summaryrefslogtreecommitdiffstats
path: root/llvm/test/Analysis/CostModel
Commit message (Expand)AuthorAgeFilesLines
* [X86][XOP] Added support for the lowering of 128-bit vector shifts to XOP shi...Simon Pilgrim2015-09-301-2/+17
* [CostModel][AArch64] Remove amortization factor for some of the vector select...Silviu Baranga2015-09-091-6/+6
* [PowerPC] Include the permutation cost for unaligned vector loadsHal Finkel2015-09-032-13/+13
* [PowerPC] Cleanup cost model for unaligned vector loads/storesHal Finkel2015-09-022-1/+405
* [CostModel][ARM] Increase cost of insert/extract operationsSilviu Baranga2015-08-171-253/+254
* [X86][SSE] Vectorize i64 ASHR operationsSimon Pilgrim2015-07-292-18/+18
* Roll forward r243250Jingyue Wu2015-07-262-24/+86
* Revert r243250Jingyue Wu2015-07-262-86/+24
* [TTI/CostModel] improve TTI::getGEPCost and use it in CostModel::getInstructi...Jingyue Wu2015-07-262-24/+86
* [X86][SSE] Updated SHL/LSHR i64 vectorization costs.Simon Pilgrim2015-07-183-25/+25
* [X86][SSE] Vectorized v4i32 non-uniform shifts.Simon Pilgrim2015-07-122-24/+24
* [X86][SSE] Vectorized i64 uniform constant SRA shiftsSimon Pilgrim2015-07-061-16/+16
* [X86][SSE][CostModel] Added full set of sitofp/uitofp costings for SSE2/AVX/A...Simon Pilgrim2015-06-202-126/+755
* [X86][SSE][CostModel] Fixed uitofp/sitofp cost target tests to specify sse2/a...Simon Pilgrim2015-06-182-5/+5
* [X86][SSE] Vectorized i8 and i16 shift operatorsSimon Pilgrim2015-06-113-36/+36
* [X86][SSE] Avoid scalarization of v2i64 vector shifts (REAPPLIED)Simon Pilgrim2015-03-182-16/+16
* TTI: Honour cost model for estimating cost of vector-intrinsic and calls.Michael Zolotukhin2015-03-171-2/+2
* [opaque pointer type] Add textual IR support for explicit type parameter to l...David Blaikie2015-02-277-43/+43
* [opaque pointer type] Add textual IR support for explicit type parameter to g...David Blaikie2015-02-275-58/+58
* [x86,sdag] Two interrelated changes to the x86 and sdag code.Chandler Carruth2015-02-191-15/+13
* [PM] Change the core design of the TTI analysis to use a polymorphicChandler Carruth2015-01-311-3/+4
* Implemented cost model for masked load/store operations.Elena Demikhovsky2015-01-251-0/+89
* AVX-512: SINT_TO_FP cost model and some bugfixesElena Demikhovsky2014-11-131-0/+45
* [X86] Custom lower UINT_TO_FP from v4f32 to v4i32, and for v8f32 to v8i32 ifQuentin Colombet2014-11-112-7/+9
* AVX-512: added cost for some AVX-512 instructionsElena Demikhovsky2014-09-162-0/+50
* Fix BasicTTI::getCmpSelInstrCost to deal with illegal vector typesHal Finkel2014-09-161-0/+14
* [ARM] Teach the cost model that cross-class copies are costly.James Molloy2014-09-121-56/+56
* [CostModel][x86] Improved cost model for alternate shuffles.Andrea Di Biagio2014-07-031-0/+347
* Reduce verbiage of lit.local.cfg filesAlp Toker2014-06-094-8/+4
* AArch64/ARM64: move ARM64 into AArch64's placeTim Northover2014-05-243-1/+1
* Added tests for the cost of lowering VSELECT instructions.Filipe Cabecinhas2014-05-161-0/+126
* TTI: Estimate @llvm.fmuladd cost as fmul + fadd when FMA's aren't legal on th...Benjamin Kramer2014-05-061-0/+28
* X86TTI: Adjust sdiv cost now that we can lower it on plain SSE2.Benjamin Kramer2014-04-271-2/+2
* X86TTI: i16/i32 vector div with a constant (splat) divisor are reasonably che...Benjamin Kramer2014-04-261-0/+92
* Don't assert in BasicTTI::getMemoryOpCost for non-simple typesHal Finkel2014-04-141-0/+3
* [PowerPC] Adjust load/store costs in PPCTTIHal Finkel2014-04-043-4/+7
* Account for scalarization costs in BasicTTI::getMemoryOpCost for extending ve...Hal Finkel2014-04-031-0/+5
* Fix multi-register costs in BasicTTI::getCastInstrCostHal Finkel2014-04-021-0/+21
* ARM64: initial backend importTim Northover2014-03-293-0/+63
* When analyzing vectors of element type that require legalization,Raul E. Silvera2014-03-102-16/+57
* Add extra CHECK prefix to tests with explicit prefixNico Rieck2014-02-161-2/+2
* Fix broken CHECK linesNico Rieck2014-02-161-1/+1
* [Vectorizer] Add a new 'OperandValueKind' in TargetTransformInfo calledAndrea Di Biagio2014-02-121-0/+167
* X86: add costs for 64-bit vector ext/trunc & rebalanceTim Northover2014-02-061-22/+75
* X86: Custom lower sext v16i8 to v16i16, and the corresponding truncate.Benjamin Kramer2013-10-231-1/+7
* X86 horizontal vector reduction cost modelYi Jiang2013-09-191-0/+271
* Costmodel: Add support for horizontal vector reductionsArnold Schwaighofer2013-09-171-0/+94
* [tests] Cleanup initialization of test suffixes.Daniel Dunbar2013-08-164-7/+0
* Fixes ARM LNT bot from SLP change in O3Renato Golin2013-08-021-0/+8
* Add the nearbyint -> FNEARBYINT mapping to BasicTargetTransformInfoHal Finkel2013-07-081-0/+28
OpenPOWER on IntegriCloud