[LAA] Add command line flag to disable unit stride speculation

This is purely so that we can expose and work through downstream codegen issues.  My intention is to see if we can get this disabled by default, but that requires fixing a bunch of downstream issues first.

diff --git a/llvm/lib/Analysis/LoopAccessAnalysis.cpp b/llvm/lib/Analysis/LoopAccessAnalysis.cpp
index c2cdd3c..351e090 100644 (file)
--- a/llvm/lib/Analysis/LoopAccessAnalysis.cpp
+++ b/llvm/lib/Analysis/LoopAccessAnalysis.cpp
@@ -137,6 +137,11 @@ static cl::opt<unsigned> MaxForkedSCEVDepth(
     cl::desc("Maximum recursion depth when finding forked SCEVs (default = 5)"),
     cl::init(5));
 
+static cl::opt<bool> SpeculateUnitStride(
+    "laa-speculate-unit-stride", cl::Hidden,
+    cl::desc("Speculate that non-constant strides are unit in LAA"),
+    cl::init(true));
+
 bool VectorizerParams::isInterleaveForced() {
   return ::VectorizationInterleave.getNumOccurrences() > 0;
 }
@@ -2694,6 +2699,11 @@ void LoopAccessInfo::collectStridedAccess(Value *MemAccess) {
                        "versioning:");
   LLVM_DEBUG(dbgs() << "  Ptr: " << *Ptr << " Stride: " << *Stride << "\n");
 
+  if (!SpeculateUnitStride) {
+    LLVM_DEBUG(dbgs() << "  Chose not to due to -laa-speculate-unit-stride\n");
+    return;
+  }
+
   // Avoid adding the "Stride == 1" predicate when we know that
   // Stride >= Trip-Count. Such a predicate will effectively optimize a single
   // or zero iteration loop, as Trip-Count <= Stride == 1.

diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/strided-accesses.ll b/llvm/test/Transforms/LoopVectorize/RISCV/strided-accesses.ll
index d44e946..4025c4e 100644 (file)
--- a/llvm/test/Transforms/LoopVectorize/RISCV/strided-accesses.ll
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/strided-accesses.ll
@@ -1,6 +1,6 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt < %s -passes=loop-vectorize -mtriple=riscv64 -mattr=+v -S | FileCheck --check-prefixes=CHECK,NOSTRIDED %s
-; RUN: opt < %s -passes=loop-vectorize -mtriple=riscv64 -mattr=+v -lv-strided-pointer-ivs=true -S | FileCheck --check-prefixes=CHECK,STRIDED %s
+; RUN: opt < %s -passes=loop-vectorize -mtriple=riscv64 -mattr=+v -lv-strided-pointer-ivs=true -laa-speculate-unit-stride=false -S | FileCheck --check-prefixes=CHECK,STRIDED %s
 
 
 define void @single_constant_stride_int_scaled(ptr %p) {
@@ -214,54 +214,70 @@ exit:
 
 
 define void @single_stride_int_scaled(ptr %p, i64 %stride) {
-; CHECK-LABEL: @single_stride_int_scaled(
-; CHECK-NEXT:  entry:
-; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 4
-; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.umax.i64(i64 8, i64 [[TMP1]])
-; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1024, [[TMP2]]
-; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_SCEVCHECK:%.*]]
-; CHECK:       vector.scevcheck:
-; CHECK-NEXT:    [[IDENT_CHECK:%.*]] = icmp ne i64 [[STRIDE:%.*]], 1
-; CHECK-NEXT:    br i1 [[IDENT_CHECK]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
-; CHECK:       vector.ph:
-; CHECK-NEXT:    [[TMP3:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP4:%.*]] = mul i64 [[TMP3]], 4
-; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP4]]
-; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 1024, [[N_MOD_VF]]
-; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
-; CHECK:       vector.body:
-; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT:    [[TMP5:%.*]] = add i64 [[INDEX]], 0
-; CHECK-NEXT:    [[TMP6:%.*]] = mul nuw nsw i64 [[TMP5]], [[STRIDE]]
-; CHECK-NEXT:    [[TMP7:%.*]] = getelementptr i32, ptr [[P:%.*]], i64 [[TMP6]]
-; CHECK-NEXT:    [[TMP8:%.*]] = getelementptr i32, ptr [[TMP7]], i32 0
-; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <vscale x 4 x i32>, ptr [[TMP8]], align 4
-; CHECK-NEXT:    [[TMP9:%.*]] = add <vscale x 4 x i32> [[WIDE_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:    store <vscale x 4 x i32> [[TMP9]], ptr [[TMP8]], align 4
-; CHECK-NEXT:    [[TMP10:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP11:%.*]] = mul i64 [[TMP10]], 4
-; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP11]]
-; CHECK-NEXT:    [[TMP12:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
-; CHECK-NEXT:    br i1 [[TMP12]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
-; CHECK:       middle.block:
-; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 1024, [[N_VEC]]
-; CHECK-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
-; CHECK:       scalar.ph:
-; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ], [ 0, [[VECTOR_SCEVCHECK]] ]
-; CHECK-NEXT:    br label [[LOOP:%.*]]
-; CHECK:       loop:
-; CHECK-NEXT:    [[I:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[NEXTI:%.*]], [[LOOP]] ]
-; CHECK-NEXT:    [[OFFSET:%.*]] = mul nuw nsw i64 [[I]], [[STRIDE]]
-; CHECK-NEXT:    [[Q0:%.*]] = getelementptr i32, ptr [[P]], i64 [[OFFSET]]
-; CHECK-NEXT:    [[X0:%.*]] = load i32, ptr [[Q0]], align 4
-; CHECK-NEXT:    [[Y0:%.*]] = add i32 [[X0]], 1
-; CHECK-NEXT:    store i32 [[Y0]], ptr [[Q0]], align 4
-; CHECK-NEXT:    [[NEXTI]] = add i64 [[I]], 1
-; CHECK-NEXT:    [[DONE:%.*]] = icmp eq i64 [[NEXTI]], 1024
-; CHECK-NEXT:    br i1 [[DONE]], label [[EXIT]], label [[LOOP]], !llvm.loop [[LOOP9:![0-9]+]]
-; CHECK:       exit:
-; CHECK-NEXT:    ret void
+; NOSTRIDED-LABEL: @single_stride_int_scaled(
+; NOSTRIDED-NEXT:  entry:
+; NOSTRIDED-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
+; NOSTRIDED-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 4
+; NOSTRIDED-NEXT:    [[TMP2:%.*]] = call i64 @llvm.umax.i64(i64 8, i64 [[TMP1]])
+; NOSTRIDED-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1024, [[TMP2]]
+; NOSTRIDED-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_SCEVCHECK:%.*]]
+; NOSTRIDED:       vector.scevcheck:
+; NOSTRIDED-NEXT:    [[IDENT_CHECK:%.*]] = icmp ne i64 [[STRIDE:%.*]], 1
+; NOSTRIDED-NEXT:    br i1 [[IDENT_CHECK]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
+; NOSTRIDED:       vector.ph:
+; NOSTRIDED-NEXT:    [[TMP3:%.*]] = call i64 @llvm.vscale.i64()
+; NOSTRIDED-NEXT:    [[TMP4:%.*]] = mul i64 [[TMP3]], 4
+; NOSTRIDED-NEXT:    [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP4]]
+; NOSTRIDED-NEXT:    [[N_VEC:%.*]] = sub i64 1024, [[N_MOD_VF]]
+; NOSTRIDED-NEXT:    br label [[VECTOR_BODY:%.*]]
+; NOSTRIDED:       vector.body:
+; NOSTRIDED-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; NOSTRIDED-NEXT:    [[TMP5:%.*]] = add i64 [[INDEX]], 0
+; NOSTRIDED-NEXT:    [[TMP6:%.*]] = mul nuw nsw i64 [[TMP5]], [[STRIDE]]
+; NOSTRIDED-NEXT:    [[TMP7:%.*]] = getelementptr i32, ptr [[P:%.*]], i64 [[TMP6]]
+; NOSTRIDED-NEXT:    [[TMP8:%.*]] = getelementptr i32, ptr [[TMP7]], i32 0
+; NOSTRIDED-NEXT:    [[WIDE_LOAD:%.*]] = load <vscale x 4 x i32>, ptr [[TMP8]], align 4
+; NOSTRIDED-NEXT:    [[TMP9:%.*]] = add <vscale x 4 x i32> [[WIDE_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)
+; NOSTRIDED-NEXT:    store <vscale x 4 x i32> [[TMP9]], ptr [[TMP8]], align 4
+; NOSTRIDED-NEXT:    [[TMP10:%.*]] = call i64 @llvm.vscale.i64()
+; NOSTRIDED-NEXT:    [[TMP11:%.*]] = mul i64 [[TMP10]], 4
+; NOSTRIDED-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP11]]
+; NOSTRIDED-NEXT:    [[TMP12:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; NOSTRIDED-NEXT:    br i1 [[TMP12]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
+; NOSTRIDED:       middle.block:
+; NOSTRIDED-NEXT:    [[CMP_N:%.*]] = icmp eq i64 1024, [[N_VEC]]
+; NOSTRIDED-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
+; NOSTRIDED:       scalar.ph:
+; NOSTRIDED-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ], [ 0, [[VECTOR_SCEVCHECK]] ]
+; NOSTRIDED-NEXT:    br label [[LOOP:%.*]]
+; NOSTRIDED:       loop:
+; NOSTRIDED-NEXT:    [[I:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[NEXTI:%.*]], [[LOOP]] ]
+; NOSTRIDED-NEXT:    [[OFFSET:%.*]] = mul nuw nsw i64 [[I]], [[STRIDE]]
+; NOSTRIDED-NEXT:    [[Q0:%.*]] = getelementptr i32, ptr [[P]], i64 [[OFFSET]]
+; NOSTRIDED-NEXT:    [[X0:%.*]] = load i32, ptr [[Q0]], align 4
+; NOSTRIDED-NEXT:    [[Y0:%.*]] = add i32 [[X0]], 1
+; NOSTRIDED-NEXT:    store i32 [[Y0]], ptr [[Q0]], align 4
+; NOSTRIDED-NEXT:    [[NEXTI]] = add i64 [[I]], 1
+; NOSTRIDED-NEXT:    [[DONE:%.*]] = icmp eq i64 [[NEXTI]], 1024
+; NOSTRIDED-NEXT:    br i1 [[DONE]], label [[EXIT]], label [[LOOP]], !llvm.loop [[LOOP9:![0-9]+]]
+; NOSTRIDED:       exit:
+; NOSTRIDED-NEXT:    ret void
+;
+; STRIDED-LABEL: @single_stride_int_scaled(
+; STRIDED-NEXT:  entry:
+; STRIDED-NEXT:    br label [[LOOP:%.*]]
+; STRIDED:       loop:
+; STRIDED-NEXT:    [[I:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[NEXTI:%.*]], [[LOOP]] ]
+; STRIDED-NEXT:    [[OFFSET:%.*]] = mul nuw nsw i64 [[I]], [[STRIDE:%.*]]
+; STRIDED-NEXT:    [[Q0:%.*]] = getelementptr i32, ptr [[P:%.*]], i64 [[OFFSET]]
+; STRIDED-NEXT:    [[X0:%.*]] = load i32, ptr [[Q0]], align 4
+; STRIDED-NEXT:    [[Y0:%.*]] = add i32 [[X0]], 1
+; STRIDED-NEXT:    store i32 [[Y0]], ptr [[Q0]], align 4
+; STRIDED-NEXT:    [[NEXTI]] = add i64 [[I]], 1
+; STRIDED-NEXT:    [[DONE:%.*]] = icmp eq i64 [[NEXTI]], 1024
+; STRIDED-NEXT:    br i1 [[DONE]], label [[EXIT:%.*]], label [[LOOP]]
+; STRIDED:       exit:
+; STRIDED-NEXT:    ret void
 ;
 entry:
   br label %loop
@@ -282,58 +298,75 @@ exit:
 }
 
 define void @single_stride_int_iv(ptr %p, i64 %stride) {
-; CHECK-LABEL: @single_stride_int_iv(
-; CHECK-NEXT:  entry:
-; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 4
-; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.umax.i64(i64 8, i64 [[TMP1]])
-; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1024, [[TMP2]]
-; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_SCEVCHECK:%.*]]
-; CHECK:       vector.scevcheck:
-; CHECK-NEXT:    [[IDENT_CHECK:%.*]] = icmp ne i64 [[STRIDE:%.*]], 1
-; CHECK-NEXT:    br i1 [[IDENT_CHECK]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
-; CHECK:       vector.ph:
-; CHECK-NEXT:    [[TMP3:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP4:%.*]] = mul i64 [[TMP3]], 4
-; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP4]]
-; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 1024, [[N_MOD_VF]]
-; CHECK-NEXT:    [[IND_END:%.*]] = mul i64 [[N_VEC]], [[STRIDE]]
-; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
-; CHECK:       vector.body:
-; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT:    [[OFFSET_IDX:%.*]] = mul i64 [[INDEX]], [[STRIDE]]
-; CHECK-NEXT:    [[TMP5:%.*]] = mul i64 0, [[STRIDE]]
-; CHECK-NEXT:    [[TMP6:%.*]] = add i64 [[OFFSET_IDX]], [[TMP5]]
-; CHECK-NEXT:    [[TMP7:%.*]] = getelementptr i32, ptr [[P:%.*]], i64 [[TMP6]]
-; CHECK-NEXT:    [[TMP8:%.*]] = getelementptr i32, ptr [[TMP7]], i32 0
-; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <vscale x 4 x i32>, ptr [[TMP8]], align 4
-; CHECK-NEXT:    [[TMP9:%.*]] = add <vscale x 4 x i32> [[WIDE_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:    store <vscale x 4 x i32> [[TMP9]], ptr [[TMP8]], align 4
-; CHECK-NEXT:    [[TMP10:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP11:%.*]] = mul i64 [[TMP10]], 4
-; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP11]]
-; CHECK-NEXT:    [[TMP12:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
-; CHECK-NEXT:    br i1 [[TMP12]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP10:![0-9]+]]
-; CHECK:       middle.block:
-; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 1024, [[N_VEC]]
-; CHECK-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
-; CHECK:       scalar.ph:
-; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ], [ 0, [[VECTOR_SCEVCHECK]] ]
-; CHECK-NEXT:    [[BC_RESUME_VAL1:%.*]] = phi i64 [ [[IND_END]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY]] ], [ 0, [[VECTOR_SCEVCHECK]] ]
-; CHECK-NEXT:    br label [[LOOP:%.*]]
-; CHECK:       loop:
-; CHECK-NEXT:    [[I:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[NEXTI:%.*]], [[LOOP]] ]
-; CHECK-NEXT:    [[OFFSET:%.*]] = phi i64 [ [[BC_RESUME_VAL1]], [[SCALAR_PH]] ], [ [[OFFSET_NEXT:%.*]], [[LOOP]] ]
-; CHECK-NEXT:    [[Q0:%.*]] = getelementptr i32, ptr [[P]], i64 [[OFFSET]]
-; CHECK-NEXT:    [[X0:%.*]] = load i32, ptr [[Q0]], align 4
-; CHECK-NEXT:    [[Y0:%.*]] = add i32 [[X0]], 1
-; CHECK-NEXT:    store i32 [[Y0]], ptr [[Q0]], align 4
-; CHECK-NEXT:    [[OFFSET_NEXT]] = add nuw nsw i64 [[OFFSET]], [[STRIDE]]
-; CHECK-NEXT:    [[NEXTI]] = add i64 [[I]], 1
-; CHECK-NEXT:    [[DONE:%.*]] = icmp eq i64 [[NEXTI]], 1024
-; CHECK-NEXT:    br i1 [[DONE]], label [[EXIT]], label [[LOOP]], !llvm.loop [[LOOP11:![0-9]+]]
-; CHECK:       exit:
-; CHECK-NEXT:    ret void
+; NOSTRIDED-LABEL: @single_stride_int_iv(
+; NOSTRIDED-NEXT:  entry:
+; NOSTRIDED-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
+; NOSTRIDED-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 4
+; NOSTRIDED-NEXT:    [[TMP2:%.*]] = call i64 @llvm.umax.i64(i64 8, i64 [[TMP1]])
+; NOSTRIDED-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1024, [[TMP2]]
+; NOSTRIDED-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_SCEVCHECK:%.*]]
+; NOSTRIDED:       vector.scevcheck:
+; NOSTRIDED-NEXT:    [[IDENT_CHECK:%.*]] = icmp ne i64 [[STRIDE:%.*]], 1
+; NOSTRIDED-NEXT:    br i1 [[IDENT_CHECK]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
+; NOSTRIDED:       vector.ph:
+; NOSTRIDED-NEXT:    [[TMP3:%.*]] = call i64 @llvm.vscale.i64()
+; NOSTRIDED-NEXT:    [[TMP4:%.*]] = mul i64 [[TMP3]], 4
+; NOSTRIDED-NEXT:    [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP4]]
+; NOSTRIDED-NEXT:    [[N_VEC:%.*]] = sub i64 1024, [[N_MOD_VF]]
+; NOSTRIDED-NEXT:    [[IND_END:%.*]] = mul i64 [[N_VEC]], [[STRIDE]]
+; NOSTRIDED-NEXT:    br label [[VECTOR_BODY:%.*]]
+; NOSTRIDED:       vector.body:
+; NOSTRIDED-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; NOSTRIDED-NEXT:    [[OFFSET_IDX:%.*]] = mul i64 [[INDEX]], [[STRIDE]]
+; NOSTRIDED-NEXT:    [[TMP5:%.*]] = mul i64 0, [[STRIDE]]
+; NOSTRIDED-NEXT:    [[TMP6:%.*]] = add i64 [[OFFSET_IDX]], [[TMP5]]
+; NOSTRIDED-NEXT:    [[TMP7:%.*]] = getelementptr i32, ptr [[P:%.*]], i64 [[TMP6]]
+; NOSTRIDED-NEXT:    [[TMP8:%.*]] = getelementptr i32, ptr [[TMP7]], i32 0
+; NOSTRIDED-NEXT:    [[WIDE_LOAD:%.*]] = load <vscale x 4 x i32>, ptr [[TMP8]], align 4
+; NOSTRIDED-NEXT:    [[TMP9:%.*]] = add <vscale x 4 x i32> [[WIDE_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)
+; NOSTRIDED-NEXT:    store <vscale x 4 x i32> [[TMP9]], ptr [[TMP8]], align 4
+; NOSTRIDED-NEXT:    [[TMP10:%.*]] = call i64 @llvm.vscale.i64()
+; NOSTRIDED-NEXT:    [[TMP11:%.*]] = mul i64 [[TMP10]], 4
+; NOSTRIDED-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP11]]
+; NOSTRIDED-NEXT:    [[TMP12:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; NOSTRIDED-NEXT:    br i1 [[TMP12]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP10:![0-9]+]]
+; NOSTRIDED:       middle.block:
+; NOSTRIDED-NEXT:    [[CMP_N:%.*]] = icmp eq i64 1024, [[N_VEC]]
+; NOSTRIDED-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
+; NOSTRIDED:       scalar.ph:
+; NOSTRIDED-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ], [ 0, [[VECTOR_SCEVCHECK]] ]
+; NOSTRIDED-NEXT:    [[BC_RESUME_VAL1:%.*]] = phi i64 [ [[IND_END]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY]] ], [ 0, [[VECTOR_SCEVCHECK]] ]
+; NOSTRIDED-NEXT:    br label [[LOOP:%.*]]
+; NOSTRIDED:       loop:
+; NOSTRIDED-NEXT:    [[I:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[NEXTI:%.*]], [[LOOP]] ]
+; NOSTRIDED-NEXT:    [[OFFSET:%.*]] = phi i64 [ [[BC_RESUME_VAL1]], [[SCALAR_PH]] ], [ [[OFFSET_NEXT:%.*]], [[LOOP]] ]
+; NOSTRIDED-NEXT:    [[Q0:%.*]] = getelementptr i32, ptr [[P]], i64 [[OFFSET]]
+; NOSTRIDED-NEXT:    [[X0:%.*]] = load i32, ptr [[Q0]], align 4
+; NOSTRIDED-NEXT:    [[Y0:%.*]] = add i32 [[X0]], 1
+; NOSTRIDED-NEXT:    store i32 [[Y0]], ptr [[Q0]], align 4
+; NOSTRIDED-NEXT:    [[OFFSET_NEXT]] = add nuw nsw i64 [[OFFSET]], [[STRIDE]]
+; NOSTRIDED-NEXT:    [[NEXTI]] = add i64 [[I]], 1
+; NOSTRIDED-NEXT:    [[DONE:%.*]] = icmp eq i64 [[NEXTI]], 1024
+; NOSTRIDED-NEXT:    br i1 [[DONE]], label [[EXIT]], label [[LOOP]], !llvm.loop [[LOOP11:![0-9]+]]
+; NOSTRIDED:       exit:
+; NOSTRIDED-NEXT:    ret void
+;
+; STRIDED-LABEL: @single_stride_int_iv(
+; STRIDED-NEXT:  entry:
+; STRIDED-NEXT:    br label [[LOOP:%.*]]
+; STRIDED:       loop:
+; STRIDED-NEXT:    [[I:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[NEXTI:%.*]], [[LOOP]] ]
+; STRIDED-NEXT:    [[OFFSET:%.*]] = phi i64 [ 0, [[ENTRY]] ], [ [[OFFSET_NEXT:%.*]], [[LOOP]] ]
+; STRIDED-NEXT:    [[Q0:%.*]] = getelementptr i32, ptr [[P:%.*]], i64 [[OFFSET]]
+; STRIDED-NEXT:    [[X0:%.*]] = load i32, ptr [[Q0]], align 4
+; STRIDED-NEXT:    [[Y0:%.*]] = add i32 [[X0]], 1
+; STRIDED-NEXT:    store i32 [[Y0]], ptr [[Q0]], align 4
+; STRIDED-NEXT:    [[OFFSET_NEXT]] = add nuw nsw i64 [[OFFSET]], [[STRIDE:%.*]]
+; STRIDED-NEXT:    [[NEXTI]] = add i64 [[I]], 1
+; STRIDED-NEXT:    [[DONE:%.*]] = icmp eq i64 [[NEXTI]], 1024
+; STRIDED-NEXT:    br i1 [[DONE]], label [[EXIT:%.*]], label [[LOOP]]
+; STRIDED:       exit:
+; STRIDED-NEXT:    ret void
 ;
 entry:
   br label %loop
@@ -391,66 +424,143 @@ exit:
 }
 
 define void @double_stride_int_scaled(ptr %p, ptr %p2, i64 %stride) {
-; CHECK-LABEL: @double_stride_int_scaled(
-; CHECK-NEXT:  entry:
-; CHECK-NEXT:    [[P3:%.*]] = ptrtoint ptr [[P:%.*]] to i64
-; CHECK-NEXT:    [[P21:%.*]] = ptrtoint ptr [[P2:%.*]] to i64
-; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 4
-; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.umax.i64(i64 16, i64 [[TMP1]])
-; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1024, [[TMP2]]
-; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_SCEVCHECK:%.*]]
-; CHECK:       vector.scevcheck:
-; CHECK-NEXT:    [[IDENT_CHECK:%.*]] = icmp ne i64 [[STRIDE:%.*]], 1
-; CHECK-NEXT:    br i1 [[IDENT_CHECK]], label [[SCALAR_PH]], label [[VECTOR_MEMCHECK:%.*]]
-; CHECK:       vector.memcheck:
-; CHECK-NEXT:    [[TMP3:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP4:%.*]] = mul i64 [[TMP3]], 4
-; CHECK-NEXT:    [[TMP5:%.*]] = mul i64 [[TMP4]], 4
-; CHECK-NEXT:    [[TMP6:%.*]] = sub i64 [[P21]], [[P3]]
-; CHECK-NEXT:    [[DIFF_CHECK:%.*]] = icmp ult i64 [[TMP6]], [[TMP5]]
-; CHECK-NEXT:    br i1 [[DIFF_CHECK]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
-; CHECK:       vector.ph:
-; CHECK-NEXT:    [[TMP7:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP8:%.*]] = mul i64 [[TMP7]], 4
-; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP8]]
-; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 1024, [[N_MOD_VF]]
-; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
-; CHECK:       vector.body:
-; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT:    [[TMP9:%.*]] = add i64 [[INDEX]], 0
-; CHECK-NEXT:    [[TMP10:%.*]] = mul nuw nsw i64 [[TMP9]], [[STRIDE]]
-; CHECK-NEXT:    [[TMP11:%.*]] = getelementptr i32, ptr [[P]], i64 [[TMP10]]
-; CHECK-NEXT:    [[TMP12:%.*]] = getelementptr i32, ptr [[TMP11]], i32 0
-; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <vscale x 4 x i32>, ptr [[TMP12]], align 4
-; CHECK-NEXT:    [[TMP13:%.*]] = add <vscale x 4 x i32> [[WIDE_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:    [[TMP14:%.*]] = getelementptr i32, ptr [[P2]], i64 [[TMP10]]
-; CHECK-NEXT:    [[TMP15:%.*]] = getelementptr i32, ptr [[TMP14]], i32 0
-; CHECK-NEXT:    store <vscale x 4 x i32> [[TMP13]], ptr [[TMP15]], align 4
-; CHECK-NEXT:    [[TMP16:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP17:%.*]] = mul i64 [[TMP16]], 4
-; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP17]]
-; CHECK-NEXT:    [[TMP18:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
-; CHECK-NEXT:    br i1 [[TMP18]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP12:![0-9]+]]
-; CHECK:       middle.block:
-; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 1024, [[N_VEC]]
-; CHECK-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
-; CHECK:       scalar.ph:
-; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ], [ 0, [[VECTOR_SCEVCHECK]] ], [ 0, [[VECTOR_MEMCHECK]] ]
-; CHECK-NEXT:    br label [[LOOP:%.*]]
-; CHECK:       loop:
-; CHECK-NEXT:    [[I:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[NEXTI:%.*]], [[LOOP]] ]
-; CHECK-NEXT:    [[OFFSET:%.*]] = mul nuw nsw i64 [[I]], [[STRIDE]]
-; CHECK-NEXT:    [[Q0:%.*]] = getelementptr i32, ptr [[P]], i64 [[OFFSET]]
-; CHECK-NEXT:    [[X0:%.*]] = load i32, ptr [[Q0]], align 4
-; CHECK-NEXT:    [[Y0:%.*]] = add i32 [[X0]], 1
-; CHECK-NEXT:    [[Q1:%.*]] = getelementptr i32, ptr [[P2]], i64 [[OFFSET]]
-; CHECK-NEXT:    store i32 [[Y0]], ptr [[Q1]], align 4
-; CHECK-NEXT:    [[NEXTI]] = add i64 [[I]], 1
-; CHECK-NEXT:    [[DONE:%.*]] = icmp eq i64 [[NEXTI]], 1024
-; CHECK-NEXT:    br i1 [[DONE]], label [[EXIT]], label [[LOOP]], !llvm.loop [[LOOP13:![0-9]+]]
-; CHECK:       exit:
-; CHECK-NEXT:    ret void
+; NOSTRIDED-LABEL: @double_stride_int_scaled(
+; NOSTRIDED-NEXT:  entry:
+; NOSTRIDED-NEXT:    [[P3:%.*]] = ptrtoint ptr [[P:%.*]] to i64
+; NOSTRIDED-NEXT:    [[P21:%.*]] = ptrtoint ptr [[P2:%.*]] to i64
+; NOSTRIDED-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
+; NOSTRIDED-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 4
+; NOSTRIDED-NEXT:    [[TMP2:%.*]] = call i64 @llvm.umax.i64(i64 16, i64 [[TMP1]])
+; NOSTRIDED-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1024, [[TMP2]]
+; NOSTRIDED-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_SCEVCHECK:%.*]]
+; NOSTRIDED:       vector.scevcheck:
+; NOSTRIDED-NEXT:    [[IDENT_CHECK:%.*]] = icmp ne i64 [[STRIDE:%.*]], 1
+; NOSTRIDED-NEXT:    br i1 [[IDENT_CHECK]], label [[SCALAR_PH]], label [[VECTOR_MEMCHECK:%.*]]
+; NOSTRIDED:       vector.memcheck:
+; NOSTRIDED-NEXT:    [[TMP3:%.*]] = call i64 @llvm.vscale.i64()
+; NOSTRIDED-NEXT:    [[TMP4:%.*]] = mul i64 [[TMP3]], 4
+; NOSTRIDED-NEXT:    [[TMP5:%.*]] = mul i64 [[TMP4]], 4
+; NOSTRIDED-NEXT:    [[TMP6:%.*]] = sub i64 [[P21]], [[P3]]
+; NOSTRIDED-NEXT:    [[DIFF_CHECK:%.*]] = icmp ult i64 [[TMP6]], [[TMP5]]
+; NOSTRIDED-NEXT:    br i1 [[DIFF_CHECK]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
+; NOSTRIDED:       vector.ph:
+; NOSTRIDED-NEXT:    [[TMP7:%.*]] = call i64 @llvm.vscale.i64()
+; NOSTRIDED-NEXT:    [[TMP8:%.*]] = mul i64 [[TMP7]], 4
+; NOSTRIDED-NEXT:    [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP8]]
+; NOSTRIDED-NEXT:    [[N_VEC:%.*]] = sub i64 1024, [[N_MOD_VF]]
+; NOSTRIDED-NEXT:    br label [[VECTOR_BODY:%.*]]
+; NOSTRIDED:       vector.body:
+; NOSTRIDED-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; NOSTRIDED-NEXT:    [[TMP9:%.*]] = add i64 [[INDEX]], 0
+; NOSTRIDED-NEXT:    [[TMP10:%.*]] = mul nuw nsw i64 [[TMP9]], [[STRIDE]]
+; NOSTRIDED-NEXT:    [[TMP11:%.*]] = getelementptr i32, ptr [[P]], i64 [[TMP10]]
+; NOSTRIDED-NEXT:    [[TMP12:%.*]] = getelementptr i32, ptr [[TMP11]], i32 0
+; NOSTRIDED-NEXT:    [[WIDE_LOAD:%.*]] = load <vscale x 4 x i32>, ptr [[TMP12]], align 4
+; NOSTRIDED-NEXT:    [[TMP13:%.*]] = add <vscale x 4 x i32> [[WIDE_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)
+; NOSTRIDED-NEXT:    [[TMP14:%.*]] = getelementptr i32, ptr [[P2]], i64 [[TMP10]]
+; NOSTRIDED-NEXT:    [[TMP15:%.*]] = getelementptr i32, ptr [[TMP14]], i32 0
+; NOSTRIDED-NEXT:    store <vscale x 4 x i32> [[TMP13]], ptr [[TMP15]], align 4
+; NOSTRIDED-NEXT:    [[TMP16:%.*]] = call i64 @llvm.vscale.i64()
+; NOSTRIDED-NEXT:    [[TMP17:%.*]] = mul i64 [[TMP16]], 4
+; NOSTRIDED-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP17]]
+; NOSTRIDED-NEXT:    [[TMP18:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; NOSTRIDED-NEXT:    br i1 [[TMP18]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP12:![0-9]+]]
+; NOSTRIDED:       middle.block:
+; NOSTRIDED-NEXT:    [[CMP_N:%.*]] = icmp eq i64 1024, [[N_VEC]]
+; NOSTRIDED-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
+; NOSTRIDED:       scalar.ph:
+; NOSTRIDED-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ], [ 0, [[VECTOR_SCEVCHECK]] ], [ 0, [[VECTOR_MEMCHECK]] ]
+; NOSTRIDED-NEXT:    br label [[LOOP:%.*]]
+; NOSTRIDED:       loop:
+; NOSTRIDED-NEXT:    [[I:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[NEXTI:%.*]], [[LOOP]] ]
+; NOSTRIDED-NEXT:    [[OFFSET:%.*]] = mul nuw nsw i64 [[I]], [[STRIDE]]
+; NOSTRIDED-NEXT:    [[Q0:%.*]] = getelementptr i32, ptr [[P]], i64 [[OFFSET]]
+; NOSTRIDED-NEXT:    [[X0:%.*]] = load i32, ptr [[Q0]], align 4
+; NOSTRIDED-NEXT:    [[Y0:%.*]] = add i32 [[X0]], 1
+; NOSTRIDED-NEXT:    [[Q1:%.*]] = getelementptr i32, ptr [[P2]], i64 [[OFFSET]]
+; NOSTRIDED-NEXT:    store i32 [[Y0]], ptr [[Q1]], align 4
+; NOSTRIDED-NEXT:    [[NEXTI]] = add i64 [[I]], 1
+; NOSTRIDED-NEXT:    [[DONE:%.*]] = icmp eq i64 [[NEXTI]], 1024
+; NOSTRIDED-NEXT:    br i1 [[DONE]], label [[EXIT]], label [[LOOP]], !llvm.loop [[LOOP13:![0-9]+]]
+; NOSTRIDED:       exit:
+; NOSTRIDED-NEXT:    ret void
+;
+; STRIDED-LABEL: @double_stride_int_scaled(
+; STRIDED-NEXT:  entry:
+; STRIDED-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
+; STRIDED-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 4
+; STRIDED-NEXT:    [[TMP2:%.*]] = call i64 @llvm.umax.i64(i64 24, i64 [[TMP1]])
+; STRIDED-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1024, [[TMP2]]
+; STRIDED-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_MEMCHECK:%.*]]
+; STRIDED:       vector.memcheck:
+; STRIDED-NEXT:    [[TMP3:%.*]] = mul i64 [[STRIDE:%.*]], 4092
+; STRIDED-NEXT:    [[SCEVGEP:%.*]] = getelementptr i8, ptr [[P2:%.*]], i64 [[TMP3]]
+; STRIDED-NEXT:    [[TMP4:%.*]] = icmp ult ptr [[P2]], [[SCEVGEP]]
+; STRIDED-NEXT:    [[UMIN:%.*]] = select i1 [[TMP4]], ptr [[P2]], ptr [[SCEVGEP]]
+; STRIDED-NEXT:    [[TMP5:%.*]] = icmp ugt ptr [[P2]], [[SCEVGEP]]
+; STRIDED-NEXT:    [[UMAX:%.*]] = select i1 [[TMP5]], ptr [[P2]], ptr [[SCEVGEP]]
+; STRIDED-NEXT:    [[SCEVGEP1:%.*]] = getelementptr i8, ptr [[UMAX]], i64 4
+; STRIDED-NEXT:    [[SCEVGEP2:%.*]] = getelementptr i8, ptr [[P:%.*]], i64 [[TMP3]]
+; STRIDED-NEXT:    [[TMP6:%.*]] = icmp ult ptr [[P]], [[SCEVGEP2]]
+; STRIDED-NEXT:    [[UMIN3:%.*]] = select i1 [[TMP6]], ptr [[P]], ptr [[SCEVGEP2]]
+; STRIDED-NEXT:    [[TMP7:%.*]] = icmp ugt ptr [[P]], [[SCEVGEP2]]
+; STRIDED-NEXT:    [[UMAX4:%.*]] = select i1 [[TMP7]], ptr [[P]], ptr [[SCEVGEP2]]
+; STRIDED-NEXT:    [[SCEVGEP5:%.*]] = getelementptr i8, ptr [[UMAX4]], i64 4
+; STRIDED-NEXT:    [[BOUND0:%.*]] = icmp ult ptr [[UMIN]], [[SCEVGEP5]]
+; STRIDED-NEXT:    [[BOUND1:%.*]] = icmp ult ptr [[UMIN3]], [[SCEVGEP1]]
+; STRIDED-NEXT:    [[FOUND_CONFLICT:%.*]] = and i1 [[BOUND0]], [[BOUND1]]
+; STRIDED-NEXT:    br i1 [[FOUND_CONFLICT]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
+; STRIDED:       vector.ph:
+; STRIDED-NEXT:    [[TMP8:%.*]] = call i64 @llvm.vscale.i64()
+; STRIDED-NEXT:    [[TMP9:%.*]] = mul i64 [[TMP8]], 4
+; STRIDED-NEXT:    [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP9]]
+; STRIDED-NEXT:    [[N_VEC:%.*]] = sub i64 1024, [[N_MOD_VF]]
+; STRIDED-NEXT:    [[TMP10:%.*]] = call <vscale x 4 x i64> @llvm.experimental.stepvector.nxv4i64()
+; STRIDED-NEXT:    [[TMP11:%.*]] = add <vscale x 4 x i64> [[TMP10]], zeroinitializer
+; STRIDED-NEXT:    [[TMP12:%.*]] = mul <vscale x 4 x i64> [[TMP11]], 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)
+; STRIDED-NEXT:    [[INDUCTION:%.*]] = add <vscale x 4 x i64> zeroinitializer, [[TMP12]]
+; STRIDED-NEXT:    [[TMP13:%.*]] = call i64 @llvm.vscale.i64()
+; STRIDED-NEXT:    [[TMP14:%.*]] = mul i64 [[TMP13]], 4
+; STRIDED-NEXT:    [[TMP15:%.*]] = mul i64 1, [[TMP14]]
+; STRIDED-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TMP15]], i64 0
+; STRIDED-NEXT:    [[DOTSPLAT:%.*]] = shufflevector <vscale x 4 x i64> [[DOTSPLATINSERT]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
+; STRIDED-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[STRIDE]], i64 0
+; STRIDED-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <vscale x 4 x i64> [[BROADCAST_SPLATINSERT]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
+; STRIDED-NEXT:    br label [[VECTOR_BODY:%.*]]
+; STRIDED:       vector.body:
+; STRIDED-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; STRIDED-NEXT:    [[VEC_IND:%.*]] = phi <vscale x 4 x i64> [ [[INDUCTION]], [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[VECTOR_BODY]] ]
+; STRIDED-NEXT:    [[TMP16:%.*]] = mul nuw nsw <vscale x 4 x i64> [[VEC_IND]], [[BROADCAST_SPLAT]]
+; STRIDED-NEXT:    [[TMP17:%.*]] = getelementptr i32, ptr [[P]], <vscale x 4 x i64> [[TMP16]]
+; STRIDED-NEXT:    [[WIDE_MASKED_GATHER:%.*]] = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32.nxv4p0(<vscale x 4 x ptr> [[TMP17]], i32 4, <vscale x 4 x i1> 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), <vscale x 4 x i32> poison), !alias.scope !8
+; STRIDED-NEXT:    [[TMP18:%.*]] = add <vscale x 4 x i32> [[WIDE_MASKED_GATHER]], 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)
+; STRIDED-NEXT:    [[TMP19:%.*]] = getelementptr i32, ptr [[P2]], <vscale x 4 x i64> [[TMP16]]
+; STRIDED-NEXT:    call void @llvm.masked.scatter.nxv4i32.nxv4p0(<vscale x 4 x i32> [[TMP18]], <vscale x 4 x ptr> [[TMP19]], i32 4, <vscale x 4 x i1> 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)), !alias.scope !11, !noalias !8
+; STRIDED-NEXT:    [[TMP20:%.*]] = call i64 @llvm.vscale.i64()
+; STRIDED-NEXT:    [[TMP21:%.*]] = mul i64 [[TMP20]], 4
+; STRIDED-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP21]]
+; STRIDED-NEXT:    [[VEC_IND_NEXT]] = add <vscale x 4 x i64> [[VEC_IND]], [[DOTSPLAT]]
+; STRIDED-NEXT:    [[TMP22:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; STRIDED-NEXT:    br i1 [[TMP22]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP13:![0-9]+]]
+; STRIDED:       middle.block:
+; STRIDED-NEXT:    [[CMP_N:%.*]] = icmp eq i64 1024, [[N_VEC]]
+; STRIDED-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
+; STRIDED:       scalar.ph:
+; STRIDED-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ], [ 0, [[VECTOR_MEMCHECK]] ]
+; STRIDED-NEXT:    br label [[LOOP:%.*]]
+; STRIDED:       loop:
+; STRIDED-NEXT:    [[I:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[NEXTI:%.*]], [[LOOP]] ]
+; STRIDED-NEXT:    [[OFFSET:%.*]] = mul nuw nsw i64 [[I]], [[STRIDE]]
+; STRIDED-NEXT:    [[Q0:%.*]] = getelementptr i32, ptr [[P]], i64 [[OFFSET]]
+; STRIDED-NEXT:    [[X0:%.*]] = load i32, ptr [[Q0]], align 4
+; STRIDED-NEXT:    [[Y0:%.*]] = add i32 [[X0]], 1
+; STRIDED-NEXT:    [[Q1:%.*]] = getelementptr i32, ptr [[P2]], i64 [[OFFSET]]
+; STRIDED-NEXT:    store i32 [[Y0]], ptr [[Q1]], align 4
+; STRIDED-NEXT:    [[NEXTI]] = add i64 [[I]], 1
+; STRIDED-NEXT:    [[DONE:%.*]] = icmp eq i64 [[NEXTI]], 1024
+; STRIDED-NEXT:    br i1 [[DONE]], label [[EXIT]], label [[LOOP]], !llvm.loop [[LOOP14:![0-9]+]]
+; STRIDED:       exit:
+; STRIDED-NEXT:    ret void
 ;
 entry:
   br label %loop
@@ -472,59 +582,77 @@ exit:
 }
 
 define void @double_stride_int_iv(ptr %p, ptr %p2, i64 %stride) {
-; CHECK-LABEL: @double_stride_int_iv(
-; CHECK-NEXT:  entry:
-; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 4
-; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.umax.i64(i64 8, i64 [[TMP1]])
-; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1024, [[TMP2]]
-; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_SCEVCHECK:%.*]]
-; CHECK:       vector.scevcheck:
-; CHECK-NEXT:    [[IDENT_CHECK:%.*]] = icmp ne i64 [[STRIDE:%.*]], 1
-; CHECK-NEXT:    br i1 [[IDENT_CHECK]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
-; CHECK:       vector.ph:
-; CHECK-NEXT:    [[TMP3:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP4:%.*]] = mul i64 [[TMP3]], 4
-; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP4]]
-; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 1024, [[N_MOD_VF]]
-; CHECK-NEXT:    [[IND_END:%.*]] = mul i64 [[N_VEC]], [[STRIDE]]
-; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
-; CHECK:       vector.body:
-; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT:    [[OFFSET_IDX:%.*]] = mul i64 [[INDEX]], [[STRIDE]]
-; CHECK-NEXT:    [[TMP5:%.*]] = mul i64 0, [[STRIDE]]
-; CHECK-NEXT:    [[TMP6:%.*]] = add i64 [[OFFSET_IDX]], [[TMP5]]
-; CHECK-NEXT:    [[TMP7:%.*]] = getelementptr i32, ptr [[P:%.*]], i64 [[TMP6]]
-; CHECK-NEXT:    [[TMP8:%.*]] = getelementptr i32, ptr [[TMP7]], i32 0
-; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <vscale x 4 x i32>, ptr [[TMP8]], align 4
-; CHECK-NEXT:    [[TMP9:%.*]] = add <vscale x 4 x i32> [[WIDE_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:    store <vscale x 4 x i32> [[TMP9]], ptr [[TMP8]], align 4
-; CHECK-NEXT:    [[TMP10:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP11:%.*]] = mul i64 [[TMP10]], 4
-; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP11]]
-; CHECK-NEXT:    [[TMP12:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
-; CHECK-NEXT:    br i1 [[TMP12]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP14:![0-9]+]]
-; CHECK:       middle.block:
-; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 1024, [[N_VEC]]
-; CHECK-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
-; CHECK:       scalar.ph:
-; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ], [ 0, [[VECTOR_SCEVCHECK]] ]
-; CHECK-NEXT:    [[BC_RESUME_VAL1:%.*]] = phi i64 [ [[IND_END]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY]] ], [ 0, [[VECTOR_SCEVCHECK]] ]
-; CHECK-NEXT:    br label [[LOOP:%.*]]
-; CHECK:       loop:
-; CHECK-NEXT:    [[I:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[NEXTI:%.*]], [[LOOP]] ]
-; CHECK-NEXT:    [[OFFSET:%.*]] = phi i64 [ [[BC_RESUME_VAL1]], [[SCALAR_PH]] ], [ [[OFFSET_NEXT:%.*]], [[LOOP]] ]
-; CHECK-NEXT:    [[Q0:%.*]] = getelementptr i32, ptr [[P]], i64 [[OFFSET]]
-; CHECK-NEXT:    [[X0:%.*]] = load i32, ptr [[Q0]], align 4
-; CHECK-NEXT:    [[Y0:%.*]] = add i32 [[X0]], 1
-; CHECK-NEXT:    [[Q1:%.*]] = getelementptr i32, ptr [[P]], i64 [[OFFSET]]
-; CHECK-NEXT:    store i32 [[Y0]], ptr [[Q1]], align 4
-; CHECK-NEXT:    [[OFFSET_NEXT]] = add nuw nsw i64 [[OFFSET]], [[STRIDE]]
-; CHECK-NEXT:    [[NEXTI]] = add i64 [[I]], 1
-; CHECK-NEXT:    [[DONE:%.*]] = icmp eq i64 [[NEXTI]], 1024
-; CHECK-NEXT:    br i1 [[DONE]], label [[EXIT]], label [[LOOP]], !llvm.loop [[LOOP15:![0-9]+]]
-; CHECK:       exit:
-; CHECK-NEXT:    ret void
+; NOSTRIDED-LABEL: @double_stride_int_iv(
+; NOSTRIDED-NEXT:  entry:
+; NOSTRIDED-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
+; NOSTRIDED-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 4
+; NOSTRIDED-NEXT:    [[TMP2:%.*]] = call i64 @llvm.umax.i64(i64 8, i64 [[TMP1]])
+; NOSTRIDED-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1024, [[TMP2]]
+; NOSTRIDED-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_SCEVCHECK:%.*]]
+; NOSTRIDED:       vector.scevcheck:
+; NOSTRIDED-NEXT:    [[IDENT_CHECK:%.*]] = icmp ne i64 [[STRIDE:%.*]], 1
+; NOSTRIDED-NEXT:    br i1 [[IDENT_CHECK]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
+; NOSTRIDED:       vector.ph:
+; NOSTRIDED-NEXT:    [[TMP3:%.*]] = call i64 @llvm.vscale.i64()
+; NOSTRIDED-NEXT:    [[TMP4:%.*]] = mul i64 [[TMP3]], 4
+; NOSTRIDED-NEXT:    [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP4]]
+; NOSTRIDED-NEXT:    [[N_VEC:%.*]] = sub i64 1024, [[N_MOD_VF]]
+; NOSTRIDED-NEXT:    [[IND_END:%.*]] = mul i64 [[N_VEC]], [[STRIDE]]
+; NOSTRIDED-NEXT:    br label [[VECTOR_BODY:%.*]]
+; NOSTRIDED:       vector.body:
+; NOSTRIDED-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; NOSTRIDED-NEXT:    [[OFFSET_IDX:%.*]] = mul i64 [[INDEX]], [[STRIDE]]
+; NOSTRIDED-NEXT:    [[TMP5:%.*]] = mul i64 0, [[STRIDE]]
+; NOSTRIDED-NEXT:    [[TMP6:%.*]] = add i64 [[OFFSET_IDX]], [[TMP5]]
+; NOSTRIDED-NEXT:    [[TMP7:%.*]] = getelementptr i32, ptr [[P:%.*]], i64 [[TMP6]]
+; NOSTRIDED-NEXT:    [[TMP8:%.*]] = getelementptr i32, ptr [[TMP7]], i32 0
+; NOSTRIDED-NEXT:    [[WIDE_LOAD:%.*]] = load <vscale x 4 x i32>, ptr [[TMP8]], align 4
+; NOSTRIDED-NEXT:    [[TMP9:%.*]] = add <vscale x 4 x i32> [[WIDE_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)
+; NOSTRIDED-NEXT:    store <vscale x 4 x i32> [[TMP9]], ptr [[TMP8]], align 4
+; NOSTRIDED-NEXT:    [[TMP10:%.*]] = call i64 @llvm.vscale.i64()
+; NOSTRIDED-NEXT:    [[TMP11:%.*]] = mul i64 [[TMP10]], 4
+; NOSTRIDED-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP11]]
+; NOSTRIDED-NEXT:    [[TMP12:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; NOSTRIDED-NEXT:    br i1 [[TMP12]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP14:![0-9]+]]
+; NOSTRIDED:       middle.block:
+; NOSTRIDED-NEXT:    [[CMP_N:%.*]] = icmp eq i64 1024, [[N_VEC]]
+; NOSTRIDED-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
+; NOSTRIDED:       scalar.ph:
+; NOSTRIDED-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ], [ 0, [[VECTOR_SCEVCHECK]] ]
+; NOSTRIDED-NEXT:    [[BC_RESUME_VAL1:%.*]] = phi i64 [ [[IND_END]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY]] ], [ 0, [[VECTOR_SCEVCHECK]] ]
+; NOSTRIDED-NEXT:    br label [[LOOP:%.*]]
+; NOSTRIDED:       loop:
+; NOSTRIDED-NEXT:    [[I:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[NEXTI:%.*]], [[LOOP]] ]
+; NOSTRIDED-NEXT:    [[OFFSET:%.*]] = phi i64 [ [[BC_RESUME_VAL1]], [[SCALAR_PH]] ], [ [[OFFSET_NEXT:%.*]], [[LOOP]] ]
+; NOSTRIDED-NEXT:    [[Q0:%.*]] = getelementptr i32, ptr [[P]], i64 [[OFFSET]]
+; NOSTRIDED-NEXT:    [[X0:%.*]] = load i32, ptr [[Q0]], align 4
+; NOSTRIDED-NEXT:    [[Y0:%.*]] = add i32 [[X0]], 1
+; NOSTRIDED-NEXT:    [[Q1:%.*]] = getelementptr i32, ptr [[P]], i64 [[OFFSET]]
+; NOSTRIDED-NEXT:    store i32 [[Y0]], ptr [[Q1]], align 4
+; NOSTRIDED-NEXT:    [[OFFSET_NEXT]] = add nuw nsw i64 [[OFFSET]], [[STRIDE]]
+; NOSTRIDED-NEXT:    [[NEXTI]] = add i64 [[I]], 1
+; NOSTRIDED-NEXT:    [[DONE:%.*]] = icmp eq i64 [[NEXTI]], 1024
+; NOSTRIDED-NEXT:    br i1 [[DONE]], label [[EXIT]], label [[LOOP]], !llvm.loop [[LOOP15:![0-9]+]]
+; NOSTRIDED:       exit:
+; NOSTRIDED-NEXT:    ret void
+;
+; STRIDED-LABEL: @double_stride_int_iv(
+; STRIDED-NEXT:  entry:
+; STRIDED-NEXT:    br label [[LOOP:%.*]]
+; STRIDED:       loop:
+; STRIDED-NEXT:    [[I:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[NEXTI:%.*]], [[LOOP]] ]
+; STRIDED-NEXT:    [[OFFSET:%.*]] = phi i64 [ 0, [[ENTRY]] ], [ [[OFFSET_NEXT:%.*]], [[LOOP]] ]
+; STRIDED-NEXT:    [[Q0:%.*]] = getelementptr i32, ptr [[P:%.*]], i64 [[OFFSET]]
+; STRIDED-NEXT:    [[X0:%.*]] = load i32, ptr [[Q0]], align 4
+; STRIDED-NEXT:    [[Y0:%.*]] = add i32 [[X0]], 1
+; STRIDED-NEXT:    [[Q1:%.*]] = getelementptr i32, ptr [[P]], i64 [[OFFSET]]
+; STRIDED-NEXT:    store i32 [[Y0]], ptr [[Q1]], align 4
+; STRIDED-NEXT:    [[OFFSET_NEXT]] = add nuw nsw i64 [[OFFSET]], [[STRIDE:%.*]]
+; STRIDED-NEXT:    [[NEXTI]] = add i64 [[I]], 1
+; STRIDED-NEXT:    [[DONE:%.*]] = icmp eq i64 [[NEXTI]], 1024
+; STRIDED-NEXT:    br i1 [[DONE]], label [[EXIT:%.*]], label [[LOOP]]
+; STRIDED:       exit:
+; STRIDED-NEXT:    ret void
 ;
 entry:
   br label %loop
@@ -570,79 +698,87 @@ define void @double_stride_ptr_iv(ptr %p, ptr %p2, i64 %stride) {
 ; STRIDED-NEXT:  entry:
 ; STRIDED-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
 ; STRIDED-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 4
-; STRIDED-NEXT:    [[TMP2:%.*]] = call i64 @llvm.umax.i64(i64 8, i64 [[TMP1]])
+; STRIDED-NEXT:    [[TMP2:%.*]] = call i64 @llvm.umax.i64(i64 16, i64 [[TMP1]])
 ; STRIDED-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1024, [[TMP2]]
-; STRIDED-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_SCEVCHECK:%.*]]
-; STRIDED:       vector.scevcheck:
-; STRIDED-NEXT:    [[IDENT_CHECK:%.*]] = icmp ne i64 [[STRIDE:%.*]], 1
-; STRIDED-NEXT:    br i1 [[IDENT_CHECK]], label [[SCALAR_PH]], label [[VECTOR_MEMCHECK:%.*]]
+; STRIDED-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_MEMCHECK:%.*]]
 ; STRIDED:       vector.memcheck:
-; STRIDED-NEXT:    [[SCEVGEP:%.*]] = getelementptr i8, ptr [[P2:%.*]], i64 1027
-; STRIDED-NEXT:    [[SCEVGEP1:%.*]] = getelementptr i8, ptr [[P:%.*]], i64 1027
-; STRIDED-NEXT:    [[BOUND0:%.*]] = icmp ult ptr [[P2]], [[SCEVGEP1]]
-; STRIDED-NEXT:    [[BOUND1:%.*]] = icmp ult ptr [[P]], [[SCEVGEP]]
+; STRIDED-NEXT:    [[TMP3:%.*]] = mul i64 [[STRIDE:%.*]], 1023
+; STRIDED-NEXT:    [[SCEVGEP:%.*]] = getelementptr i8, ptr [[P2:%.*]], i64 [[TMP3]]
+; STRIDED-NEXT:    [[TMP4:%.*]] = icmp ult ptr [[P2]], [[SCEVGEP]]
+; STRIDED-NEXT:    [[UMIN:%.*]] = select i1 [[TMP4]], ptr [[P2]], ptr [[SCEVGEP]]
+; STRIDED-NEXT:    [[TMP5:%.*]] = icmp ugt ptr [[P2]], [[SCEVGEP]]
+; STRIDED-NEXT:    [[UMAX:%.*]] = select i1 [[TMP5]], ptr [[P2]], ptr [[SCEVGEP]]
+; STRIDED-NEXT:    [[SCEVGEP1:%.*]] = getelementptr i8, ptr [[UMAX]], i64 4
+; STRIDED-NEXT:    [[SCEVGEP2:%.*]] = getelementptr i8, ptr [[P:%.*]], i64 [[TMP3]]
+; STRIDED-NEXT:    [[TMP6:%.*]] = icmp ult ptr [[P]], [[SCEVGEP2]]
+; STRIDED-NEXT:    [[UMIN3:%.*]] = select i1 [[TMP6]], ptr [[P]], ptr [[SCEVGEP2]]
+; STRIDED-NEXT:    [[TMP7:%.*]] = icmp ugt ptr [[P]], [[SCEVGEP2]]
+; STRIDED-NEXT:    [[UMAX4:%.*]] = select i1 [[TMP7]], ptr [[P]], ptr [[SCEVGEP2]]
+; STRIDED-NEXT:    [[SCEVGEP5:%.*]] = getelementptr i8, ptr [[UMAX4]], i64 4
+; STRIDED-NEXT:    [[BOUND0:%.*]] = icmp ult ptr [[UMIN]], [[SCEVGEP5]]
+; STRIDED-NEXT:    [[BOUND1:%.*]] = icmp ult ptr [[UMIN3]], [[SCEVGEP1]]
 ; STRIDED-NEXT:    [[FOUND_CONFLICT:%.*]] = and i1 [[BOUND0]], [[BOUND1]]
 ; STRIDED-NEXT:    br i1 [[FOUND_CONFLICT]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
 ; STRIDED:       vector.ph:
-; STRIDED-NEXT:    [[TMP3:%.*]] = call i64 @llvm.vscale.i64()
-; STRIDED-NEXT:    [[TMP4:%.*]] = mul i64 [[TMP3]], 4
-; STRIDED-NEXT:    [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP4]]
+; STRIDED-NEXT:    [[TMP8:%.*]] = call i64 @llvm.vscale.i64()
+; STRIDED-NEXT:    [[TMP9:%.*]] = mul i64 [[TMP8]], 4
+; STRIDED-NEXT:    [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP9]]
 ; STRIDED-NEXT:    [[N_VEC:%.*]] = sub i64 1024, [[N_MOD_VF]]
-; STRIDED-NEXT:    [[TMP5:%.*]] = mul i64 [[N_VEC]], [[STRIDE]]
-; STRIDED-NEXT:    [[IND_END:%.*]] = getelementptr i8, ptr [[P]], i64 [[TMP5]]
-; STRIDED-NEXT:    [[TMP6:%.*]] = mul i64 [[N_VEC]], [[STRIDE]]
-; STRIDED-NEXT:    [[IND_END3:%.*]] = getelementptr i8, ptr [[P2]], i64 [[TMP6]]
+; STRIDED-NEXT:    [[TMP10:%.*]] = mul i64 [[N_VEC]], [[STRIDE]]
+; STRIDED-NEXT:    [[IND_END:%.*]] = getelementptr i8, ptr [[P]], i64 [[TMP10]]
+; STRIDED-NEXT:    [[TMP11:%.*]] = mul i64 [[N_VEC]], [[STRIDE]]
+; STRIDED-NEXT:    [[IND_END7:%.*]] = getelementptr i8, ptr [[P2]], i64 [[TMP11]]
 ; STRIDED-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; STRIDED:       vector.body:
 ; STRIDED-NEXT:    [[POINTER_PHI:%.*]] = phi ptr [ [[P]], [[VECTOR_PH]] ], [ [[PTR_IND:%.*]], [[VECTOR_BODY]] ]
-; STRIDED-NEXT:    [[POINTER_PHI7:%.*]] = phi ptr [ [[P2]], [[VECTOR_PH]] ], [ [[PTR_IND8:%.*]], [[VECTOR_BODY]] ]
+; STRIDED-NEXT:    [[POINTER_PHI11:%.*]] = phi ptr [ [[P2]], [[VECTOR_PH]] ], [ [[PTR_IND12:%.*]], [[VECTOR_BODY]] ]
 ; STRIDED-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; STRIDED-NEXT:    [[TMP7:%.*]] = call i64 @llvm.vscale.i64()
-; STRIDED-NEXT:    [[TMP8:%.*]] = mul i64 [[TMP7]], 4
-; STRIDED-NEXT:    [[TMP9:%.*]] = mul i64 [[TMP8]], 1
-; STRIDED-NEXT:    [[TMP10:%.*]] = mul i64 [[STRIDE]], [[TMP9]]
-; STRIDED-NEXT:    [[TMP11:%.*]] = mul i64 [[TMP8]], 0
-; STRIDED-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TMP11]], i64 0
+; STRIDED-NEXT:    [[TMP12:%.*]] = call i64 @llvm.vscale.i64()
+; STRIDED-NEXT:    [[TMP13:%.*]] = mul i64 [[TMP12]], 4
+; STRIDED-NEXT:    [[TMP14:%.*]] = mul i64 [[TMP13]], 1
+; STRIDED-NEXT:    [[TMP15:%.*]] = mul i64 [[STRIDE]], [[TMP14]]
+; STRIDED-NEXT:    [[TMP16:%.*]] = mul i64 [[TMP13]], 0
+; STRIDED-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TMP16]], i64 0
 ; STRIDED-NEXT:    [[DOTSPLAT:%.*]] = shufflevector <vscale x 4 x i64> [[DOTSPLATINSERT]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
-; STRIDED-NEXT:    [[TMP12:%.*]] = call <vscale x 4 x i64> @llvm.experimental.stepvector.nxv4i64()
-; STRIDED-NEXT:    [[TMP13:%.*]] = add <vscale x 4 x i64> [[DOTSPLAT]], [[TMP12]]
-; STRIDED-NEXT:    [[DOTSPLATINSERT5:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[STRIDE]], i64 0
-; STRIDED-NEXT:    [[DOTSPLAT6:%.*]] = shufflevector <vscale x 4 x i64> [[DOTSPLATINSERT5]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
-; STRIDED-NEXT:    [[VECTOR_GEP:%.*]] = mul <vscale x 4 x i64> [[TMP13]], [[DOTSPLAT6]]
-; STRIDED-NEXT:    [[TMP14:%.*]] = getelementptr i8, ptr [[POINTER_PHI]], <vscale x 4 x i64> [[VECTOR_GEP]]
-; STRIDED-NEXT:    [[TMP15:%.*]] = call i64 @llvm.vscale.i64()
-; STRIDED-NEXT:    [[TMP16:%.*]] = mul i64 [[TMP15]], 4
-; STRIDED-NEXT:    [[TMP17:%.*]] = mul i64 [[TMP16]], 1
-; STRIDED-NEXT:    [[TMP18:%.*]] = mul i64 [[STRIDE]], [[TMP17]]
-; STRIDED-NEXT:    [[TMP19:%.*]] = mul i64 [[TMP16]], 0
-; STRIDED-NEXT:    [[DOTSPLATINSERT9:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TMP19]], i64 0
+; STRIDED-NEXT:    [[TMP17:%.*]] = call <vscale x 4 x i64> @llvm.experimental.stepvector.nxv4i64()
+; STRIDED-NEXT:    [[TMP18:%.*]] = add <vscale x 4 x i64> [[DOTSPLAT]], [[TMP17]]
+; STRIDED-NEXT:    [[DOTSPLATINSERT9:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[STRIDE]], i64 0
 ; STRIDED-NEXT:    [[DOTSPLAT10:%.*]] = shufflevector <vscale x 4 x i64> [[DOTSPLATINSERT9]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
-; STRIDED-NEXT:    [[TMP20:%.*]] = call <vscale x 4 x i64> @llvm.experimental.stepvector.nxv4i64()
-; STRIDED-NEXT:    [[TMP21:%.*]] = add <vscale x 4 x i64> [[DOTSPLAT10]], [[TMP20]]
-; STRIDED-NEXT:    [[VECTOR_GEP13:%.*]] = mul <vscale x 4 x i64> [[TMP21]], [[DOTSPLAT6]]
-; STRIDED-NEXT:    [[TMP22:%.*]] = getelementptr i8, ptr [[POINTER_PHI7]], <vscale x 4 x i64> [[VECTOR_GEP13]]
-; STRIDED-NEXT:    [[WIDE_MASKED_GATHER:%.*]] = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32.nxv4p0(<vscale x 4 x ptr> [[TMP14]], i32 4, <vscale x 4 x i1> 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), <vscale x 4 x i32> poison), !alias.scope !16
-; STRIDED-NEXT:    [[TMP23:%.*]] = add <vscale x 4 x i32> [[WIDE_MASKED_GATHER]], 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)
-; STRIDED-NEXT:    call void @llvm.masked.scatter.nxv4i32.nxv4p0(<vscale x 4 x i32> [[TMP23]], <vscale x 4 x ptr> [[TMP22]], i32 4, <vscale x 4 x i1> 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)), !alias.scope !19, !noalias !16
-; STRIDED-NEXT:    [[TMP24:%.*]] = call i64 @llvm.vscale.i64()
-; STRIDED-NEXT:    [[TMP25:%.*]] = mul i64 [[TMP24]], 4
-; STRIDED-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP25]]
-; STRIDED-NEXT:    [[PTR_IND]] = getelementptr i8, ptr [[POINTER_PHI]], i64 [[TMP10]]
-; STRIDED-NEXT:    [[PTR_IND8]] = getelementptr i8, ptr [[POINTER_PHI7]], i64 [[TMP18]]
-; STRIDED-NEXT:    [[TMP26:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
-; STRIDED-NEXT:    br i1 [[TMP26]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP21:![0-9]+]]
+; STRIDED-NEXT:    [[VECTOR_GEP:%.*]] = mul <vscale x 4 x i64> [[TMP18]], [[DOTSPLAT10]]
+; STRIDED-NEXT:    [[TMP19:%.*]] = getelementptr i8, ptr [[POINTER_PHI]], <vscale x 4 x i64> [[VECTOR_GEP]]
+; STRIDED-NEXT:    [[TMP20:%.*]] = call i64 @llvm.vscale.i64()
+; STRIDED-NEXT:    [[TMP21:%.*]] = mul i64 [[TMP20]], 4
+; STRIDED-NEXT:    [[TMP22:%.*]] = mul i64 [[TMP21]], 1
+; STRIDED-NEXT:    [[TMP23:%.*]] = mul i64 [[STRIDE]], [[TMP22]]
+; STRIDED-NEXT:    [[TMP24:%.*]] = mul i64 [[TMP21]], 0
+; STRIDED-NEXT:    [[DOTSPLATINSERT13:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TMP24]], i64 0
+; STRIDED-NEXT:    [[DOTSPLAT14:%.*]] = shufflevector <vscale x 4 x i64> [[DOTSPLATINSERT13]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
+; STRIDED-NEXT:    [[TMP25:%.*]] = call <vscale x 4 x i64> @llvm.experimental.stepvector.nxv4i64()
+; STRIDED-NEXT:    [[TMP26:%.*]] = add <vscale x 4 x i64> [[DOTSPLAT14]], [[TMP25]]
+; STRIDED-NEXT:    [[VECTOR_GEP17:%.*]] = mul <vscale x 4 x i64> [[TMP26]], [[DOTSPLAT10]]
+; STRIDED-NEXT:    [[TMP27:%.*]] = getelementptr i8, ptr [[POINTER_PHI11]], <vscale x 4 x i64> [[VECTOR_GEP17]]
+; STRIDED-NEXT:    [[WIDE_MASKED_GATHER:%.*]] = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32.nxv4p0(<vscale x 4 x ptr> [[TMP19]], i32 4, <vscale x 4 x i1> 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), <vscale x 4 x i32> poison), !alias.scope !15
+; STRIDED-NEXT:    [[TMP28:%.*]] = add <vscale x 4 x i32> [[WIDE_MASKED_GATHER]], 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)
+; STRIDED-NEXT:    call void @llvm.masked.scatter.nxv4i32.nxv4p0(<vscale x 4 x i32> [[TMP28]], <vscale x 4 x ptr> [[TMP27]], i32 4, <vscale x 4 x i1> 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)), !alias.scope !18, !noalias !15
+; STRIDED-NEXT:    [[TMP29:%.*]] = call i64 @llvm.vscale.i64()
+; STRIDED-NEXT:    [[TMP30:%.*]] = mul i64 [[TMP29]], 4
+; STRIDED-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP30]]
+; STRIDED-NEXT:    [[PTR_IND]] = getelementptr i8, ptr [[POINTER_PHI]], i64 [[TMP15]]
+; STRIDED-NEXT:    [[PTR_IND12]] = getelementptr i8, ptr [[POINTER_PHI11]], i64 [[TMP23]]
+; STRIDED-NEXT:    [[TMP31:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; STRIDED-NEXT:    br i1 [[TMP31]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP20:![0-9]+]]
 ; STRIDED:       middle.block:
 ; STRIDED-NEXT:    [[CMP_N:%.*]] = icmp eq i64 1024, [[N_VEC]]
 ; STRIDED-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
 ; STRIDED:       scalar.ph:
-; STRIDED-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ], [ 0, [[VECTOR_SCEVCHECK]] ], [ 0, [[VECTOR_MEMCHECK]] ]
-; STRIDED-NEXT:    [[BC_RESUME_VAL2:%.*]] = phi ptr [ [[IND_END]], [[MIDDLE_BLOCK]] ], [ [[P]], [[ENTRY]] ], [ [[P]], [[VECTOR_SCEVCHECK]] ], [ [[P]], [[VECTOR_MEMCHECK]] ]
-; STRIDED-NEXT:    [[BC_RESUME_VAL4:%.*]] = phi ptr [ [[IND_END3]], [[MIDDLE_BLOCK]] ], [ [[P2]], [[ENTRY]] ], [ [[P2]], [[VECTOR_SCEVCHECK]] ], [ [[P2]], [[VECTOR_MEMCHECK]] ]
+; STRIDED-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ], [ 0, [[VECTOR_MEMCHECK]] ]
+; STRIDED-NEXT:    [[BC_RESUME_VAL6:%.*]] = phi ptr [ [[IND_END]], [[MIDDLE_BLOCK]] ], [ [[P]], [[ENTRY]] ], [ [[P]], [[VECTOR_MEMCHECK]] ]
+; STRIDED-NEXT:    [[BC_RESUME_VAL8:%.*]] = phi ptr [ [[IND_END7]], [[MIDDLE_BLOCK]] ], [ [[P2]], [[ENTRY]] ], [ [[P2]], [[VECTOR_MEMCHECK]] ]
 ; STRIDED-NEXT:    br label [[LOOP:%.*]]
 ; STRIDED:       loop:
 ; STRIDED-NEXT:    [[I:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[NEXTI:%.*]], [[LOOP]] ]
-; STRIDED-NEXT:    [[PTR:%.*]] = phi ptr [ [[BC_RESUME_VAL2]], [[SCALAR_PH]] ], [ [[PTR_NEXT:%.*]], [[LOOP]] ]
-; STRIDED-NEXT:    [[PTR2:%.*]] = phi ptr [ [[BC_RESUME_VAL4]], [[SCALAR_PH]] ], [ [[PTR2_NEXT:%.*]], [[LOOP]] ]
+; STRIDED-NEXT:    [[PTR:%.*]] = phi ptr [ [[BC_RESUME_VAL6]], [[SCALAR_PH]] ], [ [[PTR_NEXT:%.*]], [[LOOP]] ]
+; STRIDED-NEXT:    [[PTR2:%.*]] = phi ptr [ [[BC_RESUME_VAL8]], [[SCALAR_PH]] ], [ [[PTR2_NEXT:%.*]], [[LOOP]] ]
 ; STRIDED-NEXT:    [[X0:%.*]] = load i32, ptr [[PTR]], align 4
 ; STRIDED-NEXT:    [[Y0:%.*]] = add i32 [[X0]], 1
 ; STRIDED-NEXT:    store i32 [[Y0]], ptr [[PTR2]], align 4
@@ -650,7 +786,7 @@ define void @double_stride_ptr_iv(ptr %p, ptr %p2, i64 %stride) {
 ; STRIDED-NEXT:    [[PTR2_NEXT]] = getelementptr inbounds i8, ptr [[PTR2]], i64 [[STRIDE]]
 ; STRIDED-NEXT:    [[NEXTI]] = add i64 [[I]], 1
 ; STRIDED-NEXT:    [[DONE:%.*]] = icmp eq i64 [[NEXTI]], 1024
-; STRIDED-NEXT:    br i1 [[DONE]], label [[EXIT]], label [[LOOP]], !llvm.loop [[LOOP22:![0-9]+]]
+; STRIDED-NEXT:    br i1 [[DONE]], label [[EXIT]], label [[LOOP]], !llvm.loop [[LOOP21:![0-9]+]]
 ; STRIDED:       exit:
 ; STRIDED-NEXT:    ret void
 ;