| Commit message (Expand) | Author | Age | Files | Lines |
|---|
| * | Sort the remaining #include lines in include/... and lib/.... | Chandler Carruth | 2017-06-06 | 2 | -2/+2 |
| * | [LV] Make scalarizeInstruction() non-virtual. NFC. | Ayal Zaks | 2017-06-04 | 1 | -2/+1 |
| * | Added LLVM_FALLTHROUGH to address warning: this statement may fall through. NFC. | Galina Kistanova | 2017-06-03 | 2 | -0/+3 |
| * | [SLP] Improve comments and naming of functions/variables/members, NFC. | Alexey Bataev | 2017-06-03 | 1 | -91/+59 |
| * | Revert "[SLP] Improve comments and naming of functions/variables/members, NFC." | Alexey Bataev | 2017-06-02 | 1 | -59/+91 |
| * | [SLP] Improve comments and naming of functions/variables/members, NFC. | Alexey Bataev | 2017-06-02 | 1 | -91/+59 |
| * | [LV] Reapply r303763 with fix for PR33193 | Matthew Simpson | 2017-05-30 | 1 | -10/+19 |
| * | Revert r303763, results in asserts i.e. while building Ruby. | Joerg Sonnenberger | 2017-05-29 | 1 | -15/+6 |
| * | [LV] Update type in cost model for scalarization | Matthew Simpson | 2017-05-24 | 1 | -6/+15 |
| * | [LoopVectorizer] Let target prefer scalar addressing computations. | Jonas Paulsson | 2017-05-24 | 1 | -0/+74 |
| * | [LV] Report multiple reasons for not vectorizing under allowExtraAnalysis | Ayal Zaks | 2017-05-23 | 1 | -20/+42 |
| * | Fix vector pass-through value being unused in IRBuilder::CreateMaskedGather | Amara Emerson | 2017-05-19 | 1 | -1/+1 |
| * | [IR] De-virtualize ~Value to save a vptr | Reid Kleckner | 2017-05-18 | 1 | -2/+2 |
| * | Revert 303174, 303176, and 303178 | Matthew Simpson | 2017-05-16 | 1 | -2/+2 |
| * | [LV] Avoid potentential division by zero when selecting IC | Matthew Simpson | 2017-05-16 | 1 | -2/+2 |
| * | [SLP] Enable 64-bit wide vectorization on AArch64 | Adam Nemet | 2017-05-15 | 1 | -1/+4 |
| * | [ValueTracking] Replace all uses of ComputeSignBit with computeKnownBits. | Craig Topper | 2017-05-15 | 1 | -4/+3 |
| * | [LoopOptimizer][Fix]PR32859, PR24738 | Simon Pilgrim | 2017-05-13 | 1 | -7/+9 |
| * | [KnownBits] Add bit counting methods to KnownBits struct and use them where p... | Craig Topper | 2017-05-12 | 1 | -1/+1 |
| * | [SLP] Emit optimization remarks | Adam Nemet | 2017-05-11 | 1 | -6/+36 |
| * | [LV] Refactor ILV.vectorize{Loop}() by introducing LVP.executePlan(); NFC | Ayal Zaks | 2017-05-11 | 1 | -80/+101 |
| * | [AArch64] Consider widening instructions in cost calculations | Matthew Simpson | 2017-05-09 | 1 | -4/+6 |
| * | [LV] Fix insertion point for shuffle vectors in first order recurrence | Anna Thomas | 2017-05-09 | 1 | -2/+5 |
| * | Introduce experimental generic intrinsics for horizontal vector reductions. | Amara Emerson | 2017-05-09 | 2 | -65/+20 |
| * | Use right function in LoopVectorize. | Jonas Paulsson | 2017-05-04 | 1 | -1/+1 |
| * | Rename WeakVH to WeakTrackingVH; NFC | Sanjoy Das | 2017-05-01 | 1 | -12/+15 |
| * | [ValueTracking] Introduce a KnownBits struct to wrap the two APInts for compu... | Craig Topper | 2017-04-26 | 1 | -4/+4 |
| * | Reverts commit r301424, r301425 and r301426 | Sanjoy Das | 2017-04-26 | 1 | -15/+13 |
| * | [LV] Handle external uses of floating-point induction variables | Matthew Simpson | 2017-04-26 | 1 | -2/+6 |
| * | Rename WeakVH to WeakTrackingVH; NFC | Sanjoy Das | 2017-04-26 | 1 | -13/+15 |
| * | Skip bitcasts while looking for GEP in LoadStoreVectorizer | Stanislav Mekhanoshin | 2017-04-25 | 1 | -4/+19 |
| * | [APInt] Use isSubsetOf, intersects, and bit counting methods to reduce tempor... | Craig Topper | 2017-04-25 | 1 | -2/+1 |
| * | [LV] Remove redundant basic block split | Gil Rapaport | 2017-04-25 | 1 | -3/+4 |
| * | [LV] Model if-converted phi node costs | Matthew Simpson | 2017-04-21 | 1 | -2/+10 |
| * | [SLP vectorizer] Allow phi node reordering in tryToVectorizeList. | Easwaran Raman | 2017-04-18 | 1 | -3/+9 |
| * | [LV] Cache block mask values | Gil Rapaport | 2017-04-18 | 1 | -7/+17 |
| * | [LV] Remove implicit single basic block assumption | Gil Rapaport | 2017-04-14 | 1 | -6/+5 |
| * | [LV] Fix the vector code generation for first order recurrence | Anna Thomas | 2017-04-13 | 1 | -12/+22 |
| * | [LV] Refactor ILV to provide vectorizeInstruction(); NFC | Ayal Zaks | 2017-04-13 | 1 | -310/+302 |
| * | [SLPVectorizer] Pass the right type argument to getCmpSelInstrCost() | Jonas Paulsson | 2017-04-12 | 1 | -0/+2 |
| * | [LoopVectorizer] Improve handling of branches during cost estimation. | Jonas Paulsson | 2017-04-12 | 1 | -1/+32 |
| * | [LoopVectorizer, TTI] New method supportsEfficientVectorElementLoadStore() | Jonas Paulsson | 2017-04-12 | 1 | -2/+6 |
| * | [SystemZ] TargetTransformInfo cost functions implemented. | Jonas Paulsson | 2017-04-12 | 3 | -23/+24 |
| * | [LV] Avoid vectorizing first order recurrence when phi uses are outside loop | Anna Thomas | 2017-04-11 | 1 | -1/+6 |
| * | Reapply r298620: [LV] Vectorize GEPs | Matthew Simpson | 2017-04-07 | 1 | -79/+206 |
| * | [LV] Transform truncations of non-primary induction variables | Matthew Simpson | 2017-03-27 | 1 | -11/+10 |
| * | Revert r298620: [LV] Vectorize GEPs | Ivan Krasin | 2017-03-24 | 1 | -117/+67 |
| * | [LV] Vectorize GEPs | Matthew Simpson | 2017-03-23 | 1 | -67/+117 |
| * | [LV] Delete unneeded scalar GEP creation code | Matthew Simpson | 2017-03-23 | 1 | -33/+1 |
| * | Test commit access | Yi Kong | 2017-03-21 | 1 | -10/+10 |
