| Commit message (Expand) | Author | Age | Files | Lines |
|---|
| * | [ValueTracking] Look through casts when determining non-nullness | Johannes Doerfert | 2019-01-26 | 2 | -63/+63 |
| * | [CostModel][X86] Add explicit vector select costs | Simon Pilgrim | 2019-01-20 | 2 | -55/+82 |
| * | Introduce llvm.loop.parallel_accesses and llvm.access.group metadata. | Michael Kruse | 2018-12-20 | 7 | -62/+74 |
| * | [LoopVectorize] auto-generate complete checks; NFC | Sanjay Patel | 2018-12-18 | 1 | -9/+132 |
| * | [Unroll/UnrollAndJam/Vectorizer/Distribute] Add followup loop attributes. | Michael Kruse | 2018-12-12 | 1 | -8/+7 |
| * | [X86][LoopVectorize] Replace -mcpu=skylake-avx512 with -mattr=avx512f in some... | Craig Topper | 2018-12-01 | 3 | -3/+3 |
| * | [CostModel] Add more realistic SK_InsertSubvector generic costs. | Simon Pilgrim | 2018-11-12 | 1 | -55/+58 |
| * | [LV] Avoid vectorizing loops under opt for size that involve SCEV checks | Ayal Zaks | 2018-11-02 | 1 | -0/+60 |
| * | [LV] Support vectorization of interleave-groups that require an epilog under | Dorit Nuzman | 2018-10-31 | 1 | -70/+235 |
| * | [CostModel][X86] Add realistic vXi64 uitofp vXf64 costs | Simon Pilgrim | 2018-10-25 | 1 | -2/+3 |
| * | [LV] Don't have fold-tail under optsize invalidate interleave-groups when | Dorit Nuzman | 2018-10-24 | 1 | -0/+387 |
| * | [IAI,LV] Avoid creating a scalar epilogue due to gaps in interleave-groups when | Dorit Nuzman | 2018-10-22 | 1 | -2/+112 |
| * | [LV] Fold tail by masking to vectorize loops of arbitrary trip count under op... | Ayal Zaks | 2018-10-18 | 3 | -22/+282 |
| * | [LV] Teach vectorizer about variant value store into uniform address | Anna Thomas | 2018-10-16 | 2 | -3/+169 |
| * | [LV] Add test checks when vectorizing loops under opt for size; NFC | Ayal Zaks | 2018-10-16 | 3 | -19/+253 |
| * | recommit 344472 after fixing build failure on ARM and PPC. | Dorit Nuzman | 2018-10-14 | 1 | -0/+164 |
| * | revert 344472 due to failures. | Dorit Nuzman | 2018-10-14 | 1 | -164/+0 |
| * | [IAI,LV] Add support for vectorizing predicated strided accesses using masked | Dorit Nuzman | 2018-10-14 | 1 | -0/+164 |
| * | [InstCombine] reverse 'trunc X to <N x i1>' canonicalization; 2nd try | Sanjay Patel | 2018-10-10 | 1 | -176/+160 |
| * | revert r344082: [InstCombine] reverse 'trunc X to <N x i1>' canonicalization | Sanjay Patel | 2018-10-10 | 1 | -160/+176 |
| * | [LV] Move test for r343954 into x86 subdirectory | Justin Bogner | 2018-10-09 | 1 | -0/+98 |
| * | [InstCombine] reverse 'trunc X to <N x i1>' canonicalization | Sanjay Patel | 2018-10-09 | 1 | -176/+160 |
| * | [LV] Do not create SCEVs on broken IR in emitTransformedIndex. PR39160 | Max Kazantsev | 2018-10-08 | 1 | -10/+9 |
| * | [IAI,LV] Avoid creating interleave-groups for predicated accesse | Dorit Nuzman | 2018-10-07 | 1 | -0/+60 |
| * | [LV][LAA] Vectorize loop invariant values stored into loop invariant address | Anna Thomas | 2018-09-25 | 1 | -0/+132 |
| * | InstCombine: move hasOneUse check to the top of foldICmpAddConstant | Tim Northover | 2018-09-10 | 1 | -3/+3 |
| * | [LV] Fix code gen for conditionally executed loads and stores | Anna Thomas | 2018-09-07 | 2 | -0/+724 |
| * | [LV] First order recurrence phis should not be treated as uniform | Anna Thomas | 2018-09-04 | 1 | -0/+22 |
| * | [InstCombine] Fold icmp ugt/ult (add nuw X, C2), C --> icmp ugt/ult X, (C - C2) | Nicola Zaghen | 2018-09-04 | 1 | -3/+3 |
| * | Revert "[SCEV][NFC] Check NoWrap flags before lexicographical comparison of S... | Roman Tereshin | 2018-08-27 | 1 | -4/+4 |
| * | Revert "[InstCombine] Delay foldICmpUsingKnownBits until simple transforms ar... | Max Kazantsev | 2018-07-06 | 1 | -1/+2 |
| * | NFC - Various typo fixes in tests | Gabor Buella | 2018-07-04 | 1 | -1/+1 |
| * | [InstCombine] Delay foldICmpUsingKnownBits until simple transforms are done | Max Kazantsev | 2018-07-03 | 1 | -2/+1 |
| * | Move redundant-vf2-cost.ll test to X86 directory | Diego Caballero | 2018-06-15 | 1 | -0/+34 |
| * | [TargetLibraryInfo] add mappings from LLVM sin/cos intrinsics to SVML calls | Sanjay Patel | 2018-06-07 | 1 | -4/+4 |
| * | [ConstantFold] Disallow folding vector geps into bitcasts | Karl-Johan Karlsson | 2018-06-01 | 1 | -3/+3 |
| * | [LoopVectorize, x86] add tests to show missing SVML transforms; NFC | Sanjay Patel | 2018-05-31 | 1 | -344/+356 |
| * | [LoopVectorize, x86] regenerate checks; NFC | Sanjay Patel | 2018-05-31 | 1 | -99/+403 |
| * | [X86][CET] Changing -fcf-protection behavior to comply with gcc (LLVM part) | Alexander Ivchenko | 2018-05-18 | 1 | -1/+1 |
| * | [LV] Add lit testcase for bitcast problem. NFC | Karl-Johan Karlsson | 2018-05-09 | 1 | -0/+54 |
| * | [DebugInfo] Add DILabel metadata and intrinsic llvm.dbg.label. | Shiva Chen | 2018-05-09 | 7 | -13/+13 |
| * | [LV] Move test/Transforms/LoopVectorize/pr23997.ll | Daniel Neilson | 2018-05-01 | 1 | -0/+109 |
| * | [LV] Preserve inbounds on created GEPs | Daniel Neilson | 2018-05-01 | 2 | -229/+229 |
| * | Revert r325687 (workaround for PR36032). | Evgeny Stupachenko | 2018-03-22 | 1 | -1/+1 |
| * | [LV] Let recordVectorLoopValueForInductionCast to check if IV was created fro... | Andrei Elovikov | 2018-03-20 | 1 | -0/+39 |
| * | [SCEV] Smart range calculation for SCEVUnknown Phis | Max Kazantsev | 2018-03-01 | 1 | -3/+43 |
| * | Fix r326154 buildbots test fail | Evgeny Stupachenko | 2018-02-27 | 1 | -0/+213 |
| * | [LV] Fix test checks, NFC | Alexey Bataev | 2018-02-21 | 1 | -76/+2363 |
| * | revert r325515: [TTI CostModel] change default cost of FP ops to 1 (PR36280) | Sanjay Patel | 2018-02-21 | 1 | -9/+36 |
| * | [LV] Fix test checks, NFC. | Alexey Bataev | 2018-02-20 | 2 | -140/+3506 |
