[llvm] [LV] Incorporate trip counts into selection of scalable VFs (PR #80926)
Philip Reames via llvm-commits
llvm-commits at lists.llvm.org
Mon Mar 4 16:31:28 PST 2024
https://github.com/preames updated https://github.com/llvm/llvm-project/pull/80926
>From d8770689a586ee521e241b64b14ccdc1172d842b Mon Sep 17 00:00:00 2001
From: Philip Reames <preames at rivosinc.com>
Date: Tue, 6 Feb 2024 17:44:58 -0800
Subject: [PATCH] [LV] Incorporate trip counts into selection of scalable VFs
This change contains two related changes which have the effect of
causing us to reduce the VF chosen when the trip count of a loop
is smaller than some of selectable VFs. Specifically, it does
the following:
* If a scalable vector contains more elements than the trip count,
count only the trip count when computing cost ratios. Empty
elements in the vector don't replace scalar work.
* If a fixed VF has cost equal to trip count, prefer that VF over
a scalable one with more elements.
For context, we iterate through possible VFs in the following order:
first, increasing fixed VFs, and then second, increasing scalable
VFs. We bias towards chosing a scalable VF all else being equal.
---
.../Transforms/Vectorize/LoopVectorize.cpp | 13 +-
.../AArch64/clamped-trip-count.ll | 102 +++++++-------
.../LoopVectorize/RISCV/low-trip-count.ll | 132 +++++++-----------
.../LoopVectorize/RISCV/short-trip-count.ll | 56 +++-----
4 files changed, 132 insertions(+), 171 deletions(-)
diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
index 50a073e890626e..0257071927bb12 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -4852,11 +4852,20 @@ bool LoopVectorizationPlanner::isMoreProfitable(
EstimatedWidthB *= *VScale;
}
+ // If we have an upper bound on the trip count, cap our estimate of the
+ // width so that we don't discount cost by more lanes than perform
+ // useful work for the loop.
+ if (MaxTripCount > 0) {
+ EstimatedWidthA = std::min(EstimatedWidthA, MaxTripCount);
+ EstimatedWidthB = std::min(EstimatedWidthB, MaxTripCount);
+ }
+
// 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);
+ if (A.Width.isScalable() && !B.Width.isScalable() &&
+ MaxTripCount != EstimatedWidthB)
+ return (CostA * EstimatedWidthB) <= (CostB * EstimatedWidthA);
// To avoid the need for FP division:
// (CostA / A.Width) < (CostB / B.Width)
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/clamped-trip-count.ll b/llvm/test/Transforms/LoopVectorize/AArch64/clamped-trip-count.ll
index 3e895edcd4f4f8..da62ffe3264d22 100644
--- a/llvm/test/Transforms/LoopVectorize/AArch64/clamped-trip-count.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/clamped-trip-count.ll
@@ -8,45 +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: [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 [[INDEX_NEXT]], i64 8)
-; CHECK-NEXT: [[VEC_IND_NEXT]] = add <vscale x 8 x i64> [[VEC_IND]], [[DOTSPLAT]]
-; CHECK-NEXT: [[TMP18:%.*]] = xor <vscale x 8 x i1> [[ACTIVE_LANE_MASK_NEXT]], shufflevector (<vscale x 8 x i1> insertelement (<vscale x 8 x i1> poison, i1 true, i64 0), <vscale x 8 x i1> poison, <vscale x 8 x i32> zeroinitializer)
-; 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: [[TMP19:%.*]] = extractelement <vscale x 4 x i1> [[TMP18]], i32 0
+; CHECK-NEXT: br i1 [[TMP19]], 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:
@@ -56,8 +57,8 @@ define void @clamped_tc_8(ptr nocapture %dst, i32 %n, i64 %val) vscale_range(1,1
; CHECK: for.body:
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT: [[P_OUT_TAIL_09:%.*]] = phi ptr [ [[BC_RESUME_VAL1]], [[SCALAR_PH]] ], [ [[INCDEC_PTR:%.*]], [[FOR_BODY]] ]
-; CHECK-NEXT: [[TMP19:%.*]] = shl nuw nsw i64 [[INDVARS_IV]], 3
-; CHECK-NEXT: [[SHR3:%.*]] = lshr i64 [[VAL]], [[TMP19]]
+; CHECK-NEXT: [[TMP20:%.*]] = shl nuw nsw i64 [[INDVARS_IV]], 3
+; CHECK-NEXT: [[SHR3:%.*]] = lshr i64 [[VAL]], [[TMP20]]
; CHECK-NEXT: [[CONV4:%.*]] = trunc i64 [[SHR3]] to i8
; CHECK-NEXT: store i8 [[CONV4]], ptr [[P_OUT_TAIL_09]], align 1
; CHECK-NEXT: [[INCDEC_PTR]] = getelementptr inbounds i8, ptr [[P_OUT_TAIL_09]], i64 1
@@ -100,45 +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: [[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: [[VEC_IND_NEXT]] = add <vscale x 8 x i64> [[VEC_IND]], [[DOTSPLAT]]
-; CHECK-NEXT: [[TMP18:%.*]] = xor <vscale x 8 x i1> [[ACTIVE_LANE_MASK_NEXT]], shufflevector (<vscale x 8 x i1> insertelement (<vscale x 8 x i1> poison, i1 true, i64 0), <vscale x 8 x i1> poison, <vscale x 8 x i32> zeroinitializer)
-; 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: [[TMP19:%.*]] = extractelement <vscale x 4 x i1> [[TMP18]], i32 0
+; CHECK-NEXT: br i1 [[TMP19]], 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:
@@ -148,8 +150,8 @@ define void @clamped_tc_max_8(ptr nocapture %dst, i32 %n, i64 %val) vscale_range
; CHECK: for.body:
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT: [[P_OUT_TAIL_09:%.*]] = phi ptr [ [[BC_RESUME_VAL1]], [[SCALAR_PH]] ], [ [[INCDEC_PTR:%.*]], [[FOR_BODY]] ]
-; CHECK-NEXT: [[TMP19:%.*]] = shl nuw nsw i64 [[INDVARS_IV]], 3
-; CHECK-NEXT: [[SHR3:%.*]] = lshr i64 [[VAL]], [[TMP19]]
+; CHECK-NEXT: [[TMP20:%.*]] = shl nuw nsw i64 [[INDVARS_IV]], 3
+; CHECK-NEXT: [[SHR3:%.*]] = lshr i64 [[VAL]], [[TMP20]]
; CHECK-NEXT: [[CONV4:%.*]] = trunc i64 [[SHR3]] to i8
; CHECK-NEXT: store i8 [[CONV4]], ptr [[P_OUT_TAIL_09]], align 1
; CHECK-NEXT: [[INCDEC_PTR]] = getelementptr inbounds i8, ptr [[P_OUT_TAIL_09]], i64 1
diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/low-trip-count.ll b/llvm/test/Transforms/LoopVectorize/RISCV/low-trip-count.ll
index 7ccbc98d26567c..b9753dc6f995c1 100644
--- a/llvm/test/Transforms/LoopVectorize/RISCV/low-trip-count.ll
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/low-trip-count.ll
@@ -47,45 +47,35 @@ define void @trip3_i8(ptr noalias nocapture noundef %dst, ptr noalias nocapture
; CHECK-NEXT: entry:
; 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: [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT: [[TMP3:%.*]] = mul i64 [[TMP2]], 16
-; 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: 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: [[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: [[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: [[INDEX_NEXT]] = add i64 [[INDEX]], [[TMP6]]
+; CHECK-NEXT: [[TMP0:%.*]] = add i64 [[INDEX]], 0
+; CHECK-NEXT: [[ACTIVE_LANE_MASK:%.*]] = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i64(i64 [[TMP0]], i64 3)
+; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds i8, ptr [[SRC:%.*]], i64 [[TMP0]]
+; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds i8, ptr [[TMP1]], i32 0
+; CHECK-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <4 x i8> @llvm.masked.load.v4i8.p0(ptr [[TMP2]], i32 1, <4 x i1> [[ACTIVE_LANE_MASK]], <4 x i8> poison)
+; CHECK-NEXT: [[TMP3:%.*]] = shl <4 x i8> [[WIDE_MASKED_LOAD]], <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_MASKED_LOAD1:%.*]] = call <4 x i8> @llvm.masked.load.v4i8.p0(ptr [[TMP5]], i32 1, <4 x i1> [[ACTIVE_LANE_MASK]], <4 x i8> poison)
+; CHECK-NEXT: [[TMP6:%.*]] = add <4 x i8> [[TMP3]], [[WIDE_MASKED_LOAD1]]
+; CHECK-NEXT: call void @llvm.masked.store.v4i8.p0(<4 x i8> [[TMP6]], ptr [[TMP5]], i32 1, <4 x i1> [[ACTIVE_LANE_MASK]])
+; CHECK-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], 4
; 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 [[FOR_END:%.*]], label [[SCALAR_PH]]
; CHECK: scalar.ph:
-; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
+; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ 4, [[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: [[TMP14:%.*]] = load i8, ptr [[ARRAYIDX]], align 1
-; CHECK-NEXT: [[MUL:%.*]] = shl i8 [[TMP14]], 1
+; CHECK-NEXT: [[TMP7:%.*]] = load i8, ptr [[ARRAYIDX]], align 1
+; CHECK-NEXT: [[MUL:%.*]] = shl i8 [[TMP7]], 1
; CHECK-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds i8, ptr [[DST]], i64 [[I_08]]
-; CHECK-NEXT: [[TMP15:%.*]] = load i8, ptr [[ARRAYIDX1]], align 1
-; CHECK-NEXT: [[ADD:%.*]] = add i8 [[MUL]], [[TMP15]]
+; CHECK-NEXT: [[TMP8:%.*]] = load i8, ptr [[ARRAYIDX1]], align 1
+; CHECK-NEXT: [[ADD:%.*]] = add i8 [[MUL]], [[TMP8]]
; 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]], 3
@@ -118,45 +108,35 @@ define void @trip5_i8(ptr noalias nocapture noundef %dst, ptr noalias nocapture
; CHECK-NEXT: entry:
; 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: [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT: [[TMP3:%.*]] = mul i64 [[TMP2]], 16
-; 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: 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: [[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: [[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: [[INDEX_NEXT]] = add i64 [[INDEX]], [[TMP6]]
+; CHECK-NEXT: [[TMP0:%.*]] = add i64 [[INDEX]], 0
+; CHECK-NEXT: [[ACTIVE_LANE_MASK:%.*]] = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i64(i64 [[TMP0]], i64 5)
+; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds i8, ptr [[SRC:%.*]], i64 [[TMP0]]
+; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds i8, ptr [[TMP1]], i32 0
+; CHECK-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <8 x i8> @llvm.masked.load.v8i8.p0(ptr [[TMP2]], i32 1, <8 x i1> [[ACTIVE_LANE_MASK]], <8 x i8> poison)
+; CHECK-NEXT: [[TMP3:%.*]] = shl <8 x i8> [[WIDE_MASKED_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_MASKED_LOAD1:%.*]] = call <8 x i8> @llvm.masked.load.v8i8.p0(ptr [[TMP5]], i32 1, <8 x i1> [[ACTIVE_LANE_MASK]], <8 x i8> poison)
+; CHECK-NEXT: [[TMP6:%.*]] = add <8 x i8> [[TMP3]], [[WIDE_MASKED_LOAD1]]
+; CHECK-NEXT: call void @llvm.masked.store.v8i8.p0(<8 x i8> [[TMP6]], ptr [[TMP5]], i32 1, <8 x i1> [[ACTIVE_LANE_MASK]])
+; CHECK-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], 8
; 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 [[FOR_END:%.*]], label [[SCALAR_PH]]
; CHECK: scalar.ph:
-; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
+; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ 8, [[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: [[TMP14:%.*]] = load i8, ptr [[ARRAYIDX]], align 1
-; CHECK-NEXT: [[MUL:%.*]] = shl i8 [[TMP14]], 1
+; CHECK-NEXT: [[TMP7:%.*]] = load i8, ptr [[ARRAYIDX]], align 1
+; CHECK-NEXT: [[MUL:%.*]] = shl i8 [[TMP7]], 1
; CHECK-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds i8, ptr [[DST]], i64 [[I_08]]
-; CHECK-NEXT: [[TMP15:%.*]] = load i8, ptr [[ARRAYIDX1]], align 1
-; CHECK-NEXT: [[ADD:%.*]] = add i8 [[MUL]], [[TMP15]]
+; CHECK-NEXT: [[TMP8:%.*]] = load i8, ptr [[ARRAYIDX1]], align 1
+; CHECK-NEXT: [[ADD:%.*]] = add i8 [[MUL]], [[TMP8]]
; 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]], 5
@@ -189,45 +169,35 @@ define void @trip8_i8(ptr noalias nocapture noundef %dst, ptr noalias nocapture
; CHECK-NEXT: entry:
; 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: [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT: [[TMP3:%.*]] = mul i64 [[TMP2]], 8
-; 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: 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: [[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: [[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: [[INDEX_NEXT]] = add i64 [[INDEX]], [[TMP6]]
+; CHECK-NEXT: [[TMP0:%.*]] = add i64 [[INDEX]], 0
+; CHECK-NEXT: [[ACTIVE_LANE_MASK:%.*]] = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i64(i64 [[TMP0]], i64 8)
+; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds i8, ptr [[SRC:%.*]], i64 [[TMP0]]
+; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds i8, ptr [[TMP1]], i32 0
+; CHECK-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <8 x i8> @llvm.masked.load.v8i8.p0(ptr [[TMP2]], i32 1, <8 x i1> [[ACTIVE_LANE_MASK]], <8 x i8> poison)
+; CHECK-NEXT: [[TMP3:%.*]] = shl <8 x i8> [[WIDE_MASKED_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_MASKED_LOAD1:%.*]] = call <8 x i8> @llvm.masked.load.v8i8.p0(ptr [[TMP5]], i32 1, <8 x i1> [[ACTIVE_LANE_MASK]], <8 x i8> poison)
+; CHECK-NEXT: [[TMP6:%.*]] = add <8 x i8> [[TMP3]], [[WIDE_MASKED_LOAD1]]
+; CHECK-NEXT: call void @llvm.masked.store.v8i8.p0(<8 x i8> [[TMP6]], ptr [[TMP5]], i32 1, <8 x i1> [[ACTIVE_LANE_MASK]])
+; CHECK-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], 8
; CHECK-NEXT: br i1 true, label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
; CHECK: middle.block:
; CHECK-NEXT: br i1 true, label [[FOR_END:%.*]], label [[SCALAR_PH]]
; CHECK: scalar.ph:
-; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
+; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ 8, [[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: [[TMP14:%.*]] = load i8, ptr [[ARRAYIDX]], align 1
-; CHECK-NEXT: [[MUL:%.*]] = shl i8 [[TMP14]], 1
+; CHECK-NEXT: [[TMP7:%.*]] = load i8, ptr [[ARRAYIDX]], align 1
+; CHECK-NEXT: [[MUL:%.*]] = shl i8 [[TMP7]], 1
; CHECK-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds i8, ptr [[DST]], i64 [[I_08]]
-; CHECK-NEXT: [[TMP15:%.*]] = load i8, ptr [[ARRAYIDX1]], align 1
-; CHECK-NEXT: [[ADD:%.*]] = add i8 [[MUL]], [[TMP15]]
+; CHECK-NEXT: [[TMP8:%.*]] = load i8, ptr [[ARRAYIDX1]], align 1
+; CHECK-NEXT: [[ADD:%.*]] = add i8 [[MUL]], [[TMP8]]
; 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]], 8
diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/short-trip-count.ll b/llvm/test/Transforms/LoopVectorize/RISCV/short-trip-count.ll
index 5c8037437f3e21..3ba23cf1ad05aa 100644
--- a/llvm/test/Transforms/LoopVectorize/RISCV/short-trip-count.ll
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/short-trip-count.ll
@@ -6,32 +6,22 @@ define void @small_trip_count_min_vlen_128(ptr nocapture %a) nounwind vscale_ran
; CHECK-NEXT: entry:
; 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: [[TMP2:%.*]] = call i32 @llvm.vscale.i32()
-; CHECK-NEXT: [[TMP3:%.*]] = mul i32 [[TMP2]], 4
-; 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: 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: [[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: [[INDEX_NEXT]] = add i32 [[INDEX]], [[TMP6]]
+; CHECK-NEXT: [[TMP0:%.*]] = add i32 [[INDEX]], 0
+; CHECK-NEXT: [[ACTIVE_LANE_MASK:%.*]] = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 [[TMP0]], i32 4)
+; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds i32, ptr [[A:%.*]], i32 [[TMP0]]
+; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds i32, ptr [[TMP1]], i32 0
+; CHECK-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <4 x i32> @llvm.masked.load.v4i32.p0(ptr [[TMP2]], i32 4, <4 x i1> [[ACTIVE_LANE_MASK]], <4 x i32> poison)
+; CHECK-NEXT: [[TMP3:%.*]] = add nsw <4 x i32> [[WIDE_MASKED_LOAD]], <i32 1, i32 1, i32 1, i32 1>
+; CHECK-NEXT: call void @llvm.masked.store.v4i32.p0(<4 x i32> [[TMP3]], ptr [[TMP2]], i32 4, <4 x i1> [[ACTIVE_LANE_MASK]])
+; CHECK-NEXT: [[INDEX_NEXT]] = add i32 [[INDEX]], 4
; 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 i32 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
+; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i32 [ 4, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT: br label [[LOOP:%.*]]
; CHECK: loop:
; CHECK-NEXT: [[IV:%.*]] = phi i32 [ [[IV_NEXT:%.*]], [[LOOP]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
@@ -67,32 +57,22 @@ define void @small_trip_count_min_vlen_32(ptr nocapture %a) nounwind vscale_rang
; CHECK-NEXT: entry:
; 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: [[TMP2:%.*]] = call i32 @llvm.vscale.i32()
-; CHECK-NEXT: [[TMP3:%.*]] = mul i32 [[TMP2]], 4
-; 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: 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: [[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: [[INDEX_NEXT]] = add i32 [[INDEX]], [[TMP6]]
+; CHECK-NEXT: [[TMP0:%.*]] = add i32 [[INDEX]], 0
+; CHECK-NEXT: [[ACTIVE_LANE_MASK:%.*]] = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 [[TMP0]], i32 4)
+; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds i32, ptr [[A:%.*]], i32 [[TMP0]]
+; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds i32, ptr [[TMP1]], i32 0
+; CHECK-NEXT: [[WIDE_MASKED_LOAD:%.*]] = call <4 x i32> @llvm.masked.load.v4i32.p0(ptr [[TMP2]], i32 4, <4 x i1> [[ACTIVE_LANE_MASK]], <4 x i32> poison)
+; CHECK-NEXT: [[TMP3:%.*]] = add nsw <4 x i32> [[WIDE_MASKED_LOAD]], <i32 1, i32 1, i32 1, i32 1>
+; CHECK-NEXT: call void @llvm.masked.store.v4i32.p0(<4 x i32> [[TMP3]], ptr [[TMP2]], i32 4, <4 x i1> [[ACTIVE_LANE_MASK]])
+; 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 i32 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
+; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i32 [ 4, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT: br label [[LOOP:%.*]]
; CHECK: loop:
; CHECK-NEXT: [[IV:%.*]] = phi i32 [ [[IV_NEXT:%.*]], [[LOOP]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
More information about the llvm-commits
mailing list