summaryrefslogtreecommitdiffstats
path: root/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
Commit message (Expand)AuthorAgeFilesLines
* [DAGCombine] Remove SIGN_EXTEND-related inf-loopHal Finkel2014-10-061-6/+2
* Fast-math fold: x / (y * sqrt(z)) -> x * (rsqrt(z) / y)Sanjay Patel2014-10-061-0/+22
* [x86, dag] Teach the DAG combiner to prune inputs toa vector_shuffleChandler Carruth2014-10-051-0/+93
* Use the target-specified iteration count to opt out of any further refinement...Sanjay Patel2014-09-301-60/+62
* Split the estimate() interface into separate functions for each type. NFC.Sanjay Patel2014-09-301-2/+2
* [DAG] Check in advance if a build_vector has a legal type before attempting t...Andrea Di Biagio2014-09-301-4/+4
* [AArch64] Redundant store instructions should be removed as dead codeJames Molloy2014-09-271-0/+11
* Refactor reciprocal and reciprocal square root estimate into target-independe...Sanjay Patel2014-09-261-28/+142
* Revert patch ofr218493David Xu2014-09-261-14/+0
* Redundant store instructions should be removed as dead codeDavid Xu2014-09-261-0/+14
* Use SDValue bool operator to reduce code. No functional change.Sanjay Patel2014-09-231-9/+6
* Refactor reciprocal square root estimate into target-independent function; NFC.Sanjay Patel2014-09-211-17/+62
* Optionally enable more-aggressive FMA formation in DAGCombineHal Finkel2014-09-191-5/+10
* Replace dead links to "Hacker's Delight" with general references. NFC.Sanjay Patel2014-09-151-4/+4
* Add DAG combine for shl + add of constants.Matt Arsenault2014-09-111-32/+12
* Combine fmul vector FP constants when unsafe math is allowed.Sanjay Patel2014-09-111-6/+22
* Build correct vector filled with undef nodesDavid Xu2014-09-111-4/+20
* Group unsafe fmul math folds together for easier reading. No functional change.Sanjay Patel2014-09-081-6/+10
* Fix the FIXME that was just added in r217390 - remove a bunch of redundant fo...Sanjay Patel2014-09-081-43/+2
* group unsafe math folds together for easier readingSanjay Patel2014-09-081-150/+142
* Allow vector fsub ops with constants to get the same optimizations as scalars.Sanjay Patel2014-09-051-2/+2
* clean up; NFCSanjay Patel2014-09-051-2/+2
* Fix interference caused by fmul 2, x -> fadd x, xMatt Arsenault2014-09-021-8/+21
* Fix comment and unnecessary check for FP build_vectors.Matt Arsenault2014-09-021-5/+1
* Enable splitting indexing from loads with TargetConstantsHal Finkel2014-09-021-8/+21
* Revert "Revert '[DAGCombiner] Split up an indexed load if only the base point...Hal Finkel2014-09-021-4/+39
* Move FNEG next to FABS and make them more similar, so it's easier that they c...Sanjay Patel2014-08-281-43/+46
* Do not introduce new shuffle patterns after operation legalization if SHUFFLE...Owen Anderson2014-08-281-2/+1
* Janitorial services: "Don’t duplicate function or class name at the beginni...Sanjay Patel2014-08-281-134/+119
* Remove local TLI vars that are just duplicates of the class var. No functiona...Sanjay Patel2014-08-281-2/+0
* Use local vars to improve readability. No functional change.Sanjay Patel2014-08-281-42/+37
* Use local variable in visitFADD. No functional change.Sanjay Patel2014-08-271-13/+11
* Group unsafe-math optimizations for fsub into one block. No functional change.Sanjay Patel2014-08-271-14/+17
* Use local variable to improve readability. Sanjay Patel2014-08-271-15/+10
* Simplify creation of a bunch of ArrayRefs by using None, makeArrayRef or just...Craig Topper2014-08-271-8/+4
* Use range based for loops to avoid needing to re-mention SmallPtrSet size.Craig Topper2014-08-241-4/+3
* name change: isPow2DivCheap -> isPow2SDivCheapSanjay Patel2014-08-211-1/+1
* DAGCombiner: Make concat_vector combine safe for EVTs and concat_vectors with...Benjamin Kramer2014-08-211-1/+6
* Fix fmul combines with constant splat vectorsMatt Arsenault2014-08-161-7/+26
* [DAGCombiner] Improve the folding of target independet shuffles to Undef.Andrea Di Biagio2014-08-161-0/+16
* optimize vector fneg of bitcasted integer valueSanjay Patel2014-08-141-9/+14
* [SDAG] Fix a bug in the DAG combiner where we would fail to return theChandler Carruth2014-08-141-5/+1
* [DAGCombiner] Improved target independent vector shuffle combine rule.Andrea Di Biagio2014-08-131-10/+24
* [x86] Fold extract_vector_elt of a load into the Load's address computation.Michael J. Spencer2014-08-111-90/+125
* Optimize vector fabs of bitcasted constant integer values.Sanjay Patel2014-08-051-9/+15
* [SDAG] Fix a really, really terrible bug in the DAG combiner.Chandler Carruth2014-08-041-2/+2
* Remove the TargetMachine forwards for TargetSubtargetInfo basedEric Christopher2014-08-041-3/+10
* [x86] Don't add nodes to the combined set (and prune subsequentChandler Carruth2014-08-031-8/+8
* fix for PR20354 - Miscompile of fabs due to vectorizationSanjay Patel2014-08-031-1/+5
* [AArch64] Teach DAGCombiner that converting two consecutive loads into a vect...James Molloy2014-08-021-0/+7
OpenPOWER on IntegriCloud