summaryrefslogtreecommitdiff
path: root/test/CodeGen/X86/sse41.ll
AgeCommit message (Expand)AuthorFilesLines
2015-11-04[X86][SSE] Add general memory folding for (V)INSERTPS instructionSimon Pilgrim1-8/+8
2015-09-23[X86][SSE] Replace 128-bit SSE41 PMOVSX intrinsics with native IRSimon Pilgrim1-46/+1
2015-09-20[X86][SSE] Intrinsics builtins test refresh. NFCISimon Pilgrim1-1/+1
2015-05-02Line ending fixSimon Pilgrim1-8/+8
2015-04-03[DAGCombiner] Combine shuffles of BUILD_VECTOR and SCALAR_TO_VECTORSimon Pilgrim1-16/+11
2015-03-20[X86] Prefer blendps over insertps codegen for one special caseSanjay Patel1-9/+32
2015-02-27[opaque pointer type] Add textual IR support for explicit type parameter to l...David Blaikie1-15/+15
2015-02-27[opaque pointer type] Add textual IR support for explicit type parameter to g...David Blaikie1-3/+3
2015-02-20[x86] Make the new vector shuffle legality test on by default, whichChandler Carruth1-38/+36
2015-02-16[x86] Teach the 128-bit vector shuffle lowering routines to takeChandler Carruth1-24/+32
2015-02-15[SDAG] Teach the SelectionDAG to canonicalize vector shuffles of splatsChandler Carruth1-4/+4
2015-02-04[x86] Refresh the checks of a number of tests usingChandler Carruth1-50/+50
2015-01-26Line endings fix. NFC.Simon Pilgrim1-20/+20
2015-01-23[x86] Change u8imm operands to always print as unsigned. This makes shuffle m...Craig Topper1-6/+6
2015-01-22[DAGCombine] Produce better code for constant splatsMichael Kuperstein1-2/+2
2015-01-22Revert r226811, MSVC accepts code sane compilers don't.Michael Kuperstein1-2/+2
2015-01-22[DAGCombine] Produce better code for constant splatsMichael Kuperstein1-2/+2
2015-01-21[X86][SSE] Added support for SSE3 lane duplication shuffle instructionsSimon Pilgrim1-22/+20
2014-12-02[X86][SSE] Keep 4i32 vector insertions in integer domain on SSE4.1 targetsSimon Pilgrim1-8/+8
2014-11-23[X86] Fixes bug in build_vector v4x32 loweringMichael Kuperstein1-0/+17
2014-11-21[DAG] Teach how to turn a build_vector into a shuffle if some of the operands...Andrea Di Biagio1-12/+49
2014-11-19[X86] Improved lowering of v4x32 build_vector dag nodes.Andrea Di Biagio1-13/+137
2014-11-05Improve logic that decides if its profitable to commute when some of the virt...Craig Topper1-12/+8
2014-10-05[x86] Remove the 2-addr-to-3-addr "optimization" from shufps to pshufd.Chandler Carruth1-2/+4
2014-10-04[x86] Enable the new vector shuffle lowering by default.Chandler Carruth1-52/+58
2014-10-03[x86] Adjust the patterns for lowering X86vzmovl nodes which don'tChandler Carruth1-12/+12
2014-10-03[x86] Cleanup and generate precise FileCheck assertions for a bunch ofChandler Carruth1-313/+599
2014-09-06[x86] Fix a pretty horrible bug and inconsistency in the x86 asmChandler Carruth1-1/+1
2014-07-24Fixed PR20411 - bug in getINSERTPS()Filipe Cabecinhas1-0/+18
2014-06-22Fix PR20087 by using the source index when changing the vector loadFilipe Cabecinhas1-0/+11
2014-06-06Fixed a bug in lowering shuffle_vectors to insertpsFilipe Cabecinhas1-0/+11
2014-05-19Added more insertps optimizationsFilipe Cabecinhas1-0/+108
2014-05-16Lower vselects into X86ISD::BLENDI when appropriate.Filipe Cabecinhas1-0/+8
2014-05-08Lower certain build_vectors to insertps instructionsFilipe Cabecinhas1-0/+256
2014-04-26Appease the almighty buildbots.Filipe Cabecinhas1-5/+5
2014-04-25Optimization for certain shufflevector by using insertps.Filipe Cabecinhas1-2/+73
2013-08-23Replace more uses of sse41 with sse4.1.Rafael Espindola1-2/+2
2013-07-14Mass update to CodeGen tests to use CHECK-LABEL for labels corresponding to f...Stephen Lin1-6/+6
2012-04-27Add mcpu to tests to prevent them from using AVX instructions on Sandy Bridge...Craig Topper1-2/+2
2012-04-12Fix 128-bit ptest intrinsics to take v2i64 instead of v4f32 since these are i...Craig Topper1-9/+9
2010-12-19improve the setcc -> setcc_carry optimization to happen moreChris Lattner1-2/+2
2010-08-28fix the buildvector->insertp[sd] logic to not always create a redundantChris Lattner1-0/+25
2010-04-17Start function numbering at 0.Dan Gohman1-2/+2
2009-09-08Eliminate more uses of llvm-as and llvm-dis.Dan Gohman1-2/+2
2009-07-29Add a couple more tests for the ptest intrinsics to make sure we'reEric Christopher1-0/+27
2009-07-29Add support for gcc __builtin_ia32_ptest{z,c,nzc} intrinsics. LowerEric Christopher1-1/+16
2009-07-24Move insertps tests to sse41 combo test file, convert to filecheckEric Christopher1-0/+31
2009-07-23merge one more sse41 test into sse41.llChris Lattner1-0/+44
2009-07-23merge another sse41 test into sse41.llChris Lattner1-0/+23
2009-07-23merge sse41-pmovx.ll into sse41.llChris Lattner1-6/+69
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-19 05:52:52 +0000