| Commit message (Expand) | Author | Age | Files | Lines |
|---|
| * | [LV] Build all scalar steps for non-uniform induction variables | Matthew Simpson | 2016-09-30 | 1 | -14/+3 |
| * | [LV] Port the remarks in processLoop to the new streaming API | Adam Nemet | 2016-09-30 | 1 | -22/+39 |
| * | [LV] Port the last opt remark in Hints to the new streaming interface | Adam Nemet | 2016-09-30 | 1 | -5/+6 |
| * | [LAA, LV] Port to new streaming interface for opt remarks. Update LV | Adam Nemet | 2016-09-30 | 1 | -3/+6 |
| * | Revert "[LAA, LV] Port to new streaming interface for opt remarks. Update LV" | Adam Nemet | 2016-09-29 | 1 | -6/+3 |
| * | [LAA, LV] Port to new streaming interface for opt remarks. Update LV | Adam Nemet | 2016-09-29 | 1 | -3/+6 |
| * | [LV] Port OptimizationRemarkAnalysisFPCommute and | Adam Nemet | 2016-09-29 | 1 | -10/+12 |
| * | [LV] Convert processLoop to new streaming API for opt remarks | Adam Nemet | 2016-09-29 | 1 | -10/+10 |
| * | [LV] Move static createMissedAnalysis from anonymous to global namespace | Adam Nemet | 2016-09-29 | 1 | -26/+26 |
| * | [LV] Convert CostModel to use the new streaming opt remark API | Adam Nemet | 2016-09-29 | 1 | -21/+20 |
| * | [LV] Split most of createMissedAnalysis into a static function. NFC | Adam Nemet | 2016-09-29 | 1 | -15/+28 |
| * | [LV] Convert all but one opt remark in Legality to new streaming interface | Adam Nemet | 2016-09-29 | 1 | -46/+72 |
| * | [LV] Convert emitRemark to new opt remark streaming interface | Adam Nemet | 2016-09-29 | 1 | -14/+17 |
| * | Shorten DiagnosticInfoOptimizationRemark* to OptimizationRemark*. NFC | Adam Nemet | 2016-09-27 | 1 | -1/+1 |
| * | [LV] Scalarize instructions marked scalar after vectorization | Matthew Simpson | 2016-09-26 | 1 | -0/+9 |
| * | [LV] Don't emit unused scalars for uniform instructions | Matthew Simpson | 2016-09-21 | 1 | -14/+58 |
| * | [LV] Rename "Width" to "Lane" (NFC) | Matthew Simpson | 2016-09-21 | 1 | -6/+6 |
| * | [Loop Vectorizer] Consecutive memory access - fixed and simplified | Elena Demikhovsky | 2016-09-18 | 1 | -81/+5 |
| * | [Loop vectorizer] Simplified GEP cloning. NFC. | Elena Demikhovsky | 2016-09-18 | 1 | -35/+26 |
| * | [LV] Process pointer IVs with PHINodes in collectLoopUniforms | Matthew Simpson | 2016-09-14 | 1 | -4/+22 |
| * | [LV] Clean up uniform induction variable analysis (NFC) | Matthew Simpson | 2016-09-13 | 1 | -23/+31 |
| * | [LV] Ensure proper handling of multi-use case when collecting uniforms | Matthew Simpson | 2016-09-08 | 1 | -5/+5 |
| * | [LV] Don't mark pointers used by scalarized memory accesses uniform | Matthew Simpson | 2016-09-08 | 1 | -42/+143 |
| * | [LV] Ensure reverse interleaved group GEPs remain uniform | Matthew Simpson | 2016-09-02 | 1 | -1/+11 |
| * | [LV] Use ScalarParts for ad-hoc pointer IV scalarization (NFCI) | Matthew Simpson | 2016-09-01 | 1 | -22/+9 |
| * | [LV] Move VectorParts allocation and mapping into PHI widening (NFC) | Matthew Simpson | 2016-09-01 | 1 | -29/+38 |
| * | [LoopVectorizer] Predicate instructions in blocks with several incoming edges | Michael Kuperstein | 2016-08-30 | 1 | -12/+4 |
| * | [LV] Move insertelement sequence after scalar definitions | Matthew Simpson | 2016-08-29 | 1 | -0/+11 |
| * | [LV] Unify vector and scalar maps | Matthew Simpson | 2016-08-24 | 1 | -207/+284 |
| * | [Loop Vectorizer] Support predication of div/rem | Gil Rapaport | 2016-08-24 | 1 | -73/+234 |
| * | [LoopVectorize] Don't copy std::vector in for-range loop. | Benjamin Kramer | 2016-08-19 | 1 | -1/+1 |
| * | [LV] Move LoopBodyTraits to a better place, and add comment for simplifying L... | Tim Shen | 2016-08-17 | 1 | -57/+0 |
| * | [LoopVectorize] Detect loops in the innermost loop before creating InnerLoopV... | Tim Shen | 2016-08-12 | 1 | -6/+87 |
| * | Use the range variant of find/find_if instead of unpacking begin/end | David Majnemer | 2016-08-12 | 1 | -2/+1 |
| * | [LV, X86] Be more optimistic about vectorizing shifts. | Michael Kuperstein | 2016-08-04 | 1 | -1/+3 |
| * | [Loop Vectorizer] Move store-predication into its own function, remove obsole... | Gil Rapaport | 2016-08-03 | 1 | -12/+18 |
| * | [LoopVectorize] Change comment for isOutOfScope in collectLoopUniforms, NFC | Wei Mi | 2016-08-02 | 1 | -3/+4 |
| * | [LV] Generate both scalar and vector integer induction variables | Matthew Simpson | 2016-08-02 | 1 | -34/+66 |
| * | [LV] Untangle the concepts of uniform and scalar | Matthew Simpson | 2016-08-02 | 1 | -63/+107 |
| * | [LV] Move isGatherOrScatterLegal into LoopVectorizationLegality (NFC) | Matthew Simpson | 2016-08-01 | 1 | -15/+13 |
| * | [LV] Use getPointerOperand helper where appropriate (NFC) | Matthew Simpson | 2016-08-01 | 1 | -27/+21 |
| * | Fix the assertion error in collectLoopUniforms caused by empty Worklist befor... | Wei Mi | 2016-07-27 | 1 | -2/+2 |
| * | [Loop Vectorizer] Handling loops FP induction variables. | Elena Demikhovsky | 2016-07-24 | 1 | -32/+103 |
| * | [LV] Move vector int induction update to end of latch | Matthew Simpson | 2016-07-21 | 1 | -3/+12 |
| * | [OptDiag,LV] Add hotness attribute to applied-optimization remarks | Adam Nemet | 2016-07-21 | 1 | -7/+7 |
| * | [OptDiag,LV] Add hotness attribute to the derived analysis remarks | Adam Nemet | 2016-07-20 | 1 | -7/+11 |
| * | [OptDiag,LV] Add hotness attribute to analysis remarks | Adam Nemet | 2016-07-20 | 1 | -47/+53 |
| * | [LV] Add hotness attribute to missed-optimization remarks | Adam Nemet | 2016-07-20 | 1 | -11/+17 |
| * | Recommit the patch "Use uniforms set to populate VecValuesToIgnore". | Wei Mi | 2016-07-19 | 1 | -49/+40 |
| * | Revert rL275912. | Wei Mi | 2016-07-18 | 1 | -40/+49 |
