summaryrefslogtreecommitdiffstats
path: root/llvm/test/Analysis/BlockFrequencyInfo
Commit message (Expand)AuthorAgeFilesLines
* [BFI] Use rounding while computing profile counts.Easwaran Raman2018-08-161-10/+10
* [BPI] Apply invoke heuristic before loop branch heuristicArtur Pilipenko2018-06-081-0/+35
* Revert part of "Cleanup some GraphTraits iteration code"Duncan P. N. Exon Smith2017-12-081-0/+22
* Add heuristics for irreducible loop metadata under PGOHiroshi Yamauchi2017-11-201-0/+65
* Simplify irreducible loop metadata test code.Hiroshi Yamauchi2017-11-141-54/+7
* Irreducible loop metadata for more accurate block frequency under PGO.Hiroshi Yamauchi2017-11-021-0/+208
* [BFI] Add new LazyBFI analysis passAdam Nemet2016-07-131-0/+1
* [PM] port Branch Frequency Analaysis pass to new PMXinliang David Li2016-05-0510-0/+10
* Use getEdgeProbability() instead of getEdgeWeight() in BFI and remove getEdge...Cong Hou2015-12-181-2/+2
* Use fixed-point representation for BranchProbability.Cong Hou2015-09-252-6/+6
* Fix PR 24723 - Handle 0-mass backedges in irreducible loopsDiego Novillo2015-09-081-0/+155
* Add documentation for new backedge mass propagation in irregular loops.Diego Novillo2015-06-172-83/+3
* Fix PR 23525 - Separate header mass propagation in irregular loops.Diego Novillo2015-06-162-7/+84
* [opaque pointer type] Add textual IR support for explicit type parameter to t...David Blaikie2015-04-161-3/+3
* Remove 4,096 loop scale limitation.Diego Novillo2015-04-012-1/+206
* [opaque pointer type] Add textual IR support for explicit type parameter to l...David Blaikie2015-02-271-1/+1
* [opaque pointer type] Add textual IR support for explicit type parameter to g...David Blaikie2015-02-271-1/+1
* IR: Make metadata typeless in assemblyDuncan P. N. Exon Smith2014-12-158-40/+40
* BFI: Saturate when combining edges to a successorDuncan P. N. Exon Smith2014-12-051-0/+40
* Fix typosAlp Toker2014-05-151-5/+5
* Reapply "blockfreq: Approximate irreducible control flow"Duncan P. N. Exon Smith2014-04-281-56/+281
* Revert "blockfreq: Approximate irreducible control flow"Duncan P. N. Exon Smith2014-04-251-281/+56
* blockfreq: Approximate irreducible control flowDuncan P. N. Exon Smith2014-04-251-56/+281
* blockfreq: Only one mass distribution per nodeDuncan P. N. Exon Smith2014-04-251-0/+27
* blockfreq: Use better branch weights in multiexit testDuncan P. N. Exon Smith2014-04-251-7/+8
* blockfreq: Clean up irreducible testcasesDuncan P. N. Exon Smith2014-04-251-47/+14
* blockfreq: Skip irreducible backedges inside functionsDuncan P. N. Exon Smith2014-04-221-0/+31
* Reapply "blockfreq: Rewrite BlockFrequencyInfoImpl"Duncan P. N. Exon Smith2014-04-216-24/+546
* Revert "blockfreq: Rewrite BlockFrequencyInfoImpl"Duncan P. N. Exon Smith2014-04-196-546/+24
* Reapply "blockfreq: Rewrite BlockFrequencyInfoImpl"Duncan P. N. Exon Smith2014-04-196-24/+546
* Revert "blockfreq: Rewrite BlockFrequencyInfoImpl" (#2)Duncan P. N. Exon Smith2014-04-196-546/+24
* Reapply "blockfreq: Rewrite BlockFrequencyInfoImpl" (#2)Duncan P. N. Exon Smith2014-04-186-24/+546
* Revert "blockfreq: Rewrite BlockFrequencyInfoImpl" (#2)Duncan P. N. Exon Smith2014-04-186-546/+24
* Reapply "blockfreq: Rewrite BlockFrequencyInfoImpl"Duncan P. N. Exon Smith2014-04-186-24/+546
* Revert "blockfreq: Rewrite BlockFrequencyInfoImpl"Duncan P. N. Exon Smith2014-04-186-546/+24
* blockfreq: Rewrite BlockFrequencyInfoImplDuncan P. N. Exon Smith2014-04-186-24/+546
* [tests] Cleanup initialization of test suffixes.Daniel Dunbar2013-08-161-1/+0
* Minimize precision loss when computing cyclic probabilities.Jakob Stoklund Olesen2013-06-281-0/+42
* Print block frequencies in decimal form.Jakob Stoklund Olesen2013-06-251-16/+16
* BlockFrequency: Bump up the entry frequency a bit.Benjamin Kramer2013-06-251-16/+16
* Revert "BlockFrequency: Saturate at 1 instead of 0 when multiplying a frequen...Benjamin Kramer2013-06-211-65/+0
* BlockFrequency: Saturate at 1 instead of 0 when multiplying a frequency with ...Benjamin Kramer2013-06-211-0/+65
* Replace all instances of dg.exp file with lit.local.cfg, since all tests are ...Eli Bendersky2012-02-162-3/+1
* Generalize the reading of probability metadata to work for both branchesChandler Carruth2011-10-191-0/+43
* Teach the BranchProbabilityInfo analysis pass to read any metadataChandler Carruth2011-10-191-0/+25
* Add pass printing support to BlockFrequencyInfo pass. The implementationChandler Carruth2011-10-192-0/+27
OpenPOWER on IntegriCloud