[LV] Generate both scalar and vector integer induction variables

This patch enables the vectorizer to generate both scalar and vector versions
of an integer induction variable for a given loop. Previously, we only
generated a scalar induction variable if we knew all its users were going to be
scalar. Otherwise, we generated a vector induction variable. In the case of a
loop with both scalar and vector users of the induction variable, we would
generate the vector induction variable and extract scalar values from it for
the scalar users. With this patch, we now generate both versions of the
induction variable when there are both scalar and vector users and select which
version to use based on whether the user is scalar or vector.

Differential Revision: https://reviews.llvm.org/D22869

llvm-svn: 277474

1 files changed, 34 insertions, 32 deletions

diff --git a/llvm/test/Transforms/LoopVectorize/X86/scatter_crash.ll b/llvm/test/Transforms/LoopVectorize/X86/scatter_crash.ll
index 464bbb9d4f9..4b9e996d408 100755
--- a/llvm/test/Transforms/LoopVectorize/X86/scatter_crash.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/scatter_crash.ll
@@ -19,54 +19,56 @@ define void @_Z3fn1v() #0 {
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, %vector.ph ], [ [[INDEX:%.*]].next, %vector.body ]
 ; CHECK-NEXT:    [[VEC_IND:%.*]] = phi <16 x i64> [ 
 ; CHECK-NEXT:    [[VEC_IND3:%.*]] = phi <16 x i64> [ 
+; CHECK-NEXT:    [[SHL:%.*]] = shl i64 %index, 1
+; CHECK-NEXT:    %offset.idx = add i64 [[SHL]], 8
+; CHECK-NEXT:    [[IND00:%.*]] = add i64 %offset.idx, 0
+; CHECK-NEXT:    [[IND02:%.*]] = add i64 %offset.idx, 2
+; CHECK-NEXT:    [[IND04:%.*]] = add i64 %offset.idx, 4
+; CHECK-NEXT:    [[IND06:%.*]] = add i64 %offset.idx, 6
+; CHECK-NEXT:    [[IND08:%.*]] = add i64 %offset.idx, 8
+; CHECK-NEXT:    [[IND10:%.*]] = add i64 %offset.idx, 10
+; CHECK-NEXT:    [[IND12:%.*]] = add i64 %offset.idx, 12
+; CHECK-NEXT:    [[IND14:%.*]] = add i64 %offset.idx, 14
+; CHECK-NEXT:    [[IND16:%.*]] = add i64 %offset.idx, 16
+; CHECK-NEXT:    [[IND18:%.*]] = add i64 %offset.idx, 18
+; CHECK-NEXT:    [[IND20:%.*]] = add i64 %offset.idx, 20
+; CHECK-NEXT:    [[IND22:%.*]] = add i64 %offset.idx, 22
+; CHECK-NEXT:    [[IND24:%.*]] = add i64 %offset.idx, 24
+; CHECK-NEXT:    [[IND26:%.*]] = add i64 %offset.idx, 26
+; CHECK-NEXT:    [[IND28:%.*]] = add i64 %offset.idx, 28
+; CHECK-NEXT:    [[IND30:%.*]] = add i64 %offset.idx, 30
 ; CHECK-NEXT:    [[TMP10:%.*]] = sub nsw <16 x i64> <i64 8, i64 8, i64 8, i64 8, i64 8, i64 8, i64 8, i64 8, i64 8, i64 8, i64 8, i64 8, i64 8, i64 8, i64 8, i64 8>, [[VEC_IND]]
-; CHECK-NEXT:    [[TMP11:%.*]] = extractelement <16 x i64> [[VEC_IND]], i32 0
-; CHECK-NEXT:    [[TMP12:%.*]] = getelementptr inbounds [10 x [10 x i32]], [10 x [10 x i32]]* @d, i64 0, i64 [[TMP11]]
+; CHECK-NEXT:    [[TMP12:%.*]] = getelementptr inbounds [10 x [10 x i32]], [10 x [10 x i32]]* @d, i64 0, i64 [[IND00]]
 ; CHECK-NEXT:    [[TMP13:%.*]] = insertelement <16 x [10 x i32]*> undef, [10 x i32]* [[TMP12]], i32 0
-; CHECK-NEXT:    [[TMP14:%.*]] = extractelement <16 x i64> [[VEC_IND]], i32 1
-; CHECK-NEXT:    [[TMP15:%.*]] = getelementptr inbounds [10 x [10 x i32]], [10 x [10 x i32]]* @d, i64 0, i64 [[TMP14]]
+; CHECK-NEXT:    [[TMP15:%.*]] = getelementptr inbounds [10 x [10 x i32]], [10 x [10 x i32]]* @d, i64 0, i64 [[IND02]]
 ; CHECK-NEXT:    [[TMP16:%.*]] = insertelement <16 x [10 x i32]*> [[TMP13]], [10 x i32]* [[TMP15]], i32 1
-; CHECK-NEXT:    [[TMP17:%.*]] = extractelement <16 x i64> [[VEC_IND]], i32 2
-; CHECK-NEXT:    [[TMP18:%.*]] = getelementptr inbounds [10 x [10 x i32]], [10 x [10 x i32]]* @d, i64 0, i64 [[TMP17]]
+; CHECK-NEXT:    [[TMP18:%.*]] = getelementptr inbounds [10 x [10 x i32]], [10 x [10 x i32]]* @d, i64 0, i64 [[IND04]]
 ; CHECK-NEXT:    [[TMP19:%.*]] = insertelement <16 x [10 x i32]*> [[TMP16]], [10 x i32]* [[TMP18]], i32 2
-; CHECK-NEXT:    [[TMP20:%.*]] = extractelement <16 x i64> [[VEC_IND]], i32 3
-; CHECK-NEXT:    [[TMP21:%.*]] = getelementptr inbounds [10 x [10 x i32]], [10 x [10 x i32]]* @d, i64 0, i64 [[TMP20]]
+; CHECK-NEXT:    [[TMP21:%.*]] = getelementptr inbounds [10 x [10 x i32]], [10 x [10 x i32]]* @d, i64 0, i64 [[IND06]]
 ; CHECK-NEXT:    [[TMP22:%.*]] = insertelement <16 x [10 x i32]*> [[TMP19]], [10 x i32]* [[TMP21]], i32 3
-; CHECK-NEXT:    [[TMP23:%.*]] = extractelement <16 x i64> [[VEC_IND]], i32 4
-; CHECK-NEXT:    [[TMP24:%.*]] = getelementptr inbounds [10 x [10 x i32]], [10 x [10 x i32]]* @d, i64 0, i64 [[TMP23]]
+; CHECK-NEXT:    [[TMP24:%.*]] = getelementptr inbounds [10 x [10 x i32]], [10 x [10 x i32]]* @d, i64 0, i64 [[IND08]]
 ; CHECK-NEXT:    [[TMP25:%.*]] = insertelement <16 x [10 x i32]*> [[TMP22]], [10 x i32]* [[TMP24]], i32 4
-; CHECK-NEXT:    [[TMP26:%.*]] = extractelement <16 x i64> [[VEC_IND]], i32 5
-; CHECK-NEXT:    [[TMP27:%.*]] = getelementptr inbounds [10 x [10 x i32]], [10 x [10 x i32]]* @d, i64 0, i64 [[TMP26]]
+; CHECK-NEXT:    [[TMP27:%.*]] = getelementptr inbounds [10 x [10 x i32]], [10 x [10 x i32]]* @d, i64 0, i64 [[IND10]]
 ; CHECK-NEXT:    [[TMP28:%.*]] = insertelement <16 x [10 x i32]*> [[TMP25]], [10 x i32]* [[TMP27]], i32 5
-; CHECK-NEXT:    [[TMP29:%.*]] = extractelement <16 x i64> [[VEC_IND]], i32 6
-; CHECK-NEXT:    [[TMP30:%.*]] = getelementptr inbounds [10 x [10 x i32]], [10 x [10 x i32]]* @d, i64 0, i64 [[TMP29]]
+; CHECK-NEXT:    [[TMP30:%.*]] = getelementptr inbounds [10 x [10 x i32]], [10 x [10 x i32]]* @d, i64 0, i64 [[IND12]]
 ; CHECK-NEXT:    [[TMP31:%.*]] = insertelement <16 x [10 x i32]*> [[TMP28]], [10 x i32]* [[TMP30]], i32 6
-; CHECK-NEXT:    [[TMP32:%.*]] = extractelement <16 x i64> [[VEC_IND]], i32 7
-; CHECK-NEXT:    [[TMP33:%.*]] = getelementptr inbounds [10 x [10 x i32]], [10 x [10 x i32]]* @d, i64 0, i64 [[TMP32]]
+; CHECK-NEXT:    [[TMP33:%.*]] = getelementptr inbounds [10 x [10 x i32]], [10 x [10 x i32]]* @d, i64 0, i64 [[IND14]]
 ; CHECK-NEXT:    [[TMP34:%.*]] = insertelement <16 x [10 x i32]*> [[TMP31]], [10 x i32]* [[TMP33]], i32 7
-; CHECK-NEXT:    [[TMP35:%.*]] = extractelement <16 x i64> [[VEC_IND]], i32 8
-; CHECK-NEXT:    [[TMP36:%.*]] = getelementptr inbounds [10 x [10 x i32]], [10 x [10 x i32]]* @d, i64 0, i64 [[TMP35]]
+; CHECK-NEXT:    [[TMP36:%.*]] = getelementptr inbounds [10 x [10 x i32]], [10 x [10 x i32]]* @d, i64 0, i64 [[IND16]]
 ; CHECK-NEXT:    [[TMP37:%.*]] = insertelement <16 x [10 x i32]*> [[TMP34]], [10 x i32]* [[TMP36]], i32 8
-; CHECK-NEXT:    [[TMP38:%.*]] = extractelement <16 x i64> [[VEC_IND]], i32 9
-; CHECK-NEXT:    [[TMP39:%.*]] = getelementptr inbounds [10 x [10 x i32]], [10 x [10 x i32]]* @d, i64 0, i64 [[TMP38]]
+; CHECK-NEXT:    [[TMP39:%.*]] = getelementptr inbounds [10 x [10 x i32]], [10 x [10 x i32]]* @d, i64 0, i64 [[IND18]]
 ; CHECK-NEXT:    [[TMP40:%.*]] = insertelement <16 x [10 x i32]*> [[TMP37]], [10 x i32]* [[TMP39]], i32 9
-; CHECK-NEXT:    [[TMP41:%.*]] = extractelement <16 x i64> [[VEC_IND]], i32 10
-; CHECK-NEXT:    [[TMP42:%.*]] = getelementptr inbounds [10 x [10 x i32]], [10 x [10 x i32]]* @d, i64 0, i64 [[TMP41]]
+; CHECK-NEXT:    [[TMP42:%.*]] = getelementptr inbounds [10 x [10 x i32]], [10 x [10 x i32]]* @d, i64 0, i64 [[IND20]]
 ; CHECK-NEXT:    [[TMP43:%.*]] = insertelement <16 x [10 x i32]*> [[TMP40]], [10 x i32]* [[TMP42]], i32 10
-; CHECK-NEXT:    [[TMP44:%.*]] = extractelement <16 x i64> [[VEC_IND]], i32 11
-; CHECK-NEXT:    [[TMP45:%.*]] = getelementptr inbounds [10 x [10 x i32]], [10 x [10 x i32]]* @d, i64 0, i64 [[TMP44]]
+; CHECK-NEXT:    [[TMP45:%.*]] = getelementptr inbounds [10 x [10 x i32]], [10 x [10 x i32]]* @d, i64 0, i64 [[IND22]]
 ; CHECK-NEXT:    [[TMP46:%.*]] = insertelement <16 x [10 x i32]*> [[TMP43]], [10 x i32]* [[TMP45]], i32 11
-; CHECK-NEXT:    [[TMP47:%.*]] = extractelement <16 x i64> [[VEC_IND]], i32 12
-; CHECK-NEXT:    [[TMP48:%.*]] = getelementptr inbounds [10 x [10 x i32]], [10 x [10 x i32]]* @d, i64 0, i64 [[TMP47]]
+; CHECK-NEXT:    [[TMP48:%.*]] = getelementptr inbounds [10 x [10 x i32]], [10 x [10 x i32]]* @d, i64 0, i64 [[IND24]]
 ; CHECK-NEXT:    [[TMP49:%.*]] = insertelement <16 x [10 x i32]*> [[TMP46]], [10 x i32]* [[TMP48]], i32 12
-; CHECK-NEXT:    [[TMP50:%.*]] = extractelement <16 x i64> [[VEC_IND]], i32 13
-; CHECK-NEXT:    [[TMP51:%.*]] = getelementptr inbounds [10 x [10 x i32]], [10 x [10 x i32]]* @d, i64 0, i64 [[TMP50]]
+; CHECK-NEXT:    [[TMP51:%.*]] = getelementptr inbounds [10 x [10 x i32]], [10 x [10 x i32]]* @d, i64 0, i64 [[IND26]]
 ; CHECK-NEXT:    [[TMP52:%.*]] = insertelement <16 x [10 x i32]*> [[TMP49]], [10 x i32]* [[TMP51]], i32 13
-; CHECK-NEXT:    [[TMP53:%.*]] = extractelement <16 x i64> [[VEC_IND]], i32 14
-; CHECK-NEXT:    [[TMP54:%.*]] = getelementptr inbounds [10 x [10 x i32]], [10 x [10 x i32]]* @d, i64 0, i64 [[TMP53]]
+; CHECK-NEXT:    [[TMP54:%.*]] = getelementptr inbounds [10 x [10 x i32]], [10 x [10 x i32]]* @d, i64 0, i64 [[IND28]]
 ; CHECK-NEXT:    [[TMP55:%.*]] = insertelement <16 x [10 x i32]*> [[TMP52]], [10 x i32]* [[TMP54]], i32 14
-; CHECK-NEXT:    [[TMP56:%.*]] = extractelement <16 x i64> [[VEC_IND]], i32 15
-; CHECK-NEXT:    [[TMP57:%.*]] = getelementptr inbounds [10 x [10 x i32]], [10 x [10 x i32]]* @d, i64 0, i64 [[TMP56]]
+; CHECK-NEXT:    [[TMP57:%.*]] = getelementptr inbounds [10 x [10 x i32]], [10 x [10 x i32]]* @d, i64 0, i64 [[IND30]]
 ; CHECK-NEXT:    [[TMP58:%.*]] = insertelement <16 x [10 x i32]*> [[TMP55]], [10 x i32]* [[TMP57]], i32 15
 ; CHECK-NEXT:    [[TMP59:%.*]] = add nsw <16 x i64> [[TMP10]], [[VEC_IND3]]
 ; CHECK-NEXT:    [[TMP60:%.*]] = extractelement <16 x [10 x i32]*> [[TMP58]], i32 0