[llvm] c5b9010 - [VPlan] Use nuw when computing {VF, VScale}xUF (#170710)
via llvm-commits
llvm-commits at lists.llvm.org
Mon Dec 8 07:46:06 PST 2025
Author: Ramkumar Ramachandra
Date: 2025-12-08T15:46:02Z
New Revision: c5b90103da58c261fcc9720e8700a06fac7e0388
URL: https://github.com/llvm/llvm-project/commit/c5b90103da58c261fcc9720e8700a06fac7e0388
DIFF: https://github.com/llvm/llvm-project/commit/c5b90103da58c261fcc9720e8700a06fac7e0388.diff
LOG: [VPlan] Use nuw when computing {VF,VScale}xUF (#170710)
These quantities should never unsigned-wrap. This matches the behavior
if only VFxUF is used (and not VF): when computing both VF and VFxUF,
nuw should hold for each step separately.
Added:
Modified:
llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp
llvm/test/Transforms/LoopVectorize/AArch64/pr60831-sve-inv-store-crash.ll
llvm/test/Transforms/LoopVectorize/AArch64/sve-inductions-unusual-types.ll
llvm/test/Transforms/LoopVectorize/AArch64/sve-vector-reverse.ll
llvm/test/Transforms/LoopVectorize/RISCV/riscv-vector-reverse.ll
llvm/test/Transforms/LoopVectorize/RISCV/strided-accesses.ll
llvm/test/Transforms/LoopVectorize/scalable-assume.ll
llvm/test/Transforms/LoopVectorize/scalable-first-order-recurrence.ll
llvm/test/Transforms/LoopVectorize/scalable-inductions.ll
llvm/test/Transforms/LoopVectorize/scalable-iv-outside-user.ll
Removed:
################################################################################
diff --git a/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp b/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp
index 320baeb454d46..2242f95e4226c 100644
--- a/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp
+++ b/llvm/lib/Transforms/Vectorize/VPlanTransforms.cpp
@@ -4593,7 +4593,8 @@ void VPlanTransforms::materializeVFAndVFxUF(VPlan &Plan, VPBasicBlock *VectorPH,
VF.replaceAllUsesWith(RuntimeVF);
VPValue *UF = Plan.getConstantInt(TCTy, Plan.getUF());
- VPValue *MulByUF = Builder.createNaryOp(Instruction::Mul, {RuntimeVF, UF});
+ VPValue *MulByUF = Builder.createOverflowingOp(
+ Instruction::Mul, {RuntimeVF, UF}, {true, false});
VFxUF.replaceAllUsesWith(MulByUF);
}
@@ -4881,7 +4882,8 @@ void VPlanTransforms::narrowInterleaveGroups(VPlan &Plan, ElementCount VF,
if (VF.isScalable()) {
VPValue *VScale = PHBuilder.createElementCount(
VectorLoop->getCanonicalIVType(), ElementCount::getScalable(1));
- VPValue *VScaleUF = PHBuilder.createNaryOp(Instruction::Mul, {VScale, UF});
+ VPValue *VScaleUF = PHBuilder.createOverflowingOp(
+ Instruction::Mul, {VScale, UF}, {true, false});
Inc->setOperand(1, VScaleUF);
Plan.getVF().replaceAllUsesWith(VScale);
} else {
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/pr60831-sve-inv-store-crash.ll b/llvm/test/Transforms/LoopVectorize/AArch64/pr60831-sve-inv-store-crash.ll
index 131b3d1b02727..fd560de78a6d0 100644
--- a/llvm/test/Transforms/LoopVectorize/AArch64/pr60831-sve-inv-store-crash.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/pr60831-sve-inv-store-crash.ll
@@ -59,7 +59,7 @@ define void @test_invar_gep(ptr %dst) #0 {
; IC2-NEXT: [[TMP11:%.*]] = mul nuw i64 [[TMP2]], 4
; IC2-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TMP11]], i64 0
; IC2-NEXT: [[TMP21:%.*]] = shufflevector <vscale x 4 x i64> [[BROADCAST_SPLATINSERT]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
-; IC2-NEXT: [[TMP3:%.*]] = mul i64 [[TMP11]], 2
+; IC2-NEXT: [[TMP3:%.*]] = mul nuw i64 [[TMP11]], 2
; IC2-NEXT: [[N_MOD_VF:%.*]] = urem i64 100, [[TMP3]]
; IC2-NEXT: [[N_VEC:%.*]] = sub i64 100, [[N_MOD_VF]]
; IC2-NEXT: [[TMP5:%.*]] = call <vscale x 4 x i64> @llvm.stepvector.nxv4i64()
@@ -172,7 +172,7 @@ define void @test_invar_gep_var_start(i64 %start, ptr %dst) #0 {
; IC2-NEXT: [[TMP4:%.*]] = mul nuw i64 [[TMP3]], 4
; IC2-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TMP4]], i64 0
; IC2-NEXT: [[TMP9:%.*]] = shufflevector <vscale x 4 x i64> [[BROADCAST_SPLATINSERT]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
-; IC2-NEXT: [[TMP5:%.*]] = mul i64 [[TMP4]], 2
+; IC2-NEXT: [[TMP5:%.*]] = mul nuw i64 [[TMP4]], 2
; IC2-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[TMP0]], [[TMP5]]
; IC2-NEXT: [[N_VEC:%.*]] = sub i64 [[TMP0]], [[N_MOD_VF]]
; IC2-NEXT: [[TMP6:%.*]] = add i64 [[START]], [[N_VEC]]
@@ -294,7 +294,7 @@ define void @test_invar_gep_var_start_step_2(i64 %start, ptr %dst) #0 {
; IC2-NEXT: [[TMP6:%.*]] = mul nuw i64 [[TMP5]], 4
; IC2-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TMP6]], i64 0
; IC2-NEXT: [[BROADCAST_SPLAT1:%.*]] = shufflevector <vscale x 4 x i64> [[BROADCAST_SPLATINSERT]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
-; IC2-NEXT: [[TMP7:%.*]] = mul i64 [[TMP6]], 2
+; IC2-NEXT: [[TMP7:%.*]] = mul nuw i64 [[TMP6]], 2
; IC2-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[TMP2]], [[TMP7]]
; IC2-NEXT: [[N_VEC:%.*]] = sub i64 [[TMP2]], [[N_MOD_VF]]
; IC2-NEXT: [[TMP10:%.*]] = mul i64 [[N_VEC]], 2
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-inductions-unusual-types.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-inductions-unusual-types.ll
index 47623f3b5d99e..c8e4321f2350a 100644
--- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-inductions-unusual-types.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-inductions-unusual-types.ll
@@ -15,7 +15,7 @@ define void @induction_i7(ptr %dst) #0 {
; CHECK-NEXT: [[TMP40:%.*]] = mul nuw i64 [[TMP4]], 2
; CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[TMP40]], i64 0
; CHECK-NEXT: [[DOTSPLAT_:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP5:%.*]] = mul i64 [[TMP40]], 2
+; CHECK-NEXT: [[TMP5:%.*]] = mul nuw i64 [[TMP40]], 2
; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 64, [[TMP5]]
; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 64, [[N_MOD_VF]]
; CHECK-NEXT: [[IND_END:%.*]] = trunc i64 [[N_VEC]] to i7
@@ -74,7 +74,7 @@ define void @induction_i3_zext(ptr %dst) #0 {
; CHECK-NEXT: [[TMP40:%.*]] = mul nuw i64 [[TMP4]], 2
; CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[TMP40]], i64 0
; CHECK-NEXT: [[DOTSPLAT_:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP5:%.*]] = mul i64 [[TMP40]], 2
+; CHECK-NEXT: [[TMP5:%.*]] = mul nuw i64 [[TMP40]], 2
; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 64, [[TMP5]]
; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 64, [[N_MOD_VF]]
; CHECK-NEXT: [[IND_END:%.*]] = trunc i64 [[N_VEC]] to i3
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-vector-reverse.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-vector-reverse.ll
index 9989209f8c575..ba6bd8f36f5e4 100644
--- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-vector-reverse.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-vector-reverse.ll
@@ -21,7 +21,7 @@ define void @vector_reverse_f64(i64 %N, ptr noalias %a, ptr noalias %b) #0{
; CHECK: vector.ph:
; CHECK-NEXT: [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP5:%.*]] = shl nuw i64 [[TMP4]], 3
-; CHECK-NEXT: [[TMP6:%.*]] = shl i64 [[TMP4]], 4
+; CHECK-NEXT: [[TMP6:%.*]] = shl nuw i64 [[TMP4]], 4
; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[N]], [[TMP6]]
; CHECK-NEXT: [[N_VEC:%.*]] = sub nsw i64 [[N]], [[N_MOD_VF]]
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
@@ -98,7 +98,7 @@ define void @vector_reverse_i64(i64 %N, ptr %a, ptr %b) #0 {
; CHECK: vector.ph:
; CHECK-NEXT: [[TMP7:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[TMP8:%.*]] = shl nuw i64 [[TMP7]], 3
-; CHECK-NEXT: [[TMP9:%.*]] = shl i64 [[TMP7]], 4
+; CHECK-NEXT: [[TMP9:%.*]] = shl nuw i64 [[TMP7]], 4
; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[N]], [[TMP9]]
; CHECK-NEXT: [[N_VEC:%.*]] = sub nsw i64 [[N]], [[N_MOD_VF]]
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/riscv-vector-reverse.ll b/llvm/test/Transforms/LoopVectorize/RISCV/riscv-vector-reverse.ll
index f2f65685e9bad..f7340fee47eb8 100644
--- a/llvm/test/Transforms/LoopVectorize/RISCV/riscv-vector-reverse.ll
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/riscv-vector-reverse.ll
@@ -106,7 +106,7 @@ define void @vector_reverse_i32(ptr noalias %A, ptr noalias %B) {
; RV64-UF2: [[VECTOR_PH]]:
; RV64-UF2-NEXT: [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
; RV64-UF2-NEXT: [[TMP5:%.*]] = mul nuw i64 [[TMP4]], 4
-; RV64-UF2-NEXT: [[TMP6:%.*]] = mul i64 [[TMP5]], 2
+; RV64-UF2-NEXT: [[TMP6:%.*]] = mul nuw i64 [[TMP5]], 2
; RV64-UF2-NEXT: [[N_VEC:%.*]] = urem i64 1023, [[TMP6]]
; RV64-UF2-NEXT: [[TMP7:%.*]] = sub i64 1023, [[N_VEC]]
; RV64-UF2-NEXT: [[TMP33:%.*]] = sub i64 1023, [[TMP7]]
@@ -236,7 +236,7 @@ define void @vector_reverse_i64(ptr nocapture noundef writeonly %A, ptr nocaptur
; RV64-NEXT: [[INDEX_EVL_NEXT]] = add nuw i64 [[TMP36]], [[INDEX]]
; RV64-NEXT: [[AVL_NEXT]] = sub nuw i64 [[AVL]], [[TMP36]]
; RV64-NEXT: [[TMP37:%.*]] = icmp eq i64 [[AVL_NEXT]], 0
-; RV64-NEXT: br i1 [[TMP37]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
+; RV64-NEXT: br i1 [[TMP37]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]]
; RV64: [[MIDDLE_BLOCK]]:
; RV64-NEXT: br label %[[FOR_COND_CLEANUP_LOOPEXIT:.*]]
; RV64: [[SCALAR_PH]]:
@@ -297,7 +297,7 @@ define void @vector_reverse_i64(ptr nocapture noundef writeonly %A, ptr nocaptur
; RV32-NEXT: [[INDEX_EVL_NEXT]] = add nuw i64 [[TMP29]], [[INDEX]]
; RV32-NEXT: [[AVL_NEXT]] = sub nuw i64 [[AVL]], [[TMP29]]
; RV32-NEXT: [[TMP30:%.*]] = icmp eq i64 [[AVL_NEXT]], 0
-; RV32-NEXT: br i1 [[TMP30]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
+; RV32-NEXT: br i1 [[TMP30]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]]
; RV32: [[MIDDLE_BLOCK]]:
; RV32-NEXT: br label %[[FOR_COND_CLEANUP_LOOPEXIT:.*]]
; RV32: [[SCALAR_PH]]:
@@ -340,7 +340,7 @@ define void @vector_reverse_i64(ptr nocapture noundef writeonly %A, ptr nocaptur
; RV64-UF2: [[VECTOR_PH]]:
; RV64-UF2-NEXT: [[TMP17:%.*]] = call i64 @llvm.vscale.i64()
; RV64-UF2-NEXT: [[TMP18:%.*]] = mul nuw i64 [[TMP17]], 4
-; RV64-UF2-NEXT: [[TMP19:%.*]] = mul i64 [[TMP18]], 2
+; RV64-UF2-NEXT: [[TMP19:%.*]] = mul nuw i64 [[TMP18]], 2
; RV64-UF2-NEXT: [[N_VEC:%.*]] = urem i64 [[TMP0]], [[TMP19]]
; RV64-UF2-NEXT: [[TMP20:%.*]] = sub i64 [[TMP0]], [[N_VEC]]
; RV64-UF2-NEXT: [[TMP48:%.*]] = sub i64 [[TMP0]], [[TMP20]]
@@ -487,7 +487,7 @@ define void @vector_reverse_f32(ptr nocapture noundef writeonly %A, ptr nocaptur
; RV64-NEXT: [[INDEX_EVL_NEXT]] = add nuw i64 [[TMP36]], [[INDEX]]
; RV64-NEXT: [[AVL_NEXT]] = sub nuw i64 [[AVL]], [[TMP36]]
; RV64-NEXT: [[TMP37:%.*]] = icmp eq i64 [[AVL_NEXT]], 0
-; RV64-NEXT: br i1 [[TMP37]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP10:![0-9]+]]
+; RV64-NEXT: br i1 [[TMP37]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
; RV64: [[MIDDLE_BLOCK]]:
; RV64-NEXT: br label %[[FOR_COND_CLEANUP_LOOPEXIT:.*]]
; RV64: [[SCALAR_PH]]:
@@ -548,7 +548,7 @@ define void @vector_reverse_f32(ptr nocapture noundef writeonly %A, ptr nocaptur
; RV32-NEXT: [[INDEX_EVL_NEXT]] = add nuw i64 [[TMP29]], [[INDEX]]
; RV32-NEXT: [[AVL_NEXT]] = sub nuw i64 [[AVL]], [[TMP29]]
; RV32-NEXT: [[TMP30:%.*]] = icmp eq i64 [[AVL_NEXT]], 0
-; RV32-NEXT: br i1 [[TMP30]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP10:![0-9]+]]
+; RV32-NEXT: br i1 [[TMP30]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
; RV32: [[MIDDLE_BLOCK]]:
; RV32-NEXT: br label %[[FOR_COND_CLEANUP_LOOPEXIT:.*]]
; RV32: [[SCALAR_PH]]:
@@ -591,7 +591,7 @@ define void @vector_reverse_f32(ptr nocapture noundef writeonly %A, ptr nocaptur
; RV64-UF2: [[VECTOR_PH]]:
; RV64-UF2-NEXT: [[TMP17:%.*]] = call i64 @llvm.vscale.i64()
; RV64-UF2-NEXT: [[TMP18:%.*]] = mul nuw i64 [[TMP17]], 4
-; RV64-UF2-NEXT: [[TMP19:%.*]] = mul i64 [[TMP18]], 2
+; RV64-UF2-NEXT: [[TMP19:%.*]] = mul nuw i64 [[TMP18]], 2
; RV64-UF2-NEXT: [[N_VEC:%.*]] = urem i64 [[TMP0]], [[TMP19]]
; RV64-UF2-NEXT: [[TMP20:%.*]] = sub i64 [[TMP0]], [[N_VEC]]
; RV64-UF2-NEXT: [[TMP48:%.*]] = sub i64 [[TMP0]], [[TMP20]]
@@ -714,7 +714,7 @@ define void @vector_reverse_f32_simplify(ptr noalias %A, ptr noalias %B) {
; RV64-NEXT: [[INDEX_EVL_NEXT]] = add nuw i64 [[TMP22]], [[INDEX]]
; RV64-NEXT: [[AVL_NEXT]] = sub nuw i64 [[AVL]], [[TMP22]]
; RV64-NEXT: [[TMP23:%.*]] = icmp eq i64 [[AVL_NEXT]], 0
-; RV64-NEXT: br i1 [[TMP23]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP12:![0-9]+]]
+; RV64-NEXT: br i1 [[TMP23]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP7:![0-9]+]]
; RV64: [[MIDDLE_BLOCK]]:
; RV64-NEXT: br label %[[EXIT:.*]]
; RV64: [[EXIT]]:
@@ -753,7 +753,7 @@ define void @vector_reverse_f32_simplify(ptr noalias %A, ptr noalias %B) {
; RV32-NEXT: [[INDEX_EVL_NEXT]] = add nuw i64 [[TMP23]], [[INDEX]]
; RV32-NEXT: [[AVL_NEXT]] = sub nuw i64 [[AVL]], [[TMP23]]
; RV32-NEXT: [[TMP21:%.*]] = icmp eq i64 [[AVL_NEXT]], 0
-; RV32-NEXT: br i1 [[TMP21]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP12:![0-9]+]]
+; RV32-NEXT: br i1 [[TMP21]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP7:![0-9]+]]
; RV32: [[MIDDLE_BLOCK]]:
; RV32-NEXT: br label %[[EXIT:.*]]
; RV32: [[EXIT]]:
@@ -769,7 +769,7 @@ define void @vector_reverse_f32_simplify(ptr noalias %A, ptr noalias %B) {
; RV64-UF2: [[VECTOR_PH]]:
; RV64-UF2-NEXT: [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
; RV64-UF2-NEXT: [[TMP5:%.*]] = mul nuw i64 [[TMP4]], 4
-; RV64-UF2-NEXT: [[TMP6:%.*]] = mul i64 [[TMP5]], 2
+; RV64-UF2-NEXT: [[TMP6:%.*]] = mul nuw i64 [[TMP5]], 2
; RV64-UF2-NEXT: [[N_VEC:%.*]] = urem i64 1023, [[TMP6]]
; RV64-UF2-NEXT: [[TMP7:%.*]] = sub i64 1023, [[N_VEC]]
; RV64-UF2-NEXT: [[TMP33:%.*]] = sub i64 1023, [[TMP7]]
@@ -884,7 +884,7 @@ define void @vector_reverse_irregular_type(ptr noalias %A, ptr noalias %B) {
; RV64-NEXT: store i7 [[TMP28]], ptr [[TMP24]], align 1
; RV64-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
; RV64-NEXT: [[TMP29:%.*]] = icmp eq i64 [[INDEX_NEXT]], 1020
-; RV64-NEXT: br i1 [[TMP29]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP13:![0-9]+]]
+; RV64-NEXT: br i1 [[TMP29]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
; RV64: [[MIDDLE_BLOCK]]:
; RV64-NEXT: br label %[[SCALAR_PH:.*]]
; RV64: [[SCALAR_PH]]:
@@ -935,7 +935,7 @@ define void @vector_reverse_irregular_type(ptr noalias %A, ptr noalias %B) {
; RV32-NEXT: store i7 [[TMP28]], ptr [[TMP24]], align 1
; RV32-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
; RV32-NEXT: [[TMP29:%.*]] = icmp eq i64 [[INDEX_NEXT]], 1020
-; RV32-NEXT: br i1 [[TMP29]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP13:![0-9]+]]
+; RV32-NEXT: br i1 [[TMP29]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
; RV32: [[MIDDLE_BLOCK]]:
; RV32-NEXT: br label %[[SCALAR_PH:.*]]
; RV32: [[SCALAR_PH]]:
diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/strided-accesses.ll b/llvm/test/Transforms/LoopVectorize/RISCV/strided-accesses.ll
index 414e5d9295554..96e1ebb48b02c 100644
--- a/llvm/test/Transforms/LoopVectorize/RISCV/strided-accesses.ll
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/strided-accesses.ll
@@ -46,7 +46,7 @@ define void @single_constant_stride_int_scaled(ptr %p) {
; CHECK-UF2-NEXT: [[TMP3:%.*]] = mul nuw i64 [[TMP2]], 4
; CHECK-UF2-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TMP3]], i64 0
; CHECK-UF2-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 4 x i64> [[BROADCAST_SPLATINSERT]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
-; CHECK-UF2-NEXT: [[TMP4:%.*]] = mul i64 [[TMP3]], 2
+; CHECK-UF2-NEXT: [[TMP4:%.*]] = mul nuw i64 [[TMP3]], 2
; CHECK-UF2-NEXT: [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP4]]
; CHECK-UF2-NEXT: [[TMP5:%.*]] = icmp eq i64 [[N_MOD_VF]], 0
; CHECK-UF2-NEXT: [[TMP6:%.*]] = select i1 [[TMP5]], i64 [[TMP4]], i64 [[N_MOD_VF]]
@@ -150,7 +150,7 @@ define void @single_constant_stride_int_iv(ptr %p) {
; CHECK-UF2-NEXT: [[TMP3:%.*]] = mul nuw i64 [[TMP2]], 4
; CHECK-UF2-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TMP3]], i64 0
; CHECK-UF2-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 4 x i64> [[BROADCAST_SPLATINSERT]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
-; CHECK-UF2-NEXT: [[TMP4:%.*]] = mul i64 [[TMP3]], 2
+; CHECK-UF2-NEXT: [[TMP4:%.*]] = mul nuw i64 [[TMP3]], 2
; CHECK-UF2-NEXT: [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP4]]
; CHECK-UF2-NEXT: [[N_VEC:%.*]] = sub i64 1024, [[N_MOD_VF]]
; CHECK-UF2-NEXT: [[TMP5:%.*]] = mul i64 [[N_VEC]], 64
@@ -254,7 +254,7 @@ define void @single_constant_stride_ptr_iv(ptr %p) {
; CHECK-UF2-NEXT: [[TMP3:%.*]] = mul nuw i64 [[TMP2]], 4
; CHECK-UF2-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TMP3]], i64 0
; CHECK-UF2-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 4 x i64> [[BROADCAST_SPLATINSERT]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
-; CHECK-UF2-NEXT: [[TMP4:%.*]] = mul i64 [[TMP3]], 2
+; CHECK-UF2-NEXT: [[TMP4:%.*]] = mul nuw i64 [[TMP3]], 2
; CHECK-UF2-NEXT: [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP4]]
; CHECK-UF2-NEXT: [[TMP5:%.*]] = icmp eq i64 [[N_MOD_VF]], 0
; CHECK-UF2-NEXT: [[TMP6:%.*]] = select i1 [[TMP5]], i64 [[TMP4]], i64 [[N_MOD_VF]]
@@ -876,7 +876,7 @@ define void @double_stride_int_scaled(ptr %p, ptr %p2, i64 %stride) {
; STRIDED-UF2-NEXT: [[TMP29:%.*]] = mul nuw i64 [[TMP28]], 4
; STRIDED-UF2-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TMP29]], i64 0
; STRIDED-UF2-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 4 x i64> [[BROADCAST_SPLATINSERT]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
-; STRIDED-UF2-NEXT: [[TMP30:%.*]] = mul i64 [[TMP29]], 2
+; STRIDED-UF2-NEXT: [[TMP30:%.*]] = mul nuw i64 [[TMP29]], 2
; STRIDED-UF2-NEXT: [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP30]]
; STRIDED-UF2-NEXT: [[N_VEC:%.*]] = sub i64 1024, [[N_MOD_VF]]
; STRIDED-UF2-NEXT: [[BROADCAST_SPLATINSERT10:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[STRIDE]], i64 0
@@ -1204,7 +1204,7 @@ define void @double_stride_ptr_iv(ptr %p, ptr %p2, i64 %stride) {
; STRIDED-UF2-NEXT: [[TMP8:%.*]] = mul nuw i64 [[TMP7]], 4
; STRIDED-UF2-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TMP8]], i64 0
; STRIDED-UF2-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 4 x i64> [[BROADCAST_SPLATINSERT]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
-; STRIDED-UF2-NEXT: [[TMP9:%.*]] = mul i64 [[TMP8]], 2
+; STRIDED-UF2-NEXT: [[TMP9:%.*]] = mul nuw i64 [[TMP8]], 2
; STRIDED-UF2-NEXT: [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP9]]
; STRIDED-UF2-NEXT: [[N_VEC:%.*]] = sub i64 1024, [[N_MOD_VF]]
; STRIDED-UF2-NEXT: [[BROADCAST_SPLATINSERT7:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[STRIDE]], i64 0
@@ -1335,7 +1335,7 @@ define void @constant_stride_reinterpret(ptr noalias %in, ptr noalias %out) {
; NOSTRIDED-UF2-NEXT: [[TMP3:%.*]] = mul nuw i64 [[TMP2]], 2
; NOSTRIDED-UF2-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[TMP3]], i64 0
; NOSTRIDED-UF2-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 2 x i64> [[BROADCAST_SPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
-; NOSTRIDED-UF2-NEXT: [[TMP4:%.*]] = mul i64 [[TMP3]], 2
+; NOSTRIDED-UF2-NEXT: [[TMP4:%.*]] = mul nuw i64 [[TMP3]], 2
; NOSTRIDED-UF2-NEXT: [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP4]]
; NOSTRIDED-UF2-NEXT: [[N_VEC:%.*]] = sub i64 1024, [[N_MOD_VF]]
; NOSTRIDED-UF2-NEXT: [[TMP5:%.*]] = call <vscale x 2 x i64> @llvm.stepvector.nxv2i64()
@@ -1419,7 +1419,7 @@ define void @constant_stride_reinterpret(ptr noalias %in, ptr noalias %out) {
; STRIDED-UF2-NEXT: [[TMP3:%.*]] = mul nuw i64 [[TMP2]], 2
; STRIDED-UF2-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[TMP3]], i64 0
; STRIDED-UF2-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 2 x i64> [[BROADCAST_SPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
-; STRIDED-UF2-NEXT: [[TMP4:%.*]] = mul i64 [[TMP3]], 2
+; STRIDED-UF2-NEXT: [[TMP4:%.*]] = mul nuw i64 [[TMP3]], 2
; STRIDED-UF2-NEXT: [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP4]]
; STRIDED-UF2-NEXT: [[N_VEC:%.*]] = sub i64 1024, [[N_MOD_VF]]
; STRIDED-UF2-NEXT: [[TMP5:%.*]] = call <vscale x 2 x i64> @llvm.stepvector.nxv2i64()
diff --git a/llvm/test/Transforms/LoopVectorize/scalable-assume.ll b/llvm/test/Transforms/LoopVectorize/scalable-assume.ll
index d140bc09fe731..0e93ff45f4287 100644
--- a/llvm/test/Transforms/LoopVectorize/scalable-assume.ll
+++ b/llvm/test/Transforms/LoopVectorize/scalable-assume.ll
@@ -157,7 +157,7 @@ define void @predicated_assume(ptr noalias nocapture readonly %a, ptr noalias no
; CHECK-NEXT: [[TMP5:%.*]] = mul nuw i64 [[TMP4]], 2
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[TMP5]], i64 0
; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 2 x i64> [[BROADCAST_SPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP6:%.*]] = mul i64 [[TMP5]], 2
+; CHECK-NEXT: [[TMP6:%.*]] = mul nuw i64 [[TMP5]], 2
; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[N]], [[TMP6]]
; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 [[N]], [[N_MOD_VF]]
; CHECK-NEXT: [[TMP7:%.*]] = call <vscale x 2 x i64> @llvm.stepvector.nxv2i64()
diff --git a/llvm/test/Transforms/LoopVectorize/scalable-first-order-recurrence.ll b/llvm/test/Transforms/LoopVectorize/scalable-first-order-recurrence.ll
index 1216bc1dc33cc..66fc0b830d6fc 100644
--- a/llvm/test/Transforms/LoopVectorize/scalable-first-order-recurrence.ll
+++ b/llvm/test/Transforms/LoopVectorize/scalable-first-order-recurrence.ll
@@ -673,7 +673,7 @@ define i32 @extract_second_last_iteration(ptr %cval, i32 %x) {
; CHECK-VF4UF2-NEXT: [[TMP5:%.*]] = mul nuw i32 [[TMP4]], 4
; CHECK-VF4UF2-NEXT: [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[TMP5]], i64 0
; CHECK-VF4UF2-NEXT: [[BROADCAST_SPLAT2:%.*]] = shufflevector <vscale x 4 x i32> [[BROADCAST_SPLATINSERT1]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
-; CHECK-VF4UF2-NEXT: [[TMP6:%.*]] = mul i32 [[TMP5]], 2
+; CHECK-VF4UF2-NEXT: [[TMP6:%.*]] = mul nuw i32 [[TMP5]], 2
; CHECK-VF4UF2-NEXT: [[N_MOD_VF:%.*]] = urem i32 96, [[TMP6]]
; CHECK-VF4UF2-NEXT: [[N_VEC:%.*]] = sub i32 96, [[N_MOD_VF]]
; CHECK-VF4UF2-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[X]], i64 0
diff --git a/llvm/test/Transforms/LoopVectorize/scalable-inductions.ll b/llvm/test/Transforms/LoopVectorize/scalable-inductions.ll
index d87d39e684993..fb36c864ddb5f 100644
--- a/llvm/test/Transforms/LoopVectorize/scalable-inductions.ll
+++ b/llvm/test/Transforms/LoopVectorize/scalable-inductions.ll
@@ -19,7 +19,7 @@ define void @add_ind64_unrolled(ptr noalias nocapture %a, ptr noalias nocapture
; CHECK-NEXT: [[TMP8:%.*]] = shl nuw i64 [[TMP4]], 1
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[TMP8]], i64 0
; CHECK-NEXT: [[DOTSPLAT:%.*]] = shufflevector <vscale x 2 x i64> [[BROADCAST_SPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP5:%.*]] = shl i64 [[TMP4]], 2
+; CHECK-NEXT: [[TMP5:%.*]] = shl nuw i64 [[TMP4]], 2
; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[N]], [[TMP5]]
; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 [[N]], [[N_MOD_VF]]
; CHECK-NEXT: [[TMP6:%.*]] = call <vscale x 2 x i64> @llvm.stepvector.nxv2i64()
@@ -97,7 +97,7 @@ define void @add_ind64_unrolled_nxv1i64(ptr noalias nocapture %a, ptr noalias no
; CHECK-NEXT: [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[TMP2]], i64 0
; CHECK-NEXT: [[DOTSPLAT:%.*]] = shufflevector <vscale x 1 x i64> [[BROADCAST_SPLATINSERT]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP3:%.*]] = shl i64 [[TMP2]], 1
+; CHECK-NEXT: [[TMP3:%.*]] = shl nuw i64 [[TMP2]], 1
; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[N]], [[TMP3]]
; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 [[N]], [[N_MOD_VF]]
; CHECK-NEXT: [[TMP6:%.*]] = call <vscale x 1 x i64> @llvm.stepvector.nxv1i64()
diff --git a/llvm/test/Transforms/LoopVectorize/scalable-iv-outside-user.ll b/llvm/test/Transforms/LoopVectorize/scalable-iv-outside-user.ll
index cb61fc6e0a046..7fd1c10d0f48c 100644
--- a/llvm/test/Transforms/LoopVectorize/scalable-iv-outside-user.ll
+++ b/llvm/test/Transforms/LoopVectorize/scalable-iv-outside-user.ll
@@ -16,7 +16,7 @@ define i32 @iv_live_out_wide(ptr %dst) {
; CHECK-NEXT: [[TMP5:%.*]] = mul nuw i32 [[TMP4]], 2
; CHECK-NEXT: [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <vscale x 2 x i32> poison, i32 [[TMP5]], i64 0
; CHECK-NEXT: [[BROADCAST_SPLAT2:%.*]] = shufflevector <vscale x 2 x i32> [[BROADCAST_SPLATINSERT1]], <vscale x 2 x i32> poison, <vscale x 2 x i32> zeroinitializer
-; CHECK-NEXT: [[TMP6:%.*]] = mul i32 [[TMP5]], 2
+; CHECK-NEXT: [[TMP6:%.*]] = mul nuw i32 [[TMP5]], 2
; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i32 2000, [[TMP6]]
; CHECK-NEXT: [[N_VEC:%.*]] = sub i32 2000, [[N_MOD_VF]]
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 2 x i32> poison, i32 [[STEP_2]], i64 0
More information about the llvm-commits
mailing list