diff options
| author | Matthew Simpson <mssimpso@codeaurora.org> | 2017-03-23 16:07:21 +0000 |
|---|---|---|
| committer | Matthew Simpson <mssimpso@codeaurora.org> | 2017-03-23 16:07:21 +0000 |
| commit | 1fb4064531161167324a35aa860f67f3005f3f24 (patch) | |
| tree | 73492460324584688e8848216a4410135f61bef1 /llvm/test/Transforms/LoopVectorize/float-induction.ll | |
| parent | ce26a45f7c3457c9b1953ba99b1054c123b6c055 (diff) | |
| download | bcm5719-llvm-1fb4064531161167324a35aa860f67f3005f3f24.tar.gz bcm5719-llvm-1fb4064531161167324a35aa860f67f3005f3f24.zip | |
[LV] Delete unneeded scalar GEP creation code
The code for generating scalar base pointers in vectorizeMemoryInstruction is
not needed. We currently scalarize all GEPs and maintain the scalarized values
in VectorLoopValueMap. The GEP cloning in this unneeded code is the same as
that in scalarizeInstruction. The test cases that changed as a result of this
patch changed because we were able to reuse the scalarized GEP that we
previously generated instead of cloning a new one.
Differential Revision: https://reviews.llvm.org/D30587
llvm-svn: 298615
Diffstat (limited to 'llvm/test/Transforms/LoopVectorize/float-induction.ll')
| -rw-r--r-- | llvm/test/Transforms/LoopVectorize/float-induction.ll | 3 |
1 files changed, 1 insertions, 2 deletions
diff --git a/llvm/test/Transforms/LoopVectorize/float-induction.ll b/llvm/test/Transforms/LoopVectorize/float-induction.ll index 4cd617ccde4..8eec6e262c1 100644 --- a/llvm/test/Transforms/LoopVectorize/float-induction.ll +++ b/llvm/test/Transforms/LoopVectorize/float-induction.ll @@ -298,8 +298,7 @@ for.end: ; preds = %for.end.loopexit, % ; VEC2_INTERL1_PRED_STORE-NEXT: [[TMP5:%.*]] = extractelement <2 x i1> [[TMP4]], i32 0 ; VEC2_INTERL1_PRED_STORE-NEXT: br i1 [[TMP5]], label %[[PRED_STORE_IF:.*]], label %[[PRED_STORE_CONTINUE:.*]] ; VEC2_INTERL1_PRED_STORE: [[PRED_STORE_IF]]: -; VEC2_INTERL1_PRED_STORE-NEXT: [[TMP7:%.*]] = getelementptr inbounds float, float* %A, i64 [[INDEX]] -; VEC2_INTERL1_PRED_STORE-NEXT: store float [[TMP1]], float* [[TMP7]], align 4 +; VEC2_INTERL1_PRED_STORE-NEXT: store float [[TMP1]], float* [[TMP2]], align 4 ; VEC2_INTERL1_PRED_STORE-NEXT: br label %[[PRED_STORE_CONTINUE]] ; VEC2_INTERL1_PRED_STORE: [[PRED_STORE_CONTINUE]]: ; VEC2_INTERL1_PRED_STORE-NEXT: [[TMP8:%.*]] = extractelement <2 x i1> [[TMP4]], i32 1 |
