[PREDPHI]], i32 7
-; CHECK-NEXT: store i8 0, ptr [[TMP25]], align 1
+; CHECK-NEXT: store i8 0, ptr null, align 1
; CHECK-NEXT: br label %[[PRED_STORE_CONTINUE14]]
; CHECK: [[PRED_STORE_CONTINUE14]]:
-; CHECK-NEXT: [[TMP26:%.*]] = extractelement <16 x i1> [[TMP9]], i32 8
-; CHECK-NEXT: br i1 [[TMP26]], label %[[PRED_STORE_IF15:.*]], label %[[PRED_STORE_CONTINUE16:.*]]
+; CHECK-NEXT: [[TMP13:%.*]] = extractelement <16 x i1> [[TMP5]], i32 8
+; CHECK-NEXT: br i1 [[TMP13]], label %[[PRED_STORE_IF15:.*]], label %[[PRED_STORE_CONTINUE16:.*]]
; CHECK: [[PRED_STORE_IF15]]:
-; CHECK-NEXT: [[TMP27:%.*]] = extractelement <16 x ptr> [[PREDPHI]], i32 8
-; CHECK-NEXT: store i8 0, ptr [[TMP27]], align 1
+; CHECK-NEXT: store i8 0, ptr null, align 1
; CHECK-NEXT: br label %[[PRED_STORE_CONTINUE16]]
; CHECK: [[PRED_STORE_CONTINUE16]]:
-; CHECK-NEXT: [[TMP28:%.*]] = extractelement <16 x i1> [[TMP9]], i32 9
-; CHECK-NEXT: br i1 [[TMP28]], label %[[PRED_STORE_IF17:.*]], label %[[PRED_STORE_CONTINUE18:.*]]
+; CHECK-NEXT: [[TMP14:%.*]] = extractelement <16 x i1> [[TMP5]], i32 9
+; CHECK-NEXT: br i1 [[TMP14]], label %[[PRED_STORE_IF17:.*]], label %[[PRED_STORE_CONTINUE18:.*]]
; CHECK: [[PRED_STORE_IF17]]:
-; CHECK-NEXT: [[TMP29:%.*]] = extractelement <16 x ptr> [[PREDPHI]], i32 9
-; CHECK-NEXT: store i8 0, ptr [[TMP29]], align 1
+; CHECK-NEXT: store i8 0, ptr null, align 1
; CHECK-NEXT: br label %[[PRED_STORE_CONTINUE18]]
; CHECK: [[PRED_STORE_CONTINUE18]]:
-; CHECK-NEXT: [[TMP30:%.*]] = extractelement <16 x i1> [[TMP9]], i32 10
-; CHECK-NEXT: br i1 [[TMP30]], label %[[PRED_STORE_IF19:.*]], label %[[PRED_STORE_CONTINUE20:.*]]
+; CHECK-NEXT: [[TMP15:%.*]] = extractelement <16 x i1> [[TMP5]], i32 10
+; CHECK-NEXT: br i1 [[TMP15]], label %[[PRED_STORE_IF19:.*]], label %[[PRED_STORE_CONTINUE20:.*]]
; CHECK: [[PRED_STORE_IF19]]:
-; CHECK-NEXT: [[TMP31:%.*]] = extractelement <16 x ptr> [[PREDPHI]], i32 10
-; CHECK-NEXT: store i8 0, ptr [[TMP31]], align 1
+; CHECK-NEXT: store i8 0, ptr null, align 1
; CHECK-NEXT: br label %[[PRED_STORE_CONTINUE20]]
; CHECK: [[PRED_STORE_CONTINUE20]]:
-; CHECK-NEXT: [[TMP32:%.*]] = extractelement <16 x i1> [[TMP9]], i32 11
-; CHECK-NEXT: br i1 [[TMP32]], label %[[PRED_STORE_IF21:.*]], label %[[PRED_STORE_CONTINUE22:.*]]
+; CHECK-NEXT: [[TMP16:%.*]] = extractelement <16 x i1> [[TMP5]], i32 11
+; CHECK-NEXT: br i1 [[TMP16]], label %[[PRED_STORE_IF21:.*]], label %[[PRED_STORE_CONTINUE22:.*]]
; CHECK: [[PRED_STORE_IF21]]:
-; CHECK-NEXT: [[TMP33:%.*]] = extractelement <16 x ptr> [[PREDPHI]], i32 11
-; CHECK-NEXT: store i8 0, ptr [[TMP33]], align 1
+; CHECK-NEXT: store i8 0, ptr null, align 1
; CHECK-NEXT: br label %[[PRED_STORE_CONTINUE22]]
; CHECK: [[PRED_STORE_CONTINUE22]]:
-; CHECK-NEXT: [[TMP34:%.*]] = extractelement <16 x i1> [[TMP9]], i32 12
-; CHECK-NEXT: br i1 [[TMP34]], label %[[PRED_STORE_IF23:.*]], label %[[PRED_STORE_CONTINUE24:.*]]
+; CHECK-NEXT: [[TMP17:%.*]] = extractelement <16 x i1> [[TMP5]], i32 12
+; CHECK-NEXT: br i1 [[TMP17]], label %[[PRED_STORE_IF23:.*]], label %[[PRED_STORE_CONTINUE24:.*]]
; CHECK: [[PRED_STORE_IF23]]:
-; CHECK-NEXT: [[TMP35:%.*]] = extractelement <16 x ptr> [[PREDPHI]], i32 12
-; CHECK-NEXT: store i8 0, ptr [[TMP35]], align 1
+; CHECK-NEXT: store i8 0, ptr null, align 1
; CHECK-NEXT: br label %[[PRED_STORE_CONTINUE24]]
; CHECK: [[PRED_STORE_CONTINUE24]]:
-; CHECK-NEXT: [[TMP36:%.*]] = extractelement <16 x i1> [[TMP9]], i32 13
-; CHECK-NEXT: br i1 [[TMP36]], label %[[PRED_STORE_IF25:.*]], label %[[PRED_STORE_CONTINUE26:.*]]
+; CHECK-NEXT: [[TMP18:%.*]] = extractelement <16 x i1> [[TMP5]], i32 13
+; CHECK-NEXT: br i1 [[TMP18]], label %[[PRED_STORE_IF25:.*]], label %[[PRED_STORE_CONTINUE26:.*]]
; CHECK: [[PRED_STORE_IF25]]:
-; CHECK-NEXT: [[TMP37:%.*]] = extractelement <16 x ptr> [[PREDPHI]], i32 13
-; CHECK-NEXT: store i8 0, ptr [[TMP37]], align 1
+; CHECK-NEXT: store i8 0, ptr null, align 1
; CHECK-NEXT: br label %[[PRED_STORE_CONTINUE26]]
; CHECK: [[PRED_STORE_CONTINUE26]]:
-; CHECK-NEXT: [[TMP38:%.*]] = extractelement <16 x i1> [[TMP9]], i32 14
-; CHECK-NEXT: br i1 [[TMP38]], label %[[PRED_STORE_IF27:.*]], label %[[PRED_STORE_CONTINUE28:.*]]
+; CHECK-NEXT: [[TMP19:%.*]] = extractelement <16 x i1> [[TMP5]], i32 14
+; CHECK-NEXT: br i1 [[TMP19]], label %[[PRED_STORE_IF27:.*]], label %[[PRED_STORE_CONTINUE28:.*]]
; CHECK: [[PRED_STORE_IF27]]:
-; CHECK-NEXT: [[TMP39:%.*]] = extractelement <16 x ptr> [[PREDPHI]], i32 14
-; CHECK-NEXT: store i8 0, ptr [[TMP39]], align 1
+; CHECK-NEXT: store i8 0, ptr null, align 1
; CHECK-NEXT: br label %[[PRED_STORE_CONTINUE28]]
; CHECK: [[PRED_STORE_CONTINUE28]]:
-; CHECK-NEXT: [[TMP40:%.*]] = extractelement <16 x i1> [[TMP9]], i32 15
-; CHECK-NEXT: br i1 [[TMP40]], label %[[PRED_STORE_IF29:.*]], label %[[PRED_STORE_CONTINUE30]]
+; CHECK-NEXT: [[TMP20:%.*]] = extractelement <16 x i1> [[TMP5]], i32 15
+; CHECK-NEXT: br i1 [[TMP20]], label %[[PRED_STORE_IF29:.*]], label %[[PRED_STORE_CONTINUE30]]
; CHECK: [[PRED_STORE_IF29]]:
-; CHECK-NEXT: [[TMP41:%.*]] = extractelement <16 x ptr> [[PREDPHI]], i32 15
-; CHECK-NEXT: store i8 0, ptr [[TMP41]], align 1
+; CHECK-NEXT: store i8 0, ptr null, align 1
; CHECK-NEXT: br label %[[PRED_STORE_CONTINUE30]]
; CHECK: [[PRED_STORE_CONTINUE30]]:
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 16
diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/type-info-cache-evl-crash.ll b/llvm/test/Transforms/LoopVectorize/RISCV/type-info-cache-evl-crash.ll
index 3f687e1f05b64..b4580c6b52542 100644
--- a/llvm/test/Transforms/LoopVectorize/RISCV/type-info-cache-evl-crash.ll
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/type-info-cache-evl-crash.ll
@@ -31,9 +31,8 @@ define void @type_info_cache_clobber(ptr %dstv, ptr %src, i64 %wide.trip.count)
; CHECK-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 8 x i8> @llvm.vp.load.nxv8i8.p0(ptr align 1 [[TMP13]], <vscale x 8 x i1> splat (i1 true), i32 [[TMP11]]), !alias.scope [[META0:![0-9]+]]
; CHECK-NEXT: [[TMP15:%.*]] = zext <vscale x 8 x i8> [[VP_OP_LOAD]] to <vscale x 8 x i32>
; CHECK-NEXT: [[TMP23:%.*]] = ashr <vscale x 8 x i32> [[TMP15]], zeroinitializer
-; CHECK-NEXT: [[VP_OP3:%.*]] = or <vscale x 8 x i32> [[TMP23]], zeroinitializer
; CHECK-NEXT: [[TMP16:%.*]] = icmp ult <vscale x 8 x i32> [[TMP15]], zeroinitializer
-; CHECK-NEXT: [[TMP17:%.*]] = select <vscale x 8 x i1> [[TMP16]], <vscale x 8 x i32> [[VP_OP3]], <vscale x 8 x i32> zeroinitializer
+; CHECK-NEXT: [[TMP17:%.*]] = select <vscale x 8 x i1> [[TMP16]], <vscale x 8 x i32> [[TMP23]], <vscale x 8 x i32> zeroinitializer
; CHECK-NEXT: [[TMP24:%.*]] = trunc <vscale x 8 x i32> [[TMP17]] to <vscale x 8 x i8>
; CHECK-NEXT: call void @llvm.vp.scatter.nxv8i8.nxv8p0(<vscale x 8 x i8> [[TMP24]], <vscale x 8 x ptr> align 1 [[BROADCAST_SPLAT]], <vscale x 8 x i1> splat (i1 true), i32 [[TMP11]]), !alias.scope [[META3:![0-9]+]], !noalias [[META0]]
; CHECK-NEXT: call void @llvm.vp.scatter.nxv8i16.nxv8p0(<vscale x 8 x i16> zeroinitializer, <vscale x 8 x ptr> align 2 zeroinitializer, <vscale x 8 x i1> splat (i1 true), i32 [[TMP11]])
diff --git a/llvm/test/Transforms/LoopVectorize/X86/constant-fold.ll b/llvm/test/Transforms/LoopVectorize/X86/constant-fold.ll
index 54d738388ea73..b0bedefb71aaf 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/constant-fold.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/constant-fold.ll
@@ -341,64 +341,23 @@ exit:
define void @redundant_and_2(ptr %dst, i1 %c.0, i1 %c.1) {
; CHECK-LABEL: @redundant_and_2(
; CHECK-NEXT: entry:
-; CHECK-NEXT: br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
-; CHECK: vector.ph:
-; CHECK-NEXT: [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <4 x i1> poison, i1 [[C_0:%.*]], i64 0
-; CHECK-NEXT: [[BROADCAST_SPLAT2:%.*]] = shufflevector <4 x i1> [[BROADCAST_SPLATINSERT1]], <4 x i1> poison, <4 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP0:%.*]] = xor <4 x i1> [[BROADCAST_SPLAT2]], splat (i1 true)
-; CHECK-NEXT: [[TMP1:%.*]] = select <4 x i1> [[TMP0]], <4 x i1> zeroinitializer, <4 x i1> zeroinitializer
-; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
-; CHECK: vector.body:
-; CHECK-NEXT: [[TMP4:%.*]] = select <4 x i1> <i1 true, i1 true, i1 true, i1 false>, <4 x i1> [[TMP1]], <4 x i1> zeroinitializer
-; CHECK-NEXT: [[TMP5:%.*]] = extractelement <4 x i1> [[TMP4]], i32 0
-; CHECK-NEXT: br i1 [[TMP5]], label [[PRED_STORE_IF:%.*]], label [[PRED_STORE_CONTINUE:%.*]]
-; CHECK: pred.store.if:
-; CHECK-NEXT: [[TMP7:%.*]] = getelementptr inbounds i32, ptr [[DST:%.*]], i32 0
-; CHECK-NEXT: store i32 0, ptr [[TMP7]], align 4
-; CHECK-NEXT: br label [[PRED_STORE_CONTINUE]]
-; CHECK: pred.store.continue:
-; CHECK-NEXT: [[TMP8:%.*]] = extractelement <4 x i1> [[TMP4]], i32 1
-; CHECK-NEXT: br i1 [[TMP8]], label [[PRED_STORE_IF3:%.*]], label [[PRED_STORE_CONTINUE4:%.*]]
-; CHECK: pred.store.if1:
-; CHECK-NEXT: [[TMP10:%.*]] = getelementptr inbounds i32, ptr [[DST]], i32 1
-; CHECK-NEXT: store i32 0, ptr [[TMP10]], align 4
-; CHECK-NEXT: br label [[PRED_STORE_CONTINUE4]]
-; CHECK: pred.store.continue2:
-; CHECK-NEXT: [[TMP11:%.*]] = extractelement <4 x i1> [[TMP4]], i32 2
-; CHECK-NEXT: br i1 [[TMP11]], label [[PRED_STORE_IF5:%.*]], label [[PRED_STORE_CONTINUE6:%.*]]
-; CHECK: pred.store.if3:
-; CHECK-NEXT: [[TMP13:%.*]] = getelementptr inbounds i32, ptr [[DST]], i32 2
-; CHECK-NEXT: store i32 0, ptr [[TMP13]], align 4
-; CHECK-NEXT: br label [[PRED_STORE_CONTINUE6]]
-; CHECK: pred.store.continue4:
-; CHECK-NEXT: [[TMP14:%.*]] = extractelement <4 x i1> [[TMP4]], i32 3
-; CHECK-NEXT: br i1 [[TMP14]], label [[PRED_STORE_IF7:%.*]], label [[PRED_STORE_CONTINUE8:%.*]]
-; CHECK: pred.store.if5:
-; CHECK-NEXT: [[TMP16:%.*]] = getelementptr inbounds i32, ptr [[DST]], i32 3
-; CHECK-NEXT: store i32 0, ptr [[TMP16]], align 4
-; CHECK-NEXT: br label [[PRED_STORE_CONTINUE8]]
-; CHECK: pred.store.continue6:
-; CHECK-NEXT: br label [[MIDDLE_BLOCK:%.*]]
-; CHECK: middle.block:
-; CHECK-NEXT: br label [[EXIT:%.*]]
-; CHECK: scalar.ph:
; CHECK-NEXT: br label [[LOOP_HEADER:%.*]]
; CHECK: loop.header:
-; CHECK-NEXT: [[IV:%.*]] = phi i32 [ 0, [[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], [[LOOP_LATCH:%.*]] ]
-; CHECK-NEXT: br i1 [[C_0]], label [[LOOP_LATCH]], label [[THEN_1:%.*]]
+; CHECK-NEXT: [[IV:%.*]] = phi i32 [ 0, [[SCALAR_PH:%.*]] ], [ [[IV_NEXT:%.*]], [[LOOP_LATCH:%.*]] ]
+; CHECK-NEXT: br i1 [[C_0:%.*]], label [[LOOP_LATCH]], label [[THEN_1:%.*]]
; CHECK: then.1:
; CHECK-NEXT: [[CMP:%.*]] = icmp eq i32 [[IV]], 2
; CHECK-NEXT: [[OR:%.*]] = and i1 false, [[CMP]]
; CHECK-NEXT: [[COND:%.*]] = select i1 [[OR]], i1 [[C_1:%.*]], i1 false
; CHECK-NEXT: br i1 [[COND]], label [[THEN_2:%.*]], label [[LOOP_LATCH]]
; CHECK: then.2:
-; CHECK-NEXT: [[GEP:%.*]] = getelementptr inbounds i32, ptr [[DST]], i32 [[IV]]
+; CHECK-NEXT: [[GEP:%.*]] = getelementptr inbounds i32, ptr [[DST:%.*]], i32 [[IV]]
; CHECK-NEXT: store i32 0, ptr [[GEP]], align 4
; CHECK-NEXT: br label [[LOOP_LATCH]]
; CHECK: loop.latch:
; CHECK-NEXT: [[IV_NEXT]] = add nuw nsw i32 [[IV]], 1
; CHECK-NEXT: [[EC:%.*]] = icmp eq i32 [[IV_NEXT]], 3
-; CHECK-NEXT: br i1 [[EC]], label [[EXIT]], label [[LOOP_HEADER]], !llvm.loop [[LOOP6:![0-9]+]]
+; CHECK-NEXT: br i1 [[EC]], label [[EXIT:%.*]], label [[LOOP_HEADER]]
; CHECK: exit:
; CHECK-NEXT: ret void
;
>From a9fdab731778f645c45f3a499eb4472591c6df54 Mon Sep 17 00:00:00 2001
From: Ramkumar Ramachandra <ramkumar.ramachandra at codasip.com>
Date: Wed, 3 Sep 2025 11:58:57 +0100
Subject: [PATCH 2/2] [VPlan] Some code motion
---
.../Transforms/Vectorize/VPlanTransforms.cpp | 22 +++++++++----------
1 file changed, 11 insertions(+), 11 deletions(-)
diff --git a/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp b/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp
index 497f00eaa8963..2560b1af2e5aa 100644
--- a/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp
+++ b/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp
@@ -1081,17 +1081,6 @@ static void simplifyRecipe(VPRecipeBase &R, VPTypeAnalysis &TypeInfo) {
return;
}
- // (x && y) || (x && z) -> x && (y || z)
- VPBuilder Builder(Def);
- if (match(Def, m_c_BinaryOr(m_LogicalAnd(m_VPValue(X), m_VPValue(Y)),
- m_LogicalAnd(m_Deferred(X), m_VPValue(Z)))) &&
- // Simplify only if one of the operands has one use to avoid creating an
- // extra recipe.
- (!Def->getOperand(0)->hasMoreThanOneUniqueUser() ||
- !Def->getOperand(1)->hasMoreThanOneUniqueUser()))
- return Def->replaceAllUsesWith(
- Builder.createLogicalAnd(X, Builder.createOr(Y, Z)));
-
// x | 1 -> 1
if (match(Def, m_c_BinaryOr(m_VPValue(X), m_AllOnes())))
return Def->replaceAllUsesWith(Def->getOperand(Def->getOperand(0) == X));
@@ -1108,6 +1097,17 @@ static void simplifyRecipe(VPRecipeBase &R, VPTypeAnalysis &TypeInfo) {
if (match(Def, m_LogicalAnd(m_VPValue(X), m_False())))
return Def->replaceAllUsesWith(Def->getOperand(1));
+ // (x && y) || (x && z) -> x && (y || z)
+ VPBuilder Builder(Def);
+ if (match(Def, m_c_BinaryOr(m_LogicalAnd(m_VPValue(X), m_VPValue(Y)),
+ m_LogicalAnd(m_Deferred(X), m_VPValue(Z)))) &&
+ // Simplify only if one of the operands has one use to avoid creating an
+ // extra recipe.
+ (!Def->getOperand(0)->hasMoreThanOneUniqueUser() ||
+ !Def->getOperand(1)->hasMoreThanOneUniqueUser()))
+ return Def->replaceAllUsesWith(
+ Builder.createLogicalAnd(X, Builder.createOr(Y, Z)));
+
if (match(Def, m_Select(m_VPValue(), m_VPValue(X), m_Deferred(X))))
return Def->replaceAllUsesWith(X);
More information about the llvm-commits
mailing list