summaryrefslogtreecommitdiffstats
path: root/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp
Commit message (Expand)AuthorAgeFilesLines
...
* InstCombine: Fold fabs on select of constantsMatt Arsenault2017-01-031-0/+12
* [InstCombine] use 'match' to reduce code bloat; NFCISanjay Patel2017-01-031-15/+11
* InstCombine: Add fma with constant transformsMatt Arsenault2017-01-031-3/+17
* InstCombine: Add fma + fabs/fneg transformsMatt Arsenault2017-01-031-0/+30
* [InstCombine][AVX-512] Teach InstCombine that llvm.x86.avx512.vcomi.sd and ll...Craig Topper2016-12-311-0/+2
* [InstCombine][AVX-512] When turning intrinsics with masking into native IR, d...Craig Topper2016-12-301-9/+20
* [InstCombine][X86] Add DemandedElts support for 512-bit PMULDQ/PMULUDQ instru...Craig Topper2016-12-271-1/+3
* [AVX-512][InstCombine] Teach InstCombine to turn masked scalar add/sub/mul/di...Craig Topper2016-12-271-37/+42
* [AVX-512][InstCombine] Teach InstCombine to turn packed add/sub/mul/div with ...Craig Topper2016-12-271-0/+44
* [InstCombine][X86] Add DemandedElts support for PMULDQ/PMULUDQ instructionsSimon Pilgrim2016-12-261-0/+15
* [AVX-512][InstCombine] Teach InstCombine to turn scalar add/sub/mul/div with ...Craig Topper2016-12-261-3/+49
* [AVX-512][InstCombine] Teach InstCombine to converted masked vpermv intrinsic...Craig Topper2016-12-251-4/+50
* [Analysis] Centralize objectsize lowering logic.George Burgess IV2016-12-201-10/+5
* Revert @llvm.assume with operator bundles (r289755-r289757)Daniel Jasper2016-12-191-83/+11
* [AVX-512][InstCombine] Add masked scalar FMA intrinsics to SimplifyDemandedVe...Craig Topper2016-12-151-0/+10
* Remove the AssumptionCacheHal Finkel2016-12-151-11/+11
* Make processing @llvm.assume more efficient by using operand bundlesHal Finkel2016-12-151-0/+72
* [X86][InstCombine] Handle demanded elements for operand of AVX-512 scalar flo...Craig Topper2016-12-141-1/+17
* [X86][InstCombine] Teach SimplifyDemandedVectorElts to handle masked scalar a...Craig Topper2016-12-141-20/+2
* [X86][InstCombine] Handle scalar fmadd intrinsics correctly in SimplifyDemand...Craig Topper2016-12-141-8/+8
* [X86][InstCombine] Teach SimplifyDemandedVectorElts to handle scalar round in...Craig Topper2016-12-141-27/+2
* [X86][InstCombine] Teach SimplifyDemandedVectorElts to handle scalar min/max/...Craig Topper2016-12-141-17/+6
* [X86][InstCombine] Fix SimplifyDemandedVectorElts to handle frcz scalar intri...Craig Topper2016-12-131-0/+13
* [X86][InstCombine] Teach InstCombineCalls to simplify demanded elements for s...Craig Topper2016-12-111-0/+8
* [AVX-512][InstCombine] Teach InstCombineCalls how to simplify demanded for sc...Craig Topper2016-12-111-1/+3
* [AVX-512][InstCombine] Teach InstCombineCalls how to simplify demanded elemen...Craig Topper2016-12-111-0/+31
* [AVX-512][InstCombine] Add 512-bit vpermilvar intrinsics to InstCombineCalls ...Craig Topper2016-12-111-10/+10
* [X86][InstCombine] Teach InstCombineCalls to turn pshufb intrinsic into a shu...Craig Topper2016-12-111-2/+3
* Replace some callers of setTailCall with setTailCallKindDavid Majnemer2016-11-251-6/+5
* [InstCombine][AVX-512] Teach InstCombineCalls how to handle the intrinsics fo...Craig Topper2016-11-181-0/+18
* [X86] Remove the scalar intrinsics for fadd/fsub/fdiv/fmulCraig Topper2016-11-161-8/+0
* [InstCombine][AVX-512] Teach InstCombineCalls to handle the new unmasked AVX-...Craig Topper2016-11-131-4/+18
* [InstCombine][AVX-512] Expand vector shift handling to work on the AVX-512 sh...Craig Topper2016-11-131-1/+45
* [InstCombine][SSE4a] Fix assertion failure in the insertq/insertqi combining ...Andrea Di Biagio2016-09-071-3/+3
* [InstCombine][SSE4a] Fix assertion failure caused by unsafe dyn_casts on the ...Andrea Di Biagio2016-09-071-3/+3
* [InstCombine] Preserve llvm.mem.parallel_loop_access metadata when replacingDorit Nuzman2016-09-041-0/+6
* Test commit.Dorit Nuzman2016-09-041-0/+1
* AMDGPU: Do basic folding of class intrinsicMatt Arsenault2016-09-031-0/+79
* Make cltz and cttz zero undef when the operand cannot be zero in InstCombineAmaury Sechet2016-08-181-5/+20
* Replace a few more "fall through" comments with LLVM_FALLTHROUGHJustin Bogner2016-08-171-1/+1
* Fix some Clang-tidy modernize and Include What You Use warnings.Eugene Zelenko2016-08-111-11/+39
* fix comment; NFCSanjay Patel2016-08-111-2/+3
* use auto* with dyn_cast ; NFCSanjay Patel2016-08-111-2/+1
* getParent()->getParent() == getFunction() ; NFCSanjay Patel2016-08-111-2/+1
* [InstCombine] refactor ctlz/cttz folds (NFCI)Sanjay Patel2016-08-051-34/+33
* InstCombine: Replace some never-null pointers with references. NFCJustin Bogner2016-08-051-24/+25
* Do not remove empty lifetime.start/lifetime.end rangesVitaly Buka2016-07-281-0/+5
* Should be committed as one CL.Vitaly Buka2016-07-281-5/+0
* Do not remove empty lifetime.start/lifetime.end rangesVitaly Buka2016-07-281-8/+5
* manedVitaly Buka2016-07-281-6/+8
OpenPOWER on IntegriCloud