summaryrefslogtreecommitdiffstats
path: root/llvm/test/Transforms/LoopVectorize
Commit message (Expand)AuthorAgeFilesLines
* Renamed some uses of unroll to interleave in the vectorizer.Tyler Nowicki2015-07-111-2/+2
* [LoopVectorize] Use ReplaceInstWithInst() helper where appropriate.Alexey Samsonov2015-07-011-15/+30
* Correct a typo for a LoopVectorize testDavid Majnemer2015-06-301-1/+1
* [LoopVectorize] Pointer indicies may be wider than the pointerDavid Majnemer2015-06-271-0/+20
* [LoopVectorizer] Fix bailing-out condition for OptForSize case.Michael Zolotukhin2015-06-241-0/+34
* [LoopVectorize] Teach Loop Vectorizor about interleaved memory accesses.Hao Liu2015-06-082-20/+484
* [LoopVectorize] Don't crash on zero-sized types in isInductionPHIDavid Majnemer2015-06-051-0/+27
* NFC - Test case invokes llc on a file rather than redirected from a file.Nemanja Ivanovic2015-05-151-1/+1
* Populate list of vectorizable functions for Accelerate library.Michael Zolotukhin2015-05-071-0/+450
* [X86] Disable loop unrolling in loop vectorization pass when VF is 1.Wei Mi2015-05-062-1/+40
* IR: Give 'DI' prefix to debug info metadataDuncan P. N. Exon Smith2015-04-298-129/+129
* DebugInfo: Fix bad debug info for compile units and typesDuncan P. N. Exon Smith2015-03-272-2/+2
* TLI: Add addVectorizableFunctionsFromVecLib.Michael Zolotukhin2015-03-171-0/+182
* TTI: Honour cost model for estimating cost of vector-intrinsic and calls.Michael Zolotukhin2015-03-171-18/+10
* Verifier: Check debug info intrinsic argumentsDuncan P. N. Exon Smith2015-03-152-8/+8
* [opaque pointer type] Add textual IR support for explicit type parameter to g...David Blaikie2015-03-135-66/+66
* Introduce runtime unrolling disable matadata and use it to mark the scalar lo...Kevin Qin2015-03-092-2/+4
* Do not restrict interleaved unrolling to small loops, depending on the target.Olivier Sallenave2015-03-061-0/+73
* DebugInfo: Move new hierarchy into placeDuncan P. N. Exon Smith2015-03-038-87/+87
* [opaque pointer type] Add textual IR support for explicit type parameter to l...David Blaikie2015-02-27113-771/+771
* [opaque pointer type] Add textual IR support for explicit type parameter to g...David Blaikie2015-02-27124-716/+716
* [x86,sdag] Two interrelated changes to the x86 and sdag code.Chandler Carruth2015-02-191-2/+2
* [LoopAccesses] Modify test to also check symbolic strides with memchecksAdam Nemet2015-02-181-3/+9
* Reformat test case to be easier to migrate to typeless pointers.David Blaikie2015-02-151-1/+4
* Check interleaving without relying on debug output.Olivier Sallenave2015-02-131-3/+14
* llvm/test/Transforms/LoopVectorize/PowerPC/small-loop-rdx.ll REQUIRES +Assert...NAKAMURA Takumi2015-02-131-0/+1
* Change max interleave factor to 12 for POWER7 and POWER8.Olivier Sallenave2015-02-121-0/+35
* Update test case.Benjamin Kramer2015-02-121-2/+2
* Move the target specific test case arbitrary-induction-step.ll to test/Transf...Hao Liu2015-01-301-0/+0
* [LoopVectorize] Induction variables: support arbitrary constant step.Hao Liu2015-01-303-4/+153
* Fixed a bug in masked load/store in reversed loop.Elena Demikhovsky2015-01-221-0/+82
* IR: Move MDLocation into placeDuncan P. N. Exon Smith2015-01-148-42/+42
* IR: Add 'distinct' MDNodes to bitcode and assemblyDuncan P. N. Exon Smith2015-01-082-4/+4
* Fix broken test from r225159.Michael Kuperstein2015-01-051-1/+1
* Fixed a bug in memory dependence checking module of loop vectorization. The f...Jiangning Liu2015-01-051-0/+26
* Masked Load and Store Intrinsics in loop vectorizer.Elena Demikhovsky2014-12-161-0/+420
* IR: Make metadata typeless in assemblyDuncan P. N. Exon Smith2014-12-1525-272/+272
* PR21302. Vectorize only bottom-tested loops.Michael Zolotukhin2014-12-021-0/+31
* Apply loop-rotate to several vectorizer tests.Michael Zolotukhin2014-12-023-181/+151
* Revert "Masked Vector Load and Store Intrinsics."Duncan P. N. Exon Smith2014-11-284-334/+0
* Bug 21610: Canonicalize min/max fcmp selects to use ordered comparisonsMatt Arsenault2014-11-241-8/+8
* Masked Vector Load and Store Intrinsics.Elena Demikhovsky2014-11-234-0/+334
* Addition to r216371 (SLP and Loop Vectorization) and r218607 whereSuyog Sarda2014-11-111-0/+31
* LoopVectorize: Don't assume pointees are sizedDavid Majnemer2014-11-071-0/+24
* Correctly update dom-tree after loop vectorizer.Michael Zolotukhin2014-10-311-0/+142
* Add minnum / maxnum intrinsicsMatt Arsenault2014-10-211-0/+56
* [LoopVectorize] Ignore @llvm.assume for cost estimates and legalityHal Finkel2014-10-141-0/+100
* Revert "Revert "DI: Fold constant arguments into a single MDString""Duncan P. N. Exon Smith2014-10-038-79/+79
* Revert "DI: Fold constant arguments into a single MDString"Duncan P. N. Exon Smith2014-10-028-79/+79
* DI: Fold constant arguments into a single MDStringDuncan P. N. Exon Smith2014-10-028-79/+79
OpenPOWER on IntegriCloud