summaryrefslogtreecommitdiffstats
path: root/llvm/lib/Transforms/InstCombine
Commit message (Expand)AuthorAgeFilesLines
* [InstCombine][SSE] Added support to VPERMD/VPERMPS to shuffle combine to acce...Simon Pilgrim2016-05-011-8/+13
* [InstCombine][SSE] Added support to VPERMILVAR to shuffle combine to accept U...Simon Pilgrim2016-05-011-20/+27
* [InstCombine][SSE] Added support to PSHUFB to shuffle combine to accept UNDEF...Simon Pilgrim2016-05-011-16/+17
* [InstCombine][AVX2] Combine VPERMD/VPERMPS intrinsics with constant masks to ...Simon Pilgrim2016-05-011-0/+37
* [InstCombine][AVX] VPERMILVAR to shuffle combine to use general aggregate ele...Simon Pilgrim2016-04-301-18/+20
* [InstCombine][SSE] PSHUFB to shuffle combine to use general aggregate element...Simon Pilgrim2016-04-291-17/+23
* [InstCombine] Determine the result of a select based on a dominating condition.Chad Rosier2016-04-291-0/+18
* [InstCombine] clean up; NFCSanjay Patel2016-04-291-1/+1
* [InstCombine] add helper function for ICmp with constant canonicalization; NFCISanjay Patel2016-04-291-24/+38
* [InstCombine] Propagate operand bundlesDavid Majnemer2016-04-292-3/+9
* [InstCombine] Remove trailing whitespace. NFC.Ahmed Bougacha2016-04-281-1/+1
* [InstCombine][SSE] Add MOVMSK support to SimplifyDemandedUseBitsSimon Pilgrim2016-04-281-0/+22
* isSafeToLoadUnconditionally support queries without a contextArtur Pilipenko2016-04-271-2/+2
* Optimize store of "bitcast" from vector to aggregate.Arch D. Robison2016-04-251-0/+60
* Cleanup redundant expression in InstCombineAndOrXor.Etienne Bergeron2016-04-251-2/+0
* Test commit: modified comment. NFCAnna Thomas2016-04-251-1/+1
* Tweak comments to make it clear that these combines are for SSE scalar instru...Simon Pilgrim2016-04-241-4/+5
* [InstCombine][SSE] Reduce DIVSS/DIVSD to FDIV if only first element is requiredSimon Pilgrim2016-04-241-1/+7
* [InstCombine][SSE] Demanded vector elements for scalar intrinsics (Part 2 of 2)Simon Pilgrim2016-04-241-1/+38
* [InstCombine][SSE] Demanded vector elements for scalar intrinsics (Part 1 of 2)Simon Pilgrim2016-04-241-0/+52
* [InstCombine] Avoid updating argument demanded elements in separate passes.Simon Pilgrim2016-04-241-7/+15
* [X86][InstCombine] Tidyup VPERMILVAR -> shufflevector conversion to helper fu...Simon Pilgrim2016-04-241-36/+47
* [X86][InstCombine] Tidyup PSHUFB -> shufflevector conversion to helper functi...Simon Pilgrim2016-04-241-40/+45
* Revert r267210, it makes clang assert (PR27490).Nico Weber2016-04-221-11/+6
* Re-commit optimization bisect support (r267022) without new pass manager supp...Andrew Kaylor2016-04-221-1/+1
* [unordered] sink unordered stores at end of blocksPhilip Reames2016-04-221-4/+3
* Fold compares for distinct allocationsSanjoy Das2016-04-221-5/+11
* [unordered] Extend load/store type canonicalization to handle unordered opera...Philip Reames2016-04-221-6/+11
* [InstCombine] Preserve fast math flags when combining PHIsSilviu Baranga2016-04-221-38/+11
* Revert "Initial implementation of optimization bisect support."Vedant Kumar2016-04-221-5/+1
* NFC: fix copy / paste commentJF Bastien2016-04-211-2/+2
* NFC: fix nonsensical commentJF Bastien2016-04-211-1/+1
* Folding compares with unescaped allocationsSanjoy Das2016-04-211-1/+14
* [instcombine][unordered] Extend load(select) transform to handle unordered loadsPhilip Reames2016-04-211-4/+3
* Initial implementation of optimization bisect support.Andrew Kaylor2016-04-211-1/+5
* [unordered] unordered loads from null are still unreachablePhilip Reames2016-04-211-3/+7
* [instcombine][unordered] Implement *-load forwarding for unordered atomicsPhilip Reames2016-04-211-4/+4
* [ValueTracking, VectorUtils] Refactor getIntrinsicIDForCallDavid Majnemer2016-04-191-1/+1
* [NFC] Header cleanupMehdi Amini2016-04-181-3/+2
* Fix a typo in rL265762Sanjoy Das2016-04-171-1/+1
* [InstCombine] Don't transform compares of calls to functions named fabs{f,l,}David Majnemer2016-04-151-30/+25
* [InstCombine] remove constant by inverting compare + logic (PR27105)Sanjay Patel2016-04-141-0/+9
* [InstCombine] We folded an fcmp to an i1 instead of a vector of i1David Majnemer2016-04-131-1/+1
* [x86, InstCombine] fix masked load pass-through operand to be a zero vectorSanjay Patel2016-04-121-3/+6
* Add the allocsize attribute to LLVM.George Burgess IV2016-04-121-2/+7
* add FIXME comment; NFCSanjay Patel2016-04-111-1/+3
* add an assert for safety; NFCSanjay Patel2016-04-111-0/+2
* variable names start with a capital letter; NFCSanjay Patel2016-04-111-9/+9
* [InstCombine] use canEvaluateShiftedShift() to handle the lshr case (NFCI)Sanjay Patel2016-04-111-33/+12
* [InstCombine] don't try to shift an illegal amount (PR26760)Sanjay Patel2016-04-111-1/+3
OpenPOWER on IntegriCloud