llvm/test/Transforms/LoopVectorize/X86/illegal-parallel-loop-uniform-write.ll - toolchain/llvm-project - Git at Google

 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt < %s -passes=loop-vectorize,dce -force-vector-interleave=1 -force-vector-width=4 -S | FileCheck %s

 target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
 target triple = "x86_64-unknown-linux-gnu"

 ; PR15794
 ; incorrect addition of llvm.mem.parallel_loop_access metadata is undefined
 ; behaviour. Vectorizer ignores the memory dependency checks and goes ahead and
 ; vectorizes this loop with uniform stores which has an output dependency.

 ; void foo(int *a, int *b, int k, int m) {
 ;   for (int i = 0; i < m; i++) {
 ;     for (int j = 0; j < m; j++) {
 ;       a[i] = a[i + j + k] + 1; <<<
 ;     }
 ;     b[i] = b[i] + 3;
 ;   }
 ; }

 ; Function Attrs: nounwind uwtable
 define void @foo(ptr nocapture %a, ptr nocapture %b, i32 %k, i32 %m) #0 {
 ; CHECK-LABEL: @foo(
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[CMP27:%.*]] = icmp sgt i32 [[M:%.*]], 0
 ; CHECK-NEXT:    br i1 [[CMP27]], label [[FOR_BODY3_LR_PH_US_PREHEADER:%.*]], label [[FOR_END15:%.*]]
 ; CHECK:       for.body3.lr.ph.us.preheader:
 ; CHECK-NEXT:    [[TMP0:%.*]] = add i32 [[M]], -1
 ; CHECK-NEXT:    [[TMP1:%.*]] = zext i32 [[K:%.*]] to i64
 ; CHECK-NEXT:    [[TMP2:%.*]] = zext i32 [[M]] to i64
 ; CHECK-NEXT:    br label [[FOR_BODY3_LR_PH_US:%.*]]
 ; CHECK:       for.end.us:
 ; CHECK-NEXT:    [[ARRAYIDX9_US:%.*]] = getelementptr inbounds i32, ptr [[B:%.*]], i64 [[INDVARS_IV33:%.*]]
 ; CHECK-NEXT:    [[TMP3:%.*]] = load i32, ptr [[ARRAYIDX9_US]], align 4, !llvm.mem.parallel_loop_access !0
 ; CHECK-NEXT:    [[ADD10_US:%.*]] = add nsw i32 [[TMP3]], 3
 ; CHECK-NEXT:    store i32 [[ADD10_US]], ptr [[ARRAYIDX9_US]], align 4, !llvm.mem.parallel_loop_access !0
 ; CHECK-NEXT:    [[INDVARS_IV_NEXT34:%.*]] = add i64 [[INDVARS_IV33]], 1
 ; CHECK-NEXT:    [[LFTR_WIDEIV35:%.*]] = trunc i64 [[INDVARS_IV_NEXT34]] to i32
 ; CHECK-NEXT:    [[EXITCOND36:%.*]] = icmp eq i32 [[LFTR_WIDEIV35]], [[M]]
 ; CHECK-NEXT:    br i1 [[EXITCOND36]], label [[FOR_END15_LOOPEXIT:%.*]], label [[FOR_BODY3_LR_PH_US]], !llvm.loop [[LOOP2:![0-9]+]]
 ; CHECK:       for.body3.us:
 ; CHECK-NEXT:    [[INDVARS_IV29:%.*]] = phi i64 [ [[BC_RESUME_VAL:%.*]], [[SCALAR_PH:%.*]] ], [ [[INDVARS_IV_NEXT30:%.*]], [[FOR_BODY3_US:%.*]] ]
 ; CHECK-NEXT:    [[TMP4:%.*]] = trunc i64 [[INDVARS_IV29]] to i32
 ; CHECK-NEXT:    [[ADD4_US:%.*]] = add i32 [[ADD_US:%.*]], [[TMP4]]
 ; CHECK-NEXT:    [[IDXPROM_US:%.*]] = sext i32 [[ADD4_US]] to i64
 ; CHECK-NEXT:    [[ARRAYIDX_US:%.*]] = getelementptr inbounds i32, ptr [[A:%.*]], i64 [[IDXPROM_US]]
 ; CHECK-NEXT:    [[TMP5:%.*]] = load i32, ptr [[ARRAYIDX_US]], align 4, !llvm.mem.parallel_loop_access !0
 ; CHECK-NEXT:    [[ADD5_US:%.*]] = add nsw i32 [[TMP5]], 1
 ; CHECK-NEXT:    store i32 [[ADD5_US]], ptr [[ARRAYIDX7_US:%.*]], align 4, !llvm.mem.parallel_loop_access !0
 ; CHECK-NEXT:    [[INDVARS_IV_NEXT30]] = add i64 [[INDVARS_IV29]], 1
 ; CHECK-NEXT:    [[LFTR_WIDEIV31:%.*]] = trunc i64 [[INDVARS_IV_NEXT30]] to i32
 ; CHECK-NEXT:    [[EXITCOND32:%.*]] = icmp eq i32 [[LFTR_WIDEIV31]], [[M]]
 ; CHECK-NEXT:    br i1 [[EXITCOND32]], label [[FOR_END_US:%.*]], label [[FOR_BODY3_US]], !llvm.loop [[LOOP3:![0-9]+]]
 ; CHECK:       for.body3.lr.ph.us:
 ; CHECK-NEXT:    [[INDVARS_IV33]] = phi i64 [ [[INDVARS_IV_NEXT34]], [[FOR_END_US]] ], [ 0, [[FOR_BODY3_LR_PH_US_PREHEADER]] ]
 ; CHECK-NEXT:    [[TMP6:%.*]] = add i64 [[TMP1]], [[INDVARS_IV33]]
 ; CHECK-NEXT:    [[TMP7:%.*]] = trunc i64 [[TMP6]] to i32
 ; CHECK-NEXT:    [[TMP8:%.*]] = trunc i64 [[INDVARS_IV33]] to i32
 ; CHECK-NEXT:    [[ADD_US]] = add i32 [[TMP8]], [[K]]
 ; CHECK-NEXT:    [[ARRAYIDX7_US]] = getelementptr inbounds i32, ptr [[A]], i64 [[INDVARS_IV33]]
 ; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[TMP2]], 4
 ; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH]], label [[VECTOR_SCEVCHECK:%.*]]
 ; CHECK:       vector.scevcheck:
 ; CHECK-NEXT:    [[TMP9:%.*]] = add i32 [[TMP7]], [[TMP0]]
 ; CHECK-NEXT:    [[TMP10:%.*]] = icmp slt i32 [[TMP9]], [[TMP7]]
 ; CHECK-NEXT:    br i1 [[TMP10]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
 ; CHECK:       vector.ph:
 ; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[TMP2]], 4
 ; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[TMP2]], [[N_MOD_VF]]
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[OFFSET_IDX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[TMP11:%.*]] = trunc i64 [[OFFSET_IDX]] to i32
 ; CHECK-NEXT:    [[TMP12:%.*]] = add i32 [[TMP11]], 0
 ; CHECK-NEXT:    [[TMP13:%.*]] = add i32 [[ADD_US]], [[TMP12]]
 ; CHECK-NEXT:    [[TMP14:%.*]] = sext i32 [[TMP13]] to i64
 ; CHECK-NEXT:    [[TMP15:%.*]] = getelementptr inbounds i32, ptr [[A]], i64 [[TMP14]]
 ; CHECK-NEXT:    [[TMP16:%.*]] = getelementptr inbounds i32, ptr [[TMP15]], i32 0
 ; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x i32>, ptr [[TMP16]], align 4
 ; CHECK-NEXT:    [[TMP17:%.*]] = add nsw <4 x i32> [[WIDE_LOAD]], <i32 1, i32 1, i32 1, i32 1>
 ; CHECK-NEXT:    [[TMP18:%.*]] = extractelement <4 x i32> [[TMP17]], i32 3
 ; CHECK-NEXT:    store i32 [[TMP18]], ptr [[ARRAYIDX7_US]], align 4, !llvm.mem.parallel_loop_access !0
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[OFFSET_IDX]], 4
 ; CHECK-NEXT:    [[TMP19:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
 ; CHECK-NEXT:    br i1 [[TMP19]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
 ; CHECK:       middle.block:
 ; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 [[TMP2]], [[N_VEC]]
 ; CHECK-NEXT:    br i1 [[CMP_N]], label [[FOR_END_US]], label [[SCALAR_PH]]
 ; CHECK:       scalar.ph:
 ; CHECK-NEXT:    [[BC_RESUME_VAL]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[FOR_BODY3_LR_PH_US]] ], [ 0, [[VECTOR_SCEVCHECK]] ]
 ; CHECK-NEXT:    br label [[FOR_BODY3_US]]
 ; CHECK:       for.end15.loopexit:
 ; CHECK-NEXT:    br label [[FOR_END15]]
 ; CHECK:       for.end15:
 ; CHECK-NEXT:    ret void
 ;
 entry:
   %cmp27 = icmp sgt i32 %m, 0
   br i1 %cmp27, label %for.body3.lr.ph.us, label %for.end15

 for.end.us:                                       ; preds = %for.body3.us
   %arrayidx9.us = getelementptr inbounds i32, ptr %b, i64 %indvars.iv33
   %0 = load i32, ptr %arrayidx9.us, align 4, !llvm.mem.parallel_loop_access !3
   %add10.us = add nsw i32 %0, 3
   store i32 %add10.us, ptr %arrayidx9.us, align 4, !llvm.mem.parallel_loop_access !3
   %indvars.iv.next34 = add i64 %indvars.iv33, 1
   %lftr.wideiv35 = trunc i64 %indvars.iv.next34 to i32
   %exitcond36 = icmp eq i32 %lftr.wideiv35, %m
   br i1 %exitcond36, label %for.end15, label %for.body3.lr.ph.us, !llvm.loop !5

 for.body3.us:                                     ; preds = %for.body3.us, %for.body3.lr.ph.us
   %indvars.iv29 = phi i64 [ 0, %for.body3.lr.ph.us ], [ %indvars.iv.next30, %for.body3.us ]
   %1 = trunc i64 %indvars.iv29 to i32
   %add4.us = add i32 %add.us, %1
   %idxprom.us = sext i32 %add4.us to i64
   %arrayidx.us = getelementptr inbounds i32, ptr %a, i64 %idxprom.us
   %2 = load i32, ptr %arrayidx.us, align 4, !llvm.mem.parallel_loop_access !3
   %add5.us = add nsw i32 %2, 1
   store i32 %add5.us, ptr %arrayidx7.us, align 4, !llvm.mem.parallel_loop_access !3
   %indvars.iv.next30 = add i64 %indvars.iv29, 1
   %lftr.wideiv31 = trunc i64 %indvars.iv.next30 to i32
   %exitcond32 = icmp eq i32 %lftr.wideiv31, %m
   br i1 %exitcond32, label %for.end.us, label %for.body3.us, !llvm.loop !4

 for.body3.lr.ph.us:                               ; preds = %for.end.us, %entry
   %indvars.iv33 = phi i64 [ %indvars.iv.next34, %for.end.us ], [ 0, %entry ]
   %3 = trunc i64 %indvars.iv33 to i32
   %add.us = add i32 %3, %k
   %arrayidx7.us = getelementptr inbounds i32, ptr %a, i64 %indvars.iv33
   br label %for.body3.us

 for.end15:                                        ; preds = %for.end.us, %entry
   ret void
 }

 ; Same test as above, but without the invalid parallel_loop_access metadata.

 ; Here we can see the vectorizer does the mem dep checks and decides it is
 ; unsafe to vectorize.
 define void @no-par-mem-metadata(ptr nocapture %a, ptr nocapture %b, i32 %k, i32 %m) #0 {
 ; CHECK-LABEL: @no-par-mem-metadata(
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[CMP27:%.*]] = icmp sgt i32 [[M:%.*]], 0
 ; CHECK-NEXT:    br i1 [[CMP27]], label [[FOR_BODY3_LR_PH_US_PREHEADER:%.*]], label [[FOR_END15:%.*]]
 ; CHECK:       for.body3.lr.ph.us.preheader:
 ; CHECK-NEXT:    br label [[FOR_BODY3_LR_PH_US:%.*]]
 ; CHECK:       for.end.us:
 ; CHECK-NEXT:    [[ARRAYIDX9_US:%.*]] = getelementptr inbounds i32, ptr [[B:%.*]], i64 [[INDVARS_IV33:%.*]]
 ; CHECK-NEXT:    [[TMP0:%.*]] = load i32, ptr [[ARRAYIDX9_US]], align 4
 ; CHECK-NEXT:    [[ADD10_US:%.*]] = add nsw i32 [[TMP0]], 3
 ; CHECK-NEXT:    store i32 [[ADD10_US]], ptr [[ARRAYIDX9_US]], align 4
 ; CHECK-NEXT:    [[INDVARS_IV_NEXT34:%.*]] = add i64 [[INDVARS_IV33]], 1
 ; CHECK-NEXT:    [[LFTR_WIDEIV35:%.*]] = trunc i64 [[INDVARS_IV_NEXT34]] to i32
 ; CHECK-NEXT:    [[EXITCOND36:%.*]] = icmp eq i32 [[LFTR_WIDEIV35]], [[M]]
 ; CHECK-NEXT:    br i1 [[EXITCOND36]], label [[FOR_END15_LOOPEXIT:%.*]], label [[FOR_BODY3_LR_PH_US]], !llvm.loop [[LOOP2]]
 ; CHECK:       for.body3.us:
 ; CHECK-NEXT:    [[INDVARS_IV29:%.*]] = phi i64 [ 0, [[FOR_BODY3_LR_PH_US]] ], [ [[INDVARS_IV_NEXT30:%.*]], [[FOR_BODY3_US:%.*]] ]
 ; CHECK-NEXT:    [[TMP1:%.*]] = trunc i64 [[INDVARS_IV29]] to i32
 ; CHECK-NEXT:    [[ADD4_US:%.*]] = add i32 [[ADD_US:%.*]], [[TMP1]]
 ; CHECK-NEXT:    [[IDXPROM_US:%.*]] = sext i32 [[ADD4_US]] to i64
 ; CHECK-NEXT:    [[ARRAYIDX_US:%.*]] = getelementptr inbounds i32, ptr [[A:%.*]], i64 [[IDXPROM_US]]
 ; CHECK-NEXT:    [[TMP2:%.*]] = load i32, ptr [[ARRAYIDX_US]], align 4
 ; CHECK-NEXT:    [[ADD5_US:%.*]] = add nsw i32 [[TMP2]], 1
 ; CHECK-NEXT:    store i32 [[ADD5_US]], ptr [[ARRAYIDX7_US:%.*]], align 4
 ; CHECK-NEXT:    [[INDVARS_IV_NEXT30]] = add i64 [[INDVARS_IV29]], 1
 ; CHECK-NEXT:    [[LFTR_WIDEIV31:%.*]] = trunc i64 [[INDVARS_IV_NEXT30]] to i32
 ; CHECK-NEXT:    [[EXITCOND32:%.*]] = icmp eq i32 [[LFTR_WIDEIV31]], [[M]]
 ; CHECK-NEXT:    br i1 [[EXITCOND32]], label [[FOR_END_US:%.*]], label [[FOR_BODY3_US]], !llvm.loop [[LOOP1:![0-9]+]]
 ; CHECK:       for.body3.lr.ph.us:
 ; CHECK-NEXT:    [[INDVARS_IV33]] = phi i64 [ [[INDVARS_IV_NEXT34]], [[FOR_END_US]] ], [ 0, [[FOR_BODY3_LR_PH_US_PREHEADER]] ]
 ; CHECK-NEXT:    [[TMP3:%.*]] = trunc i64 [[INDVARS_IV33]] to i32
 ; CHECK-NEXT:    [[ADD_US]] = add i32 [[TMP3]], [[K:%.*]]
 ; CHECK-NEXT:    [[ARRAYIDX7_US]] = getelementptr inbounds i32, ptr [[A]], i64 [[INDVARS_IV33]]
 ; CHECK-NEXT:    br label [[FOR_BODY3_US]]
 ; CHECK:       for.end15.loopexit:
 ; CHECK-NEXT:    br label [[FOR_END15]]
 ; CHECK:       for.end15:
 ; CHECK-NEXT:    ret void
 ;
 entry:
   %cmp27 = icmp sgt i32 %m, 0
   br i1 %cmp27, label %for.body3.lr.ph.us, label %for.end15

 for.end.us:                                       ; preds = %for.body3.us
   %arrayidx9.us = getelementptr inbounds i32, ptr %b, i64 %indvars.iv33
   %0 = load i32, ptr %arrayidx9.us, align 4
   %add10.us = add nsw i32 %0, 3
   store i32 %add10.us, ptr %arrayidx9.us, align 4
   %indvars.iv.next34 = add i64 %indvars.iv33, 1
   %lftr.wideiv35 = trunc i64 %indvars.iv.next34 to i32
   %exitcond36 = icmp eq i32 %lftr.wideiv35, %m
   br i1 %exitcond36, label %for.end15, label %for.body3.lr.ph.us, !llvm.loop !5

 for.body3.us:                                     ; preds = %for.body3.us, %for.body3.lr.ph.us
   %indvars.iv29 = phi i64 [ 0, %for.body3.lr.ph.us ], [ %indvars.iv.next30, %for.body3.us ]
   %1 = trunc i64 %indvars.iv29 to i32
   %add4.us = add i32 %add.us, %1
   %idxprom.us = sext i32 %add4.us to i64
   %arrayidx.us = getelementptr inbounds i32, ptr %a, i64 %idxprom.us
   %2 = load i32, ptr %arrayidx.us, align 4
   %add5.us = add nsw i32 %2, 1
   store i32 %add5.us, ptr %arrayidx7.us, align 4
   %indvars.iv.next30 = add i64 %indvars.iv29, 1
   %lftr.wideiv31 = trunc i64 %indvars.iv.next30 to i32
   %exitcond32 = icmp eq i32 %lftr.wideiv31, %m
   br i1 %exitcond32, label %for.end.us, label %for.body3.us, !llvm.loop !4

 for.body3.lr.ph.us:                               ; preds = %for.end.us, %entry
   %indvars.iv33 = phi i64 [ %indvars.iv.next34, %for.end.us ], [ 0, %entry ]
   %3 = trunc i64 %indvars.iv33 to i32
   %add.us = add i32 %3, %k
   %arrayidx7.us = getelementptr inbounds i32, ptr %a, i64 %indvars.iv33
   br label %for.body3.us

 for.end15:                                        ; preds = %for.end.us, %entry
   ret void
 }

 attributes #0 = { nounwind uwtable "less-precise-fpmad"="false" "frame-pointer"="none" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "unsafe-fp-math"="false" "use-soft-float"="false" }

 !3 = !{!4, !5}
 !4 = !{!4}
 !5 = !{!5}
	; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
	; RUN: opt < %s -passes=loop-vectorize,dce -force-vector-interleave=1 -force-vector-width=4 -S \| FileCheck %s

	target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
	target triple = "x86_64-unknown-linux-gnu"

	; PR15794
	; incorrect addition of llvm.mem.parallel_loop_access metadata is undefined
	; behaviour. Vectorizer ignores the memory dependency checks and goes ahead and
	; vectorizes this loop with uniform stores which has an output dependency.

	; void foo(int a, int b, int k, int m) {
	; for (int i = 0; i < m; i++) {
	; for (int j = 0; j < m; j++) {
	; a[i] = a[i + j + k] + 1; <<<
	; }
	; b[i] = b[i] + 3;
	; }
	; }

	; Function Attrs: nounwind uwtable
	define void @foo(ptr nocapture %a, ptr nocapture %b, i32 %k, i32 %m) #0 {
	; CHECK-LABEL: @foo(
	; CHECK-NEXT: entry:
	; CHECK-NEXT: [[CMP27:%.]] = icmp sgt i32 [[M:%.]], 0
	; CHECK-NEXT: br i1 [[CMP27]], label [[FOR_BODY3_LR_PH_US_PREHEADER:%.]], label [[FOR_END15:%.]]
	; CHECK: for.body3.lr.ph.us.preheader:
	; CHECK-NEXT: [[TMP0:%.*]] = add i32 [[M]], -1
	; CHECK-NEXT: [[TMP1:%.]] = zext i32 [[K:%.]] to i64
	; CHECK-NEXT: [[TMP2:%.*]] = zext i32 [[M]] to i64
	; CHECK-NEXT: br label [[FOR_BODY3_LR_PH_US:%.*]]
	; CHECK: for.end.us:
	; CHECK-NEXT: [[ARRAYIDX9_US:%.]] = getelementptr inbounds i32, ptr [[B:%.]], i64 [[INDVARS_IV33:%.*]]
	; CHECK-NEXT: [[TMP3:%.*]] = load i32, ptr [[ARRAYIDX9_US]], align 4, !llvm.mem.parallel_loop_access !0
	; CHECK-NEXT: [[ADD10_US:%.*]] = add nsw i32 [[TMP3]], 3
	; CHECK-NEXT: store i32 [[ADD10_US]], ptr [[ARRAYIDX9_US]], align 4, !llvm.mem.parallel_loop_access !0
	; CHECK-NEXT: [[INDVARS_IV_NEXT34:%.*]] = add i64 [[INDVARS_IV33]], 1
	; CHECK-NEXT: [[LFTR_WIDEIV35:%.*]] = trunc i64 [[INDVARS_IV_NEXT34]] to i32
	; CHECK-NEXT: [[EXITCOND36:%.*]] = icmp eq i32 [[LFTR_WIDEIV35]], [[M]]
	; CHECK-NEXT: br i1 [[EXITCOND36]], label [[FOR_END15_LOOPEXIT:%.*]], label [[FOR_BODY3_LR_PH_US]], !llvm.loop [[LOOP2:![0-9]+]]
	; CHECK: for.body3.us:
	; CHECK-NEXT: [[INDVARS_IV29:%.]] = phi i64 [ [[BC_RESUME_VAL:%.]], [[SCALAR_PH:%.]] ], [ [[INDVARS_IV_NEXT30:%.]], [[FOR_BODY3_US:%.*]] ]
	; CHECK-NEXT: [[TMP4:%.*]] = trunc i64 [[INDVARS_IV29]] to i32
	; CHECK-NEXT: [[ADD4_US:%.]] = add i32 [[ADD_US:%.]], [[TMP4]]
	; CHECK-NEXT: [[IDXPROM_US:%.*]] = sext i32 [[ADD4_US]] to i64
	; CHECK-NEXT: [[ARRAYIDX_US:%.]] = getelementptr inbounds i32, ptr [[A:%.]], i64 [[IDXPROM_US]]
	; CHECK-NEXT: [[TMP5:%.*]] = load i32, ptr [[ARRAYIDX_US]], align 4, !llvm.mem.parallel_loop_access !0
	; CHECK-NEXT: [[ADD5_US:%.*]] = add nsw i32 [[TMP5]], 1
	; CHECK-NEXT: store i32 [[ADD5_US]], ptr [[ARRAYIDX7_US:%.*]], align 4, !llvm.mem.parallel_loop_access !0
	; CHECK-NEXT: [[INDVARS_IV_NEXT30]] = add i64 [[INDVARS_IV29]], 1
	; CHECK-NEXT: [[LFTR_WIDEIV31:%.*]] = trunc i64 [[INDVARS_IV_NEXT30]] to i32
	; CHECK-NEXT: [[EXITCOND32:%.*]] = icmp eq i32 [[LFTR_WIDEIV31]], [[M]]
	; CHECK-NEXT: br i1 [[EXITCOND32]], label [[FOR_END_US:%.*]], label [[FOR_BODY3_US]], !llvm.loop [[LOOP3:![0-9]+]]
	; CHECK: for.body3.lr.ph.us:
	; CHECK-NEXT: [[INDVARS_IV33]] = phi i64 [ [[INDVARS_IV_NEXT34]], [[FOR_END_US]] ], [ 0, [[FOR_BODY3_LR_PH_US_PREHEADER]] ]
	; CHECK-NEXT: [[TMP6:%.*]] = add i64 [[TMP1]], [[INDVARS_IV33]]
	; CHECK-NEXT: [[TMP7:%.*]] = trunc i64 [[TMP6]] to i32
	; CHECK-NEXT: [[TMP8:%.*]] = trunc i64 [[INDVARS_IV33]] to i32
	; CHECK-NEXT: [[ADD_US]] = add i32 [[TMP8]], [[K]]
	; CHECK-NEXT: [[ARRAYIDX7_US]] = getelementptr inbounds i32, ptr [[A]], i64 [[INDVARS_IV33]]
	; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[TMP2]], 4
	; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH]], label [[VECTOR_SCEVCHECK:%.*]]
	; CHECK: vector.scevcheck:
	; CHECK-NEXT: [[TMP9:%.*]] = add i32 [[TMP7]], [[TMP0]]
	; CHECK-NEXT: [[TMP10:%.*]] = icmp slt i32 [[TMP9]], [[TMP7]]
	; CHECK-NEXT: br i1 [[TMP10]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
	; CHECK: vector.ph:
	; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[TMP2]], 4
	; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 [[TMP2]], [[N_MOD_VF]]
	; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
	; CHECK: vector.body:
	; CHECK-NEXT: [[OFFSET_IDX:%.]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.]], [[VECTOR_BODY]] ]
	; CHECK-NEXT: [[TMP11:%.*]] = trunc i64 [[OFFSET_IDX]] to i32
	; CHECK-NEXT: [[TMP12:%.*]] = add i32 [[TMP11]], 0
	; CHECK-NEXT: [[TMP13:%.*]] = add i32 [[ADD_US]], [[TMP12]]
	; CHECK-NEXT: [[TMP14:%.*]] = sext i32 [[TMP13]] to i64
	; CHECK-NEXT: [[TMP15:%.*]] = getelementptr inbounds i32, ptr [[A]], i64 [[TMP14]]
	; CHECK-NEXT: [[TMP16:%.*]] = getelementptr inbounds i32, ptr [[TMP15]], i32 0
	; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <4 x i32>, ptr [[TMP16]], align 4
	; CHECK-NEXT: [[TMP17:%.*]] = add nsw <4 x i32> [[WIDE_LOAD]], <i32 1, i32 1, i32 1, i32 1>
	; CHECK-NEXT: [[TMP18:%.*]] = extractelement <4 x i32> [[TMP17]], i32 3
	; CHECK-NEXT: store i32 [[TMP18]], ptr [[ARRAYIDX7_US]], align 4, !llvm.mem.parallel_loop_access !0
	; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[OFFSET_IDX]], 4
	; CHECK-NEXT: [[TMP19:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
	; CHECK-NEXT: br i1 [[TMP19]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
	; CHECK: middle.block:
	; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[TMP2]], [[N_VEC]]
	; CHECK-NEXT: br i1 [[CMP_N]], label [[FOR_END_US]], label [[SCALAR_PH]]
	; CHECK: scalar.ph:
	; CHECK-NEXT: [[BC_RESUME_VAL]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[FOR_BODY3_LR_PH_US]] ], [ 0, [[VECTOR_SCEVCHECK]] ]
	; CHECK-NEXT: br label [[FOR_BODY3_US]]
	; CHECK: for.end15.loopexit:
	; CHECK-NEXT: br label [[FOR_END15]]
	; CHECK: for.end15:
	; CHECK-NEXT: ret void
	;
	entry:
	%cmp27 = icmp sgt i32 %m, 0
	br i1 %cmp27, label %for.body3.lr.ph.us, label %for.end15

	for.end.us: ; preds = %for.body3.us
	%arrayidx9.us = getelementptr inbounds i32, ptr %b, i64 %indvars.iv33
	%0 = load i32, ptr %arrayidx9.us, align 4, !llvm.mem.parallel_loop_access !3
	%add10.us = add nsw i32 %0, 3
	store i32 %add10.us, ptr %arrayidx9.us, align 4, !llvm.mem.parallel_loop_access !3
	%indvars.iv.next34 = add i64 %indvars.iv33, 1
	%lftr.wideiv35 = trunc i64 %indvars.iv.next34 to i32
	%exitcond36 = icmp eq i32 %lftr.wideiv35, %m
	br i1 %exitcond36, label %for.end15, label %for.body3.lr.ph.us, !llvm.loop !5

	for.body3.us: ; preds = %for.body3.us, %for.body3.lr.ph.us
	%indvars.iv29 = phi i64 [ 0, %for.body3.lr.ph.us ], [ %indvars.iv.next30, %for.body3.us ]
	%1 = trunc i64 %indvars.iv29 to i32
	%add4.us = add i32 %add.us, %1
	%idxprom.us = sext i32 %add4.us to i64
	%arrayidx.us = getelementptr inbounds i32, ptr %a, i64 %idxprom.us
	%2 = load i32, ptr %arrayidx.us, align 4, !llvm.mem.parallel_loop_access !3
	%add5.us = add nsw i32 %2, 1
	store i32 %add5.us, ptr %arrayidx7.us, align 4, !llvm.mem.parallel_loop_access !3
	%indvars.iv.next30 = add i64 %indvars.iv29, 1
	%lftr.wideiv31 = trunc i64 %indvars.iv.next30 to i32
	%exitcond32 = icmp eq i32 %lftr.wideiv31, %m
	br i1 %exitcond32, label %for.end.us, label %for.body3.us, !llvm.loop !4

	for.body3.lr.ph.us: ; preds = %for.end.us, %entry
	%indvars.iv33 = phi i64 [ %indvars.iv.next34, %for.end.us ], [ 0, %entry ]
	%3 = trunc i64 %indvars.iv33 to i32
	%add.us = add i32 %3, %k
	%arrayidx7.us = getelementptr inbounds i32, ptr %a, i64 %indvars.iv33
	br label %for.body3.us

	for.end15: ; preds = %for.end.us, %entry
	ret void
	}

	; Same test as above, but without the invalid parallel_loop_access metadata.

	; Here we can see the vectorizer does the mem dep checks and decides it is
	; unsafe to vectorize.
	define void @no-par-mem-metadata(ptr nocapture %a, ptr nocapture %b, i32 %k, i32 %m) #0 {
	; CHECK-LABEL: @no-par-mem-metadata(
	; CHECK-NEXT: entry:
	; CHECK-NEXT: [[CMP27:%.]] = icmp sgt i32 [[M:%.]], 0
	; CHECK-NEXT: br i1 [[CMP27]], label [[FOR_BODY3_LR_PH_US_PREHEADER:%.]], label [[FOR_END15:%.]]
	; CHECK: for.body3.lr.ph.us.preheader:
	; CHECK-NEXT: br label [[FOR_BODY3_LR_PH_US:%.*]]
	; CHECK: for.end.us:
	; CHECK-NEXT: [[ARRAYIDX9_US:%.]] = getelementptr inbounds i32, ptr [[B:%.]], i64 [[INDVARS_IV33:%.*]]
	; CHECK-NEXT: [[TMP0:%.*]] = load i32, ptr [[ARRAYIDX9_US]], align 4
	; CHECK-NEXT: [[ADD10_US:%.*]] = add nsw i32 [[TMP0]], 3
	; CHECK-NEXT: store i32 [[ADD10_US]], ptr [[ARRAYIDX9_US]], align 4
	; CHECK-NEXT: [[INDVARS_IV_NEXT34:%.*]] = add i64 [[INDVARS_IV33]], 1
	; CHECK-NEXT: [[LFTR_WIDEIV35:%.*]] = trunc i64 [[INDVARS_IV_NEXT34]] to i32
	; CHECK-NEXT: [[EXITCOND36:%.*]] = icmp eq i32 [[LFTR_WIDEIV35]], [[M]]
	; CHECK-NEXT: br i1 [[EXITCOND36]], label [[FOR_END15_LOOPEXIT:%.*]], label [[FOR_BODY3_LR_PH_US]], !llvm.loop [[LOOP2]]
	; CHECK: for.body3.us:
	; CHECK-NEXT: [[INDVARS_IV29:%.]] = phi i64 [ 0, [[FOR_BODY3_LR_PH_US]] ], [ [[INDVARS_IV_NEXT30:%.]], [[FOR_BODY3_US:%.*]] ]
	; CHECK-NEXT: [[TMP1:%.*]] = trunc i64 [[INDVARS_IV29]] to i32
	; CHECK-NEXT: [[ADD4_US:%.]] = add i32 [[ADD_US:%.]], [[TMP1]]
	; CHECK-NEXT: [[IDXPROM_US:%.*]] = sext i32 [[ADD4_US]] to i64
	; CHECK-NEXT: [[ARRAYIDX_US:%.]] = getelementptr inbounds i32, ptr [[A:%.]], i64 [[IDXPROM_US]]
	; CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr [[ARRAYIDX_US]], align 4
	; CHECK-NEXT: [[ADD5_US:%.*]] = add nsw i32 [[TMP2]], 1
	; CHECK-NEXT: store i32 [[ADD5_US]], ptr [[ARRAYIDX7_US:%.*]], align 4
	; CHECK-NEXT: [[INDVARS_IV_NEXT30]] = add i64 [[INDVARS_IV29]], 1
	; CHECK-NEXT: [[LFTR_WIDEIV31:%.*]] = trunc i64 [[INDVARS_IV_NEXT30]] to i32
	; CHECK-NEXT: [[EXITCOND32:%.*]] = icmp eq i32 [[LFTR_WIDEIV31]], [[M]]
	; CHECK-NEXT: br i1 [[EXITCOND32]], label [[FOR_END_US:%.*]], label [[FOR_BODY3_US]], !llvm.loop [[LOOP1:![0-9]+]]
	; CHECK: for.body3.lr.ph.us:
	; CHECK-NEXT: [[INDVARS_IV33]] = phi i64 [ [[INDVARS_IV_NEXT34]], [[FOR_END_US]] ], [ 0, [[FOR_BODY3_LR_PH_US_PREHEADER]] ]
	; CHECK-NEXT: [[TMP3:%.*]] = trunc i64 [[INDVARS_IV33]] to i32
	; CHECK-NEXT: [[ADD_US]] = add i32 [[TMP3]], [[K:%.*]]
	; CHECK-NEXT: [[ARRAYIDX7_US]] = getelementptr inbounds i32, ptr [[A]], i64 [[INDVARS_IV33]]
	; CHECK-NEXT: br label [[FOR_BODY3_US]]
	; CHECK: for.end15.loopexit:
	; CHECK-NEXT: br label [[FOR_END15]]
	; CHECK: for.end15:
	; CHECK-NEXT: ret void
	;
	entry:
	%cmp27 = icmp sgt i32 %m, 0
	br i1 %cmp27, label %for.body3.lr.ph.us, label %for.end15

	for.end.us: ; preds = %for.body3.us
	%arrayidx9.us = getelementptr inbounds i32, ptr %b, i64 %indvars.iv33
	%0 = load i32, ptr %arrayidx9.us, align 4
	%add10.us = add nsw i32 %0, 3
	store i32 %add10.us, ptr %arrayidx9.us, align 4
	%indvars.iv.next34 = add i64 %indvars.iv33, 1
	%lftr.wideiv35 = trunc i64 %indvars.iv.next34 to i32
	%exitcond36 = icmp eq i32 %lftr.wideiv35, %m
	br i1 %exitcond36, label %for.end15, label %for.body3.lr.ph.us, !llvm.loop !5

	for.body3.us: ; preds = %for.body3.us, %for.body3.lr.ph.us
	%indvars.iv29 = phi i64 [ 0, %for.body3.lr.ph.us ], [ %indvars.iv.next30, %for.body3.us ]
	%1 = trunc i64 %indvars.iv29 to i32
	%add4.us = add i32 %add.us, %1
	%idxprom.us = sext i32 %add4.us to i64
	%arrayidx.us = getelementptr inbounds i32, ptr %a, i64 %idxprom.us
	%2 = load i32, ptr %arrayidx.us, align 4
	%add5.us = add nsw i32 %2, 1
	store i32 %add5.us, ptr %arrayidx7.us, align 4
	%indvars.iv.next30 = add i64 %indvars.iv29, 1
	%lftr.wideiv31 = trunc i64 %indvars.iv.next30 to i32
	%exitcond32 = icmp eq i32 %lftr.wideiv31, %m
	br i1 %exitcond32, label %for.end.us, label %for.body3.us, !llvm.loop !4

	for.body3.lr.ph.us: ; preds = %for.end.us, %entry
	%indvars.iv33 = phi i64 [ %indvars.iv.next34, %for.end.us ], [ 0, %entry ]
	%3 = trunc i64 %indvars.iv33 to i32
	%add.us = add i32 %3, %k
	%arrayidx7.us = getelementptr inbounds i32, ptr %a, i64 %indvars.iv33
	br label %for.body3.us

	for.end15: ; preds = %for.end.us, %entry
	ret void
	}

	attributes #0 = { nounwind uwtable "less-precise-fpmad"="false" "frame-pointer"="none" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "unsafe-fp-math"="false" "use-soft-float"="false" }

	!3 = !{!4, !5}
	!4 = !{!4}
	!5 = !{!5}