summaryrefslogtreecommitdiffstats
path: root/llvm/lib/Transforms/Vectorize
Commit message (Expand)AuthorAgeFilesLines
* [llvm] API for encoding/decoding DWARF discriminators.Mircea Trofin2018-12-211-2/+9
* Test commitAnton Afanasyev2018-12-191-4/+4
* [LoopVectorize] Rename pass options. NFC.Michael Kruse2018-12-182-14/+18
* [Unroll/UnrollAndJam/Vectorizer/Distribute] Add followup loop attributes.Michael Kruse2018-12-121-30/+43
* [PM] Port LoadStoreVectorizer to the new pass manager.Markus Lavin2018-12-072-16/+34
* [SLP]PR39774: Update references of the replaced external instructions.Alexey Bataev2018-11-301-0/+2
* [SLP]Fix PR39774: Set ReductionRoot if the original instruction is vectorized.Alexey Bataev2018-11-281-5/+9
* [IR] Add hasNPredecessors, hasNPredecessorsOrMore to BasicBlockVedant Kumar2018-11-191-1/+1
* [LV] Avoid vectorizing unsafe dependencies in uniform addressAnna Thomas2018-11-191-4/+3
* [VPlan, SLP] Use SmallPtrSet for Candidates.Florian Hahn2018-11-142-27/+26
* [VPlan] Remove LLVM_DEBUG from VPlanSlp::dumpBundle.Florian Hahn2018-11-141-4/+4
* [VPlan] Update ifdef.Florian Hahn2018-11-141-2/+2
* [VPlan, SLP] Add simple SLP analysis on top of VPlan.Florian Hahn2018-11-145-1/+623
* [VPlan] VPlan version of InterleavedAccessInfo.Florian Hahn2018-11-134-9/+102
* [CostModel] Add more realistic SK_ExtractSubvector generic costs.Simon Pilgrim2018-11-121-1/+2
* [LV] Avoid vectorizing loops under opt for size that involve SCEV checksAyal Zaks2018-11-021-1/+25
* [LV] Support vectorization of interleave-groups that require an epilog underDorit Nuzman2018-10-311-32/+82
* [TTI] Fix uses of SK_ExtractSubvector shuffle costs (PR39368)Simon Pilgrim2018-10-301-1/+1
* [LoopVectorizer] Fix for cost values of memory accesses.Jonas Paulsson2018-10-301-1/+8
* [LV] Don't have fold-tail under optsize invalidate interleave-groups whenDorit Nuzman2018-10-241-1/+7
* [SLPVectorizer] Add basic support for mul/and/or/xor horizontal reductionsSimon Pilgrim2018-10-231-2/+5
* Leftover bits from https://reviews.llvm.org/D53420 that were accidentally leftDorit Nuzman2018-10-231-2/+1
* [IAI,LV] Avoid creating a scalar epilogue due to gaps in interleave-groups when Dorit Nuzman2018-10-221-2/+8
* [LV] Fold tail by masking to vectorize loops of arbitrary trip count under op...Ayal Zaks2018-10-184-38/+188
* [LV] Teach vectorizer about variant value store into uniform addressAnna Thomas2018-10-162-4/+4
* [TI removal] Make `getTerminator()` return a generic `Instruction`.Chandler Carruth2018-10-151-9/+9
* [TI removal] Make variables declared as `TerminatorInst` and initializedChandler Carruth2018-10-151-1/+1
* [LV] Fix comments reported when not vectorizing single iteration loops; NFCAyal Zaks2018-10-141-1/+8
* recommit 344472 after fixing build failure on ARM and PPC.Dorit Nuzman2018-10-143-21/+116
* revert 344472 due to failures.Dorit Nuzman2018-10-143-116/+21
* [IAI,LV] Add support for vectorizing predicated strided accesses using maskedDorit Nuzman2018-10-143-21/+116
* [LV] Use SmallVector instead of DenseMap in calculateRegisterUsage (NFC).Florian Hahn2018-10-111-5/+4
* [LV] Ignore more debug info.Florian Hahn2018-10-111-2/+2
* [VPlan] Fix CondBit quoting in dumpBasicBlockRenato Golin2018-10-101-1/+3
* [LV] Do not create SCEVs on broken IR in emitTransformedIndex. PR39160Max Kazantsev2018-10-081-17/+36
* [LoopVectorizer] Use TTI.getOperandInfo()Jonas Paulsson2018-10-051-28/+8
* [LV][LAA] Vectorize loop invariant values stored into loop invariant addressAnna Thomas2018-09-252-13/+32
* [Loop Vectorizer] Abandon vectorization when no integer IV foundWarren Ristow2018-09-212-0/+5
* LSV: Fix adjust alloca alignment trick for AMDGPUMatt Arsenault2018-09-181-29/+31
* Fix for the buildbot failure http://lab.llvm.org:8011/builders/sanitizer-x86_...Hideki Saito2018-09-143-4/+11
* [VPlan] Implement initial vector code generation support for simple outer loops.Hideki Saito2018-09-146-15/+287
* [LV] Move InterleaveGroup and InterleavedAccessInfo to VectorUtils.h (NFC)Florian Hahn2018-09-121-694/+11
* Move a transformation routine from LoopUtils to LoopVectorize.Vikram TV2018-09-101-4/+84
* Move createMinMaxOp() out of RecurrenceDescriptor.Vikram TV2018-09-101-2/+2
* [LV] Fix code gen for conditionally executed loads and storesAnna Thomas2018-09-071-8/+41
* [LV] First order recurrence phis should not be treated as uniformAnna Thomas2018-09-041-0/+5
* SLPVectorizer: Fix assert with different sized address spacesMatt Arsenault2018-08-311-1/+1
* [LoopVectorize][NFCI] Use find instead of countDavid Bolvansky2018-08-231-42/+58
* [LV] Vectorize loops where non-phi instructions used outside loopAnna Thomas2018-08-212-7/+36
* NFC: Clarify comment in loop vectorization legalityAnna Thomas2018-08-141-1/+2
OpenPOWER on IntegriCloud