summaryrefslogtreecommitdiffstats
path: root/llvm/lib/Transforms/InstCombine
Commit message (Expand)AuthorAgeFilesLines
* [InstCombine] Limit a vector demanded elts rule which was producing invalid IR.Philip Reames2019-04-301-0/+12
* [InstCombine] reduce code duplication; NFCSanjay Patel2019-04-291-5/+7
* [InstCombine] visitFCmpInst - appease copy+paste pattern warning. NFCI.Simon Pilgrim2019-04-291-1/+1
* [InstCombine][X86] Tweak generic expansion of PACKSS/PACKUS to shuffle then t...Simon Pilgrim2019-04-251-7/+4
* Fix include order. NFCI.Simon Pilgrim2019-04-251-1/+1
* Consolidate existing utilities for interpreting vector predicate maskes [NFC]Philip Reames2019-04-251-31/+1
* [InstCombine] Be consistent w/handling of masked intrinsics style wise [NFC]Philip Reames2019-04-252-5/+6
* [InstCombine][X86] Use generic expansion of PACKSS/PACKUS for constant foldin...Simon Pilgrim2019-04-241-51/+45
* [InstCombine] Convert a masked.load of a dereferenceable address to an uncond...Philip Reames2019-04-231-4/+14
* [InstCombine] Eliminate stores to constant memoryPhilip Reames2019-04-222-0/+24
* [InstSimplify] Move masked.gather w/no active lanes handling to InstSimplify ...Philip Reames2019-04-221-5/+0
* [InstCombine] Factor out unreachable inst idiom creation [NFC]Philip Reames2019-04-173-13/+15
* [InstCombine] Prune fshl/fshr with masked operandsNikita Popov2019-04-161-0/+4
* [IR] Add WithOverflowInst classNikita Popov2019-04-161-45/+20
* [PGO] Profile guided code size optimization.Hiroshi Yamauchi2019-04-153-8/+33
* [InstCombine] canonicalize fdiv after fmul if reassociation is allowedSanjay Patel2019-04-151-0/+8
* [InstCombine] Remove redundant/bogus mul_with_overflow combinesNikita Popov2019-04-131-8/+0
* [InstCombine] Canonicalize (-X srem Y) to -(X srem Y).Chen Zheng2019-04-131-0/+5
* [InstCombine] Fix a nasty miscompile introduced w/masked.gather demanded eltsPhilip Reames2019-04-121-1/+5
* [InstCombine] Handle ssubo always overflowNikita Popov2019-04-101-3/+3
* [InstCombine] ssubo X, C -> saddo X, -CNikita Popov2019-04-101-0/+21
* [InstCombine] Handle saddo always overflowNikita Popov2019-04-101-3/+3
* [InstCombine] Handle usubo always overflowNikita Popov2019-04-101-0/+3
* [InstCombine] Directly call computeOverflow methods in OptimizeOverflowCheck;...Nikita Popov2019-04-101-6/+13
* [InstCombine] Canonicalize (-X s/ Y) to -(X s/ Y).Chen Zheng2019-04-101-0/+6
* Revert "[InstCombine] [InstCombine] Canonicalize (-X s/ Y) to -(X s/ Y)."Nikita Popov2019-04-091-6/+0
* [InstCombine] Restructure OptimizeOverflowCheck; NFCNikita Popov2019-04-091-31/+28
* [InstCombine] [InstCombine] Canonicalize (-X s/ Y) to -(X s/ Y).Chen Zheng2019-04-091-0/+6
* [InstCombine] prevent possible miscompile with sdiv+negate of vector opSanjay Patel2019-04-091-10/+11
* [InstCombine] prevent possible miscompile with negate+sdiv of vector opSanjay Patel2019-04-091-3/+6
* [InstCombine] peek through fdiv to find a squared sqrtSanjay Patel2019-04-081-0/+19
* [InstCombine] remove overzealous assert for shuffles (PR41419)Sanjay Patel2019-04-081-2/+2
* [InstCombine][X86] Expand MOVMSK to generic IR (PR39927)Simon Pilgrim2019-04-081-40/+14
* [InstCombine] sdiv exact flag fixup.Chen Zheng2019-04-081-2/+5
* [IR] Refactor attribute methods in Function class (NFC)Evandro Menezes2019-04-041-1/+1
* [InstCombine] Combine no-wrap sub and icmp w/ constant.Luqman Aden2019-04-041-1/+10
* [InstCombine] Simplify ctpop with bitreverse/bswapDavid Bolvansky2019-04-031-0/+8
* [InstCombine] Simplify ctlz/cttz with bitreverseDavid Bolvansky2019-04-021-1/+9
* [InstCombine] Handle vector gep with scalar argument in evaluateInDifferentEl...Mikael Holmen2019-04-011-1/+8
* Revert "[InstCombine] Handle vector gep with scalar argument in evaluateInDif...Mikael Holmen2019-04-011-8/+1
* [InstCombine] Handle vector gep with scalar argument in evaluateInDifferentEl...Mikael Holmen2019-04-011-1/+8
* [InstCombine] eliminate commuted select-shuffles + binop (PR41304)Sanjay Patel2019-04-011-0/+24
* [InstCombine] canonicalize select shuffles by commutingSanjay Patel2019-03-311-0/+9
* [InstCombine] move shuffle canonicalizations before other transformsSanjay Patel2019-03-291-30/+27
* [InstCombine] Use uadd.sat and usub.sat for canonicalizationNikita Popov2019-03-271-28/+21
* [InstCombine] form uaddsat from add+umin (PR14613)Sanjay Patel2019-03-261-0/+25
* InstCombineSimplifyDemanded: Allow v3 results for AMDGCN buffer and image int...Tim Renouf2019-03-221-2/+1
* [InstCombine] Don't transform ((C1 OP zext(X)) & C2) -> zext((C1 OP X) & C2) ...Craig Topper2019-03-211-1/+5
* [instcombine] Add some todos, and arrange code for readibilityPhilip Reames2019-03-212-32/+38
* Simplify operands of masked stores and scatters based on demanded elementsPhilip Reames2019-03-202-8/+52
OpenPOWER on IntegriCloud