summaryrefslogtreecommitdiffstats
path: root/llvm/test/Transforms/SLPVectorizer
Commit message (Expand)AuthorAgeFilesLines
* [SLPVectorizer] Flag ADD/SUB SSAT/USAT intrinsics trivially vectorizable (PR4...Simon Pilgrim2019-01-034-1544/+300
* [SLPVectorizer][X86] Add ADD/SUB SSAT/USAT tests (PR40123)Simon Pilgrim2019-01-034-0/+4056
* [CostModel][X86][AArch64] Adjust cost of the scalarization part of min/max re...Craig Topper2018-12-101-36/+54
* [CostModel][X86] Fix overcounting arithmetic cost in illegal types in getArit...Craig Topper2018-12-072-344/+83
* Add common check prefix. NFCI.Simon Pilgrim2018-12-041-177/+89
* [TTI] Reduction costs only need to include a single extract element cost (REA...Simon Pilgrim2018-12-014-301/+188
* [X86] Split skylake-avx512 run lines in SLP vectorizer tests to cover -mprefe...Craig Topper2018-11-3014-368/+493
* [SLP]PR39774: Update references of the replaced external instructions.Alexey Bataev2018-11-304-6/+95
* [SLP]Fix PR39774: Set ReductionRoot if the original instruction is vectorized.Alexey Bataev2018-11-281-0/+108
* Revert "[TTI] Reduction costs only need to include a single extract element c...Fedor Sergeev2018-11-263-133/+282
* [TTI] Reduction costs only need to include a single extract element costSimon Pilgrim2018-11-153-282/+133
* [SLPVectorizer][X86] Regenerate reduction minmax tests and cleanup check pref...Simon Pilgrim2018-11-151-659/+272
* [SLPVectorizer][X86] Regenerate reduction tests and add PR37731 testSimon Pilgrim2018-11-151-210/+196
* [CostModel][X86] SK_ExtractSubvector is free if the subvector is at the start...Simon Pilgrim2018-11-091-1/+1
* [CostModel][X86] Add realistic vXi64 uitofp vXf64 costsSimon Pilgrim2018-10-251-138/+39
* [CostModel][X86] Add realistic i64 uitofp f64 scalar costsSimon Pilgrim2018-10-251-43/+73
* [SLPVectorizer] Add basic support for mul/and/or/xor horizontal reductionsSimon Pilgrim2018-10-231-51/+54
* [SLPVectorizer][X86] Add mul/and/or/xor unrolled reduction testsSimon Pilgrim2018-10-201-7/+351
* [SLPVectorizer] regenerate test checks; NFCSanjay Patel2018-10-201-30/+31
* [SLPVectorizer] Check that lowered type is floating point before calling isFa...Sam Clegg2018-10-091-0/+29
* Fix vectorization of canonicalizeMatt Arsenault2018-09-171-0/+17
* SLPVectorizer: Fix assert with different sized address spacesMatt Arsenault2018-08-311-0/+149
* [SLP] Fix insert point for reused extract instructions.Alexey Bataev2018-08-071-0/+95
* [SLP] Fix PR38339: Instruction does not dominate all uses!Alexey Bataev2018-07-311-0/+29
* [SCEV] Add [zs]ext{C,+,x} -> (D + [zs]ext{C-D,+,x})<nuw><nsw> transformRoman Tereshin2018-07-251-0/+162
* [SLPVectorizer] Don't attempt horizontal reduction on pointer types (PR38191)Simon Pilgrim2018-07-171-0/+128
* [SLPVectorizer] Add initial alternate opcode support for cast instructions. (...Simon Pilgrim2018-07-131-76/+289
* Revert "[SLPVectorizer] Add initial alternate opcode support for cast instruc...Martin Storsjo2018-07-121-154/+76
* [SLPVectorizer] Add initial alternate opcode support for cast instructions. (...Simon Pilgrim2018-07-111-76/+154
* [SLPVectorizer] Ensure alternate/passthrough doesn't vectorize sdiv with unde...Simon Pilgrim2018-07-111-0/+81
* [SLPVectorizer] Add some additional alternate cast testsSimon Pilgrim2018-07-111-0/+107
* Revert rL336804: [SLPVectorizer] Add initial alternate opcode support for cas...Simon Pilgrim2018-07-111-151/+52
* [SLPVectorizer] Add initial alternate opcode support for cast instructions.Simon Pilgrim2018-07-111-52/+151
* [SLP] Recognize min/max pattern using instructions producing same values.Farhana Aleen2018-07-021-65/+55
* [SLPVectorizer][X86] Begin adding alternate tests for call operatorsSimon Pilgrim2018-07-021-0/+65
* [SLPVectorizer] Fix alternate opcode + shuffle cost function to correct handl...Simon Pilgrim2018-07-021-3/+24
* [SLPVectorizer][X86] Add some alternate tests for cast operatorsSimon Pilgrim2018-07-011-0/+169
* [SLPVectorizer] Recognise non uniform power of 2 constantsSimon Pilgrim2018-06-261-32/+53
* [SLPVectorizer] Support alternate opcodes in tryToVectorizeListSimon Pilgrim2018-06-224-503/+261
* [SLPVectorizer] Relax alternate opcodes to accept any BinaryOperator pairSimon Pilgrim2018-06-221-19/+15
* [SLPVectorizer][X86] Add alternate opcode tests for simple build vector casesSimon Pilgrim2018-06-222-0/+840
* [CostModel][AArch64] Add some initial costs for SK_Select and SK_PermuteSingl...Simon Pilgrim2018-06-221-83/+50
* [X86][AVX] Reduce v4f64/v4i64 shuffle costs (PR37882)Simon Pilgrim2018-06-212-60/+20
* [SLPVectorizer][X86] Add horizontal add/sub testsSimon Pilgrim2018-06-212-0/+1094
* [SLPVectorizer] Relax "alternate" opcode vectorisation to work with any SK_Se...Simon Pilgrim2018-06-202-34/+36
* [SLP][X86] Add AVX2 run to POW2 SDIV TestsSimon Pilgrim2018-06-151-1/+2
* [SLP][X86] Regenerate POW2 SDIV TestsSimon Pilgrim2018-06-151-9/+91
* [SLP] Add testcases of min/max reduction pattern for AMDGPU.Farhana Aleen2018-06-111-0/+260
* AMDGPU: Make v2i16/v2f16 legal on VIMatt Arsenault2018-05-221-26/+17
* [AMDGPU] Support horizontal vectorization of min/max.Farhana Aleen2018-05-091-16/+392
OpenPOWER on IntegriCloud