| Commit message (Expand) | Author | Age | Files | Lines |
|---|
| * | Revert r255691 "[LoopVectorizer] Refine loop vectorizer's register usage calc... | Hans Wennborg | 2016-02-19 | 1 | -106/+31 |
| * | [LV] Vectorize first-order recurrences | Matthew Simpson | 2016-02-19 | 1 | -6/+197 |
| * | [LV] Fix PR26600: avoid out of bounds loads for interleaved access vectorization | Silviu Baranga | 2016-02-19 | 1 | -0/+10 |
| * | Create masked gather and scatter intrinsics in Loop Vectorizer. | Elena Demikhovsky | 2016-02-17 | 1 | -96/+184 |
| * | [LV] Add support for insertelt/extractelt processing during type truncation | Silviu Baranga | 2016-02-15 | 1 | -0/+14 |
| * | [SCEV][LAA] Re-commit r260085 and r260086, this time with a fix for the memory | Silviu Baranga | 2016-02-08 | 1 | -1/+1 |
| * | Revert r260086 and r260085. They have broken the memory | Silviu Baranga | 2016-02-08 | 1 | -1/+1 |
| * | [SCEV][LAA] Add no wrap SCEV predicates and use use them to improve strided p... | Silviu Baranga | 2016-02-08 | 1 | -1/+1 |
| * | [SCEV] Try to reuse existing value during SCEV expansion | Wei Mi | 2016-02-04 | 1 | -4/+16 |
| * | Minor code cleanups. NFC. | Junmo Park | 2016-02-03 | 1 | -18/+18 |
| * | Revert r259662, which caused regressions on polly tests. | Wei Mi | 2016-02-03 | 1 | -16/+4 |
| * | [SCEV] Try to reuse existing value during SCEV expansion | Wei Mi | 2016-02-03 | 1 | -4/+16 |
| * | [LV] Rename RdxPHIsToFix to PHIsToFix (NFC) | Matthew Simpson | 2016-02-01 | 1 | -39/+32 |
| * | [LV] Avoid creating empty reduction entries (NFC) | Matthew Simpson | 2016-01-06 | 1 | -6/+6 |
| * | [SCEV] Add and use SCEVConstant::getAPInt; NFCI | Sanjoy Das | 2015-12-17 | 1 | -2/+2 |
| * | [LoopVectorizer] Refine loop vectorizer's register usage calculator by ignori... | Cong Hou | 2015-12-15 | 1 | -31/+106 |
| * | Revert r255460, which still causes test failures on some platforms. | Cong Hou | 2015-12-13 | 1 | -106/+31 |
| * | [LoopVectorizer] Refine loop vectorizer's register usage calculator by ignori... | Cong Hou | 2015-12-13 | 1 | -31/+106 |
| * | Revert r255454 as it leads to several test failers on buildbots. | Cong Hou | 2015-12-13 | 1 | -106/+31 |
| * | [LoopVectorizer] Refine loop vectorizer's register usage calculator by ignori... | Cong Hou | 2015-12-13 | 1 | -31/+106 |
| * | Re-commit r255115, with the PredicatedScalarEvolution class moved to | Silviu Baranga | 2015-12-09 | 1 | -85/+80 |
| * | Revert r255115 until we figure out how to fix the bot failures. | Silviu Baranga | 2015-12-09 | 1 | -80/+85 |
| * | [LV][LAA] Add a layer over SCEV to apply run-time checked knowledge on SCEV e... | Silviu Baranga | 2015-12-09 | 1 | -85/+80 |
| * | Fix a typo in LoopVectorize.cpp. NFC. | Cong Hou | 2015-12-05 | 1 | -1/+1 |
| * | Fix a typo in LoopVectorize.cpp. NFC. | Cong Hou | 2015-12-02 | 1 | -1/+1 |
| * | [LoopVectorize] Use MapVector rather than DenseMap for MinBWs. | Charlie Turner | 2015-11-26 | 1 | -3/+3 |
| * | [LV] Add a helper function, isReductionVariable. NFC. | Chad Rosier | 2015-11-19 | 1 | -5/+7 |
| * | Fix several long lines (>80) in LoopVectorize.cpp. NFC. | Cong Hou | 2015-11-19 | 1 | -13/+19 |
| * | Typo. | Chad Rosier | 2015-11-17 | 1 | -1/+1 |
| * | [LoopVectorize] Address post-commit feedback on r250032 | James Molloy | 2015-11-09 | 1 | -3/+4 |
| * | LoopVectorizer - skip 'bitcast' between GEP and load. | Elena Demikhovsky | 2015-11-03 | 1 | -2/+28 |
| * | Add a flag vectorizer-maximize-bandwidth in loop vectorizer to enable using l... | Cong Hou | 2015-11-02 | 1 | -28/+102 |
| * | [SCEV][LV] Add SCEV Predicates and use them to re-implement stride versioning | Silviu Baranga | 2015-11-02 | 1 | -97/+95 |
| * | Revert the revision 251592 as it fails a test on some platforms. | Cong Hou | 2015-10-29 | 1 | -93/+28 |
| * | Add a flag vectorizer-maximize-bandwidth in loop vectorizer to enable using l... | Cong Hou | 2015-10-29 | 1 | -28/+93 |
| * | Whitespace. | NAKAMURA Takumi | 2015-10-27 | 1 | -1/+1 |
| * | Revert r251291, "Loop Vectorizer - skipping "bitcast" before GEP" | NAKAMURA Takumi | 2015-10-27 | 1 | -16/+3 |
| * | Loop Vectorizer - skipping "bitcast" before GEP | Elena Demikhovsky | 2015-10-26 | 1 | -3/+16 |
| * | Refactor: Simplify boolean conditional return statements in lib/Transforms/Ve... | Michael Zolotukhin | 2015-10-24 | 1 | -3/+2 |
| * | Vectorize: Remove implicit ilist iterator conversions, NFC | Duncan P. N. Exon Smith | 2015-10-19 | 1 | -51/+49 |
| * | Removed parameter "Consecutive" from isLegalMaskedLoad() / isLegalMaskedStore(). | Elena Demikhovsky | 2015-10-19 | 1 | -2/+2 |
| * | [LoopVectorize] Shrink integer operations into the smallest type possible | James Molloy | 2015-10-12 | 1 | -11/+180 |
| * | [SCEV] Introduce ScalarEvolution::getOne and getZero. | Sanjoy Das | 2015-09-23 | 1 | -3/+2 |
| * | [LoopUtils,LV] Propagate fast-math flags on generated FCmp instructions | James Molloy | 2015-09-21 | 1 | -2/+4 |
| * | [PM/AA] Rebuild LLVM's alias analysis infrastructure in a way compatible | Chandler Carruth | 2015-09-09 | 1 | -4/+10 |
| * | Rename ExitCount to BackedgeTakenCount, because that's what it is. | James Molloy | 2015-09-09 | 1 | -8/+9 |
| * | Delay predication of stores until near the end of vector code generation | James Molloy | 2015-09-09 | 1 | -56/+28 |
| * | [LV] Don't bail to MiddleBlock if a runtime check fails, bail to ScalarPH ins... | James Molloy | 2015-09-02 | 1 | -60/+27 |
| * | [LV] Move some code around slightly to make the intent of the function more c... | James Molloy | 2015-09-02 | 1 | -3/+1 |
| * | [LV] Cleanup: Sink an IRBuilder closer to its uses. | James Molloy | 2015-09-02 | 1 | -10/+5 |
