summaryrefslogtreecommitdiffstats
path: root/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
Commit message (Expand)AuthorAgeFilesLines
* Revert r164910 because it causes failures to several phase2 builds.Nadav Rotem2012-09-301-254/+0
* A DAGCombine optimization for merging consecutive stores. This optimization i...Nadav Rotem2012-09-301-0/+254
* Speculatively revert commit 164885 (nadav) in the hope of ressurecting a pile ofDuncan Sands2012-09-291-252/+0
* Tidy up to match coding standards. Remove 'else' after 'return' and moving op...Craig Topper2012-09-291-27/+24
* Replace a couple if/elses around similar calls with conditional operators on ...Craig Topper2012-09-291-17/+6
* A DAGCombine optimization for merging consecutive stores. This optimization i...Nadav Rotem2012-09-291-0/+252
* Revert 'Fix a typo 'iff' => 'if''. iff is an abreviation of if and only if. S...Sylvestre Ledru2012-09-271-19/+19
* Fix a typo 'iff' => 'if'Sylvestre Ledru2012-09-271-19/+19
* Fix 80-col violations.Nadav Rotem2012-09-201-13/+19
* Fix a dagcombine optimization. The optimization attempts to optimize a bitcas...Nadav Rotem2012-09-131-1/+2
* Teach DAG combiner to constant fold FABS of a BUILD_VECTOR of ConstantFPs. Fa...Craig Topper2012-09-111-22/+47
* Fix an assertion failure when optimising a shufflevector incorrectly into con...James Molloy2012-09-101-0/+6
* Teach DAG combiner to constant fold fneg of a BUILD_VECTOR of constants.Craig Topper2012-09-091-1/+25
* Constify this properly. Found by gcc48 -Wcast-qual.Roman Divacky2012-09-051-4/+4
* Fixed the DAG combiner to better handle the folding of AND nodes for vector t...Silviu Baranga2012-09-051-1/+11
* Teach DAG combine a number of tricks to simplify FMA expressions in fast-math...Owen Anderson2012-09-011-0/+64
* Fix typoMichael Liao2012-09-011-1/+1
* Teach the DAG combiner to turn chains of FADDs (x+x+x+x+...) into FMULs by co...Owen Anderson2012-08-301-1/+122
* Rejected 169195. As Duncan commented, bitcasting to proper type is wrong appr...Stepan Dyatkovskiy2012-08-221-23/+3
* Fixed DAGCombiner bug (found and localized by James Malloy):Stepan Dyatkovskiy2012-08-201-3/+23
* Add a roundToIntegral method to APFloat, which can be parameterized over vari...Owen Anderson2012-08-131-0/+42
* Added FMA functionality to X86 target.Elena Demikhovsky2012-08-011-8/+20
* Fixed DAGCombine optimizations which generate select_cc for targetsNadav Rotem2012-07-231-33/+47
* Remove tabs.Bill Wendling2012-07-191-1/+1
* Back out r160101 and instead implement a dag combine to recover from instcomb...Evan Cheng2012-07-171-0/+28
* Refactor the code that checks that all operands of a node are UNDEFs.Nadav Rotem2012-07-151-13/+7
* Add a dagcombine optimization to convert concat_vectors of undefs into a sing...Nadav Rotem2012-07-141-0/+11
* Only apply the SETCC+SITOFP -> SELECTCC optimization when the SETCC returns a...Owen Anderson2012-07-111-1/+2
* Improve the loading of load-anyext vectors by allowing the codegen to loadNadav Rotem2012-07-101-1/+1
* Teach the DAG combiner to turn sitofp/uitofp from i1 into a conditional move,...Owen Anderson2012-07-091-0/+36
* Make sure type is not extended or untyped before create a constant of the typ...Evan Cheng2012-06-261-0/+4
* Rename -allow-excess-fp-precision flag to -fuse-fp-ops, and switch from aLang Hames2012-06-221-2/+2
* Fix potential crash if DAGCombine on stores sees a half typePete Cooper2012-06-211-1/+2
* Add users of a MERGE_VALUE node to the worklist to process again when the nod...Pete Cooper2012-06-201-0/+3
* Fix DAGCombine to deal with ext-conversion of pre/post_inc loads.Hal Finkel2012-06-201-1/+8
* Add DAG-combines for aggressive FMA formation.Lang Hames2012-06-191-0/+43
* Make comment slightly more helpful.Lang Hames2012-06-141-1/+1
* Switch the canonical FMA term operand order to match both the comment I wrote...Owen Anderson2012-05-301-1/+1
* Teach DAGCombine to canonicalize the position of a constant in the term opera...Owen Anderson2012-05-301-0/+4
* DAGCombiner should not change the type of an extract_vector index.Jim Grosbach2012-05-081-3/+4
* Teach DAG combine to fold x-x to 0.0 when unsafe FP math is enabled.Owen Anderson2012-05-071-0/+4
* Teach DAGCombine the same multiply-by-1.0 folding trick when doing FMAs, just...Owen Anderson2012-05-021-0/+18
* Teach DAG combine that multiplication by 1.0 can always be constant folded.Owen Anderson2012-05-021-0/+3
* ZERO_EXTEND/SIGN_EXTEND/TRUNCATE optimization for AVX2Elena Demikhovsky2012-04-221-0/+2
* Register DAGUpdateListeners with SelectionDAG.Jakob Stoklund Olesen2012-04-201-48/+30
* Remove dead SD nodes after the combining pass. Fixes PR12201.Hal Finkel2012-04-161-0/+1
* Reapply 154397. Original message:Nadav Rotem2012-04-111-11/+18
* Add a comment noting that the fdiv -> fmul conversion won't generateDuncan Sands2012-04-101-3/+3
* Revert r154397, which was causing make check failures on the buildbots.Owen Anderson2012-04-101-13/+6
* Fix a dagcombine optimization which assumes that the vsetcc result type is al...Nadav Rotem2012-04-101-6/+13
OpenPOWER on IntegriCloud