[llvm] f1243fa - [LV] Autogen a partially autogened test for ease of update

Philip Reames via llvm-commits llvm-commits at lists.llvm.org
Tue Jul 19 14:19:01 PDT 2022


Author: Philip Reames
Date: 2022-07-19T14:18:53-07:00
New Revision: f1243fa1933fdbcf292f134e0628604c4b9e5487

URL: https://github.com/llvm/llvm-project/commit/f1243fa1933fdbcf292f134e0628604c4b9e5487
DIFF: https://github.com/llvm/llvm-project/commit/f1243fa1933fdbcf292f134e0628604c4b9e5487.diff

LOG: [LV] Autogen a partially autogened test for ease of update

Added: 
    

Modified: 
    llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding.ll

Removed: 
    


################################################################################
diff  --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding.ll
index b2da9d44b8b15..cf8eee7068909 100644
--- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding.ll
@@ -1,3 +1,4 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt -S -hints-allow-reordering=false -loop-vectorize -prefer-predicate-over-epilogue=predicate-else-scalar-epilogue < %s | FileCheck %s
 
 target triple = "aarch64-unknown-linux-gnu"
@@ -7,10 +8,10 @@ define void @simple_memset(i32 %val, i32* %ptr, i64 %n) #0 {
 ; CHECK-LABEL: @simple_memset(
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[UMAX:%.*]] = call i64 @llvm.umax.i64(i64 [[N:%.*]], i64 1)
-; CHECK-NEXT:    [[TMP2:%.*]] = sub i64 -1, [[UMAX]]
-; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 4
-; CHECK-NEXT:    [[TMP3:%.*]] = icmp ult i64 [[TMP2]], [[TMP1]]
+; CHECK-NEXT:    [[TMP0:%.*]] = sub i64 -1, [[UMAX]]
+; CHECK-NEXT:    [[TMP1:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP2:%.*]] = mul i64 [[TMP1]], 4
+; CHECK-NEXT:    [[TMP3:%.*]] = icmp ult i64 [[TMP0]], [[TMP2]]
 ; CHECK-NEXT:    br i1 [[TMP3]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
 ; CHECK:       vector.ph:
 ; CHECK-NEXT:    [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
@@ -21,27 +22,39 @@ define void @simple_memset(i32 %val, i32* %ptr, i64 %n) #0 {
 ; CHECK-NEXT:    [[N_RND_UP:%.*]] = add i64 [[UMAX]], [[TMP8]]
 ; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP5]]
 ; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 0, i64 [[UMAX]])
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK_ENTRY:%.*]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 0, i64 [[UMAX]])
 ; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[VAL:%.*]], i32 0
 ; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 4 x i32> [[BROADCAST_SPLATINSERT]], <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
-; CHECK-NEXT:    [[INDEX1:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT3:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK2:%.*]] = phi <vscale x 4 x i1> [ [[ACTIVE_LANE_MASK]], [[VECTOR_PH]] ], [ [[ACTIVE_LANE_MASK4:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[INDEX1:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT2:%.*]], [[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:    [[TMP9:%.*]] = add i64 [[INDEX1]], 0
 ; CHECK-NEXT:    [[TMP10:%.*]] = getelementptr i32, i32* [[PTR:%.*]], i64 [[TMP9]]
 ; CHECK-NEXT:    [[TMP11:%.*]] = getelementptr i32, i32* [[TMP10]], i32 0
 ; CHECK-NEXT:    [[TMP12:%.*]] = bitcast i32* [[TMP11]] to <vscale x 4 x i32>*
-; CHECK-NEXT:    call void @llvm.masked.store.nxv4i32.p0nxv4i32(<vscale x 4 x i32> [[BROADCAST_SPLAT]], <vscale x 4 x i32>* [[TMP12]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK2]])
+; CHECK-NEXT:    call void @llvm.masked.store.nxv4i32.p0nxv4i32(<vscale x 4 x i32> [[BROADCAST_SPLAT]], <vscale x 4 x i32>* [[TMP12]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]])
 ; CHECK-NEXT:    [[TMP13:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP14:%.*]] = mul i64 [[TMP13]], 4
-; CHECK-NEXT:    [[INDEX_NEXT3]] = add i64 [[INDEX1]], [[TMP14]]
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK4]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX_NEXT3]], i64 [[UMAX]])
-; CHECK-NEXT:    [[TMP15:%.*]] = xor <vscale x 4 x i1> [[ACTIVE_LANE_MASK4]], shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i32 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer)
+; CHECK-NEXT:    [[INDEX_NEXT2]] = add i64 [[INDEX1]], [[TMP14]]
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX_NEXT2]], i64 [[UMAX]])
+; CHECK-NEXT:    [[TMP15:%.*]] = 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, i32 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer)
 ; CHECK-NEXT:    [[TMP16:%.*]] = extractelement <vscale x 4 x i1> [[TMP15]], i32 0
 ; CHECK-NEXT:    br i1 [[TMP16]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
 ; CHECK:       middle.block:
 ; CHECK-NEXT:    br i1 true, label [[WHILE_END_LOOPEXIT:%.*]], label [[SCALAR_PH]]
+; CHECK:       scalar.ph:
+; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
+; CHECK-NEXT:    br label [[WHILE_BODY:%.*]]
+; CHECK:       while.body:
+; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ [[INDEX_NEXT:%.*]], [[WHILE_BODY]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
+; CHECK-NEXT:    [[GEP:%.*]] = getelementptr i32, i32* [[PTR]], i64 [[INDEX]]
+; CHECK-NEXT:    store i32 [[VAL]], i32* [[GEP]], align 4
+; CHECK-NEXT:    [[INDEX_NEXT]] = add nsw i64 [[INDEX]], 1
+; CHECK-NEXT:    [[CMP10:%.*]] = icmp ult i64 [[INDEX_NEXT]], [[N]]
+; CHECK-NEXT:    br i1 [[CMP10]], label [[WHILE_BODY]], label [[WHILE_END_LOOPEXIT]], !llvm.loop [[LOOP2:![0-9]+]]
+; CHECK:       while.end.loopexit:
+; CHECK-NEXT:    ret void
 ;
 entry:
   br label %while.body
@@ -68,25 +81,37 @@ define void @simple_memset_v4i32(i32 %val, i32* %ptr, i64 %n) #0 {
 ; CHECK-NEXT:    [[N_RND_UP:%.*]] = add i64 [[UMAX]], 3
 ; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], 4
 ; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i64(i64 0, i64 [[UMAX]])
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK_ENTRY:%.*]] = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i64(i64 0, i64 [[UMAX]])
 ; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i32> poison, i32 [[VAL:%.*]], i32 0
 ; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT]], <4 x i32> poison, <4 x i32> zeroinitializer
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
-; CHECK-NEXT:    [[INDEX1:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT3:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK2:%.*]] = phi <4 x i1> [ [[ACTIVE_LANE_MASK]], [[VECTOR_PH]] ], [ [[ACTIVE_LANE_MASK4:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[INDEX1:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT2:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = phi <4 x i1> [ [[ACTIVE_LANE_MASK_ENTRY]], [[VECTOR_PH]] ], [ [[ACTIVE_LANE_MASK_NEXT:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[TMP0:%.*]] = add i64 [[INDEX1]], 0
 ; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr i32, i32* [[PTR:%.*]], i64 [[TMP0]]
 ; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr i32, i32* [[TMP1]], i32 0
 ; CHECK-NEXT:    [[TMP3:%.*]] = bitcast i32* [[TMP2]] to <4 x i32>*
-; CHECK-NEXT:    call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> [[BROADCAST_SPLAT]], <4 x i32>* [[TMP3]], i32 4, <4 x i1> [[ACTIVE_LANE_MASK2]])
-; CHECK-NEXT:    [[INDEX_NEXT3]] = add i64 [[INDEX1]], 4
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK4]] = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i64(i64 [[INDEX_NEXT3]], i64 [[UMAX]])
-; CHECK-NEXT:    [[TMP4:%.*]] = xor <4 x i1> [[ACTIVE_LANE_MASK4]], <i1 true, i1 true, i1 true, i1 true>
+; CHECK-NEXT:    call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> [[BROADCAST_SPLAT]], <4 x i32>* [[TMP3]], i32 4, <4 x i1> [[ACTIVE_LANE_MASK]])
+; CHECK-NEXT:    [[INDEX_NEXT2]] = add i64 [[INDEX1]], 4
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i64(i64 [[INDEX_NEXT2]], i64 [[UMAX]])
+; CHECK-NEXT:    [[TMP4:%.*]] = xor <4 x i1> [[ACTIVE_LANE_MASK_NEXT]], <i1 true, i1 true, i1 true, i1 true>
 ; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <4 x i1> [[TMP4]], i32 0
 ; CHECK-NEXT:    br i1 [[TMP5]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
 ; CHECK:       middle.block:
 ; CHECK-NEXT:    br i1 true, label [[WHILE_END_LOOPEXIT:%.*]], label [[SCALAR_PH]]
+; CHECK:       scalar.ph:
+; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
+; CHECK-NEXT:    br label [[WHILE_BODY:%.*]]
+; CHECK:       while.body:
+; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ [[INDEX_NEXT:%.*]], [[WHILE_BODY]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
+; CHECK-NEXT:    [[GEP:%.*]] = getelementptr i32, i32* [[PTR]], i64 [[INDEX]]
+; CHECK-NEXT:    store i32 [[VAL]], i32* [[GEP]], align 4
+; CHECK-NEXT:    [[INDEX_NEXT]] = add nsw i64 [[INDEX]], 1
+; CHECK-NEXT:    [[CMP10:%.*]] = icmp ult i64 [[INDEX_NEXT]], [[N]]
+; CHECK-NEXT:    br i1 [[CMP10]], label [[WHILE_BODY]], label [[WHILE_END_LOOPEXIT]], !llvm.loop [[LOOP5:![0-9]+]]
+; CHECK:       while.end.loopexit:
+; CHECK-NEXT:    ret void
 ;
 entry:
   br label %while.body
@@ -108,10 +133,10 @@ define void @simple_memcpy(i32* noalias %dst, i32* noalias %src, i64 %n) #0 {
 ; CHECK-LABEL: @simple_memcpy(
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[UMAX:%.*]] = call i64 @llvm.umax.i64(i64 [[N:%.*]], i64 1)
-; CHECK-NEXT:    [[TMP2:%.*]] = sub i64 -1, [[UMAX]]
-; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 4
-; CHECK-NEXT:    [[TMP3:%.*]] = icmp ult i64 [[TMP2]], [[TMP1]]
+; CHECK-NEXT:    [[TMP0:%.*]] = sub i64 -1, [[UMAX]]
+; CHECK-NEXT:    [[TMP1:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP2:%.*]] = mul i64 [[TMP1]], 4
+; CHECK-NEXT:    [[TMP3:%.*]] = icmp ult i64 [[TMP0]], [[TMP2]]
 ; CHECK-NEXT:    br i1 [[TMP3]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
 ; CHECK:       vector.ph:
 ; CHECK-NEXT:    [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
@@ -122,29 +147,43 @@ define void @simple_memcpy(i32* noalias %dst, i32* noalias %src, i64 %n) #0 {
 ; CHECK-NEXT:    [[N_RND_UP:%.*]] = add i64 [[UMAX]], [[TMP8]]
 ; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP5]]
 ; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 0, i64 [[UMAX]])
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK_ENTRY:%.*]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 0, i64 [[UMAX]])
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
-; CHECK-NEXT:    [[INDEX1:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT3:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK2:%.*]] = phi <vscale x 4 x i1> [ [[ACTIVE_LANE_MASK]], [[VECTOR_PH]] ], [ [[ACTIVE_LANE_MASK4:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[INDEX1:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT2:%.*]], [[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:    [[TMP9:%.*]] = add i64 [[INDEX1]], 0
 ; CHECK-NEXT:    [[TMP10:%.*]] = getelementptr i32, i32* [[SRC:%.*]], i64 [[TMP9]]
 ; CHECK-NEXT:    [[TMP11:%.*]] = getelementptr i32, i32* [[TMP10]], i32 0
 ; CHECK-NEXT:    [[TMP12:%.*]] = bitcast i32* [[TMP11]] to <vscale x 4 x i32>*
-; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 4 x i32> @llvm.masked.load.nxv4i32.p0nxv4i32(<vscale x 4 x i32>* [[TMP12]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK2]], <vscale x 4 x i32> poison)
+; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 4 x i32> @llvm.masked.load.nxv4i32.p0nxv4i32(<vscale x 4 x i32>* [[TMP12]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x i32> poison)
 ; CHECK-NEXT:    [[TMP13:%.*]] = getelementptr i32, i32* [[DST:%.*]], i64 [[TMP9]]
 ; CHECK-NEXT:    [[TMP14:%.*]] = getelementptr i32, i32* [[TMP13]], i32 0
 ; CHECK-NEXT:    [[TMP15:%.*]] = bitcast i32* [[TMP14]] to <vscale x 4 x i32>*
-; CHECK-NEXT:    call void @llvm.masked.store.nxv4i32.p0nxv4i32(<vscale x 4 x i32> [[WIDE_MASKED_LOAD]], <vscale x 4 x i32>* [[TMP15]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK2]])
+; CHECK-NEXT:    call void @llvm.masked.store.nxv4i32.p0nxv4i32(<vscale x 4 x i32> [[WIDE_MASKED_LOAD]], <vscale x 4 x i32>* [[TMP15]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]])
 ; CHECK-NEXT:    [[TMP16:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP17:%.*]] = mul i64 [[TMP16]], 4
-; CHECK-NEXT:    [[INDEX_NEXT3]] = add i64 [[INDEX1]], [[TMP17]]
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK4]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX_NEXT3]], i64 [[UMAX]])
-; CHECK-NEXT:    [[TMP18:%.*]] = xor <vscale x 4 x i1> [[ACTIVE_LANE_MASK4]], shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i32 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer)
+; CHECK-NEXT:    [[INDEX_NEXT2]] = add i64 [[INDEX1]], [[TMP17]]
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX_NEXT2]], i64 [[UMAX]])
+; 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, i32 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer)
 ; 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 [[LOOP6:![0-9]+]]
 ; CHECK:       middle.block:
 ; CHECK-NEXT:    br i1 true, label [[WHILE_END_LOOPEXIT:%.*]], label [[SCALAR_PH]]
+; CHECK:       scalar.ph:
+; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
+; CHECK-NEXT:    br label [[WHILE_BODY:%.*]]
+; CHECK:       while.body:
+; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ [[INDEX_NEXT:%.*]], [[WHILE_BODY]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
+; CHECK-NEXT:    [[GEP1:%.*]] = getelementptr i32, i32* [[SRC]], i64 [[INDEX]]
+; CHECK-NEXT:    [[VAL:%.*]] = load i32, i32* [[GEP1]], align 4
+; CHECK-NEXT:    [[GEP2:%.*]] = getelementptr i32, i32* [[DST]], i64 [[INDEX]]
+; CHECK-NEXT:    store i32 [[VAL]], i32* [[GEP2]], align 4
+; CHECK-NEXT:    [[INDEX_NEXT]] = add nsw i64 [[INDEX]], 1
+; CHECK-NEXT:    [[CMP10:%.*]] = icmp ult i64 [[INDEX_NEXT]], [[N]]
+; CHECK-NEXT:    br i1 [[CMP10]], label [[WHILE_BODY]], label [[WHILE_END_LOOPEXIT]], !llvm.loop [[LOOP7:![0-9]+]]
+; CHECK:       while.end.loopexit:
+; CHECK-NEXT:    ret void
 ;
 entry:
   br label %while.body
@@ -171,10 +210,10 @@ define void @copy_stride4(i32* noalias %dst, i32* noalias %src, i64 %n) #0 {
 ; CHECK-NEXT:    [[TMP0:%.*]] = add i64 [[UMAX]], -1
 ; CHECK-NEXT:    [[TMP1:%.*]] = lshr i64 [[TMP0]], 2
 ; CHECK-NEXT:    [[TMP2:%.*]] = add nuw nsw i64 [[TMP1]], 1
-; CHECK-NEXT:    [[TMP5:%.*]] = sub i64 -1, [[TMP2]]
-; CHECK-NEXT:    [[TMP3:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP4:%.*]] = mul i64 [[TMP3]], 4
-; CHECK-NEXT:    [[TMP6:%.*]] = icmp ult i64 [[TMP5]], [[TMP4]]
+; CHECK-NEXT:    [[TMP3:%.*]] = sub i64 -1, [[TMP2]]
+; CHECK-NEXT:    [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP5:%.*]] = mul i64 [[TMP4]], 4
+; CHECK-NEXT:    [[TMP6:%.*]] = icmp ult i64 [[TMP3]], [[TMP5]]
 ; CHECK-NEXT:    br i1 [[TMP6]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
 ; CHECK:       vector.ph:
 ; CHECK-NEXT:    [[TMP7:%.*]] = call i64 @llvm.vscale.i64()
@@ -186,7 +225,7 @@ define void @copy_stride4(i32* noalias %dst, i32* noalias %src, i64 %n) #0 {
 ; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP8]]
 ; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
 ; CHECK-NEXT:    [[IND_END:%.*]] = mul i64 [[N_VEC]], 4
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 0, i64 [[TMP2]])
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK_ENTRY:%.*]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 0, i64 [[TMP2]])
 ; CHECK-NEXT:    [[TMP12:%.*]] = call <vscale x 4 x i64> @llvm.experimental.stepvector.nxv4i64()
 ; CHECK-NEXT:    [[TMP13:%.*]] = add <vscale x 4 x i64> [[TMP12]], zeroinitializer
 ; CHECK-NEXT:    [[TMP14:%.*]] = mul <vscale x 4 x i64> [[TMP13]], shufflevector (<vscale x 4 x i64> insertelement (<vscale x 4 x i64> poison, i64 4, i32 0), <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer)
@@ -198,23 +237,37 @@ define void @copy_stride4(i32* noalias %dst, i32* noalias %src, i64 %n) #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:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
-; CHECK-NEXT:    [[INDEX1:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT3:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK2:%.*]] = phi <vscale x 4 x i1> [ [[ACTIVE_LANE_MASK]], [[VECTOR_PH]] ], [ [[ACTIVE_LANE_MASK4:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[INDEX1:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT2:%.*]], [[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:    [[TMP18:%.*]] = getelementptr i32, i32* [[SRC:%.*]], <vscale x 4 x i64> [[VEC_IND]]
-; CHECK-NEXT:    [[WIDE_MASKED_GATHER:%.*]] = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32.nxv4p0i32(<vscale x 4 x i32*> [[TMP18]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK2]], <vscale x 4 x i32> undef)
+; CHECK-NEXT:    [[WIDE_MASKED_GATHER:%.*]] = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32.nxv4p0i32(<vscale x 4 x i32*> [[TMP18]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x i32> undef)
 ; CHECK-NEXT:    [[TMP19:%.*]] = getelementptr i32, i32* [[DST:%.*]], <vscale x 4 x i64> [[VEC_IND]]
-; CHECK-NEXT:    call void @llvm.masked.scatter.nxv4i32.nxv4p0i32(<vscale x 4 x i32> [[WIDE_MASKED_GATHER]], <vscale x 4 x i32*> [[TMP19]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK2]])
+; CHECK-NEXT:    call void @llvm.masked.scatter.nxv4i32.nxv4p0i32(<vscale x 4 x i32> [[WIDE_MASKED_GATHER]], <vscale x 4 x i32*> [[TMP19]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]])
 ; CHECK-NEXT:    [[TMP20:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP21:%.*]] = mul i64 [[TMP20]], 4
-; CHECK-NEXT:    [[INDEX_NEXT3]] = add i64 [[INDEX1]], [[TMP21]]
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK4]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX_NEXT3]], i64 [[TMP2]])
-; CHECK-NEXT:    [[TMP22:%.*]] = xor <vscale x 4 x i1> [[ACTIVE_LANE_MASK4]], shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i32 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer)
+; CHECK-NEXT:    [[INDEX_NEXT2]] = add i64 [[INDEX1]], [[TMP21]]
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX_NEXT2]], i64 [[TMP2]])
+; CHECK-NEXT:    [[TMP22:%.*]] = 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, i32 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:    [[TMP23:%.*]] = extractelement <vscale x 4 x i1> [[TMP22]], i32 0
 ; CHECK-NEXT:    br i1 [[TMP23]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
 ; CHECK:       middle.block:
 ; CHECK-NEXT:    br i1 true, label [[WHILE_END_LOOPEXIT:%.*]], label [[SCALAR_PH]]
+; CHECK:       scalar.ph:
+; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[IND_END]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
+; CHECK-NEXT:    br label [[WHILE_BODY:%.*]]
+; CHECK:       while.body:
+; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ [[INDEX_NEXT:%.*]], [[WHILE_BODY]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
+; CHECK-NEXT:    [[GEP1:%.*]] = getelementptr i32, i32* [[SRC]], i64 [[INDEX]]
+; CHECK-NEXT:    [[VAL:%.*]] = load i32, i32* [[GEP1]], align 4
+; CHECK-NEXT:    [[GEP2:%.*]] = getelementptr i32, i32* [[DST]], i64 [[INDEX]]
+; CHECK-NEXT:    store i32 [[VAL]], i32* [[GEP2]], align 4
+; CHECK-NEXT:    [[INDEX_NEXT]] = add nsw i64 [[INDEX]], 4
+; CHECK-NEXT:    [[CMP10:%.*]] = icmp ult i64 [[INDEX_NEXT]], [[N]]
+; CHECK-NEXT:    br i1 [[CMP10]], label [[WHILE_BODY]], label [[WHILE_END_LOOPEXIT]], !llvm.loop [[LOOP9:![0-9]+]]
+; CHECK:       while.end.loopexit:
+; CHECK-NEXT:    ret void
 ;
 entry:
   br label %while.body
@@ -238,10 +291,10 @@ define void @simple_gather_scatter(i32* noalias %dst, i32* noalias %src, i32* no
 ; CHECK-LABEL: @simple_gather_scatter(
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[UMAX:%.*]] = call i64 @llvm.umax.i64(i64 [[N:%.*]], i64 1)
-; CHECK-NEXT:    [[TMP2:%.*]] = sub i64 -1, [[UMAX]]
-; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 4
-; CHECK-NEXT:    [[TMP3:%.*]] = icmp ult i64 [[TMP2]], [[TMP1]]
+; CHECK-NEXT:    [[TMP0:%.*]] = sub i64 -1, [[UMAX]]
+; CHECK-NEXT:    [[TMP1:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP2:%.*]] = mul i64 [[TMP1]], 4
+; CHECK-NEXT:    [[TMP3:%.*]] = icmp ult i64 [[TMP0]], [[TMP2]]
 ; CHECK-NEXT:    br i1 [[TMP3]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
 ; CHECK:       vector.ph:
 ; CHECK-NEXT:    [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
@@ -252,29 +305,45 @@ define void @simple_gather_scatter(i32* noalias %dst, i32* noalias %src, i32* no
 ; CHECK-NEXT:    [[N_RND_UP:%.*]] = add i64 [[UMAX]], [[TMP8]]
 ; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP5]]
 ; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 0, i64 [[UMAX]])
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK_ENTRY:%.*]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 0, i64 [[UMAX]])
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
-; CHECK-NEXT:    [[INDEX1:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT3:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK2:%.*]] = phi <vscale x 4 x i1> [ [[ACTIVE_LANE_MASK]], [[VECTOR_PH]] ], [ [[ACTIVE_LANE_MASK4:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[INDEX1:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT2:%.*]], [[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:    [[TMP9:%.*]] = add i64 [[INDEX1]], 0
 ; CHECK-NEXT:    [[TMP10:%.*]] = getelementptr i32, i32* [[IND:%.*]], i64 [[TMP9]]
 ; CHECK-NEXT:    [[TMP11:%.*]] = getelementptr i32, i32* [[TMP10]], i32 0
 ; CHECK-NEXT:    [[TMP12:%.*]] = bitcast i32* [[TMP11]] to <vscale x 4 x i32>*
-; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 4 x i32> @llvm.masked.load.nxv4i32.p0nxv4i32(<vscale x 4 x i32>* [[TMP12]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK2]], <vscale x 4 x i32> poison)
+; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 4 x i32> @llvm.masked.load.nxv4i32.p0nxv4i32(<vscale x 4 x i32>* [[TMP12]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x i32> poison)
 ; CHECK-NEXT:    [[TMP13:%.*]] = getelementptr i32, i32* [[SRC:%.*]], <vscale x 4 x i32> [[WIDE_MASKED_LOAD]]
-; CHECK-NEXT:    [[WIDE_MASKED_GATHER:%.*]] = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32.nxv4p0i32(<vscale x 4 x i32*> [[TMP13]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK2]], <vscale x 4 x i32> undef)
+; CHECK-NEXT:    [[WIDE_MASKED_GATHER:%.*]] = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32.nxv4p0i32(<vscale x 4 x i32*> [[TMP13]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x i32> undef)
 ; CHECK-NEXT:    [[TMP14:%.*]] = getelementptr i32, i32* [[DST:%.*]], <vscale x 4 x i32> [[WIDE_MASKED_LOAD]]
-; CHECK-NEXT:    call void @llvm.masked.scatter.nxv4i32.nxv4p0i32(<vscale x 4 x i32> [[WIDE_MASKED_GATHER]], <vscale x 4 x i32*> [[TMP14]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK2]])
+; CHECK-NEXT:    call void @llvm.masked.scatter.nxv4i32.nxv4p0i32(<vscale x 4 x i32> [[WIDE_MASKED_GATHER]], <vscale x 4 x i32*> [[TMP14]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]])
 ; CHECK-NEXT:    [[TMP15:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP16:%.*]] = mul i64 [[TMP15]], 4
-; CHECK-NEXT:    [[INDEX_NEXT3]] = add i64 [[INDEX1]], [[TMP16]]
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK4]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX_NEXT3]], i64 [[UMAX]])
-; CHECK-NEXT:    [[TMP17:%.*]] = xor <vscale x 4 x i1> [[ACTIVE_LANE_MASK4]], shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i32 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer)
+; CHECK-NEXT:    [[INDEX_NEXT2]] = add i64 [[INDEX1]], [[TMP16]]
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX_NEXT2]], i64 [[UMAX]])
+; CHECK-NEXT:    [[TMP17:%.*]] = 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, i32 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer)
 ; CHECK-NEXT:    [[TMP18:%.*]] = extractelement <vscale x 4 x i1> [[TMP17]], i32 0
 ; CHECK-NEXT:    br i1 [[TMP18]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP10:![0-9]+]]
 ; CHECK:       middle.block:
 ; CHECK-NEXT:    br i1 true, label [[WHILE_END_LOOPEXIT:%.*]], label [[SCALAR_PH]]
+; CHECK:       scalar.ph:
+; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
+; CHECK-NEXT:    br label [[WHILE_BODY:%.*]]
+; CHECK:       while.body:
+; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ [[INDEX_NEXT:%.*]], [[WHILE_BODY]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
+; CHECK-NEXT:    [[GEP1:%.*]] = getelementptr i32, i32* [[IND]], i64 [[INDEX]]
+; CHECK-NEXT:    [[IND_VAL:%.*]] = load i32, i32* [[GEP1]], align 4
+; CHECK-NEXT:    [[GEP2:%.*]] = getelementptr i32, i32* [[SRC]], i32 [[IND_VAL]]
+; CHECK-NEXT:    [[VAL:%.*]] = load i32, i32* [[GEP2]], align 4
+; CHECK-NEXT:    [[GEP3:%.*]] = getelementptr i32, i32* [[DST]], i32 [[IND_VAL]]
+; CHECK-NEXT:    store i32 [[VAL]], i32* [[GEP3]], align 4
+; CHECK-NEXT:    [[INDEX_NEXT]] = add nsw i64 [[INDEX]], 1
+; CHECK-NEXT:    [[CMP10:%.*]] = icmp ult i64 [[INDEX_NEXT]], [[N]]
+; CHECK-NEXT:    br i1 [[CMP10]], label [[WHILE_BODY]], label [[WHILE_END_LOOPEXIT]], !llvm.loop [[LOOP11:![0-9]+]]
+; CHECK:       while.end.loopexit:
+; CHECK-NEXT:    ret void
 ;
 entry:
   br label %while.body
@@ -301,10 +370,10 @@ while.end.loopexit:                               ; preds = %while.body
 define void @uniform_load(i32* noalias %dst, i32* noalias readonly %src, i64 %n) #0 {
 ; CHECK-LABEL: @uniform_load(
 ; CHECK-NEXT:  entry:
-; CHECK-NEXT:    [[TMP2:%.*]] = sub i64 -1, [[N:%.*]]
-; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 4
-; CHECK-NEXT:    [[TMP3:%.*]] = icmp ult i64 [[TMP2]], [[TMP1]]
+; CHECK-NEXT:    [[TMP0:%.*]] = sub i64 -1, [[N:%.*]]
+; CHECK-NEXT:    [[TMP1:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP2:%.*]] = mul i64 [[TMP1]], 4
+; CHECK-NEXT:    [[TMP3:%.*]] = icmp ult i64 [[TMP0]], [[TMP2]]
 ; CHECK-NEXT:    br i1 [[TMP3]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
 ; CHECK:       vector.ph:
 ; CHECK-NEXT:    [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
@@ -315,11 +384,11 @@ define void @uniform_load(i32* noalias %dst, i32* noalias readonly %src, i64 %n)
 ; CHECK-NEXT:    [[N_RND_UP:%.*]] = add i64 [[N]], [[TMP8]]
 ; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP5]]
 ; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 0, i64 [[N]])
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK_ENTRY:%.*]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 0, i64 [[N]])
 ; 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_MASK1:%.*]] = phi <vscale x 4 x i1> [ [[ACTIVE_LANE_MASK]], [[VECTOR_PH]] ], [ [[ACTIVE_LANE_MASK2:%.*]], [[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:    [[TMP9:%.*]] = add i64 [[INDEX]], 0
 ; CHECK-NEXT:    [[TMP10:%.*]] = load i32, i32* [[SRC:%.*]], align 4
 ; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 4 x i32> poison, i32 [[TMP10]], i32 0
@@ -327,16 +396,29 @@ define void @uniform_load(i32* noalias %dst, i32* noalias readonly %src, i64 %n)
 ; CHECK-NEXT:    [[TMP11:%.*]] = getelementptr inbounds i32, i32* [[DST:%.*]], i64 [[TMP9]]
 ; CHECK-NEXT:    [[TMP12:%.*]] = getelementptr inbounds i32, i32* [[TMP11]], i32 0
 ; CHECK-NEXT:    [[TMP13:%.*]] = bitcast i32* [[TMP12]] to <vscale x 4 x i32>*
-; CHECK-NEXT:    call void @llvm.masked.store.nxv4i32.p0nxv4i32(<vscale x 4 x i32> [[BROADCAST_SPLAT]], <vscale x 4 x i32>* [[TMP13]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK1]])
+; CHECK-NEXT:    call void @llvm.masked.store.nxv4i32.p0nxv4i32(<vscale x 4 x i32> [[BROADCAST_SPLAT]], <vscale x 4 x i32>* [[TMP13]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]])
 ; CHECK-NEXT:    [[TMP14:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP15:%.*]] = mul i64 [[TMP14]], 4
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], [[TMP15]]
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK2]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX_NEXT]], i64 [[N]])
-; CHECK-NEXT:    [[TMP16:%.*]] = xor <vscale x 4 x i1> [[ACTIVE_LANE_MASK2]], shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i32 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer)
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX_NEXT]], i64 [[N]])
+; CHECK-NEXT:    [[TMP16:%.*]] = 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, i32 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer)
 ; CHECK-NEXT:    [[TMP17:%.*]] = extractelement <vscale x 4 x i1> [[TMP16]], i32 0
 ; CHECK-NEXT:    br i1 [[TMP17]], 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:       scalar.ph:
+; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
+; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
+; CHECK:       for.body:
+; CHECK-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ]
+; CHECK-NEXT:    [[VAL:%.*]] = load i32, i32* [[SRC]], align 4
+; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[DST]], i64 [[INDVARS_IV]]
+; CHECK-NEXT:    store i32 [[VAL]], i32* [[ARRAYIDX]], align 4
+; CHECK-NEXT:    [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
+; CHECK-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], [[N]]
+; CHECK-NEXT:    br i1 [[EXITCOND_NOT]], label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP13:![0-9]+]]
+; CHECK:       for.end:
+; CHECK-NEXT:    ret void
 ;
 
 entry:
@@ -363,10 +445,10 @@ for.end:                                          ; preds = %for.body, %entry
 define void @cond_uniform_load(i32* noalias %dst, i32* noalias readonly %src, i32* noalias readonly %cond, i64 %n) #0 {
 ; CHECK-LABEL: @cond_uniform_load(
 ; CHECK-NEXT:  entry:
-; CHECK-NEXT:    [[TMP2:%.*]] = sub i64 -1, [[N:%.*]]
-; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 4
-; CHECK-NEXT:    [[TMP3:%.*]] = icmp ult i64 [[TMP2]], [[TMP1]]
+; CHECK-NEXT:    [[TMP0:%.*]] = sub i64 -1, [[N:%.*]]
+; CHECK-NEXT:    [[TMP1:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP2:%.*]] = mul i64 [[TMP1]], 4
+; CHECK-NEXT:    [[TMP3:%.*]] = icmp ult i64 [[TMP0]], [[TMP2]]
 ; CHECK-NEXT:    br i1 [[TMP3]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
 ; CHECK:       vector.ph:
 ; CHECK-NEXT:    [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
@@ -377,23 +459,23 @@ define void @cond_uniform_load(i32* noalias %dst, i32* noalias readonly %src, i3
 ; CHECK-NEXT:    [[N_RND_UP:%.*]] = add i64 [[N]], [[TMP8]]
 ; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP5]]
 ; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 0, i64 [[N]])
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK_ENTRY:%.*]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 0, i64 [[N]])
 ; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 4 x i32*> poison, i32* [[SRC:%.*]], i32 0
 ; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 4 x i32*> [[BROADCAST_SPLATINSERT]], <vscale x 4 x i32*> poison, <vscale x 4 x i32> zeroinitializer
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
-; CHECK-NEXT:    [[INDEX1:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT3:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK2:%.*]] = phi <vscale x 4 x i1> [ [[ACTIVE_LANE_MASK]], [[VECTOR_PH]] ], [ [[ACTIVE_LANE_MASK4:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[INDEX1:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT2:%.*]], [[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:    [[TMP9:%.*]] = add i64 [[INDEX1]], 0
 ; CHECK-NEXT:    [[TMP10:%.*]] = getelementptr inbounds i32, i32* [[COND:%.*]], i64 [[TMP9]]
 ; CHECK-NEXT:    [[TMP11:%.*]] = getelementptr inbounds i32, i32* [[TMP10]], i32 0
 ; CHECK-NEXT:    [[TMP12:%.*]] = bitcast i32* [[TMP11]] to <vscale x 4 x i32>*
-; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 4 x i32> @llvm.masked.load.nxv4i32.p0nxv4i32(<vscale x 4 x i32>* [[TMP12]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK2]], <vscale x 4 x i32> poison)
+; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 4 x i32> @llvm.masked.load.nxv4i32.p0nxv4i32(<vscale x 4 x i32>* [[TMP12]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x i32> poison)
 ; CHECK-NEXT:    [[TMP13:%.*]] = icmp eq <vscale x 4 x i32> [[WIDE_MASKED_LOAD]], zeroinitializer
 ; CHECK-NEXT:    [[TMP14:%.*]] = xor <vscale x 4 x i1> [[TMP13]], shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i32 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer)
-; CHECK-NEXT:    [[TMP15:%.*]] = select <vscale x 4 x i1> [[ACTIVE_LANE_MASK2]], <vscale x 4 x i1> [[TMP14]], <vscale x 4 x i1> zeroinitializer
+; CHECK-NEXT:    [[TMP15:%.*]] = select <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x i1> [[TMP14]], <vscale x 4 x i1> zeroinitializer
 ; CHECK-NEXT:    [[WIDE_MASKED_GATHER:%.*]] = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32.nxv4p0i32(<vscale x 4 x i32*> [[BROADCAST_SPLAT]], i32 4, <vscale x 4 x i1> [[TMP15]], <vscale x 4 x i32> undef)
-; CHECK-NEXT:    [[TMP16:%.*]] = select <vscale x 4 x i1> [[ACTIVE_LANE_MASK2]], <vscale x 4 x i1> [[TMP13]], <vscale x 4 x i1> zeroinitializer
+; CHECK-NEXT:    [[TMP16:%.*]] = select <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x i1> [[TMP13]], <vscale x 4 x i1> zeroinitializer
 ; CHECK-NEXT:    [[PREDPHI:%.*]] = select <vscale x 4 x i1> [[TMP16]], <vscale x 4 x i32> zeroinitializer, <vscale x 4 x i32> [[WIDE_MASKED_GATHER]]
 ; CHECK-NEXT:    [[TMP17:%.*]] = getelementptr inbounds i32, i32* [[DST:%.*]], i64 [[TMP9]]
 ; CHECK-NEXT:    [[TMP18:%.*]] = or <vscale x 4 x i1> [[TMP15]], [[TMP16]]
@@ -402,13 +484,34 @@ define void @cond_uniform_load(i32* noalias %dst, i32* noalias readonly %src, i3
 ; CHECK-NEXT:    call void @llvm.masked.store.nxv4i32.p0nxv4i32(<vscale x 4 x i32> [[PREDPHI]], <vscale x 4 x i32>* [[TMP20]], i32 4, <vscale x 4 x i1> [[TMP18]])
 ; CHECK-NEXT:    [[TMP21:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP22:%.*]] = mul i64 [[TMP21]], 4
-; CHECK-NEXT:    [[INDEX_NEXT3]] = add i64 [[INDEX1]], [[TMP22]]
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK4]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX_NEXT3]], i64 [[N]])
-; CHECK-NEXT:    [[TMP23:%.*]] = xor <vscale x 4 x i1> [[ACTIVE_LANE_MASK4]], shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i32 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer)
+; CHECK-NEXT:    [[INDEX_NEXT2]] = add i64 [[INDEX1]], [[TMP22]]
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX_NEXT2]], i64 [[N]])
+; CHECK-NEXT:    [[TMP23:%.*]] = 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, i32 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer)
 ; CHECK-NEXT:    [[TMP24:%.*]] = extractelement <vscale x 4 x i1> [[TMP23]], i32 0
 ; CHECK-NEXT:    br i1 [[TMP24]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP14:![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:    br label [[FOR_BODY:%.*]]
+; CHECK:       for.body:
+; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ [[INDEX_NEXT:%.*]], [[IF_END:%.*]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
+; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[COND]], i64 [[INDEX]]
+; CHECK-NEXT:    [[TMP25:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
+; CHECK-NEXT:    [[TOBOOL_NOT:%.*]] = icmp eq i32 [[TMP25]], 0
+; CHECK-NEXT:    br i1 [[TOBOOL_NOT]], label [[IF_END]], label [[IF_THEN:%.*]]
+; CHECK:       if.then:
+; CHECK-NEXT:    [[TMP26:%.*]] = load i32, i32* [[SRC]], align 4
+; CHECK-NEXT:    br label [[IF_END]]
+; CHECK:       if.end:
+; CHECK-NEXT:    [[VAL_0:%.*]] = phi i32 [ [[TMP26]], [[IF_THEN]] ], [ 0, [[FOR_BODY]] ]
+; CHECK-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds i32, i32* [[DST]], i64 [[INDEX]]
+; CHECK-NEXT:    store i32 [[VAL_0]], i32* [[ARRAYIDX1]], align 4
+; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 1
+; CHECK-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N]]
+; CHECK-NEXT:    br i1 [[EXITCOND_NOT]], label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP15:![0-9]+]]
+; CHECK:       for.end:
+; CHECK-NEXT:    ret void
 ;
 
 entry:
@@ -443,10 +546,10 @@ for.end:                                          ; preds = %for.inc, %entry
 define void @uniform_store(i32* noalias %dst, i32* noalias readonly %src, i64 %n) #0 {
 ; CHECK-LABEL: @uniform_store(
 ; CHECK-NEXT:  entry:
-; CHECK-NEXT:    [[TMP2:%.*]] = sub i64 -1, [[N:%.*]]
-; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 4
-; CHECK-NEXT:    [[TMP3:%.*]] = icmp ult i64 [[TMP2]], [[TMP1]]
+; CHECK-NEXT:    [[TMP0:%.*]] = sub i64 -1, [[N:%.*]]
+; CHECK-NEXT:    [[TMP1:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP2:%.*]] = mul i64 [[TMP1]], 4
+; CHECK-NEXT:    [[TMP3:%.*]] = icmp ult i64 [[TMP0]], [[TMP2]]
 ; CHECK-NEXT:    br i1 [[TMP3]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
 ; CHECK:       vector.ph:
 ; CHECK-NEXT:    [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
@@ -457,28 +560,41 @@ define void @uniform_store(i32* noalias %dst, i32* noalias readonly %src, i64 %n
 ; CHECK-NEXT:    [[N_RND_UP:%.*]] = add i64 [[N]], [[TMP8]]
 ; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP5]]
 ; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 0, i64 [[N]])
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK_ENTRY:%.*]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 0, i64 [[N]])
 ; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 4 x i32*> poison, i32* [[DST:%.*]], i32 0
 ; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 4 x i32*> [[BROADCAST_SPLATINSERT]], <vscale x 4 x i32*> 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_MASK1:%.*]] = phi <vscale x 4 x i1> [ [[ACTIVE_LANE_MASK]], [[VECTOR_PH]] ], [ [[ACTIVE_LANE_MASK2:%.*]], [[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:    [[TMP9:%.*]] = add i64 [[INDEX]], 0
 ; CHECK-NEXT:    [[TMP10:%.*]] = getelementptr inbounds i32, i32* [[SRC:%.*]], i64 [[TMP9]]
 ; CHECK-NEXT:    [[TMP11:%.*]] = getelementptr inbounds i32, i32* [[TMP10]], i32 0
 ; CHECK-NEXT:    [[TMP12:%.*]] = bitcast i32* [[TMP11]] to <vscale x 4 x i32>*
-; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 4 x i32> @llvm.masked.load.nxv4i32.p0nxv4i32(<vscale x 4 x i32>* [[TMP12]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK1]], <vscale x 4 x i32> poison)
-; CHECK-NEXT:    call void @llvm.masked.scatter.nxv4i32.nxv4p0i32(<vscale x 4 x i32> [[WIDE_MASKED_LOAD]], <vscale x 4 x i32*> [[BROADCAST_SPLAT]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK1]])
+; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 4 x i32> @llvm.masked.load.nxv4i32.p0nxv4i32(<vscale x 4 x i32>* [[TMP12]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x i32> poison)
+; CHECK-NEXT:    call void @llvm.masked.scatter.nxv4i32.nxv4p0i32(<vscale x 4 x i32> [[WIDE_MASKED_LOAD]], <vscale x 4 x i32*> [[BROADCAST_SPLAT]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]])
 ; CHECK-NEXT:    [[TMP13:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP14:%.*]] = mul i64 [[TMP13]], 4
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], [[TMP14]]
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK2]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX_NEXT]], i64 [[N]])
-; CHECK-NEXT:    [[TMP15:%.*]] = xor <vscale x 4 x i1> [[ACTIVE_LANE_MASK2]], shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i32 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer)
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX_NEXT]], i64 [[N]])
+; CHECK-NEXT:    [[TMP15:%.*]] = 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, i32 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer)
 ; CHECK-NEXT:    [[TMP16:%.*]] = extractelement <vscale x 4 x i1> [[TMP15]], i32 0
 ; CHECK-NEXT:    br i1 [[TMP16]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP16:![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:    br label [[FOR_BODY:%.*]]
+; CHECK:       for.body:
+; CHECK-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ]
+; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[SRC]], i64 [[INDVARS_IV]]
+; CHECK-NEXT:    [[VAL:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
+; CHECK-NEXT:    store i32 [[VAL]], i32* [[DST]], align 4
+; CHECK-NEXT:    [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
+; CHECK-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], [[N]]
+; CHECK-NEXT:    br i1 [[EXITCOND_NOT]], label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP17:![0-9]+]]
+; CHECK:       for.end:
+; CHECK-NEXT:    ret void
 ;
 
 entry:
@@ -502,10 +618,10 @@ define void @simple_fdiv(float* noalias %dst, float* noalias %src, i64 %n) #0 {
 ; CHECK-LABEL: @simple_fdiv(
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[UMAX:%.*]] = call i64 @llvm.umax.i64(i64 [[N:%.*]], i64 1)
-; CHECK-NEXT:    [[TMP2:%.*]] = sub i64 -1, [[UMAX]]
-; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 4
-; CHECK-NEXT:    [[TMP3:%.*]] = icmp ult i64 [[TMP2]], [[TMP1]]
+; CHECK-NEXT:    [[TMP0:%.*]] = sub i64 -1, [[UMAX]]
+; CHECK-NEXT:    [[TMP1:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP2:%.*]] = mul i64 [[TMP1]], 4
+; CHECK-NEXT:    [[TMP3:%.*]] = icmp ult i64 [[TMP0]], [[TMP2]]
 ; CHECK-NEXT:    br i1 [[TMP3]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
 ; CHECK:       vector.ph:
 ; CHECK-NEXT:    [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
@@ -516,32 +632,48 @@ define void @simple_fdiv(float* noalias %dst, float* noalias %src, i64 %n) #0 {
 ; CHECK-NEXT:    [[N_RND_UP:%.*]] = add i64 [[UMAX]], [[TMP8]]
 ; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], [[TMP5]]
 ; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK:%.*]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 0, i64 [[UMAX]])
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK_ENTRY:%.*]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 0, i64 [[UMAX]])
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
-; CHECK-NEXT:    [[INDEX1:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT4:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK2:%.*]] = phi <vscale x 4 x i1> [ [[ACTIVE_LANE_MASK]], [[VECTOR_PH]] ], [ [[ACTIVE_LANE_MASK5:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[INDEX1:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT3:%.*]], [[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:    [[TMP9:%.*]] = add i64 [[INDEX1]], 0
 ; CHECK-NEXT:    [[TMP10:%.*]] = getelementptr float, float* [[SRC:%.*]], i64 [[TMP9]]
 ; CHECK-NEXT:    [[TMP11:%.*]] = getelementptr float, float* [[DST:%.*]], i64 [[TMP9]]
 ; CHECK-NEXT:    [[TMP12:%.*]] = getelementptr float, float* [[TMP10]], i32 0
 ; CHECK-NEXT:    [[TMP13:%.*]] = bitcast float* [[TMP12]] to <vscale x 4 x float>*
-; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 4 x float> @llvm.masked.load.nxv4f32.p0nxv4f32(<vscale x 4 x float>* [[TMP13]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK2]], <vscale x 4 x float> poison)
+; CHECK-NEXT:    [[WIDE_MASKED_LOAD:%.*]] = call <vscale x 4 x float> @llvm.masked.load.nxv4f32.p0nxv4f32(<vscale x 4 x float>* [[TMP13]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x float> poison)
 ; CHECK-NEXT:    [[TMP14:%.*]] = getelementptr float, float* [[TMP11]], i32 0
 ; CHECK-NEXT:    [[TMP15:%.*]] = bitcast float* [[TMP14]] to <vscale x 4 x float>*
-; CHECK-NEXT:    [[WIDE_MASKED_LOAD3:%.*]] = call <vscale x 4 x float> @llvm.masked.load.nxv4f32.p0nxv4f32(<vscale x 4 x float>* [[TMP15]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK2]], <vscale x 4 x float> poison)
-; CHECK-NEXT:    [[TMP16:%.*]] = fdiv <vscale x 4 x float> [[WIDE_MASKED_LOAD]], [[WIDE_MASKED_LOAD3]]
+; CHECK-NEXT:    [[WIDE_MASKED_LOAD2:%.*]] = call <vscale x 4 x float> @llvm.masked.load.nxv4f32.p0nxv4f32(<vscale x 4 x float>* [[TMP15]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]], <vscale x 4 x float> poison)
+; CHECK-NEXT:    [[TMP16:%.*]] = fdiv <vscale x 4 x float> [[WIDE_MASKED_LOAD]], [[WIDE_MASKED_LOAD2]]
 ; CHECK-NEXT:    [[TMP17:%.*]] = bitcast float* [[TMP14]] to <vscale x 4 x float>*
-; CHECK-NEXT:    call void @llvm.masked.store.nxv4f32.p0nxv4f32(<vscale x 4 x float> [[TMP16]], <vscale x 4 x float>* [[TMP17]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK2]])
+; CHECK-NEXT:    call void @llvm.masked.store.nxv4f32.p0nxv4f32(<vscale x 4 x float> [[TMP16]], <vscale x 4 x float>* [[TMP17]], i32 4, <vscale x 4 x i1> [[ACTIVE_LANE_MASK]])
 ; CHECK-NEXT:    [[TMP18:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP19:%.*]] = mul i64 [[TMP18]], 4
-; CHECK-NEXT:    [[INDEX_NEXT4]] = add i64 [[INDEX1]], [[TMP19]]
-; CHECK-NEXT:    [[ACTIVE_LANE_MASK5]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX_NEXT4]], i64 [[UMAX]])
-; CHECK-NEXT:    [[TMP20:%.*]] = xor <vscale x 4 x i1> [[ACTIVE_LANE_MASK5]], shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i32 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer)
+; CHECK-NEXT:    [[INDEX_NEXT3]] = add i64 [[INDEX1]], [[TMP19]]
+; CHECK-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 [[INDEX_NEXT3]], i64 [[UMAX]])
+; CHECK-NEXT:    [[TMP20:%.*]] = 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, i32 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer)
 ; CHECK-NEXT:    [[TMP21:%.*]] = extractelement <vscale x 4 x i1> [[TMP20]], i32 0
 ; CHECK-NEXT:    br i1 [[TMP21]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP18:![0-9]+]]
 ; CHECK:       middle.block:
 ; CHECK-NEXT:    br i1 true, label [[WHILE_END_LOOPEXIT:%.*]], label [[SCALAR_PH]]
+; CHECK:       scalar.ph:
+; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
+; CHECK-NEXT:    br label [[WHILE_BODY:%.*]]
+; CHECK:       while.body:
+; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ [[INDEX_NEXT:%.*]], [[WHILE_BODY]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
+; CHECK-NEXT:    [[GEP1:%.*]] = getelementptr float, float* [[SRC]], i64 [[INDEX]]
+; CHECK-NEXT:    [[GEP2:%.*]] = getelementptr float, float* [[DST]], i64 [[INDEX]]
+; CHECK-NEXT:    [[VAL1:%.*]] = load float, float* [[GEP1]], align 4
+; CHECK-NEXT:    [[VAL2:%.*]] = load float, float* [[GEP2]], align 4
+; CHECK-NEXT:    [[RES:%.*]] = fdiv float [[VAL1]], [[VAL2]]
+; CHECK-NEXT:    store float [[RES]], float* [[GEP2]], align 4
+; CHECK-NEXT:    [[INDEX_NEXT]] = add nsw i64 [[INDEX]], 1
+; CHECK-NEXT:    [[CMP10:%.*]] = icmp ult i64 [[INDEX_NEXT]], [[N]]
+; CHECK-NEXT:    br i1 [[CMP10]], label [[WHILE_BODY]], label [[WHILE_END_LOOPEXIT]], !llvm.loop [[LOOP19:![0-9]+]]
+; CHECK:       while.end.loopexit:
+; CHECK-NEXT:    ret void
 ;
 entry:
   br label %while.body
@@ -568,7 +700,21 @@ while.end.loopexit:                               ; preds = %while.body
 ; divides for scalable vectors we just don't bother vectorizing.
 define void @simple_idiv(i32* noalias %dst, i32* noalias %src, i64 %n) #0 {
 ; CHECK-LABEL: @simple_idiv(
-; CHECK-NOT:   vector.body
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    br label [[WHILE_BODY:%.*]]
+; CHECK:       while.body:
+; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ [[INDEX_NEXT:%.*]], [[WHILE_BODY]] ], [ 0, [[ENTRY:%.*]] ]
+; CHECK-NEXT:    [[GEP1:%.*]] = getelementptr i32, i32* [[SRC:%.*]], i64 [[INDEX]]
+; CHECK-NEXT:    [[GEP2:%.*]] = getelementptr i32, i32* [[DST:%.*]], i64 [[INDEX]]
+; CHECK-NEXT:    [[VAL1:%.*]] = load i32, i32* [[GEP1]], align 4
+; CHECK-NEXT:    [[VAL2:%.*]] = load i32, i32* [[GEP2]], align 4
+; CHECK-NEXT:    [[RES:%.*]] = udiv i32 [[VAL1]], [[VAL2]]
+; CHECK-NEXT:    store i32 [[RES]], i32* [[GEP2]], align 4
+; CHECK-NEXT:    [[INDEX_NEXT]] = add nsw i64 [[INDEX]], 1
+; CHECK-NEXT:    [[CMP10:%.*]] = icmp ult i64 [[INDEX_NEXT]], [[N:%.*]]
+; CHECK-NEXT:    br i1 [[CMP10]], label [[WHILE_BODY]], label [[WHILE_END_LOOPEXIT:%.*]], !llvm.loop [[LOOP20:![0-9]+]]
+; CHECK:       while.end.loopexit:
+; CHECK-NEXT:    ret void
 ;
 entry:
   br label %while.body


        


More information about the llvm-commits mailing list