summaryrefslogtreecommitdiffstats
path: root/llvm/test/Transforms/LoopVectorize
Commit message (Expand)AuthorAgeFilesLines
* [LV] Preserve order of dependences in interleaved accesses analysisMatthew Simpson2016-06-241-0/+305
* reverted the prev commit due to assertion failureElena Demikhovsky2016-06-211-43/+0
* Fixed consecutive memory access detection in Loop Vectorizer.Elena Demikhovsky2016-06-211-0/+43
* Recommit [LV] Enable vectorization of loops where the IV has an external useMichael Kuperstein2016-06-152-32/+110
* Reverting r272715 since it broke libcxx.Michael Kuperstein2016-06-142-84/+32
* [LV] Enable vectorization of loops where the IV has an external useMichael Kuperstein2016-06-142-32/+84
* Reapply "[TTI] Refine default cost for interleaved load groups with gaps"Matthew Simpson2016-06-101-0/+42
* Revert "[TTI] Refine default cost for interleaved load groups with gaps"Matthew Simpson2016-06-101-42/+0
* [TTI] Refine default cost for interleaved load groups with gapsMatthew Simpson2016-06-101-0/+42
* [LV] Use vector phis for some secondary induction variablesMichael Kuperstein2016-06-092-8/+57
* Quick fix for the test from rL272014 "[LAA] Improve non-wrapping pointerAndrey Turetskiy2016-06-071-1/+1
* [LAA] Improve non-wrapping pointer detection by handling loop-invariant case.Andrey Turetskiy2016-06-071-0/+65
* [InstCombine] scalarizePHI should not assume the code it sees has been CSE'dMichael Kuperstein2016-06-061-1/+1
* Revert "Claim NoAlias if two GEPs index different fields of the same struct"Daniel Berlin2016-06-011-77/+81
* Claim NoAlias if two GEPs index different fields of the same structDaniel Berlin2016-06-011-81/+77
* [LV] For some IVs, use vector phis instead of widening in the loop bodyMichael Kuperstein2016-06-018-20/+85
* Move test to X86 directory: I think it depends on X86 TTI.Tim Northover2016-05-271-0/+0
* Vectorizer: track non-fast FP instructions through phis when finding reductions.Tim Northover2016-05-271-0/+75
* Look for a loop's starting location in the llvm.loop metadataHal Finkel2016-05-251-0/+74
* [x86] avoid code explosion from LoopVectorizer for gather loop (PR27826) Sanjay Patel2016-05-251-0/+41
* Recommit r255691 since PR26509 has been fixed.Wei Mi2016-05-192-1/+72
* [LAA] Rename forwarding conflict detection option (NFC)Matthew Simpson2016-05-161-1/+1
* [LV] Ensure safe VF for loops with interleaved accessesMatthew Simpson2016-05-161-0/+56
* [InstCombine] canonicalize* LE/GE vector integer comparisons to LT/GT (PR2670...Sanjay Patel2016-05-131-1/+1
* Revert "[VectorUtils] Query number of sign bits to allow more truncations"James Molloy2016-05-101-36/+0
* [LoopVectorize] Handling induction variable with non-constant step.Elena Demikhovsky2016-05-101-0/+124
* [LV] Hint at the new loop distribution pragma in optimization remarkAdam Nemet2016-05-091-0/+74
* [VectorUtils] Query number of sign bits to allow more truncationsJames Molloy2016-05-091-0/+36
* [LV] Identify more induction PHIs by coercing expressions to AddRecExprsSilviu Baranga2016-05-051-0/+75
* [LoopVectorize] Add operand bundles to vectorized functionsDavid Majnemer2016-04-291-0/+45
* [PR25281] Remove AAResultsWrapper from preserved analyses of loop vectorizer.Michael Zolotukhin2016-04-291-0/+59
* [LoopVectorize] Keep hints from original loop on the vector loopHal Finkel2016-04-291-0/+30
* [LV] Reallow positive-stride interleaved load groups with gapsMatthew Simpson2016-04-271-6/+99
* Masked Store in Loop Vectorizer - bugfixElena Demikhovsky2016-04-261-0/+46
* [LoopVectorize] Don't consider conditional-load dereferenceability for marked...Hal Finkel2016-04-261-0/+41
* [ARM] AArch32 v8 NEON is still not IEEE-754 compliantRenato Golin2016-04-181-14/+8
* Convert this sample-based-profiling testcase to use a NoDebug CU.Adrian Prantl2016-04-151-4/+1
* [PR27284] Reverse the ownership between DICompileUnit and DISubprogram.Adrian Prantl2016-04-1511-36/+26
* [test] Require 'asserts' for a test which uses -debug-onlyVedant Kumar2016-04-141-0/+1
* [ARM] Adding IEEE-754 SIMD detection to loop vectorizerRenato Golin2016-04-141-0/+335
* Revert "Support arbitrary addrspace pointers in masked load/store intrinsics"Adam Nemet2016-04-141-95/+20
* Support arbitrary addrspace pointers in masked load/store intrinsicsArtur Pilipenko2016-04-121-20/+95
* [DebugInfo/Test] Add CU as required.Davide Italiano2016-04-111-0/+2
* [LoopUtils, LV] Fix PR27246 (first-order recurrences)Matthew Simpson2016-04-111-0/+41
* Loop vectorization with uniform loadElena Demikhovsky2016-04-101-0/+47
* [LoopVectorize] Register cloned assumptionsDavid Majnemer2016-04-081-0/+32
* Re-commit [SCEV] Introduce a guarded backedge taken count and use it in LAA a...Silviu Baranga2016-04-082-1/+168
* Revert r265535 until we know how we can fix the bots Silviu Baranga2016-04-062-168/+1
* [SCEV] Introduce a guarded backedge taken count and use it in LAA and LVSilviu Baranga2016-04-062-1/+168
* [SLPVectorizer] Vectorizing the libm sqrt to llvm's sqrt intrinsic requires nnanDavid Majnemer2016-04-061-1/+25
OpenPOWER on IntegriCloud