[llvm] LV: clamp VF with TC only when scalar epilogue is needed (PR #91253)
Ramkumar Ramachandra via llvm-commits
llvm-commits at lists.llvm.org
Tue May 28 09:56:14 PDT 2024
https://github.com/artagnon updated https://github.com/llvm/llvm-project/pull/91253
>From 9261244d283fc91ce509b81ccd9f85dde579d4aa Mon Sep 17 00:00:00 2001
From: Ramkumar Ramachandra <r at artagnon.com>
Date: Tue, 28 May 2024 13:47:16 +0100
Subject: [PATCH 1/4] [LV] add crash-test for incomplete cases in VPlan
The test is identical to the one in vplan-infer-not-or-type.ll, except
that the trip count is now 3 instead of 2.
---
.../LoopVectorize/vplan-incomplete-cases.ll | 25 +++++++++++++++++++
1 file changed, 25 insertions(+)
create mode 100644 llvm/test/Transforms/LoopVectorize/vplan-incomplete-cases.ll
diff --git a/llvm/test/Transforms/LoopVectorize/vplan-incomplete-cases.ll b/llvm/test/Transforms/LoopVectorize/vplan-incomplete-cases.ll
new file mode 100644
index 0000000000000..2f3ed0d69d269
--- /dev/null
+++ b/llvm/test/Transforms/LoopVectorize/vplan-incomplete-cases.ll
@@ -0,0 +1,25 @@
+; REQUIRES: asserts
+; RUN: not --crash opt %s -passes=loop-vectorize -S
+
+define void @vplan_incomplete_cases_tc3(i8 %x, i8 %y) {
+entry:
+ br label %loop.header
+
+loop.header: ; preds = %latch, %entry
+ %iv = phi i8 [ %iv.next, %latch ], [ 0, %entry ]
+ %and = and i8 %x, %y
+ %extract.t = trunc i8 %and to i1
+ br i1 %extract.t, label %latch, label %indirect.latch
+
+indirect.latch: ; preds = %loop.header
+ br label %latch
+
+latch: ; preds = %indirect.latch, loop.header
+ %iv.next = add i8 %iv, 1
+ %zext = zext i8 %iv to i32
+ %cmp = icmp ult i32 %zext, 2
+ br i1 %cmp, label %loop.header, label %exit
+
+exit: ; preds = %latch
+ ret void
+}
>From e5d61f7cf87a9b819b1db7bda8c5e5f2c2bd490e Mon Sep 17 00:00:00 2001
From: Ramkumar Ramachandra <r at artagnon.com>
Date: Tue, 28 May 2024 15:00:27 +0100
Subject: [PATCH 2/4] LV/VPlan: add missing case for LogicalAnd; fix crash
VPTypeAnalysis::inferScalarTypeForRecipe is missing the case for
VPInstruction::LogicalAnd, due to which the test
vplan-incomplete-cases.ll crashes. Add this missing case, and move the
test in vplan-infer-not-or-type.ll to vplan-incomplete-cases.ll, showing
correct codegen for trip-counts 2 and 3.
---
.../Transforms/Vectorize/VPlanAnalysis.cpp | 2 +
.../LoopVectorize/vplan-incomplete-cases.ll | 97 ++++++++++++++++++-
.../LoopVectorize/vplan-infer-not-or-type.ll | 64 ------------
3 files changed, 97 insertions(+), 66 deletions(-)
delete mode 100644 llvm/test/Transforms/LoopVectorize/vplan-infer-not-or-type.ll
diff --git a/llvm/lib/Transforms/Vectorize/VPlanAnalysis.cpp b/llvm/lib/Transforms/Vectorize/VPlanAnalysis.cpp
index efe8c21874a3a..860f2a33697fe 100644
--- a/llvm/lib/Transforms/Vectorize/VPlanAnalysis.cpp
+++ b/llvm/lib/Transforms/Vectorize/VPlanAnalysis.cpp
@@ -51,6 +51,8 @@ Type *VPTypeAnalysis::inferScalarTypeForRecipe(const VPInstruction *R) {
"unexpected scalar type inferred for operand");
return ResTy;
}
+ case VPInstruction::LogicalAnd:
+ return IntegerType::get(Ctx, 1);
case VPInstruction::PtrAdd:
// Return the type based on the pointer argument (i.e. first operand).
return inferScalarType(R->getOperand(0));
diff --git a/llvm/test/Transforms/LoopVectorize/vplan-incomplete-cases.ll b/llvm/test/Transforms/LoopVectorize/vplan-incomplete-cases.ll
index 2f3ed0d69d269..2007155fe5485 100644
--- a/llvm/test/Transforms/LoopVectorize/vplan-incomplete-cases.ll
+++ b/llvm/test/Transforms/LoopVectorize/vplan-incomplete-cases.ll
@@ -1,7 +1,92 @@
-; REQUIRES: asserts
-; RUN: not --crash opt %s -passes=loop-vectorize -S
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
+; RUN: opt -passes=loop-vectorize -S %s | FileCheck %s
+; This test used to crash due to missing Or/Not cases in inferScalarTypeForRecipe.
+define void @vplan_incomplete_cases_tc2(i8 %x, i8 %y) {
+; CHECK-LABEL: define void @vplan_incomplete_cases_tc2(
+; CHECK-SAME: i8 [[X:%.*]], i8 [[Y:%.*]]) {
+; CHECK-NEXT: [[ENTRY:.*]]:
+; CHECK-NEXT: br i1 false, label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
+; CHECK: [[VECTOR_PH]]:
+; CHECK-NEXT: br label %[[VECTOR_BODY:.*]]
+; CHECK: [[VECTOR_BODY]]:
+; CHECK-NEXT: [[INDEX:%.*]] = phi i32 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 2
+; CHECK-NEXT: br i1 true, label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
+; CHECK: [[MIDDLE_BLOCK]]:
+; CHECK-NEXT: br i1 true, label %[[EXIT:.*]], label %[[SCALAR_PH]]
+; CHECK: [[SCALAR_PH]]:
+; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i8 [ 2, %[[MIDDLE_BLOCK]] ], [ 0, %[[ENTRY]] ]
+; CHECK-NEXT: br label %[[LOOP_HEADER:.*]]
+; CHECK: [[LOOP_HEADER]]:
+; CHECK-NEXT: [[IV:%.*]] = phi i8 [ [[IV_NEXT:%.*]], %[[LATCH:.*]] ], [ [[BC_RESUME_VAL]], %[[SCALAR_PH]] ]
+; CHECK-NEXT: [[AND:%.*]] = and i8 [[X]], [[Y]]
+; CHECK-NEXT: [[EXTRACT_T:%.*]] = trunc i8 [[AND]] to i1
+; CHECK-NEXT: br i1 [[EXTRACT_T]], label %[[LATCH]], label %[[INDIRECT_LATCH:.*]]
+; CHECK: [[INDIRECT_LATCH]]:
+; CHECK-NEXT: br label %[[LATCH]]
+; CHECK: [[LATCH]]:
+; CHECK-NEXT: [[IV_NEXT]] = add i8 [[IV]], 1
+; CHECK-NEXT: [[ZEXT:%.*]] = zext i8 [[IV]] to i32
+; CHECK-NEXT: [[CMP:%.*]] = icmp ult i32 [[ZEXT]], 1
+; CHECK-NEXT: br i1 [[CMP]], label %[[LOOP_HEADER]], label %[[EXIT]], !llvm.loop [[LOOP3:![0-9]+]]
+; CHECK: [[EXIT]]:
+; CHECK-NEXT: ret void
+;
+entry:
+ br label %loop.header
+
+loop.header: ; preds = %latch, %entry
+ %iv = phi i8 [ %iv.next, %latch ], [ 0, %entry ]
+ %and = and i8 %x, %y
+ %extract.t = trunc i8 %and to i1
+ br i1 %extract.t, label %latch, label %indirect.latch
+
+indirect.latch: ; preds = %loop.header
+ br label %latch
+
+latch: ; preds = %indirect.latch, loop.header
+ %iv.next = add i8 %iv, 1
+ %zext = zext i8 %iv to i32
+ %cmp = icmp ult i32 %zext, 1
+ br i1 %cmp, label %loop.header, label %exit
+
+exit: ; preds = %latch
+ ret void
+}
+
+; This test used to crash due to missing the LogicalAnd case in inferScalarTypeForRecipe.
define void @vplan_incomplete_cases_tc3(i8 %x, i8 %y) {
+; CHECK-LABEL: define void @vplan_incomplete_cases_tc3(
+; CHECK-SAME: i8 [[X:%.*]], i8 [[Y:%.*]]) {
+; CHECK-NEXT: [[ENTRY:.*]]:
+; CHECK-NEXT: br i1 false, label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
+; CHECK: [[VECTOR_PH]]:
+; CHECK-NEXT: br label %[[VECTOR_BODY:.*]]
+; CHECK: [[VECTOR_BODY]]:
+; CHECK-NEXT: [[INDEX:%.*]] = phi i32 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT: [[INDEX_NEXT]] = add i32 [[INDEX]], 4
+; CHECK-NEXT: br i1 true, label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
+; CHECK: [[MIDDLE_BLOCK]]:
+; CHECK-NEXT: br i1 true, label %[[EXIT:.*]], label %[[SCALAR_PH]]
+; CHECK: [[SCALAR_PH]]:
+; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i8 [ 4, %[[MIDDLE_BLOCK]] ], [ 0, %[[ENTRY]] ]
+; CHECK-NEXT: br label %[[LOOP_HEADER:.*]]
+; CHECK: [[LOOP_HEADER]]:
+; CHECK-NEXT: [[IV:%.*]] = phi i8 [ [[IV_NEXT:%.*]], %[[LATCH:.*]] ], [ [[BC_RESUME_VAL]], %[[SCALAR_PH]] ]
+; CHECK-NEXT: [[AND:%.*]] = and i8 [[X]], [[Y]]
+; CHECK-NEXT: [[EXTRACT_T:%.*]] = trunc i8 [[AND]] to i1
+; CHECK-NEXT: br i1 [[EXTRACT_T]], label %[[LATCH]], label %[[INDIRECT_LATCH:.*]]
+; CHECK: [[INDIRECT_LATCH]]:
+; CHECK-NEXT: br label %[[LATCH]]
+; CHECK: [[LATCH]]:
+; CHECK-NEXT: [[IV_NEXT]] = add i8 [[IV]], 1
+; CHECK-NEXT: [[ZEXT:%.*]] = zext i8 [[IV]] to i32
+; CHECK-NEXT: [[CMP:%.*]] = icmp ult i32 [[ZEXT]], 2
+; CHECK-NEXT: br i1 [[CMP]], label %[[LOOP_HEADER]], label %[[EXIT]], !llvm.loop [[LOOP5:![0-9]+]]
+; CHECK: [[EXIT]]:
+; CHECK-NEXT: ret void
+;
entry:
br label %loop.header
@@ -23,3 +108,11 @@ latch: ; preds = %indirect.latch, l
exit: ; preds = %latch
ret void
}
+;.
+; CHECK: [[LOOP0]] = distinct !{[[LOOP0]], [[META1:![0-9]+]], [[META2:![0-9]+]]}
+; CHECK: [[META1]] = !{!"llvm.loop.isvectorized", i32 1}
+; CHECK: [[META2]] = !{!"llvm.loop.unroll.runtime.disable"}
+; CHECK: [[LOOP3]] = distinct !{[[LOOP3]], [[META2]], [[META1]]}
+; CHECK: [[LOOP4]] = distinct !{[[LOOP4]], [[META1]], [[META2]]}
+; CHECK: [[LOOP5]] = distinct !{[[LOOP5]], [[META2]], [[META1]]}
+;.
diff --git a/llvm/test/Transforms/LoopVectorize/vplan-infer-not-or-type.ll b/llvm/test/Transforms/LoopVectorize/vplan-infer-not-or-type.ll
deleted file mode 100644
index 102ef699cb379..0000000000000
--- a/llvm/test/Transforms/LoopVectorize/vplan-infer-not-or-type.ll
+++ /dev/null
@@ -1,64 +0,0 @@
-; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 4
-; RUN: opt < %s -passes=loop-vectorize -S | FileCheck %s
-
-; This test used to crash due to missing Or/Not cases in
-; inferScalarTypeForRecipe.
-
-define void @foo(i8 %arg.0, i8 %arg.1) {
-; CHECK-LABEL: define void @foo(
-; CHECK-SAME: i8 [[ARG_0:%.*]], i8 [[ARG_1:%.*]]) {
-; CHECK-NEXT: entry:
-; CHECK-NEXT: br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
-; CHECK: vector.ph:
-; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
-; CHECK: vector.body:
-; CHECK-NEXT: [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 2
-; CHECK-NEXT: br i1 true, label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
-; CHECK: middle.block:
-; CHECK-NEXT: br i1 true, label [[LOOPEXIT:%.*]], label [[SCALAR_PH]]
-; CHECK: scalar.ph:
-; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i8 [ 2, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
-; CHECK-NEXT: br label [[LOOP_HEADER:%.*]]
-; CHECK: loop.header:
-; CHECK-NEXT: [[INCREMENTOR:%.*]] = phi i8 [ [[ADD:%.*]], [[LATCH:%.*]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
-; CHECK-NEXT: [[AND:%.*]] = and i8 [[ARG_0]], [[ARG_1]]
-; CHECK-NEXT: [[EXTRACT_T:%.*]] = trunc i8 [[AND]] to i1
-; CHECK-NEXT: br i1 [[EXTRACT_T]], label [[LATCH]], label [[INDIRECT_LATCH:%.*]]
-; CHECK: indirect.latch:
-; CHECK-NEXT: br label [[LATCH]]
-; CHECK: latch:
-; CHECK-NEXT: [[ADD]] = add i8 [[INCREMENTOR]], 1
-; CHECK-NEXT: [[CONV:%.*]] = zext i8 [[INCREMENTOR]] to i32
-; CHECK-NEXT: [[CMP:%.*]] = icmp ult i32 [[CONV]], 1
-; CHECK-NEXT: br i1 [[CMP]], label [[LOOP_HEADER]], label [[LOOPEXIT]], !llvm.loop [[LOOP3:![0-9]+]]
-; CHECK: loop.exit:
-; CHECK-NEXT: ret void
-;
-entry:
- br label %loop.header
-
-loop.header: ; preds = %latch, %entry
- %incrementor = phi i8 [ %add, %latch ], [ 0, %entry ]
- %and = and i8 %arg.0, %arg.1
- %extract.t = trunc i8 %and to i1
- br i1 %extract.t, label %latch, label %indirect.latch
-
-indirect.latch: ; preds = %loop.header
- br label %latch
-
-latch: ; preds = %loop.header16, %loop.header
- %add = add i8 %incrementor, 1
- %conv = zext i8 %incrementor to i32
- %cmp = icmp ult i32 %conv, 1
- br i1 %cmp, label %loop.header, label %loop.exit
-
-loop.exit:
- ret void
-}
-;.
-; CHECK: [[LOOP0]] = distinct !{[[LOOP0]], [[META1:![0-9]+]], [[META2:![0-9]+]]}
-; CHECK: [[META1]] = !{!"llvm.loop.isvectorized", i32 1}
-; CHECK: [[META2]] = !{!"llvm.loop.unroll.runtime.disable"}
-; CHECK: [[LOOP3]] = distinct !{[[LOOP3]], [[META2]], [[META1]]}
-;.
>From 58289fd7bf9240b66958277d5260866e1f7a4cb1 Mon Sep 17 00:00:00 2001
From: Ramkumar Ramachandra <r at artagnon.com>
Date: Fri, 24 May 2024 12:52:34 +0100
Subject: [PATCH 3/4] [LV] generalize profitability criterion over TC
Generalize LoopVectorizationPlanner::isMoreProfitable smoothly across
the fixed-vector and scalable-vector cases, taking the trip-count into
account, and fixing logical pitfalls that arise from a lack of
generality.
---
.../Transforms/Vectorize/LoopVectorize.cpp | 55 +++++------
.../AArch64/clamped-trip-count.ll | 92 ++++++++++---------
.../LoopVectorize/RISCV/low-trip-count.ll | 54 +++++------
.../LoopVectorize/RISCV/short-trip-count.ll | 14 +--
4 files changed, 110 insertions(+), 105 deletions(-)
diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
index e20073d8de696..e4e7502e3961d 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -4858,28 +4858,6 @@ bool LoopVectorizationPlanner::isMoreProfitable(
unsigned MaxTripCount = PSE.getSE()->getSmallConstantMaxTripCount(OrigLoop);
- if (!A.Width.isScalable() && !B.Width.isScalable() && MaxTripCount) {
- // If the trip count is a known (possibly small) constant, the trip count
- // will be rounded up to an integer number of iterations under
- // FoldTailByMasking. The total cost in that case will be
- // VecCost*ceil(TripCount/VF). When not folding the tail, the total
- // cost will be VecCost*floor(TC/VF) + ScalarCost*(TC%VF). There will be
- // some extra overheads, but for the purpose of comparing the costs of
- // different VFs we can use this to compare the total loop-body cost
- // expected after vectorization.
- auto GetCostForTC = [MaxTripCount, this](unsigned VF,
- InstructionCost VectorCost,
- InstructionCost ScalarCost) {
- return CM.foldTailByMasking() ? VectorCost * divideCeil(MaxTripCount, VF)
- : VectorCost * (MaxTripCount / VF) +
- ScalarCost * (MaxTripCount % VF);
- };
- auto RTCostA = GetCostForTC(A.Width.getFixedValue(), CostA, A.ScalarCost);
- auto RTCostB = GetCostForTC(B.Width.getFixedValue(), CostB, B.ScalarCost);
-
- return RTCostA < RTCostB;
- }
-
// Improve estimate for the vector width if it is scalable.
unsigned EstimatedWidthA = A.Width.getKnownMinValue();
unsigned EstimatedWidthB = B.Width.getKnownMinValue();
@@ -4893,13 +4871,36 @@ bool LoopVectorizationPlanner::isMoreProfitable(
// Assume vscale may be larger than 1 (or the value being tuned for),
// so that scalable vectorization is slightly favorable over fixed-width
// vectorization.
- if (A.Width.isScalable() && !B.Width.isScalable())
- return (CostA * B.Width.getFixedValue()) <= (CostB * EstimatedWidthA);
+ bool PreferScalable = A.Width.isScalable() && !B.Width.isScalable();
+ auto CmpFn = [PreferScalable](const InstructionCost &LHS,
+ const InstructionCost &RHS) {
+ return PreferScalable ? LHS <= RHS : LHS < RHS;
+ };
// To avoid the need for FP division:
- // (CostA / A.Width) < (CostB / B.Width)
- // <=> (CostA * B.Width) < (CostB * A.Width)
- return (CostA * EstimatedWidthB) < (CostB * EstimatedWidthA);
+ // (CostA / EstimatedWidthA) < (CostB / EstimatedWidthB)
+ // <=> (CostA * EstimatedWidthB) < (CostB * EstimatedWidthA)
+ if (!MaxTripCount)
+ return CmpFn(CostA * EstimatedWidthB, CostB * EstimatedWidthA);
+
+ auto GetCost = [MaxTripCount, this](unsigned VF, InstructionCost VectorCost,
+ InstructionCost ScalarCost) {
+ // If the trip count is a known (possibly small) constant, the trip count
+ // will be rounded up to an integer number of iterations under
+ // FoldTailByMasking. The total cost in that case will be
+ // VecCost*ceil(TripCount/VF). When not folding the tail, the total
+ // cost will be VecCost*floor(TC/VF) + ScalarCost*(TC%VF). There will be
+ // some extra overheads, but for the purpose of comparing the costs of
+ // different VFs we can use this to compare the total loop-body cost
+ // expected after vectorization.
+ if (CM.foldTailByMasking())
+ return VectorCost * divideCeil(MaxTripCount, VF);
+ return VectorCost * (MaxTripCount / VF) + ScalarCost * (MaxTripCount % VF);
+ };
+
+ auto RTCostA = GetCost(EstimatedWidthA, CostA, A.ScalarCost);
+ auto RTCostB = GetCost(EstimatedWidthB, CostB, B.ScalarCost);
+ return CmpFn(RTCostA, RTCostB);
}
static void emitInvalidCostRemarks(SmallVector<InstructionVFPair> InvalidCosts,
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/clamped-trip-count.ll b/llvm/test/Transforms/LoopVectorize/AArch64/clamped-trip-count.ll
index afd49aa9f0b81..ba4c2376d7922 100644
--- a/llvm/test/Transforms/LoopVectorize/AArch64/clamped-trip-count.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/clamped-trip-count.ll
@@ -8,44 +8,46 @@ define void @clamped_tc_8(ptr nocapture %dst, i32 %n, i64 %val) vscale_range(1,1
; CHECK-NEXT: br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
; CHECK-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT: [[TMP1:%.*]] = mul i64 [[TMP0]], 8
+; CHECK-NEXT: [[TMP1:%.*]] = mul i64 [[TMP0]], 4
; CHECK-NEXT: [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT: [[TMP3:%.*]] = mul i64 [[TMP2]], 8
+; CHECK-NEXT: [[TMP3:%.*]] = mul i64 [[TMP2]], 4
; CHECK-NEXT: [[TMP4:%.*]] = sub i64 [[TMP3]], 1
; CHECK-NEXT: [[N_RND_UP:%.*]] = add i64 8, [[TMP4]]
; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP1]]
; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
; CHECK-NEXT: [[IND_END:%.*]] = getelementptr i8, ptr [[DST]], i64 [[N_VEC]]
; CHECK-NEXT: [[TMP5:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT: [[TMP6:%.*]] = mul i64 [[TMP5]], 8
-; CHECK-NEXT: [[ACTIVE_LANE_MASK_ENTRY:%.*]] = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 0, i64 8)
-; CHECK-NEXT: [[TMP7:%.*]] = call <vscale x 8 x i64> @llvm.experimental.stepvector.nxv8i64()
-; CHECK-NEXT: [[TMP8:%.*]] = add <vscale x 8 x i64> [[TMP7]], zeroinitializer
-; CHECK-NEXT: [[TMP9:%.*]] = mul <vscale x 8 x i64> [[TMP8]], shufflevector (<vscale x 8 x i64> insertelement (<vscale x 8 x i64> poison, i64 1, i64 0), <vscale x 8 x i64> poison, <vscale x 8 x i32> zeroinitializer)
-; CHECK-NEXT: [[INDUCTION:%.*]] = add <vscale x 8 x i64> zeroinitializer, [[TMP9]]
+; CHECK-NEXT: [[TMP6:%.*]] = mul i64 [[TMP5]], 4
+; CHECK-NEXT: [[ACTIVE_LANE_MASK_ENTRY:%.*]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 0, i64 8)
+; CHECK-NEXT: [[TMP7:%.*]] = call <vscale x 4 x i64> @llvm.experimental.stepvector.nxv4i64()
+; CHECK-NEXT: [[TMP8:%.*]] = add <vscale x 4 x i64> [[TMP7]], zeroinitializer
+; CHECK-NEXT: [[TMP9:%.*]] = mul <vscale x 4 x i64> [[TMP8]], shufflevector (<vscale x 4 x i64> insertelement (<vscale x 4 x i64> poison, i64 1, i64 0), <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer)
+; CHECK-NEXT: [[INDUCTION:%.*]] = add <vscale x 4 x i64> zeroinitializer, [[TMP9]]
; CHECK-NEXT: [[TMP10:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT: [[TMP11:%.*]] = mul i64 [[TMP10]], 8
+; CHECK-NEXT: [[TMP11:%.*]] = mul i64 [[TMP10]], 4
; CHECK-NEXT: [[TMP12:%.*]] = mul i64 1, [[TMP11]]
-; CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i64> poison, i64 [[TMP12]], i64 0
-; CHECK-NEXT: [[DOTSPLAT:%.*]] = shufflevector <vscale x 8 x i64> [[DOTSPLATINSERT]], <vscale x 8 x i64> poison, <vscale x 8 x i32> zeroinitializer
-; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 8 x i64> poison, i64 [[VAL]], i64 0
-; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 8 x i64> [[BROADCAST_SPLATINSERT]], <vscale x 8 x i64> poison, <vscale x 8 x i32> zeroinitializer
+; CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TMP12]], i64 0
+; CHECK-NEXT: [[DOTSPLAT:%.*]] = shufflevector <vscale x 4 x i64> [[DOTSPLATINSERT]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
+; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[VAL]], i64 0
+; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 4 x i64> [[BROADCAST_SPLATINSERT]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT: [[ACTIVE_LANE_MASK:%.*]] = phi <vscale x 8 x i1> [ [[ACTIVE_LANE_MASK_ENTRY]], [[VECTOR_PH]] ], [ [[ACTIVE_LANE_MASK_NEXT:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT: [[VEC_IND:%.*]] = phi <vscale x 8 x i64> [ [[INDUCTION]], [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT: [[ACTIVE_LANE_MASK:%.*]] = phi <vscale x 4 x i1> [ [[ACTIVE_LANE_MASK_ENTRY]], [[VECTOR_PH]] ], [ [[ACTIVE_LANE_MASK_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT: [[VEC_IND:%.*]] = phi <vscale x 4 x i64> [ [[INDUCTION]], [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP13:%.*]] = add i64 [[INDEX]], 0
; CHECK-NEXT: [[NEXT_GEP:%.*]] = getelementptr i8, ptr [[DST]], i64 [[TMP13]]
-; CHECK-NEXT: [[TMP14:%.*]] = shl nuw nsw <vscale x 8 x i64> [[VEC_IND]], shufflevector (<vscale x 8 x i64> insertelement (<vscale x 8 x i64> poison, i64 3, i64 0), <vscale x 8 x i64> poison, <vscale x 8 x i32> zeroinitializer)
-; CHECK-NEXT: [[TMP15:%.*]] = lshr <vscale x 8 x i64> [[BROADCAST_SPLAT]], [[TMP14]]
-; CHECK-NEXT: [[TMP16:%.*]] = trunc <vscale x 8 x i64> [[TMP15]] to <vscale x 8 x i8>
+; CHECK-NEXT: [[TMP14:%.*]] = shl nuw nsw <vscale x 4 x i64> [[VEC_IND]], shufflevector (<vscale x 4 x i64> insertelement (<vscale x 4 x i64> poison, i64 3, i64 0), <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer)
+; CHECK-NEXT: [[TMP15:%.*]] = lshr <vscale x 4 x i64> [[BROADCAST_SPLAT]], [[TMP14]]
+; CHECK-NEXT: [[TMP16:%.*]] = trunc <vscale x 4 x i64> [[TMP15]] to <vscale x 4 x i8>
; CHECK-NEXT: [[TMP17:%.*]] = getelementptr i8, ptr [[NEXT_GEP]], i32 0
-; CHECK-NEXT: call void @llvm.masked.store.nxv8i8.p0(<vscale x 8 x i8> [[TMP16]], ptr [[TMP17]], i32 1, <vscale x 8 x i1> [[ACTIVE_LANE_MASK]])
+; CHECK-NEXT: call void @llvm.masked.store.nxv4i8.p0(<vscale x 4 x i8> [[TMP16]], ptr [[TMP17]], i32 1, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]])
; CHECK-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], [[TMP6]]
-; CHECK-NEXT: [[VEC_IND_NEXT]] = add <vscale x 8 x i64> [[VEC_IND]], [[DOTSPLAT]]
-; CHECK-NEXT: [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 [[INDEX_NEXT]], i64 8)
-; CHECK-NEXT: br i1 true, label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
+; CHECK-NEXT: [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX_NEXT]], i64 8)
+; CHECK-NEXT: [[TMP18:%.*]] = xor <vscale x 4 x i1> [[ACTIVE_LANE_MASK_NEXT]], shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer)
+; CHECK-NEXT: [[VEC_IND_NEXT]] = add <vscale x 4 x i64> [[VEC_IND]], [[DOTSPLAT]]
+; CHECK-NEXT: [[TMP20:%.*]] = extractelement <vscale x 4 x i1> [[TMP18]], i32 0
+; CHECK-NEXT: br i1 [[TMP20]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK: middle.block:
; CHECK-NEXT: br i1 true, label [[FOR_COND_CLEANUP:%.*]], label [[SCALAR_PH]]
; CHECK: scalar.ph:
@@ -99,44 +101,46 @@ define void @clamped_tc_max_8(ptr nocapture %dst, i32 %n, i64 %val) vscale_range
; CHECK-NEXT: br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
; CHECK-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT: [[TMP1:%.*]] = mul i64 [[TMP0]], 8
+; CHECK-NEXT: [[TMP1:%.*]] = mul i64 [[TMP0]], 4
; CHECK-NEXT: [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT: [[TMP3:%.*]] = mul i64 [[TMP2]], 8
+; CHECK-NEXT: [[TMP3:%.*]] = mul i64 [[TMP2]], 4
; CHECK-NEXT: [[TMP4:%.*]] = sub i64 [[TMP3]], 1
; CHECK-NEXT: [[N_RND_UP:%.*]] = add i64 [[WIDE_TRIP_COUNT]], [[TMP4]]
; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP1]]
; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
; CHECK-NEXT: [[IND_END:%.*]] = getelementptr i8, ptr [[DST]], i64 [[N_VEC]]
; CHECK-NEXT: [[TMP5:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT: [[TMP6:%.*]] = mul i64 [[TMP5]], 8
-; CHECK-NEXT: [[ACTIVE_LANE_MASK_ENTRY:%.*]] = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 0, i64 [[WIDE_TRIP_COUNT]])
-; CHECK-NEXT: [[TMP7:%.*]] = call <vscale x 8 x i64> @llvm.experimental.stepvector.nxv8i64()
-; CHECK-NEXT: [[TMP8:%.*]] = add <vscale x 8 x i64> [[TMP7]], zeroinitializer
-; CHECK-NEXT: [[TMP9:%.*]] = mul <vscale x 8 x i64> [[TMP8]], shufflevector (<vscale x 8 x i64> insertelement (<vscale x 8 x i64> poison, i64 1, i64 0), <vscale x 8 x i64> poison, <vscale x 8 x i32> zeroinitializer)
-; CHECK-NEXT: [[INDUCTION:%.*]] = add <vscale x 8 x i64> zeroinitializer, [[TMP9]]
+; CHECK-NEXT: [[TMP6:%.*]] = mul i64 [[TMP5]], 4
+; CHECK-NEXT: [[ACTIVE_LANE_MASK_ENTRY:%.*]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 0, i64 [[WIDE_TRIP_COUNT]])
+; CHECK-NEXT: [[TMP7:%.*]] = call <vscale x 4 x i64> @llvm.experimental.stepvector.nxv4i64()
+; CHECK-NEXT: [[TMP8:%.*]] = add <vscale x 4 x i64> [[TMP7]], zeroinitializer
+; CHECK-NEXT: [[TMP9:%.*]] = mul <vscale x 4 x i64> [[TMP8]], shufflevector (<vscale x 4 x i64> insertelement (<vscale x 4 x i64> poison, i64 1, i64 0), <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer)
+; CHECK-NEXT: [[INDUCTION:%.*]] = add <vscale x 4 x i64> zeroinitializer, [[TMP9]]
; CHECK-NEXT: [[TMP10:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT: [[TMP11:%.*]] = mul i64 [[TMP10]], 8
+; CHECK-NEXT: [[TMP11:%.*]] = mul i64 [[TMP10]], 4
; CHECK-NEXT: [[TMP12:%.*]] = mul i64 1, [[TMP11]]
-; CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 8 x i64> poison, i64 [[TMP12]], i64 0
-; CHECK-NEXT: [[DOTSPLAT:%.*]] = shufflevector <vscale x 8 x i64> [[DOTSPLATINSERT]], <vscale x 8 x i64> poison, <vscale x 8 x i32> zeroinitializer
-; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 8 x i64> poison, i64 [[VAL]], i64 0
-; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 8 x i64> [[BROADCAST_SPLATINSERT]], <vscale x 8 x i64> poison, <vscale x 8 x i32> zeroinitializer
+; CHECK-NEXT: [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TMP12]], i64 0
+; CHECK-NEXT: [[DOTSPLAT:%.*]] = shufflevector <vscale x 4 x i64> [[DOTSPLATINSERT]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
+; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[VAL]], i64 0
+; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 4 x i64> [[BROADCAST_SPLATINSERT]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT: [[ACTIVE_LANE_MASK:%.*]] = phi <vscale x 8 x i1> [ [[ACTIVE_LANE_MASK_ENTRY]], [[VECTOR_PH]] ], [ [[ACTIVE_LANE_MASK_NEXT:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT: [[VEC_IND:%.*]] = phi <vscale x 8 x i64> [ [[INDUCTION]], [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT: [[ACTIVE_LANE_MASK:%.*]] = phi <vscale x 4 x i1> [ [[ACTIVE_LANE_MASK_ENTRY]], [[VECTOR_PH]] ], [ [[ACTIVE_LANE_MASK_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT: [[VEC_IND:%.*]] = phi <vscale x 4 x i64> [ [[INDUCTION]], [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP13:%.*]] = add i64 [[INDEX]], 0
; CHECK-NEXT: [[NEXT_GEP:%.*]] = getelementptr i8, ptr [[DST]], i64 [[TMP13]]
-; CHECK-NEXT: [[TMP14:%.*]] = shl nuw nsw <vscale x 8 x i64> [[VEC_IND]], shufflevector (<vscale x 8 x i64> insertelement (<vscale x 8 x i64> poison, i64 3, i64 0), <vscale x 8 x i64> poison, <vscale x 8 x i32> zeroinitializer)
-; CHECK-NEXT: [[TMP15:%.*]] = lshr <vscale x 8 x i64> [[BROADCAST_SPLAT]], [[TMP14]]
-; CHECK-NEXT: [[TMP16:%.*]] = trunc <vscale x 8 x i64> [[TMP15]] to <vscale x 8 x i8>
+; CHECK-NEXT: [[TMP14:%.*]] = shl nuw nsw <vscale x 4 x i64> [[VEC_IND]], shufflevector (<vscale x 4 x i64> insertelement (<vscale x 4 x i64> poison, i64 3, i64 0), <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer)
+; CHECK-NEXT: [[TMP15:%.*]] = lshr <vscale x 4 x i64> [[BROADCAST_SPLAT]], [[TMP14]]
+; CHECK-NEXT: [[TMP16:%.*]] = trunc <vscale x 4 x i64> [[TMP15]] to <vscale x 4 x i8>
; CHECK-NEXT: [[TMP17:%.*]] = getelementptr i8, ptr [[NEXT_GEP]], i32 0
-; CHECK-NEXT: call void @llvm.masked.store.nxv8i8.p0(<vscale x 8 x i8> [[TMP16]], ptr [[TMP17]], i32 1, <vscale x 8 x i1> [[ACTIVE_LANE_MASK]])
+; CHECK-NEXT: call void @llvm.masked.store.nxv4i8.p0(<vscale x 4 x i8> [[TMP16]], ptr [[TMP17]], i32 1, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]])
; CHECK-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], [[TMP6]]
-; CHECK-NEXT: [[VEC_IND_NEXT]] = add <vscale x 8 x i64> [[VEC_IND]], [[DOTSPLAT]]
-; CHECK-NEXT: [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 [[INDEX_NEXT]], i64 [[WIDE_TRIP_COUNT]])
-; CHECK-NEXT: br i1 true, label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
+; CHECK-NEXT: [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX_NEXT]], i64 [[WIDE_TRIP_COUNT]])
+; CHECK-NEXT: [[TMP18:%.*]] = xor <vscale x 4 x i1> [[ACTIVE_LANE_MASK_NEXT]], shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer)
+; CHECK-NEXT: [[VEC_IND_NEXT]] = add <vscale x 4 x i64> [[VEC_IND]], [[DOTSPLAT]]
+; CHECK-NEXT: [[TMP20:%.*]] = extractelement <vscale x 4 x i1> [[TMP18]], i32 0
+; CHECK-NEXT: br i1 [[TMP20]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
; CHECK: middle.block:
; CHECK-NEXT: br i1 true, label [[FOR_COND_CLEANUP_LOOPEXIT:%.*]], label [[SCALAR_PH]]
; CHECK: scalar.ph:
diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/low-trip-count.ll b/llvm/test/Transforms/LoopVectorize/RISCV/low-trip-count.ll
index 7ccbc98d26567..2ce42c332a9c2 100644
--- a/llvm/test/Transforms/LoopVectorize/RISCV/low-trip-count.ll
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/low-trip-count.ll
@@ -48,29 +48,29 @@ define void @trip3_i8(ptr noalias nocapture noundef %dst, ptr noalias nocapture
; CHECK-NEXT: br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
; CHECK-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT: [[TMP1:%.*]] = mul i64 [[TMP0]], 16
+; CHECK-NEXT: [[TMP1:%.*]] = mul i64 [[TMP0]], 2
; CHECK-NEXT: [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT: [[TMP3:%.*]] = mul i64 [[TMP2]], 16
+; CHECK-NEXT: [[TMP3:%.*]] = mul i64 [[TMP2]], 2
; CHECK-NEXT: [[TMP4:%.*]] = sub i64 [[TMP3]], 1
; CHECK-NEXT: [[N_RND_UP:%.*]] = add i64 3, [[TMP4]]
; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP1]]
; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
; CHECK-NEXT: [[TMP5:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT: [[TMP6:%.*]] = mul i64 [[TMP5]], 16
+; CHECK-NEXT: [[TMP6:%.*]] = mul i64 [[TMP5]], 2
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP7:%.*]] = add i64 [[INDEX]], 0
-; CHECK-NEXT: [[ACTIVE_LANE_MASK:%.*]] = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i64(i64 [[TMP7]], i64 3)
+; CHECK-NEXT: [[ACTIVE_LANE_MASK:%.*]] = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 [[TMP7]], i64 3)
; CHECK-NEXT: [[TMP8:%.*]] = getelementptr inbounds i8, ptr [[SRC:%.*]], i64 [[TMP7]]
; CHECK-NEXT: [[TMP9:%.*]] = getelementptr inbounds i8, ptr [[TMP8]], i32 0
-; CHECK-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 16 x i8> @llvm.masked.load.nxv16i8.p0(ptr [[TMP9]], i32 1, <vscale x 16 x i1> [[ACTIVE_LANE_MASK]], <vscale x 16 x i8> poison)
-; CHECK-NEXT: [[TMP10:%.*]] = shl <vscale x 16 x i8> [[WIDE_MASKED_LOAD]], shufflevector (<vscale x 16 x i8> insertelement (<vscale x 16 x i8> poison, i8 1, i64 0), <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer)
+; CHECK-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 2 x i8> @llvm.masked.load.nxv2i8.p0(ptr [[TMP9]], i32 1, <vscale x 2 x i1> [[ACTIVE_LANE_MASK]], <vscale x 2 x i8> poison)
+; CHECK-NEXT: [[TMP10:%.*]] = shl <vscale x 2 x i8> [[WIDE_MASKED_LOAD]], shufflevector (<vscale x 2 x i8> insertelement (<vscale x 2 x i8> poison, i8 1, i64 0), <vscale x 2 x i8> poison, <vscale x 2 x i32> zeroinitializer)
; CHECK-NEXT: [[TMP11:%.*]] = getelementptr inbounds i8, ptr [[DST:%.*]], i64 [[TMP7]]
; CHECK-NEXT: [[TMP12:%.*]] = getelementptr inbounds i8, ptr [[TMP11]], i32 0
-; CHECK-NEXT: [[WIDE_MASKED_LOAD1:%.*]] = call <vscale x 16 x i8> @llvm.masked.load.nxv16i8.p0(ptr [[TMP12]], i32 1, <vscale x 16 x i1> [[ACTIVE_LANE_MASK]], <vscale x 16 x i8> poison)
-; CHECK-NEXT: [[TMP13:%.*]] = add <vscale x 16 x i8> [[TMP10]], [[WIDE_MASKED_LOAD1]]
-; CHECK-NEXT: call void @llvm.masked.store.nxv16i8.p0(<vscale x 16 x i8> [[TMP13]], ptr [[TMP12]], i32 1, <vscale x 16 x i1> [[ACTIVE_LANE_MASK]])
+; CHECK-NEXT: [[WIDE_MASKED_LOAD1:%.*]] = call <vscale x 2 x i8> @llvm.masked.load.nxv2i8.p0(ptr [[TMP12]], i32 1, <vscale x 2 x i1> [[ACTIVE_LANE_MASK]], <vscale x 2 x i8> poison)
+; CHECK-NEXT: [[TMP13:%.*]] = add <vscale x 2 x i8> [[TMP10]], [[WIDE_MASKED_LOAD1]]
+; CHECK-NEXT: call void @llvm.masked.store.nxv2i8.p0(<vscale x 2 x i8> [[TMP13]], ptr [[TMP12]], i32 1, <vscale x 2 x i1> [[ACTIVE_LANE_MASK]])
; CHECK-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], [[TMP6]]
; CHECK-NEXT: br i1 true, label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK: middle.block:
@@ -119,29 +119,29 @@ define void @trip5_i8(ptr noalias nocapture noundef %dst, ptr noalias nocapture
; CHECK-NEXT: br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
; CHECK-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT: [[TMP1:%.*]] = mul i64 [[TMP0]], 16
+; CHECK-NEXT: [[TMP1:%.*]] = mul i64 [[TMP0]], 4
; CHECK-NEXT: [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT: [[TMP3:%.*]] = mul i64 [[TMP2]], 16
+; CHECK-NEXT: [[TMP3:%.*]] = mul i64 [[TMP2]], 4
; CHECK-NEXT: [[TMP4:%.*]] = sub i64 [[TMP3]], 1
; CHECK-NEXT: [[N_RND_UP:%.*]] = add i64 5, [[TMP4]]
; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP1]]
; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
; CHECK-NEXT: [[TMP5:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT: [[TMP6:%.*]] = mul i64 [[TMP5]], 16
+; CHECK-NEXT: [[TMP6:%.*]] = mul i64 [[TMP5]], 4
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP7:%.*]] = add i64 [[INDEX]], 0
-; CHECK-NEXT: [[ACTIVE_LANE_MASK:%.*]] = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i64(i64 [[TMP7]], i64 5)
+; CHECK-NEXT: [[ACTIVE_LANE_MASK:%.*]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[TMP7]], i64 5)
; CHECK-NEXT: [[TMP8:%.*]] = getelementptr inbounds i8, ptr [[SRC:%.*]], i64 [[TMP7]]
; CHECK-NEXT: [[TMP9:%.*]] = getelementptr inbounds i8, ptr [[TMP8]], i32 0
-; CHECK-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 16 x i8> @llvm.masked.load.nxv16i8.p0(ptr [[TMP9]], i32 1, <vscale x 16 x i1> [[ACTIVE_LANE_MASK]], <vscale x 16 x i8> poison)
-; CHECK-NEXT: [[TMP10:%.*]] = shl <vscale x 16 x i8> [[WIDE_MASKED_LOAD]], shufflevector (<vscale x 16 x i8> insertelement (<vscale x 16 x i8> poison, i8 1, i64 0), <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer)
+; CHECK-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 4 x i8> @llvm.masked.load.nxv4i8.p0(ptr [[TMP9]], i32 1, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x i8> poison)
+; CHECK-NEXT: [[TMP10:%.*]] = shl <vscale x 4 x i8> [[WIDE_MASKED_LOAD]], shufflevector (<vscale x 4 x i8> insertelement (<vscale x 4 x i8> poison, i8 1, i64 0), <vscale x 4 x i8> poison, <vscale x 4 x i32> zeroinitializer)
; CHECK-NEXT: [[TMP11:%.*]] = getelementptr inbounds i8, ptr [[DST:%.*]], i64 [[TMP7]]
; CHECK-NEXT: [[TMP12:%.*]] = getelementptr inbounds i8, ptr [[TMP11]], i32 0
-; CHECK-NEXT: [[WIDE_MASKED_LOAD1:%.*]] = call <vscale x 16 x i8> @llvm.masked.load.nxv16i8.p0(ptr [[TMP12]], i32 1, <vscale x 16 x i1> [[ACTIVE_LANE_MASK]], <vscale x 16 x i8> poison)
-; CHECK-NEXT: [[TMP13:%.*]] = add <vscale x 16 x i8> [[TMP10]], [[WIDE_MASKED_LOAD1]]
-; CHECK-NEXT: call void @llvm.masked.store.nxv16i8.p0(<vscale x 16 x i8> [[TMP13]], ptr [[TMP12]], i32 1, <vscale x 16 x i1> [[ACTIVE_LANE_MASK]])
+; CHECK-NEXT: [[WIDE_MASKED_LOAD1:%.*]] = call <vscale x 4 x i8> @llvm.masked.load.nxv4i8.p0(ptr [[TMP12]], i32 1, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x i8> poison)
+; CHECK-NEXT: [[TMP13:%.*]] = add <vscale x 4 x i8> [[TMP10]], [[WIDE_MASKED_LOAD1]]
+; CHECK-NEXT: call void @llvm.masked.store.nxv4i8.p0(<vscale x 4 x i8> [[TMP13]], ptr [[TMP12]], i32 1, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]])
; CHECK-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], [[TMP6]]
; CHECK-NEXT: br i1 true, label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
; CHECK: middle.block:
@@ -190,29 +190,29 @@ define void @trip8_i8(ptr noalias nocapture noundef %dst, ptr noalias nocapture
; CHECK-NEXT: br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
; CHECK-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT: [[TMP1:%.*]] = mul i64 [[TMP0]], 8
+; CHECK-NEXT: [[TMP1:%.*]] = mul i64 [[TMP0]], 4
; CHECK-NEXT: [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT: [[TMP3:%.*]] = mul i64 [[TMP2]], 8
+; CHECK-NEXT: [[TMP3:%.*]] = mul i64 [[TMP2]], 4
; CHECK-NEXT: [[TMP4:%.*]] = sub i64 [[TMP3]], 1
; CHECK-NEXT: [[N_RND_UP:%.*]] = add i64 8, [[TMP4]]
; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP1]]
; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
; CHECK-NEXT: [[TMP5:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT: [[TMP6:%.*]] = mul i64 [[TMP5]], 8
+; CHECK-NEXT: [[TMP6:%.*]] = mul i64 [[TMP5]], 4
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP7:%.*]] = add i64 [[INDEX]], 0
-; CHECK-NEXT: [[ACTIVE_LANE_MASK:%.*]] = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 [[TMP7]], i64 8)
+; CHECK-NEXT: [[ACTIVE_LANE_MASK:%.*]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[TMP7]], i64 8)
; CHECK-NEXT: [[TMP8:%.*]] = getelementptr inbounds i8, ptr [[SRC:%.*]], i64 [[TMP7]]
; CHECK-NEXT: [[TMP9:%.*]] = getelementptr inbounds i8, ptr [[TMP8]], i32 0
-; CHECK-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 8 x i8> @llvm.masked.load.nxv8i8.p0(ptr [[TMP9]], i32 1, <vscale x 8 x i1> [[ACTIVE_LANE_MASK]], <vscale x 8 x i8> poison)
-; CHECK-NEXT: [[TMP10:%.*]] = shl <vscale x 8 x i8> [[WIDE_MASKED_LOAD]], shufflevector (<vscale x 8 x i8> insertelement (<vscale x 8 x i8> poison, i8 1, i64 0), <vscale x 8 x i8> poison, <vscale x 8 x i32> zeroinitializer)
+; CHECK-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 4 x i8> @llvm.masked.load.nxv4i8.p0(ptr [[TMP9]], i32 1, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x i8> poison)
+; CHECK-NEXT: [[TMP10:%.*]] = shl <vscale x 4 x i8> [[WIDE_MASKED_LOAD]], shufflevector (<vscale x 4 x i8> insertelement (<vscale x 4 x i8> poison, i8 1, i64 0), <vscale x 4 x i8> poison, <vscale x 4 x i32> zeroinitializer)
; CHECK-NEXT: [[TMP11:%.*]] = getelementptr inbounds i8, ptr [[DST:%.*]], i64 [[TMP7]]
; CHECK-NEXT: [[TMP12:%.*]] = getelementptr inbounds i8, ptr [[TMP11]], i32 0
-; CHECK-NEXT: [[WIDE_MASKED_LOAD1:%.*]] = call <vscale x 8 x i8> @llvm.masked.load.nxv8i8.p0(ptr [[TMP12]], i32 1, <vscale x 8 x i1> [[ACTIVE_LANE_MASK]], <vscale x 8 x i8> poison)
-; CHECK-NEXT: [[TMP13:%.*]] = add <vscale x 8 x i8> [[TMP10]], [[WIDE_MASKED_LOAD1]]
-; CHECK-NEXT: call void @llvm.masked.store.nxv8i8.p0(<vscale x 8 x i8> [[TMP13]], ptr [[TMP12]], i32 1, <vscale x 8 x i1> [[ACTIVE_LANE_MASK]])
+; CHECK-NEXT: [[WIDE_MASKED_LOAD1:%.*]] = call <vscale x 4 x i8> @llvm.masked.load.nxv4i8.p0(ptr [[TMP12]], i32 1, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x i8> poison)
+; CHECK-NEXT: [[TMP13:%.*]] = add <vscale x 4 x i8> [[TMP10]], [[WIDE_MASKED_LOAD1]]
+; CHECK-NEXT: call void @llvm.masked.store.nxv4i8.p0(<vscale x 4 x i8> [[TMP13]], ptr [[TMP12]], i32 1, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]])
; CHECK-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], [[TMP6]]
; CHECK-NEXT: br i1 true, label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
; CHECK: middle.block:
diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/short-trip-count.ll b/llvm/test/Transforms/LoopVectorize/RISCV/short-trip-count.ll
index 5c8037437f3e2..5cdb35bdec595 100644
--- a/llvm/test/Transforms/LoopVectorize/RISCV/short-trip-count.ll
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/short-trip-count.ll
@@ -7,25 +7,25 @@ define void @small_trip_count_min_vlen_128(ptr nocapture %a) nounwind vscale_ran
; CHECK-NEXT: br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
; CHECK-NEXT: [[TMP0:%.*]] = call i32 @llvm.vscale.i32()
-; CHECK-NEXT: [[TMP1:%.*]] = mul i32 [[TMP0]], 4
+; CHECK-NEXT: [[TMP1:%.*]] = mul i32 [[TMP0]], 2
; CHECK-NEXT: [[TMP2:%.*]] = call i32 @llvm.vscale.i32()
-; CHECK-NEXT: [[TMP3:%.*]] = mul i32 [[TMP2]], 4
+; CHECK-NEXT: [[TMP3:%.*]] = mul i32 [[TMP2]], 2
; CHECK-NEXT: [[TMP4:%.*]] = sub i32 [[TMP3]], 1
; CHECK-NEXT: [[N_RND_UP:%.*]] = add i32 4, [[TMP4]]
; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i32 [[N_RND_UP]], [[TMP1]]
; CHECK-NEXT: [[N_VEC:%.*]] = sub i32 [[N_RND_UP]], [[N_MOD_VF]]
; CHECK-NEXT: [[TMP5:%.*]] = call i32 @llvm.vscale.i32()
-; CHECK-NEXT: [[TMP6:%.*]] = mul i32 [[TMP5]], 4
+; CHECK-NEXT: [[TMP6:%.*]] = mul i32 [[TMP5]], 2
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP7:%.*]] = add i32 [[INDEX]], 0
-; CHECK-NEXT: [[ACTIVE_LANE_MASK:%.*]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i32(i32 [[TMP7]], i32 4)
+; CHECK-NEXT: [[ACTIVE_LANE_MASK:%.*]] = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i32(i32 [[TMP7]], i32 4)
; CHECK-NEXT: [[TMP8:%.*]] = getelementptr inbounds i32, ptr [[A:%.*]], i32 [[TMP7]]
; CHECK-NEXT: [[TMP9:%.*]] = getelementptr inbounds i32, ptr [[TMP8]], i32 0
-; CHECK-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 4 x i32> @llvm.masked.load.nxv4i32.p0(ptr [[TMP9]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x i32> poison)
-; CHECK-NEXT: [[TMP10:%.*]] = add nsw <vscale x 4 x i32> [[WIDE_MASKED_LOAD]], shufflevector (<vscale x 4 x i32> insertelement (<vscale x 4 x i32> poison, i32 1, i64 0), <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer)
-; CHECK-NEXT: call void @llvm.masked.store.nxv4i32.p0(<vscale x 4 x i32> [[TMP10]], ptr [[TMP9]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]])
+; CHECK-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 2 x i32> @llvm.masked.load.nxv2i32.p0(ptr [[TMP9]], i32 4, <vscale x 2 x i1> [[ACTIVE_LANE_MASK]], <vscale x 2 x i32> poison)
+; CHECK-NEXT: [[TMP10:%.*]] = add nsw <vscale x 2 x i32> [[WIDE_MASKED_LOAD]], shufflevector (<vscale x 2 x i32> insertelement (<vscale x 2 x i32> poison, i32 1, i64 0), <vscale x 2 x i32> poison, <vscale x 2 x i32> zeroinitializer)
+; CHECK-NEXT: call void @llvm.masked.store.nxv2i32.p0(<vscale x 2 x i32> [[TMP10]], ptr [[TMP9]], i32 4, <vscale x 2 x i1> [[ACTIVE_LANE_MASK]])
; CHECK-NEXT: [[INDEX_NEXT]] = add i32 [[INDEX]], [[TMP6]]
; CHECK-NEXT: br i1 true, label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK: middle.block:
>From b93a9c31b6fe58f71b6da700862ca6f62c0119e4 Mon Sep 17 00:00:00 2001
From: Ramkumar Ramachandra <r at artagnon.com>
Date: Mon, 6 May 2024 18:56:31 +0100
Subject: [PATCH 4/4] LoopVectorize: optimize VF for low TC, when tail-folding
9a087a3 (LoopVectorize: MaxVF should not be larger than the loop trip
count) was the first commit to add the condition PowerOf2_32() of the
trip-count to, what is now getMaximizedVFForTarget(). It made sense at
the time, as there was no tail-folding support. Much later, 2025e09
([LV] Make sure VF doesn't exceed compile time known TC) came along to
patch this with an extra condition on FoldTailByMasking, in order to
ensure that that the VF doesn't exceed the trip-count. However, it
didn't go far enough, and we can do better, as there is existing code to
clamp the trip-count, and do tail-folding.
Fixes #82626.
---
.../Transforms/Vectorize/LoopVectorize.cpp | 27 ++--
.../LoopVectorize/RISCV/low-trip-count.ll | 142 +++++++++++-------
.../LoopVectorize/vplan-incomplete-cases.ll | 2 +-
3 files changed, 98 insertions(+), 73 deletions(-)
diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
index e4e7502e3961d..34d24c5c29e4c 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -4758,26 +4758,21 @@ ElementCount LoopVectorizationCostModel::getMaximizedVFForTarget(
WidestRegisterMinEC *= Min;
}
- // When a scalar epilogue is required, at least one iteration of the scalar
- // loop has to execute. Adjust MaxTripCount accordingly to avoid picking a
- // max VF that results in a dead vector loop.
- if (MaxTripCount > 0 && requiresScalarEpilogue(true))
- MaxTripCount -= 1;
-
- if (MaxTripCount && MaxTripCount <= WidestRegisterMinEC &&
- (!FoldTailByMasking || isPowerOf2_32(MaxTripCount))) {
- // If upper bound loop trip count (TC) is known at compile time there is no
- // point in choosing VF greater than TC (as done in the loop below). Select
- // maximum power of two which doesn't exceed TC. If MaxVectorElementCount is
- // scalable, we only fall back on a fixed VF when the TC is less than or
- // equal to the known number of lanes.
+ if (MaxTripCount > 0 && MaxTripCount <= WidestRegisterMinEC &&
+ requiresScalarEpilogue(true)) {
+ // When a scalar epilogue is required, at least one iteration of the scalar
+ // loop has to execute. Adjust MaxTripCount accordingly to avoid picking a
+ // max VF that results in a dead vector loop.
+ --MaxTripCount;
+
+ // When a scalar epilogue is required, if upper bound loop trip count (TC)
+ // is known at compile time, clamp the VF to a maximum power of two which
+ // doesn't exceed TC, and vectorize using a fixed-length vector.
auto ClampedUpperTripCount = llvm::bit_floor(MaxTripCount);
LLVM_DEBUG(dbgs() << "LV: Clamping the MaxVF to maximum power of two not "
"exceeding the constant trip count: "
<< ClampedUpperTripCount << "\n");
- return ElementCount::get(
- ClampedUpperTripCount,
- FoldTailByMasking ? MaxVectorElementCount.isScalable() : false);
+ return ElementCount::getFixed(ClampedUpperTripCount);
}
TargetTransformInfo::RegisterKind RegKind =
diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/low-trip-count.ll b/llvm/test/Transforms/LoopVectorize/RISCV/low-trip-count.ll
index 2ce42c332a9c2..97fb4919f39f5 100644
--- a/llvm/test/Transforms/LoopVectorize/RISCV/low-trip-count.ll
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/low-trip-count.ll
@@ -258,36 +258,46 @@ for.end: ; preds = %for.body
define void @trip16_i8(ptr noalias nocapture noundef %dst, ptr noalias nocapture noundef readonly %src) #0 {
; CHECK-LABEL: @trip16_i8(
; CHECK-NEXT: entry:
-; CHECK-NEXT: br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; CHECK-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT: [[TMP1:%.*]] = mul i64 [[TMP0]], 8
+; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 16, [[TMP1]]
+; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
+; CHECK-NEXT: [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT: [[TMP3:%.*]] = mul i64 [[TMP2]], 8
+; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 16, [[TMP3]]
+; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 16, [[N_MOD_VF]]
+; CHECK-NEXT: [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT: [[TMP5:%.*]] = mul i64 [[TMP4]], 8
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT: [[TMP0:%.*]] = add i64 [[INDEX]], 0
-; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds i8, ptr [[SRC:%.*]], i64 [[TMP0]]
-; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds i8, ptr [[TMP1]], i32 0
-; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <16 x i8>, ptr [[TMP2]], align 1
-; CHECK-NEXT: [[TMP3:%.*]] = shl <16 x i8> [[WIDE_LOAD]], <i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1>
-; CHECK-NEXT: [[TMP4:%.*]] = getelementptr inbounds i8, ptr [[DST:%.*]], i64 [[TMP0]]
-; CHECK-NEXT: [[TMP5:%.*]] = getelementptr inbounds i8, ptr [[TMP4]], i32 0
-; CHECK-NEXT: [[WIDE_LOAD1:%.*]] = load <16 x i8>, ptr [[TMP5]], align 1
-; CHECK-NEXT: [[TMP6:%.*]] = add <16 x i8> [[TMP3]], [[WIDE_LOAD1]]
-; CHECK-NEXT: store <16 x i8> [[TMP6]], ptr [[TMP5]], align 1
-; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 16
+; CHECK-NEXT: [[TMP6:%.*]] = add i64 [[INDEX]], 0
+; CHECK-NEXT: [[TMP7:%.*]] = getelementptr inbounds i8, ptr [[SRC:%.*]], i64 [[TMP6]]
+; CHECK-NEXT: [[TMP8:%.*]] = getelementptr inbounds i8, ptr [[TMP7]], i32 0
+; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <vscale x 8 x i8>, ptr [[TMP8]], align 1
+; CHECK-NEXT: [[TMP9:%.*]] = shl <vscale x 8 x i8> [[WIDE_LOAD]], shufflevector (<vscale x 8 x i8> insertelement (<vscale x 8 x i8> poison, i8 1, i64 0), <vscale x 8 x i8> poison, <vscale x 8 x i32> zeroinitializer)
+; CHECK-NEXT: [[TMP10:%.*]] = getelementptr inbounds i8, ptr [[DST:%.*]], i64 [[TMP6]]
+; CHECK-NEXT: [[TMP11:%.*]] = getelementptr inbounds i8, ptr [[TMP10]], i32 0
+; CHECK-NEXT: [[WIDE_LOAD1:%.*]] = load <vscale x 8 x i8>, ptr [[TMP11]], align 1
+; CHECK-NEXT: [[TMP12:%.*]] = add <vscale x 8 x i8> [[TMP9]], [[WIDE_LOAD1]]
+; CHECK-NEXT: store <vscale x 8 x i8> [[TMP12]], ptr [[TMP11]], align 1
+; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP5]]
; CHECK-NEXT: br i1 true, label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
; CHECK: middle.block:
-; CHECK-NEXT: br i1 true, label [[FOR_END:%.*]], label [[SCALAR_PH]]
+; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 16, [[N_VEC]]
+; CHECK-NEXT: br i1 [[CMP_N]], label [[FOR_END:%.*]], label [[SCALAR_PH]]
; CHECK: scalar.ph:
-; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ 16, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
+; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[I_08:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INC:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i8, ptr [[SRC]], i64 [[I_08]]
-; CHECK-NEXT: [[TMP7:%.*]] = load i8, ptr [[ARRAYIDX]], align 1
-; CHECK-NEXT: [[MUL:%.*]] = shl i8 [[TMP7]], 1
+; CHECK-NEXT: [[TMP13:%.*]] = load i8, ptr [[ARRAYIDX]], align 1
+; CHECK-NEXT: [[MUL:%.*]] = shl i8 [[TMP13]], 1
; CHECK-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds i8, ptr [[DST]], i64 [[I_08]]
-; CHECK-NEXT: [[TMP8:%.*]] = load i8, ptr [[ARRAYIDX1]], align 1
-; CHECK-NEXT: [[ADD:%.*]] = add i8 [[MUL]], [[TMP8]]
+; CHECK-NEXT: [[TMP14:%.*]] = load i8, ptr [[ARRAYIDX1]], align 1
+; CHECK-NEXT: [[ADD:%.*]] = add i8 [[MUL]], [[TMP14]]
; CHECK-NEXT: store i8 [[ADD]], ptr [[ARRAYIDX1]], align 1
; CHECK-NEXT: [[INC]] = add nuw nsw i64 [[I_08]], 1
; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INC]], 16
@@ -319,36 +329,46 @@ for.end: ; preds = %for.body
define void @trip32_i8(ptr noalias nocapture noundef %dst, ptr noalias nocapture noundef readonly %src) #0 {
; CHECK-LABEL: @trip32_i8(
; CHECK-NEXT: entry:
-; CHECK-NEXT: br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; CHECK-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT: [[TMP1:%.*]] = mul i64 [[TMP0]], 16
+; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 32, [[TMP1]]
+; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
+; CHECK-NEXT: [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT: [[TMP3:%.*]] = mul i64 [[TMP2]], 16
+; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 32, [[TMP3]]
+; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 32, [[N_MOD_VF]]
+; CHECK-NEXT: [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT: [[TMP5:%.*]] = mul i64 [[TMP4]], 16
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT: [[TMP0:%.*]] = add i64 [[INDEX]], 0
-; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds i8, ptr [[SRC:%.*]], i64 [[TMP0]]
-; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds i8, ptr [[TMP1]], i32 0
-; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <32 x i8>, ptr [[TMP2]], align 1
-; CHECK-NEXT: [[TMP3:%.*]] = shl <32 x i8> [[WIDE_LOAD]], <i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1>
-; CHECK-NEXT: [[TMP4:%.*]] = getelementptr inbounds i8, ptr [[DST:%.*]], i64 [[TMP0]]
-; CHECK-NEXT: [[TMP5:%.*]] = getelementptr inbounds i8, ptr [[TMP4]], i32 0
-; CHECK-NEXT: [[WIDE_LOAD1:%.*]] = load <32 x i8>, ptr [[TMP5]], align 1
-; CHECK-NEXT: [[TMP6:%.*]] = add <32 x i8> [[TMP3]], [[WIDE_LOAD1]]
-; CHECK-NEXT: store <32 x i8> [[TMP6]], ptr [[TMP5]], align 1
-; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 32
+; CHECK-NEXT: [[TMP6:%.*]] = add i64 [[INDEX]], 0
+; CHECK-NEXT: [[TMP7:%.*]] = getelementptr inbounds i8, ptr [[SRC:%.*]], i64 [[TMP6]]
+; CHECK-NEXT: [[TMP8:%.*]] = getelementptr inbounds i8, ptr [[TMP7]], i32 0
+; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <vscale x 16 x i8>, ptr [[TMP8]], align 1
+; CHECK-NEXT: [[TMP9:%.*]] = shl <vscale x 16 x i8> [[WIDE_LOAD]], shufflevector (<vscale x 16 x i8> insertelement (<vscale x 16 x i8> poison, i8 1, i64 0), <vscale x 16 x i8> poison, <vscale x 16 x i32> zeroinitializer)
+; CHECK-NEXT: [[TMP10:%.*]] = getelementptr inbounds i8, ptr [[DST:%.*]], i64 [[TMP6]]
+; CHECK-NEXT: [[TMP11:%.*]] = getelementptr inbounds i8, ptr [[TMP10]], i32 0
+; CHECK-NEXT: [[WIDE_LOAD1:%.*]] = load <vscale x 16 x i8>, ptr [[TMP11]], align 1
+; CHECK-NEXT: [[TMP12:%.*]] = add <vscale x 16 x i8> [[TMP9]], [[WIDE_LOAD1]]
+; CHECK-NEXT: store <vscale x 16 x i8> [[TMP12]], ptr [[TMP11]], align 1
+; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP5]]
; CHECK-NEXT: br i1 true, label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP10:![0-9]+]]
; CHECK: middle.block:
-; CHECK-NEXT: br i1 true, label [[FOR_END:%.*]], label [[SCALAR_PH]]
+; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 32, [[N_VEC]]
+; CHECK-NEXT: br i1 [[CMP_N]], label [[FOR_END:%.*]], label [[SCALAR_PH]]
; CHECK: scalar.ph:
-; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ 32, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
+; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[I_08:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INC:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i8, ptr [[SRC]], i64 [[I_08]]
-; CHECK-NEXT: [[TMP7:%.*]] = load i8, ptr [[ARRAYIDX]], align 1
-; CHECK-NEXT: [[MUL:%.*]] = shl i8 [[TMP7]], 1
+; CHECK-NEXT: [[TMP13:%.*]] = load i8, ptr [[ARRAYIDX]], align 1
+; CHECK-NEXT: [[MUL:%.*]] = shl i8 [[TMP13]], 1
; CHECK-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds i8, ptr [[DST]], i64 [[I_08]]
-; CHECK-NEXT: [[TMP8:%.*]] = load i8, ptr [[ARRAYIDX1]], align 1
-; CHECK-NEXT: [[ADD:%.*]] = add i8 [[MUL]], [[TMP8]]
+; CHECK-NEXT: [[TMP14:%.*]] = load i8, ptr [[ARRAYIDX1]], align 1
+; CHECK-NEXT: [[ADD:%.*]] = add i8 [[MUL]], [[TMP14]]
; CHECK-NEXT: store i8 [[ADD]], ptr [[ARRAYIDX1]], align 1
; CHECK-NEXT: [[INC]] = add nuw nsw i64 [[I_08]], 1
; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INC]], 32
@@ -379,37 +399,47 @@ for.end: ; preds = %for.body
define void @trip24_i8(ptr noalias nocapture noundef %dst, ptr noalias nocapture noundef readonly %src) #0 {
; CHECK-LABEL: @trip24_i8(
; CHECK-NEXT: entry:
-; CHECK-NEXT: br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; CHECK-NEXT: [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT: [[TMP1:%.*]] = mul i64 [[TMP0]], 4
+; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 24, [[TMP1]]
+; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
+; CHECK-NEXT: [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT: [[TMP3:%.*]] = mul i64 [[TMP2]], 4
+; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 24, [[TMP3]]
+; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 24, [[N_MOD_VF]]
+; CHECK-NEXT: [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT: [[TMP5:%.*]] = mul i64 [[TMP4]], 4
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT: [[TMP0:%.*]] = add i64 [[INDEX]], 0
-; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds i8, ptr [[SRC:%.*]], i64 [[TMP0]]
-; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds i8, ptr [[TMP1]], i32 0
-; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <8 x i8>, ptr [[TMP2]], align 1
-; CHECK-NEXT: [[TMP3:%.*]] = shl <8 x i8> [[WIDE_LOAD]], <i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1>
-; CHECK-NEXT: [[TMP4:%.*]] = getelementptr inbounds i8, ptr [[DST:%.*]], i64 [[TMP0]]
-; CHECK-NEXT: [[TMP5:%.*]] = getelementptr inbounds i8, ptr [[TMP4]], i32 0
-; CHECK-NEXT: [[WIDE_LOAD1:%.*]] = load <8 x i8>, ptr [[TMP5]], align 1
-; CHECK-NEXT: [[TMP6:%.*]] = add <8 x i8> [[TMP3]], [[WIDE_LOAD1]]
-; CHECK-NEXT: store <8 x i8> [[TMP6]], ptr [[TMP5]], align 1
-; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 8
-; CHECK-NEXT: [[TMP7:%.*]] = icmp eq i64 [[INDEX_NEXT]], 24
-; CHECK-NEXT: br i1 [[TMP7]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP12:![0-9]+]]
+; CHECK-NEXT: [[TMP6:%.*]] = add i64 [[INDEX]], 0
+; CHECK-NEXT: [[TMP7:%.*]] = getelementptr inbounds i8, ptr [[SRC:%.*]], i64 [[TMP6]]
+; CHECK-NEXT: [[TMP8:%.*]] = getelementptr inbounds i8, ptr [[TMP7]], i32 0
+; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <vscale x 4 x i8>, ptr [[TMP8]], align 1
+; CHECK-NEXT: [[TMP9:%.*]] = shl <vscale x 4 x i8> [[WIDE_LOAD]], shufflevector (<vscale x 4 x i8> insertelement (<vscale x 4 x i8> poison, i8 1, i64 0), <vscale x 4 x i8> poison, <vscale x 4 x i32> zeroinitializer)
+; CHECK-NEXT: [[TMP10:%.*]] = getelementptr inbounds i8, ptr [[DST:%.*]], i64 [[TMP6]]
+; CHECK-NEXT: [[TMP11:%.*]] = getelementptr inbounds i8, ptr [[TMP10]], i32 0
+; CHECK-NEXT: [[WIDE_LOAD1:%.*]] = load <vscale x 4 x i8>, ptr [[TMP11]], align 1
+; CHECK-NEXT: [[TMP12:%.*]] = add <vscale x 4 x i8> [[TMP9]], [[WIDE_LOAD1]]
+; CHECK-NEXT: store <vscale x 4 x i8> [[TMP12]], ptr [[TMP11]], align 1
+; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP5]]
+; CHECK-NEXT: [[TMP13:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-NEXT: br i1 [[TMP13]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP12:![0-9]+]]
; CHECK: middle.block:
-; CHECK-NEXT: br i1 true, label [[FOR_END:%.*]], label [[SCALAR_PH]]
+; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 24, [[N_VEC]]
+; CHECK-NEXT: br i1 [[CMP_N]], label [[FOR_END:%.*]], label [[SCALAR_PH]]
; CHECK: scalar.ph:
-; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ 24, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
+; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[I_08:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INC:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i8, ptr [[SRC]], i64 [[I_08]]
-; CHECK-NEXT: [[TMP8:%.*]] = load i8, ptr [[ARRAYIDX]], align 1
-; CHECK-NEXT: [[MUL:%.*]] = shl i8 [[TMP8]], 1
+; CHECK-NEXT: [[TMP14:%.*]] = load i8, ptr [[ARRAYIDX]], align 1
+; CHECK-NEXT: [[MUL:%.*]] = shl i8 [[TMP14]], 1
; CHECK-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds i8, ptr [[DST]], i64 [[I_08]]
-; CHECK-NEXT: [[TMP9:%.*]] = load i8, ptr [[ARRAYIDX1]], align 1
-; CHECK-NEXT: [[ADD:%.*]] = add i8 [[MUL]], [[TMP9]]
+; CHECK-NEXT: [[TMP15:%.*]] = load i8, ptr [[ARRAYIDX1]], align 1
+; CHECK-NEXT: [[ADD:%.*]] = add i8 [[MUL]], [[TMP15]]
; CHECK-NEXT: store i8 [[ADD]], ptr [[ARRAYIDX1]], align 1
; CHECK-NEXT: [[INC]] = add nuw nsw i64 [[I_08]], 1
; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INC]], 24
diff --git a/llvm/test/Transforms/LoopVectorize/vplan-incomplete-cases.ll b/llvm/test/Transforms/LoopVectorize/vplan-incomplete-cases.ll
index 2007155fe5485..02c4c252e8af0 100644
--- a/llvm/test/Transforms/LoopVectorize/vplan-incomplete-cases.ll
+++ b/llvm/test/Transforms/LoopVectorize/vplan-incomplete-cases.ll
@@ -11,7 +11,7 @@ define void @vplan_incomplete_cases_tc2(i8 %x, i8 %y) {
; CHECK-NEXT: br label %[[VECTOR_BODY:.*]]
; CHECK: [[VECTOR_BODY]]:
; CHECK-NEXT: [[INDEX:%.*]] = phi i32 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
-; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 2
+; CHECK-NEXT: [[INDEX_NEXT]] = add i32 [[INDEX]], 2
; CHECK-NEXT: br i1 true, label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK: [[MIDDLE_BLOCK]]:
; CHECK-NEXT: br i1 true, label %[[EXIT:.*]], label %[[SCALAR_PH]]
More information about the llvm-commits
mailing list