llvm/llvm/test/Transforms/LoopVectorize/RISCV/strided-accesses.ll

; 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 -laa-speculate-unit-stride=false -S | FileCheck --check-prefixes=CHECK,STRIDED %s


define void @single_constant_stride_int_scaled(ptr %p) {
; CHECK-LABEL: @single_constant_stride_int_scaled(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 4
; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ule i64 1024, [[TMP1]]
; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP3:%.*]] = mul i64 [[TMP2]], 4
; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP3]]
; CHECK-NEXT:    [[TMP4:%.*]] = icmp eq i64 [[N_MOD_VF]], 0
; CHECK-NEXT:    [[TMP5:%.*]] = select i1 [[TMP4]], i64 [[TMP3]], i64 [[N_MOD_VF]]
; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 1024, [[TMP5]]
; CHECK-NEXT:    [[TMP6:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP7:%.*]] = mul i64 [[TMP6]], 4
; CHECK-NEXT:    [[TMP8:%.*]] = call <vscale x 4 x i64> @llvm.stepvector.nxv4i64()
; CHECK-NEXT:    [[TMP9:%.*]] = add <vscale x 4 x i64> [[TMP8]], zeroinitializer
; CHECK-NEXT:    [[TMP10:%.*]] = mul <vscale x 4 x i64> [[TMP9]], shufflevector (<vscale x 4 x i64> insertelement (<vscale x 4 x i64> poison, i64 1, i64 0), <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer)
; CHECK-NEXT:    [[INDUCTION:%.*]] = add <vscale x 4 x i64> zeroinitializer, [[TMP10]]
; CHECK-NEXT:    [[TMP13:%.*]] = mul i64 1, [[TMP7]]
; CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TMP13]], i64 0
; CHECK-NEXT:    [[DOTSPLAT:%.*]] = shufflevector <vscale x 4 x i64> [[DOTSPLATINSERT]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[VEC_IND:%.*]] = phi <vscale x 4 x i64> [ [[INDUCTION]], [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP14:%.*]] = mul nuw nsw <vscale x 4 x i64> [[VEC_IND]], shufflevector (<vscale x 4 x i64> insertelement (<vscale x 4 x i64> poison, i64 8, i64 0), <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer)
; CHECK-NEXT:    [[TMP15:%.*]] = getelementptr i32, ptr [[P:%.*]], <vscale x 4 x i64> [[TMP14]]
; CHECK-NEXT:    [[WIDE_MASKED_GATHER:%.*]] = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32.nxv4p0(<vscale x 4 x ptr> [[TMP15]], 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)
; CHECK-NEXT:    [[TMP16:%.*]] = 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)
; CHECK-NEXT:    call void @llvm.masked.scatter.nxv4i32.nxv4p0(<vscale x 4 x i32> [[TMP16]], <vscale x 4 x ptr> [[TMP15]], 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))
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP7]]
; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <vscale x 4 x i64> [[VEC_IND]], [[DOTSPLAT]]
; CHECK-NEXT:    [[TMP17:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP17]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    br label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; 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]], 8
; 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 [[LOOP3:![0-9]+]]
; CHECK:       exit:
; CHECK-NEXT:    ret void
;
entry:
  br label %loop
loop:
  %i = phi i64 [0, %entry], [%nexti, %loop]

  %offset = mul nsw nuw i64 %i, 8
  %q0 = getelementptr i32, ptr %p, i64 %offset
  %x0 = load i32, ptr %q0
  %y0 = add i32 %x0, 1
  store i32 %y0, ptr %q0

  %nexti = add i64 %i, 1
  %done = icmp eq i64 %nexti, 1024
  br i1 %done, label %exit, label %loop
exit:
  ret void
}

define void @single_constant_stride_int_iv(ptr %p) {
; CHECK-LABEL: @single_constant_stride_int_iv(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 4
; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1024, [[TMP1]]
; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP3:%.*]] = mul i64 [[TMP2]], 4
; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP3]]
; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 1024, [[N_MOD_VF]]
; CHECK-NEXT:    [[IND_END:%.*]] = mul i64 [[N_VEC]], 64
; CHECK-NEXT:    [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP5:%.*]] = mul i64 [[TMP4]], 4
; CHECK-NEXT:    [[TMP6:%.*]] = call <vscale x 4 x i64> @llvm.stepvector.nxv4i64()
; CHECK-NEXT:    [[TMP7:%.*]] = add <vscale x 4 x i64> [[TMP6]], zeroinitializer
; CHECK-NEXT:    [[TMP8:%.*]] = mul <vscale x 4 x i64> [[TMP7]], shufflevector (<vscale x 4 x i64> insertelement (<vscale x 4 x i64> poison, i64 64, i64 0), <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer)
; CHECK-NEXT:    [[INDUCTION:%.*]] = add <vscale x 4 x i64> zeroinitializer, [[TMP8]]
; CHECK-NEXT:    [[TMP11:%.*]] = mul i64 64, [[TMP5]]
; CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TMP11]], i64 0
; CHECK-NEXT:    [[DOTSPLAT:%.*]] = shufflevector <vscale x 4 x i64> [[DOTSPLATINSERT]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[VEC_IND:%.*]] = phi <vscale x 4 x i64> [ [[INDUCTION]], [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP12:%.*]] = getelementptr i32, ptr [[P:%.*]], <vscale x 4 x i64> [[VEC_IND]]
; CHECK-NEXT:    [[WIDE_MASKED_GATHER:%.*]] = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32.nxv4p0(<vscale x 4 x ptr> [[TMP12]], 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)
; CHECK-NEXT:    [[TMP13:%.*]] = 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)
; CHECK-NEXT:    call void @llvm.masked.scatter.nxv4i32.nxv4p0(<vscale x 4 x i32> [[TMP13]], <vscale x 4 x ptr> [[TMP12]], 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))
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP5]]
; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <vscale x 4 x i64> [[VEC_IND]], [[DOTSPLAT]]
; CHECK-NEXT:    [[TMP14:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP14]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP4:![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:%.*]] ]
; CHECK-NEXT:    [[BC_RESUME_VAL1:%.*]] = phi i64 [ [[IND_END]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY]] ]
; 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]], 64
; 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 [[LOOP5:![0-9]+]]
; CHECK:       exit:
; CHECK-NEXT:    ret void
;
entry:
  br label %loop
loop:
  %i = phi i64 [0, %entry], [%nexti, %loop]
  %offset = phi i64 [0, %entry], [%offset.next, %loop]

  %q0 = getelementptr i32, ptr %p, i64 %offset
  %x0 = load i32, ptr %q0
  %y0 = add i32 %x0, 1
  store i32 %y0, ptr %q0

  %offset.next = add nsw nuw i64 %offset, 64
  %nexti = add i64 %i, 1
  %done = icmp eq i64 %nexti, 1024
  br i1 %done, label %exit, label %loop
exit:
  ret void
}


define void @single_constant_stride_ptr_iv(ptr %p) {
; CHECK-LABEL: @single_constant_stride_ptr_iv(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 4
; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ule i64 1024, [[TMP1]]
; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK:       vector.ph:
; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP3:%.*]] = mul i64 [[TMP2]], 4
; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP3]]
; CHECK-NEXT:    [[TMP4:%.*]] = icmp eq i64 [[N_MOD_VF]], 0
; CHECK-NEXT:    [[TMP5:%.*]] = select i1 [[TMP4]], i64 [[TMP3]], i64 [[N_MOD_VF]]
; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 1024, [[TMP5]]
; CHECK-NEXT:    [[TMP6:%.*]] = mul i64 [[N_VEC]], 8
; CHECK-NEXT:    [[IND_END:%.*]] = getelementptr i8, ptr [[P:%.*]], i64 [[TMP6]]
; CHECK-NEXT:    [[TMP7:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP8:%.*]] = mul i64 [[TMP7]], 4
; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
; CHECK:       vector.body:
; CHECK-NEXT:    [[POINTER_PHI:%.*]] = phi ptr [ [[P]], [[VECTOR_PH]] ], [ [[PTR_IND:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP9:%.*]] = call i64 @llvm.vscale.i64()
; CHECK-NEXT:    [[TMP10:%.*]] = mul i64 [[TMP9]], 4
; CHECK-NEXT:    [[TMP11:%.*]] = mul i64 [[TMP10]], 1
; CHECK-NEXT:    [[TMP12:%.*]] = mul i64 8, [[TMP11]]
; CHECK-NEXT:    [[TMP13:%.*]] = mul i64 [[TMP10]], 0
; CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TMP13]], i64 0
; CHECK-NEXT:    [[DOTSPLAT:%.*]] = shufflevector <vscale x 4 x i64> [[DOTSPLATINSERT]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
; CHECK-NEXT:    [[TMP14:%.*]] = call <vscale x 4 x i64> @llvm.stepvector.nxv4i64()
; CHECK-NEXT:    [[TMP15:%.*]] = add <vscale x 4 x i64> [[DOTSPLAT]], [[TMP14]]
; CHECK-NEXT:    [[TMP16:%.*]] = mul <vscale x 4 x i64> [[TMP15]], shufflevector (<vscale x 4 x i64> insertelement (<vscale x 4 x i64> poison, i64 8, i64 0), <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer)
; CHECK-NEXT:    [[VECTOR_GEP:%.*]] = getelementptr i8, ptr [[POINTER_PHI]], <vscale x 4 x i64> [[TMP16]]
; CHECK-NEXT:    [[TMP17:%.*]] = extractelement <vscale x 4 x ptr> [[VECTOR_GEP]], i32 0
; CHECK-NEXT:    [[TMP18:%.*]] = getelementptr i32, ptr [[TMP17]], i32 0
; CHECK-NEXT:    [[WIDE_VEC:%.*]] = load <vscale x 8 x i32>, ptr [[TMP18]], align 4
; CHECK-NEXT:    [[STRIDED_VEC:%.*]] = call { <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.vector.deinterleave2.nxv8i32(<vscale x 8 x i32> [[WIDE_VEC]])
; CHECK-NEXT:    [[TMP19:%.*]] = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32> } [[STRIDED_VEC]], 0
; CHECK-NEXT:    [[TMP20:%.*]] = add <vscale x 4 x i32> [[TMP19]], shufflevector (<vscale x 4 x i32> insertelement (<vscale x 4 x i32> poison, i32 1, i64 0), <vscale x 4 x i32> poison, <vscale x 4 x i32> zeroinitializer)
; CHECK-NEXT:    call void @llvm.masked.scatter.nxv4i32.nxv4p0(<vscale x 4 x i32> [[TMP20]], <vscale x 4 x ptr> [[VECTOR_GEP]], 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))
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP8]]
; CHECK-NEXT:    [[PTR_IND]] = getelementptr i8, ptr [[POINTER_PHI]], i64 [[TMP12]]
; CHECK-NEXT:    [[TMP21:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP21]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
; CHECK:       middle.block:
; CHECK-NEXT:    br label [[SCALAR_PH]]
; CHECK:       scalar.ph:
; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT:    [[BC_RESUME_VAL1:%.*]] = phi ptr [ [[IND_END]], [[MIDDLE_BLOCK]] ], [ [[P]], [[ENTRY]] ]
; CHECK-NEXT:    br label [[LOOP:%.*]]
; CHECK:       loop:
; CHECK-NEXT:    [[I:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[NEXTI:%.*]], [[LOOP]] ]
; CHECK-NEXT:    [[PTR:%.*]] = phi ptr [ [[BC_RESUME_VAL1]], [[SCALAR_PH]] ], [ [[PTR_NEXT:%.*]], [[LOOP]] ]
; CHECK-NEXT:    [[X0:%.*]] = load i32, ptr [[PTR]], align 4
; CHECK-NEXT:    [[Y0:%.*]] = add i32 [[X0]], 1
; CHECK-NEXT:    store i32 [[Y0]], ptr [[PTR]], align 4
; CHECK-NEXT:    [[PTR_NEXT]] = getelementptr inbounds i8, ptr [[PTR]], i64 8
; 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 [[LOOP7:![0-9]+]]
; CHECK:       exit:
; CHECK-NEXT:    ret void
;
entry:
  br label %loop
loop:
  %i = phi i64 [0, %entry], [%nexti, %loop]
  %ptr = phi ptr [%p, %entry], [%ptr.next, %loop]

  %x0 = load i32, ptr %ptr
  %y0 = add i32 %x0, 1
  store i32 %y0, ptr %ptr

  %ptr.next = getelementptr inbounds i8, ptr %ptr, i64 8
  %nexti = add i64 %i, 1
  %done = icmp eq i64 %nexti, 1024
  br i1 %done, label %exit, label %loop
exit:
  ret void
}


define void @single_stride_int_scaled(ptr %p, i64 %stride) {
; 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:    [[TMP5:%.*]] = call i64 @llvm.vscale.i64()
; NOSTRIDED-NEXT:    [[TMP6:%.*]] = mul i64 [[TMP5]], 4
; NOSTRIDED-NEXT:    br label [[VECTOR_BODY:%.*]]
; NOSTRIDED:       vector.body:
; NOSTRIDED-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; NOSTRIDED-NEXT:    [[TMP7:%.*]] = add i64 [[INDEX]], 0
; NOSTRIDED-NEXT:    [[TMP8:%.*]] = getelementptr i32, ptr [[P:%.*]], i64 [[TMP7]]
; NOSTRIDED-NEXT:    [[TMP9:%.*]] = getelementptr i32, ptr [[TMP8]], i32 0
; NOSTRIDED-NEXT:    [[WIDE_LOAD:%.*]] = load <vscale x 4 x i32>, ptr [[TMP9]], align 4
; NOSTRIDED-NEXT:    [[TMP10:%.*]] = 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> [[TMP10]], ptr [[TMP9]], align 4
; NOSTRIDED-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP6]]
; NOSTRIDED-NEXT:    [[TMP11:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; NOSTRIDED-NEXT:    br i1 [[TMP11]], 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
loop:
  %i = phi i64 [0, %entry], [%nexti, %loop]

  %offset = mul nsw nuw i64 %i, %stride
  %q0 = getelementptr i32, ptr %p, i64 %offset
  %x0 = load i32, ptr %q0
  %y0 = add i32 %x0, 1
  store i32 %y0, ptr %q0

  %nexti = add i64 %i, 1
  %done = icmp eq i64 %nexti, 1024
  br i1 %done, label %exit, label %loop
exit:
  ret void
}

define void @single_stride_int_iv(ptr %p, i64 %stride) {
; 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:    [[TMP5:%.*]] = call i64 @llvm.vscale.i64()
; NOSTRIDED-NEXT:    [[TMP6:%.*]] = mul i64 [[TMP5]], 4
; NOSTRIDED-NEXT:    br label [[VECTOR_BODY:%.*]]
; NOSTRIDED:       vector.body:
; NOSTRIDED-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; NOSTRIDED-NEXT:    [[TMP7:%.*]] = add i64 [[INDEX]], 0
; NOSTRIDED-NEXT:    [[TMP8:%.*]] = getelementptr i32, ptr [[P:%.*]], i64 [[TMP7]]
; NOSTRIDED-NEXT:    [[TMP9:%.*]] = getelementptr i32, ptr [[TMP8]], i32 0
; NOSTRIDED-NEXT:    [[WIDE_LOAD:%.*]] = load <vscale x 4 x i32>, ptr [[TMP9]], align 4
; NOSTRIDED-NEXT:    [[TMP10:%.*]] = 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> [[TMP10]], ptr [[TMP9]], align 4
; NOSTRIDED-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP6]]
; NOSTRIDED-NEXT:    [[TMP11:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; NOSTRIDED-NEXT:    br i1 [[TMP11]], 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
loop:
  %i = phi i64 [0, %entry], [%nexti, %loop]
  %offset = phi i64 [0, %entry], [%offset.next, %loop]

  %q0 = getelementptr i32, ptr %p, i64 %offset
  %x0 = load i32, ptr %q0
  %y0 = add i32 %x0, 1
  store i32 %y0, ptr %q0

  %offset.next = add nsw nuw i64 %offset, %stride
  %nexti = add i64 %i, 1
  %done = icmp eq i64 %nexti, 1024
  br i1 %done, label %exit, label %loop
exit:
  ret void
}


define void @single_stride_ptr_iv(ptr %p, i64 %stride) {
; CHECK-LABEL: @single_stride_ptr_iv(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    br label [[LOOP:%.*]]
; CHECK:       loop:
; CHECK-NEXT:    [[I:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[NEXTI:%.*]], [[LOOP]] ]
; CHECK-NEXT:    [[PTR:%.*]] = phi ptr [ [[P:%.*]], [[ENTRY]] ], [ [[PTR_NEXT:%.*]], [[LOOP]] ]
; CHECK-NEXT:    [[X0:%.*]] = load i32, ptr [[PTR]], align 4
; CHECK-NEXT:    [[Y0:%.*]] = add i32 [[X0]], 1
; CHECK-NEXT:    store i32 [[Y0]], ptr [[PTR]], align 4
; CHECK-NEXT:    [[PTR_NEXT]] = getelementptr inbounds i8, ptr [[PTR]], i64 [[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]]
; CHECK:       exit:
; CHECK-NEXT:    ret void
;
entry:
  br label %loop
loop:
  %i = phi i64 [0, %entry], [%nexti, %loop]
  %ptr = phi ptr [%p, %entry], [%ptr.next, %loop]

  %x0 = load i32, ptr %ptr
  %y0 = add i32 %x0, 1
  store i32 %y0, ptr %ptr

  %ptr.next = getelementptr inbounds i8, ptr %ptr, i64 %stride
  %nexti = add i64 %i, 1
  %done = icmp eq i64 %nexti, 1024
  br i1 %done, label %exit, label %loop
exit:
  ret void
}

define void @double_stride_int_scaled(ptr %p, ptr %p2, i64 %stride) {
; 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:    [[TMP9:%.*]] = call i64 @llvm.vscale.i64()
; NOSTRIDED-NEXT:    [[TMP10:%.*]] = mul i64 [[TMP9]], 4
; NOSTRIDED-NEXT:    br label [[VECTOR_BODY:%.*]]
; NOSTRIDED:       vector.body:
; NOSTRIDED-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; NOSTRIDED-NEXT:    [[TMP11:%.*]] = add i64 [[INDEX]], 0
; NOSTRIDED-NEXT:    [[TMP12:%.*]] = getelementptr i32, ptr [[P]], i64 [[TMP11]]
; NOSTRIDED-NEXT:    [[TMP13:%.*]] = getelementptr i32, ptr [[TMP12]], i32 0
; NOSTRIDED-NEXT:    [[WIDE_LOAD:%.*]] = load <vscale x 4 x i32>, ptr [[TMP13]], align 4
; NOSTRIDED-NEXT:    [[TMP14:%.*]] = 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:    [[TMP15:%.*]] = getelementptr i32, ptr [[P2]], i64 [[TMP11]]
; NOSTRIDED-NEXT:    [[TMP16:%.*]] = getelementptr i32, ptr [[TMP15]], i32 0
; NOSTRIDED-NEXT:    store <vscale x 4 x i32> [[TMP14]], ptr [[TMP16]], align 4
; NOSTRIDED-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP10]]
; NOSTRIDED-NEXT:    [[TMP17:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; NOSTRIDED-NEXT:    br i1 [[TMP17]], 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 i64 @llvm.vscale.i64()
; STRIDED-NEXT:    [[TMP11:%.*]] = mul i64 [[TMP10]], 4
; STRIDED-NEXT:    [[TMP12:%.*]] = call <vscale x 4 x i64> @llvm.stepvector.nxv4i64()
; STRIDED-NEXT:    [[TMP13:%.*]] = add <vscale x 4 x i64> [[TMP12]], zeroinitializer
; STRIDED-NEXT:    [[TMP14:%.*]] = mul <vscale x 4 x i64> [[TMP13]], 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, [[TMP14]]
; STRIDED-NEXT:    [[TMP17:%.*]] = mul i64 1, [[TMP11]]
; STRIDED-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TMP17]], 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:    [[TMP18:%.*]] = mul nuw nsw <vscale x 4 x i64> [[VEC_IND]], [[BROADCAST_SPLAT]]
; STRIDED-NEXT:    [[TMP19:%.*]] = getelementptr i32, ptr [[P]], <vscale x 4 x i64> [[TMP18]]
; 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 [[META8:![0-9]+]]
; STRIDED-NEXT:    [[TMP20:%.*]] = 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:    [[TMP21:%.*]] = getelementptr i32, ptr [[P2]], <vscale x 4 x i64> [[TMP18]]
; STRIDED-NEXT:    call void @llvm.masked.scatter.nxv4i32.nxv4p0(<vscale x 4 x i32> [[TMP20]], <vscale x 4 x ptr> [[TMP21]], 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 [[META11:![0-9]+]], !noalias [[META8]]
; STRIDED-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP11]]
; 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
loop:
  %i = phi i64 [0, %entry], [%nexti, %loop]

  %offset = mul nsw nuw i64 %i, %stride
  %q0 = getelementptr i32, ptr %p, i64 %offset
  %x0 = load i32, ptr %q0
  %y0 = add i32 %x0, 1
  %q1 = getelementptr i32, ptr %p2, i64 %offset
  store i32 %y0, ptr %q1

  %nexti = add i64 %i, 1
  %done = icmp eq i64 %nexti, 1024
  br i1 %done, label %exit, label %loop
exit:
  ret void
}

define void @double_stride_int_iv(ptr %p, ptr %p2, i64 %stride) {
; 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:    [[TMP5:%.*]] = call i64 @llvm.vscale.i64()
; NOSTRIDED-NEXT:    [[TMP6:%.*]] = mul i64 [[TMP5]], 4
; NOSTRIDED-NEXT:    br label [[VECTOR_BODY:%.*]]
; NOSTRIDED:       vector.body:
; NOSTRIDED-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; NOSTRIDED-NEXT:    [[TMP7:%.*]] = add i64 [[INDEX]], 0
; NOSTRIDED-NEXT:    [[TMP8:%.*]] = getelementptr i32, ptr [[P:%.*]], i64 [[TMP7]]
; NOSTRIDED-NEXT:    [[TMP9:%.*]] = getelementptr i32, ptr [[TMP8]], i32 0
; NOSTRIDED-NEXT:    [[WIDE_LOAD:%.*]] = load <vscale x 4 x i32>, ptr [[TMP9]], align 4
; NOSTRIDED-NEXT:    [[TMP10:%.*]] = 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> [[TMP10]], ptr [[TMP9]], align 4
; NOSTRIDED-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP6]]
; NOSTRIDED-NEXT:    [[TMP11:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; NOSTRIDED-NEXT:    br i1 [[TMP11]], 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
loop:
  %i = phi i64 [0, %entry], [%nexti, %loop]
  %offset = phi i64 [0, %entry], [%offset.next, %loop]

  %q0 = getelementptr i32, ptr %p, i64 %offset
  %x0 = load i32, ptr %q0
  %y0 = add i32 %x0, 1
  %q1 = getelementptr i32, ptr %p, i64 %offset
  store i32 %y0, ptr %q1

  %offset.next = add nsw nuw i64 %offset, %stride
  %nexti = add i64 %i, 1
  %done = icmp eq i64 %nexti, 1024
  br i1 %done, label %exit, label %loop
exit:
  ret void
}


define void @double_stride_ptr_iv(ptr %p, ptr %p2, i64 %stride) {
; NOSTRIDED-LABEL: @double_stride_ptr_iv(
; NOSTRIDED-NEXT:  entry:
; NOSTRIDED-NEXT:    br label [[LOOP:%.*]]
; NOSTRIDED:       loop:
; NOSTRIDED-NEXT:    [[I:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[NEXTI:%.*]], [[LOOP]] ]
; NOSTRIDED-NEXT:    [[PTR:%.*]] = phi ptr [ [[P:%.*]], [[ENTRY]] ], [ [[PTR_NEXT:%.*]], [[LOOP]] ]
; NOSTRIDED-NEXT:    [[PTR2:%.*]] = phi ptr [ [[P2:%.*]], [[ENTRY]] ], [ [[PTR2_NEXT:%.*]], [[LOOP]] ]
; NOSTRIDED-NEXT:    [[X0:%.*]] = load i32, ptr [[PTR]], align 4
; NOSTRIDED-NEXT:    [[Y0:%.*]] = add i32 [[X0]], 1
; NOSTRIDED-NEXT:    store i32 [[Y0]], ptr [[PTR2]], align 4
; NOSTRIDED-NEXT:    [[PTR_NEXT]] = getelementptr inbounds i8, ptr [[PTR]], i64 [[STRIDE:%.*]]
; NOSTRIDED-NEXT:    [[PTR2_NEXT]] = getelementptr inbounds i8, ptr [[PTR2]], i64 [[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]]
; NOSTRIDED:       exit:
; NOSTRIDED-NEXT:    ret void
;
; STRIDED-LABEL: @double_stride_ptr_iv(
; 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 32, 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:%.*]], 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:    [[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:%.*]] = 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:    [[TMP12:%.*]] = call i64 @llvm.vscale.i64()
; STRIDED-NEXT:    [[TMP13:%.*]] = mul i64 [[TMP12]], 4
; 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_PHI11:%.*]] = phi ptr [ [[P2]], [[VECTOR_PH]] ], [ [[PTR_IND12:%.*]], [[VECTOR_BODY]] ]
; STRIDED-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; STRIDED-NEXT:    [[TMP14:%.*]] = call i64 @llvm.vscale.i64()
; STRIDED-NEXT:    [[TMP15:%.*]] = mul i64 [[TMP14]], 4
; STRIDED-NEXT:    [[TMP16:%.*]] = mul i64 [[TMP15]], 1
; STRIDED-NEXT:    [[TMP17:%.*]] = mul i64 [[STRIDE]], [[TMP16]]
; STRIDED-NEXT:    [[TMP18:%.*]] = mul i64 [[TMP15]], 0
; STRIDED-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TMP18]], 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:    [[TMP19:%.*]] = call <vscale x 4 x i64> @llvm.stepvector.nxv4i64()
; STRIDED-NEXT:    [[TMP20:%.*]] = add <vscale x 4 x i64> [[DOTSPLAT]], [[TMP19]]
; 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:    [[TMP21:%.*]] = mul <vscale x 4 x i64> [[TMP20]], [[DOTSPLAT10]]
; STRIDED-NEXT:    [[VECTOR_GEP:%.*]] = getelementptr i8, ptr [[POINTER_PHI]], <vscale x 4 x i64> [[TMP21]]
; STRIDED-NEXT:    [[TMP22:%.*]] = call i64 @llvm.vscale.i64()
; STRIDED-NEXT:    [[TMP23:%.*]] = mul i64 [[TMP22]], 4
; STRIDED-NEXT:    [[TMP24:%.*]] = mul i64 [[TMP23]], 1
; STRIDED-NEXT:    [[TMP25:%.*]] = mul i64 [[STRIDE]], [[TMP24]]
; STRIDED-NEXT:    [[TMP26:%.*]] = mul i64 [[TMP23]], 0
; STRIDED-NEXT:    [[DOTSPLATINSERT13:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TMP26]], 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:    [[TMP27:%.*]] = call <vscale x 4 x i64> @llvm.stepvector.nxv4i64()
; STRIDED-NEXT:    [[TMP28:%.*]] = add <vscale x 4 x i64> [[DOTSPLAT14]], [[TMP27]]
; STRIDED-NEXT:    [[TMP29:%.*]] = mul <vscale x 4 x i64> [[TMP28]], [[DOTSPLAT10]]
; STRIDED-NEXT:    [[VECTOR_GEP17:%.*]] = getelementptr i8, ptr [[POINTER_PHI11]], <vscale x 4 x i64> [[TMP29]]
; STRIDED-NEXT:    [[WIDE_MASKED_GATHER:%.*]] = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32.nxv4p0(<vscale x 4 x ptr> [[VECTOR_GEP]], 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 [[META15:![0-9]+]]
; STRIDED-NEXT:    [[TMP30:%.*]] = 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> [[TMP30]], <vscale x 4 x ptr> [[VECTOR_GEP17]], 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 [[META18:![0-9]+]], !noalias [[META15]]
; STRIDED-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP13]]
; STRIDED-NEXT:    [[PTR_IND]] = getelementptr i8, ptr [[POINTER_PHI]], i64 [[TMP17]]
; STRIDED-NEXT:    [[PTR_IND12]] = getelementptr i8, ptr [[POINTER_PHI11]], i64 [[TMP25]]
; 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_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_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
; STRIDED-NEXT:    [[PTR_NEXT]] = getelementptr inbounds i8, ptr [[PTR]], 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 [[LOOP21:![0-9]+]]
; STRIDED:       exit:
; STRIDED-NEXT:    ret void
;
entry:
  br label %loop
loop:
  %i = phi i64 [0, %entry], [%nexti, %loop]
  %ptr = phi ptr [%p, %entry], [%ptr.next, %loop]
  %ptr2 = phi ptr [%p2, %entry], [%ptr2.next, %loop]

  %x0 = load i32, ptr %ptr
  %y0 = add i32 %x0, 1
  store i32 %y0, ptr %ptr2

  %ptr.next = getelementptr inbounds i8, ptr %ptr, i64 %stride
  %ptr2.next = getelementptr inbounds i8, ptr %ptr2, i64 %stride
  %nexti = add i64 %i, 1
  %done = icmp eq i64 %nexti, 1024
  br i1 %done, label %exit, label %loop
exit:
  ret void
}