llvm/test/Transforms/LoopVectorize/pr34681.ll

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --check-globals none --filter-out-after "scalar.ph:" --version 5
; RUN: opt -S -passes=loop-vectorize -force-vector-width=4 -force-vector-interleave=1 < %s | FileCheck %s

target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"

; Check the scenario where we have an unknown Stride, which happens to also be
; the loop iteration count, so if we specialize the loop for the Stride==1 case,
; this also implies that the loop will iterate no more than a single iteration,
; as in the following example:
;
;       unsigned int N;
;       int tmp = 0;
;       for(unsigned int k=0;k<N;k++) {
;         tmp+=(int)B[k*N+j];
;       }
;
; We check here that the following runtime scev guard for Stride==1 is NOT generated:
; vector.scevcheck:
;   %ident.check = icmp ne i32 %N, 1
;   %0 = or i1 false, %ident.check
;   br i1 %0, label %scalar.ph, label %vector.ph
; Instead the loop is vectorized with an unknown stride.



define i32 @foo1(i32 %N, ptr nocapture readnone %A, ptr nocapture readonly %B, i32 %i, i32 %j)  {
; CHECK-LABEL: define i32 @foo1(
; CHECK-SAME: i32 [[N:%.*]], ptr readnone captures(none) [[A:%.*]], ptr readonly captures(none) [[B:%.*]], i32 [[I:%.*]], i32 [[J:%.*]]) {
; CHECK-NEXT:  [[ENTRY:.*:]]
; CHECK-NEXT:    [[CMP8:%.*]] = icmp eq i32 [[N]], 0
; CHECK-NEXT:    br i1 [[CMP8]], [[FOR_END:label %.*]], label %[[FOR_BODY_LR_PH:.*]]
; CHECK:       [[FOR_BODY_LR_PH]]:
; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i32 [[N]], 4
; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label %[[SCALAR_PH:.*]], label %[[VECTOR_SCEVCHECK:.*]]
; CHECK:       [[VECTOR_SCEVCHECK]]:
; CHECK-NEXT:    [[TMP0:%.*]] = add i32 [[N]], -1
; CHECK-NEXT:    [[TMP1:%.*]] = sub i32 0, [[N]]
; CHECK-NEXT:    [[TMP2:%.*]] = icmp slt i32 [[N]], 0
; CHECK-NEXT:    [[TMP3:%.*]] = select i1 [[TMP2]], i32 [[TMP1]], i32 [[N]]
; CHECK-NEXT:    [[MUL1:%.*]] = call { i32, i1 } @llvm.umul.with.overflow.i32(i32 [[TMP3]], i32 [[TMP0]])
; CHECK-NEXT:    [[MUL_RESULT:%.*]] = extractvalue { i32, i1 } [[MUL1]], 0
; CHECK-NEXT:    [[MUL_OVERFLOW:%.*]] = extractvalue { i32, i1 } [[MUL1]], 1
; CHECK-NEXT:    [[TMP4:%.*]] = add i32 [[J]], [[MUL_RESULT]]
; CHECK-NEXT:    [[TMP5:%.*]] = sub i32 [[J]], [[MUL_RESULT]]
; CHECK-NEXT:    [[TMP6:%.*]] = icmp slt i32 [[TMP4]], [[J]]
; CHECK-NEXT:    [[TMP7:%.*]] = icmp sgt i32 [[TMP5]], [[J]]
; CHECK-NEXT:    [[TMP8:%.*]] = select i1 [[TMP2]], i1 [[TMP7]], i1 [[TMP6]]
; CHECK-NEXT:    [[TMP9:%.*]] = or i1 [[TMP8]], [[MUL_OVERFLOW]]
; CHECK-NEXT:    br i1 [[TMP9]], label %[[SCALAR_PH]], label %[[VECTOR_PH:.*]]
; CHECK:       [[VECTOR_PH]]:
; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i32 [[N]], 4
; CHECK-NEXT:    [[N_VEC:%.*]] = sub i32 [[N]], [[N_MOD_VF]]
; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i32> poison, i32 [[N]], i64 0
; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT]], <4 x i32> poison, <4 x i32> zeroinitializer
; CHECK-NEXT:    [[BROADCAST_SPLATINSERT2:%.*]] = insertelement <4 x i32> poison, i32 [[J]], i64 0
; CHECK-NEXT:    [[BROADCAST_SPLAT3:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT2]], <4 x i32> poison, <4 x i32> zeroinitializer
; CHECK-NEXT:    br label %[[VECTOR_BODY:.*]]
; CHECK:       [[VECTOR_BODY]]:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi <4 x i32> [ zeroinitializer, %[[VECTOR_PH]] ], [ [[TMP29:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT:    [[VEC_IND:%.*]] = phi <4 x i32> [ <i32 0, i32 1, i32 2, i32 3>, %[[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP10:%.*]] = mul <4 x i32> [[VEC_IND]], [[BROADCAST_SPLAT]]
; CHECK-NEXT:    [[TMP11:%.*]] = add <4 x i32> [[TMP10]], [[BROADCAST_SPLAT3]]
; CHECK-NEXT:    [[TMP12:%.*]] = extractelement <4 x i32> [[TMP11]], i32 0
; CHECK-NEXT:    [[TMP13:%.*]] = getelementptr inbounds i16, ptr [[B]], i32 [[TMP12]]
; CHECK-NEXT:    [[TMP14:%.*]] = extractelement <4 x i32> [[TMP11]], i32 1
; CHECK-NEXT:    [[TMP15:%.*]] = getelementptr inbounds i16, ptr [[B]], i32 [[TMP14]]
; CHECK-NEXT:    [[TMP16:%.*]] = extractelement <4 x i32> [[TMP11]], i32 2
; CHECK-NEXT:    [[TMP17:%.*]] = getelementptr inbounds i16, ptr [[B]], i32 [[TMP16]]
; CHECK-NEXT:    [[TMP18:%.*]] = extractelement <4 x i32> [[TMP11]], i32 3
; CHECK-NEXT:    [[TMP19:%.*]] = getelementptr inbounds i16, ptr [[B]], i32 [[TMP18]]
; CHECK-NEXT:    [[TMP20:%.*]] = load i16, ptr [[TMP13]], align 2
; CHECK-NEXT:    [[TMP21:%.*]] = load i16, ptr [[TMP15]], align 2
; CHECK-NEXT:    [[TMP22:%.*]] = load i16, ptr [[TMP17]], align 2
; CHECK-NEXT:    [[TMP23:%.*]] = load i16, ptr [[TMP19]], align 2
; CHECK-NEXT:    [[TMP24:%.*]] = insertelement <4 x i16> poison, i16 [[TMP20]], i32 0
; CHECK-NEXT:    [[TMP25:%.*]] = insertelement <4 x i16> [[TMP24]], i16 [[TMP21]], i32 1
; CHECK-NEXT:    [[TMP26:%.*]] = insertelement <4 x i16> [[TMP25]], i16 [[TMP22]], i32 2
; CHECK-NEXT:    [[TMP27:%.*]] = insertelement <4 x i16> [[TMP26]], i16 [[TMP23]], i32 3
; CHECK-NEXT:    [[TMP28:%.*]] = sext <4 x i16> [[TMP27]] to <4 x i32>
; CHECK-NEXT:    [[TMP29]] = add <4 x i32> [[VEC_PHI]], [[TMP28]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 4
; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <4 x i32> [[VEC_IND]], splat (i32 4)
; CHECK-NEXT:    [[TMP30:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP30]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK:       [[MIDDLE_BLOCK]]:
; CHECK-NEXT:    [[TMP31:%.*]] = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> [[TMP29]])
; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i32 [[N]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[CMP_N]], [[FOR_END_LOOPEXIT:label %.*]], label %[[SCALAR_PH]]
; CHECK:       [[SCALAR_PH]]:
;
entry:
  %cmp8 = icmp eq i32 %N, 0
  br i1 %cmp8, label %for.end, label %for.body.lr.ph

for.body.lr.ph:
  br label %for.body

for.body:
  %tmp.010 = phi i32 [ 0, %for.body.lr.ph ], [ %add1, %for.body ]
  %k.09 = phi i32 [ 0, %for.body.lr.ph ], [ %inc, %for.body ]
  %mul = mul i32 %k.09, %N
  %add = add i32 %mul, %j
  %arrayidx = getelementptr inbounds i16, ptr %B, i32 %add
  %0 = load i16, ptr %arrayidx, align 2
  %conv = sext i16 %0 to i32
  %add1 = add nsw i32 %tmp.010, %conv
  %inc = add nuw i32 %k.09, 1
  %exitcond = icmp eq i32 %inc, %N
  br i1 %exitcond, label %for.end.loopexit, label %for.body

for.end.loopexit:
  %add1.lcssa = phi i32 [ %add1, %for.body ]
  br label %for.end

for.end:
  %tmp.0.lcssa = phi i32 [ 0, %entry ], [ %add1.lcssa, %for.end.loopexit ]
  ret i32 %tmp.0.lcssa
}


; Check the same, but also where the Stride and the loop iteration count
; are not of the same data type.
;
;       unsigned short N;
;       int tmp = 0;
;       for(unsigned int k=0;k<N;k++) {
;         tmp+=(int)B[k*N+j];
;       }
;
; We check here that the following runtime scev guard for Stride==1 is NOT generated:
; vector.scevcheck:
; %ident.check = icmp ne i16 %N, 1
; %0 = or i1 false, %ident.check
; br i1 %0, label %scalar.ph, label %vector.ph
define i32 @foo2(i16 zeroext %N, ptr nocapture readnone %A, ptr nocapture readonly %B, i32 %i, i32 %j) {
; CHECK-LABEL: define i32 @foo2(
; CHECK-SAME: i16 zeroext [[N:%.*]], ptr readnone captures(none) [[A:%.*]], ptr readonly captures(none) [[B:%.*]], i32 [[I:%.*]], i32 [[J:%.*]]) {
; CHECK-NEXT:  [[ENTRY:.*:]]
; CHECK-NEXT:    [[CONV:%.*]] = zext i16 [[N]] to i32
; CHECK-NEXT:    [[CMP11:%.*]] = icmp eq i16 [[N]], 0
; CHECK-NEXT:    br i1 [[CMP11]], [[FOR_END:label %.*]], label %[[FOR_BODY_LR_PH:.*]]
; CHECK:       [[FOR_BODY_LR_PH]]:
; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i32 [[CONV]], 4
; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label %[[SCALAR_PH:.*]], label %[[VECTOR_SCEVCHECK:.*]]
; CHECK:       [[VECTOR_SCEVCHECK]]:
; CHECK-NEXT:    [[TMP0:%.*]] = add nsw i32 [[CONV]], -1
; CHECK-NEXT:    [[TMP1:%.*]] = sub i32 0, [[CONV]]
; CHECK-NEXT:    [[MUL1:%.*]] = call { i32, i1 } @llvm.umul.with.overflow.i32(i32 [[CONV]], i32 [[TMP0]])
; CHECK-NEXT:    [[MUL_RESULT:%.*]] = extractvalue { i32, i1 } [[MUL1]], 0
; CHECK-NEXT:    [[MUL_OVERFLOW:%.*]] = extractvalue { i32, i1 } [[MUL1]], 1
; CHECK-NEXT:    [[TMP2:%.*]] = add i32 [[J]], [[MUL_RESULT]]
; CHECK-NEXT:    [[TMP3:%.*]] = sub i32 [[J]], [[MUL_RESULT]]
; CHECK-NEXT:    [[TMP4:%.*]] = icmp slt i32 [[TMP2]], [[J]]
; CHECK-NEXT:    [[TMP5:%.*]] = icmp sgt i32 [[TMP3]], [[J]]
; CHECK-NEXT:    [[TMP6:%.*]] = or i1 [[TMP4]], [[MUL_OVERFLOW]]
; CHECK-NEXT:    br i1 [[TMP6]], label %[[SCALAR_PH]], label %[[VECTOR_PH:.*]]
; CHECK:       [[VECTOR_PH]]:
; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i32 [[CONV]], 4
; CHECK-NEXT:    [[N_VEC:%.*]] = sub i32 [[CONV]], [[N_MOD_VF]]
; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i32> poison, i32 [[CONV]], i64 0
; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT]], <4 x i32> poison, <4 x i32> zeroinitializer
; CHECK-NEXT:    [[BROADCAST_SPLATINSERT2:%.*]] = insertelement <4 x i32> poison, i32 [[J]], i64 0
; CHECK-NEXT:    [[BROADCAST_SPLAT3:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT2]], <4 x i32> poison, <4 x i32> zeroinitializer
; CHECK-NEXT:    br label %[[VECTOR_BODY:.*]]
; CHECK:       [[VECTOR_BODY]]:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi <4 x i32> [ zeroinitializer, %[[VECTOR_PH]] ], [ [[TMP26:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT:    [[VEC_IND:%.*]] = phi <4 x i32> [ <i32 0, i32 1, i32 2, i32 3>, %[[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT:    [[TMP7:%.*]] = mul nuw <4 x i32> [[VEC_IND]], [[BROADCAST_SPLAT]]
; CHECK-NEXT:    [[TMP8:%.*]] = add <4 x i32> [[TMP7]], [[BROADCAST_SPLAT3]]
; CHECK-NEXT:    [[TMP9:%.*]] = extractelement <4 x i32> [[TMP8]], i32 0
; CHECK-NEXT:    [[TMP10:%.*]] = getelementptr inbounds i16, ptr [[B]], i32 [[TMP9]]
; CHECK-NEXT:    [[TMP11:%.*]] = extractelement <4 x i32> [[TMP8]], i32 1
; CHECK-NEXT:    [[TMP12:%.*]] = getelementptr inbounds i16, ptr [[B]], i32 [[TMP11]]
; CHECK-NEXT:    [[TMP13:%.*]] = extractelement <4 x i32> [[TMP8]], i32 2
; CHECK-NEXT:    [[TMP14:%.*]] = getelementptr inbounds i16, ptr [[B]], i32 [[TMP13]]
; CHECK-NEXT:    [[TMP15:%.*]] = extractelement <4 x i32> [[TMP8]], i32 3
; CHECK-NEXT:    [[TMP16:%.*]] = getelementptr inbounds i16, ptr [[B]], i32 [[TMP15]]
; CHECK-NEXT:    [[TMP17:%.*]] = load i16, ptr [[TMP10]], align 2
; CHECK-NEXT:    [[TMP18:%.*]] = load i16, ptr [[TMP12]], align 2
; CHECK-NEXT:    [[TMP19:%.*]] = load i16, ptr [[TMP14]], align 2
; CHECK-NEXT:    [[TMP20:%.*]] = load i16, ptr [[TMP16]], align 2
; CHECK-NEXT:    [[TMP21:%.*]] = insertelement <4 x i16> poison, i16 [[TMP17]], i32 0
; CHECK-NEXT:    [[TMP22:%.*]] = insertelement <4 x i16> [[TMP21]], i16 [[TMP18]], i32 1
; CHECK-NEXT:    [[TMP23:%.*]] = insertelement <4 x i16> [[TMP22]], i16 [[TMP19]], i32 2
; CHECK-NEXT:    [[TMP24:%.*]] = insertelement <4 x i16> [[TMP23]], i16 [[TMP20]], i32 3
; CHECK-NEXT:    [[TMP25:%.*]] = sext <4 x i16> [[TMP24]] to <4 x i32>
; CHECK-NEXT:    [[TMP26]] = add <4 x i32> [[VEC_PHI]], [[TMP25]]
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 4
; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <4 x i32> [[VEC_IND]], splat (i32 4)
; CHECK-NEXT:    [[TMP27:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[TMP27]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
; CHECK:       [[MIDDLE_BLOCK]]:
; CHECK-NEXT:    [[TMP28:%.*]] = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> [[TMP26]])
; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i32 [[CONV]], [[N_VEC]]
; CHECK-NEXT:    br i1 [[CMP_N]], [[FOR_END_LOOPEXIT:label %.*]], label %[[SCALAR_PH]]
; CHECK:       [[SCALAR_PH]]:
;
entry:
  %conv = zext i16 %N to i32
  %cmp11 = icmp eq i16 %N, 0
  br i1 %cmp11, label %for.end, label %for.body.lr.ph

for.body.lr.ph:
  br label %for.body

for.body:
  %tmp.013 = phi i32 [ 0, %for.body.lr.ph ], [ %add4, %for.body ]
  %k.012 = phi i32 [ 0, %for.body.lr.ph ], [ %inc, %for.body ]
  %mul = mul nuw i32 %k.012, %conv
  %add = add i32 %mul, %j
  %arrayidx = getelementptr inbounds i16, ptr %B, i32 %add
  %0 = load i16, ptr %arrayidx, align 2
  %conv3 = sext i16 %0 to i32
  %add4 = add nsw i32 %tmp.013, %conv3
  %inc = add nuw nsw i32 %k.012, 1
  %exitcond = icmp eq i32 %inc, %conv
  br i1 %exitcond, label %for.end.loopexit, label %for.body

for.end.loopexit:
  %add4.lcssa = phi i32 [ %add4, %for.body ]
  br label %for.end

for.end:
  %tmp.0.lcssa = phi i32 [ 0, %entry ], [ %add4.lcssa, %for.end.loopexit ]
  ret i32 %tmp.0.lcssa
}