aboutsummaryrefslogtreecommitdiff
path: root/lib/Target/X86/X86ISelLowering.cpp
AgeCommit message (Expand)Author
2015-05-26[X86] Always return the sret parameter in eax/rax, even on 32-bitrelease_36Reid Kleckner
2015-03-24[ndk][x86] Add option to store sp cookie in var.Logan Chien
2015-03-20[release_36] Cherry-pick r232046.Andrea Di Biagio
2015-03-20[release_36] Cherry-pick r231601.Andrea Di Biagio
2015-03-19[release_36] Cherry-pick r232179.Andrea Di Biagio
2015-03-12[release_36] Cherry-pick r232085.Quentin Colombet
2015-02-17Merging r226808:Hans Wennborg
2015-02-12Merging r228979:Hans Wennborg
2015-01-13[AVX512] Unpack support in new shuffle loweringAdam Nemet
2015-01-12[X86][SSE] Minor regression fix for r225551Simon Pilgrim
2015-01-12[X86] Also create+widen FMIN/FMAX nodes for v2f32.Ahmed Bougacha
2015-01-11Revert most of r225597David Majnemer
2015-01-11X86: Properly decode shuffle masks when the constant pool type is weirdDavid Majnemer
2015-01-11X86: teach X86TargetLowering about L,M,O constraintsSaleem Abdulrasool
2015-01-10[X86][SSE] Improved (v)insertps shuffle matchingSimon Pilgrim
2015-01-09[X86][SSE] Avoid vector byte shuffles with zero by using pshufb to create zerosSimon Pilgrim
2015-01-09[x86] Add a flag to control the vector shuffle legality predicates thatChandler Carruth
2015-01-08[X86] Reflow comment. NFC.Ahmed Bougacha
2015-01-08[X86] Don't try to generate direct calls to TLS globalsMichael Kuperstein
2015-01-08[SelectionDAG] Allow targets to specify legality of extloads' resultAhmed Bougacha
2015-01-07[CodeGen] Use MVT iterator_ranges in legality loops. NFC intended.Ahmed Bougacha
2015-01-07[X86] Fix 512->256 typo in comments. NFC.Ahmed Bougacha
2015-01-07[X86] Teach FCOPYSIGN lowering to recognize constant magnitudes.Ahmed Bougacha
2015-01-06X86: Don't make illegal GOTTPOFF relocationsDavid Majnemer
2015-01-06[X86] Make isel select the shorter form of jump instructions instead of the l...Craig Topper
2015-01-05[X86][SSE] lowerVectorShuffleAsByteShift tidyupSimon Pilgrim
2015-01-05[X86][SSE] Fixed description for isSequentialOrUndefInRange. NFC.Simon Pilgrim
2015-01-02Improved comments. No functional change intended.Andrea Di Biagio
2014-12-28[CodeGenPrepare] Teach when it is profitable to speculate calls to @llvm.cttz...Andrea Di Biagio
2014-12-27Fixing another -Wunused-variable warning, this time in release builds without...Aaron Ballman
2014-12-27Removing a variable that is set but never used, to silence a -Wunused-but-set...Aaron Ballman
2014-12-23AVX-512: Added FMA instructions, intrinsics an tests for KNL and SKX targetsElena Demikhovsky
2014-12-23AVX-512: BLENDM - fixed encoding of the broadcast versionElena Demikhovsky
2014-12-23X86: Don't over-align combined loads.Jim Grosbach
2014-12-22Make musttail more robust for vector types on x86Reid Kleckner
2014-12-22[x86] Add vector @llvm.ctpop intrinsic custom loweringBruno Cardoso Lopes
2014-12-22AVX-512: Added all forms of BLENDM instructions,Elena Demikhovsky
2014-12-19Masked load and store codegen - fixed 128-bit vectorsElena Demikhovsky
2014-12-18[AVX512] Enable FP arithmetic lowering for AVX512VL subsets.Robert Khasanov
2014-12-17[DAGCombine] Slightly improve lowering of BUILD_VECTOR into a shuffle.Michael Kuperstein
2014-12-17[CodeGenPrepare] Reapply r224351 with a fix for the assertion failure:Quentin Colombet
2014-12-17Revert "[CodeGenPrepare] Move sign/zero extensions near loads using type prom...Reid Kleckner
2014-12-16[CodeGenPrepare] Move sign/zero extensions near loads using type promotion.Quentin Colombet
2014-12-16[AVX512] Enable integer arithmetic lowering for AVX512BW/VL subsets.Robert Khasanov
2014-12-15AVX-512: Added EXPAND instructions and intrinsics.Elena Demikhovsky
2014-12-12[AVX512] Enabling bit logic loweringRobert Khasanov
2014-12-12[AVX512] Enabling MIN/MAX lowering.Robert Khasanov
2014-12-11remove function names from comments; NFCSanjay Patel
2014-12-11return without temporary; NFCSanjay Patel
2014-12-11AVX-512: Added all forms of COMPRESS instructionElena Demikhovsky