summaryrefslogtreecommitdiffstats
path: root/llvm/lib/IR/AutoUpgrade.cpp
Commit message (Expand)AuthorAgeFilesLines
...
* [X86][AVX512] Dropped avx512 VPSLLDQ/VPSRLDQ intrinsicsSimon Pilgrim2016-06-091-10/+14
* [AVX512] Remove masked palignr intrinsics and auto-upgrade them to native IR ...Craig Topper2016-06-061-0/+54
* [X86][XOP] Support for VPERMIL2PD/VPERMIL2PS 2-input shuffle instructionsSimon Pilgrim2016-06-031-0/+35
* [X86][SSE] Replace (V)CVTTPS2DQ and VCVTTPD2DQ truncating (round to zero) f32...Simon Pilgrim2016-06-021-0/+8
* [AVX512] Remove masked load intrinsics. Clang now emits generic masked load i...Craig Topper2016-06-021-2/+62
* Revert r271362 "[AVX512] Remove masked load intrinsics. Clang now emits gener...Craig Topper2016-06-011-62/+2
* [AVX512] Remove masked load intrinsics. Clang now emits generic masked load i...Craig Topper2016-06-011-2/+62
* [AVX512] Remove masked store intrinsics. Clang now emits generic masked store...Craig Topper2016-05-311-0/+66
* [X86] Remove SSE/AVX unaligned store intrinsics as clang no longer uses them....Craig Topper2016-05-301-0/+17
* [X86] Simplify and remove some unnecessary auto-upgrade code.Craig Topper2016-05-301-10/+2
* [X86] Reduce the number of string compares in the autoupgrade logic by checki...Craig Topper2016-05-301-41/+17
* [X86] Simplify some of the autoupgrade code. NFCCraig Topper2016-05-291-61/+38
* [X86][SSE] (Reapplied) Replace (V)PMOVSX and (V)PMOVZX integer extension intr...Simon Pilgrim2016-05-281-3/+12
* Revert: r270973 - [X86][SSE] Replace (V)PMOVSX and (V)PMOVZX integer extensio...Simon Pilgrim2016-05-271-12/+3
* [X86][SSE] Replace (V)PMOVSX and (V)PMOVZX integer extension intrinsics with ...Simon Pilgrim2016-05-271-3/+12
* Objective-C Class Properties: Autoupgrade "Class Properties" module flag.Manman Ren2016-05-251-0/+31
* [X86][SSE] Replace (V)CVTDQ2PD(Y) and (V)CVTPS2PD(Y) lossless conversion intr...Simon Pilgrim2016-05-251-0/+27
* [X86] Remove the llvm.x86.sse2.storel.dq intrinsic. It hasn't been used in a ...Craig Topper2016-05-251-0/+20
* [AArch64] [ARM] Make a target-independent llvm.thread.pointer intrinsic.Marcin Koscielnicki2016-04-191-0/+10
* try to make comments more meaningful; NFCSanjay Patel2016-04-181-9/+7
* Revert "use range loop, try to make comments more meaningful; NFCI"Duncan P. N. Exon Smith2016-04-171-7/+10
* use range loop, try to make comments more meaningful; NFCISanjay Patel2016-04-161-10/+7
* Revert "Support arbitrary addrspace pointers in masked load/store intrinsics"Adam Nemet2016-04-141-34/+0
* Support arbitrary addrspace pointers in masked load/store intrinsicsArtur Pilipenko2016-04-121-0/+34
* [SSP] Remove llvm.stackprotectorcheck.Tim Shen2016-04-081-1/+10
* IR: Stop upgrading !llvm.loop attachments via MDStringDuncan P. N. Exon Smith2016-03-251-7/+60
* Revert "Support arbitrary addrspace pointers in masked load/store intrinsics"Matthias Braun2016-03-221-34/+0
* Support arbitrary addrspace pointers in masked load/store intrinsicsArtur Pilipenko2016-03-101-0/+34
* Revert "Change memcpy/memset/memmove to have dest and source alignments."Pete Cooper2015-11-191-55/+0
* Change memcpy/memset/memmove to have dest and source alignments.Pete Cooper2015-11-181-0/+55
* [X86][XOP] Add support for the matching of the VPCMOV bit select instructionSimon Pilgrim2015-11-031-0/+11
* Make a bunch of static arrays const.Craig Topper2015-10-181-8/+9
* IR: Remove implicit iterator conversions from lib/IR, NFCDuncan P. N. Exon Smith2015-10-081-2/+2
* [ARM][NEON] Use address space in vld([1234]|[234]lane) and vst([1234]|[234]la...Jeroen Ketema2015-09-301-0/+55
* [X86][SSE] Replace 128-bit SSE41 PMOVSX intrinsics with native IRSimon Pilgrim2015-09-231-3/+17
* [X86] Require 32-byte alignment for 32-byte VMOVNTs.Ahmed Bougacha2015-09-021-1/+1
* [X86] Replace avx2 broadcast intrinsics with native IR.Ahmed Bougacha2015-08-201-0/+10
* Remove always-true comparison, NFC.Filipe Cabecinhas2015-07-031-9/+8
* [opaque pointer type] Pass explicit type to Load instruction creation in Auto...David Blaikie2015-05-201-5/+5
* Change Function::getIntrinsicID() to return an Intrinsic::ID. NFC.Pete Cooper2015-05-201-3/+2
* Simplify IRBuilder::CreateCall* by using ArrayRef+initializer_list/braced ini...David Blaikie2015-05-181-15/+12
* AVX-512: Changed CC parameter in "cmp" intrinsicElena Demikhovsky2015-05-111-89/+0
* AVX-512: Added all forms of FP compare instructions for KNL and SKX.Elena Demikhovsky2015-05-071-23/+0
* [opaque pointer type] Verifier/AutoUpgrade: Remove a few uses of PointerType:...David Blaikie2015-04-241-10/+8
* AutoUpgrade: Remove obsolete dbg.declare/value upgradeDuncan P. N. Exon Smith2015-04-061-49/+0
* Trying to fix the Hexagon and debian-fast bots arm32_neon_vcnt_upgrade.ll test.Yaron Keren2015-03-301-1/+1
* Remove more superfluous .str() and replace std::string concatenation with Twine.Yaron Keren2015-03-301-1/+1
* [X86, AVX2] Replace inserti128 and extracti128 intrinsics with generic shufflesSanjay Patel2015-03-121-2/+6
* make an array of constants explicitly constSanjay Patel2015-03-121-1/+1
* IRBuilder: add a CreateShuffleVector function that takes an ArrayRef of intSanjay Patel2015-03-121-4/+2
OpenPOWER on IntegriCloud