Separate the concept of 16-bit/32-bit operand size controlled by 0x66 prefix and...
[oota-llvm.git] / lib / Target / X86 / X86InstrMMX.td
2014-01-14 Craig TopperSeparate the concept of 16-bit/32-bit operand size...
2013-10-14 Craig TopperAllow pinsrw/pinsrb/pextrb/pextrw/movmskps/movmskpd...
2013-10-09 Craig TopperReplace a couple instructions with patterns referring...
2013-10-09 Craig TopperAdd in64BitMode/in32BitMode to the MMX/SSE2/AVX maskmov...
2013-10-08 Craig TopperRemove unneeded MMX instruction definition by moving...
2013-09-13 Preston GurdAdds support for Atom Silvermont (SLM) - -march=slm
2013-06-14 Benjamin KramerX86: cvtpi2ps is just an SSE instruction with MMX opera...
2013-05-14 Eric ChristopherReapply "Subtract isn't commutative, fix this for MMX...
2013-05-14 Eric ChristopherTemporarily revert "Subtract isn't commutative, fix...
2013-05-14 Eric ChristopherSubtract isn't commutative, fix this for MMX psub.
2013-03-26 Jakob Stoklund OlesenAnnotate x87 and mmx instructions with SchedRW lists.
2013-03-25 Jakob Stoklund OlesenRemove IIC_DEFAULT from X86Schedule.td
2012-10-30 Manman RenX86 MMX: optimize transfer from mmx to i32
2012-08-30 Michael LiaoIntroduce 'UseSSEx' to force SSE legacy encoding
2012-08-13 Craig TopperRemove the LowerMMXCONCAT_VECTORS function. It could...
2012-07-30 Craig TopperFix patterns for CVTTPS2DQ to specify SSE2 instead...
2012-05-11 Preston GurdAdded X86 Atom latencies to X86InstrMMX.td.
2012-02-18 Jia LiuEmacs-tag and some comment fix for all ARM, CellSPU...
2012-02-01 Andrew TrickInstruction scheduling itinerary for Intel Atom.
2012-01-10 Craig TopperInstruction selection priority fixes to remove the...
2012-01-09 Craig TopperDon't disable MMX support when AVX is enabled. Fix...
2011-05-05 Eli FriedmanPR9848: pandn is not commutative.
2010-10-04 Bill WendlingThe pshufw instruction came about in MMX2 when SSE...
2010-10-03 Chris Lattnerthe immediate field of pshufw is actually an 8-bit...
2010-10-03 Chris Lattneradd support for the prefetch/prefetchw instructions...
2010-10-02 Chris Lattnerstub out a header to put 3dNow! instructions into.
2010-10-02 Chris Lattnerfix a regression introduced in r115243, in which the...
2010-09-30 Dale JohannesenMassive rewrite of MMX:
2010-09-09 Dale JohannesenMove remaining MMX instructions from SSE to MMX.
2010-09-09 Dale JohannesenMove most MMX instructions (defined as anything that
2010-09-08 Dale JohannesenAdd intrinsic-based patterns for MMX PINSRW and PEXTRW.
2010-09-08 Dale JohannesenSlight cleanup, use only one form of MMXI_binop_rm_int.
2010-09-08 Dale JohannesenAdd intrinsic forms of mmx<->sse conversions. Notes:
2010-09-07 Dale JohannesenAdd patterns for MMX that use the new intrinsics.
2010-07-15 Chris Lattnerfix the encoding of MMX_MOVFR642Qrr, it starts with...
2010-07-05 Chris Lattnerrip out even more sporadic v2f32 support.
2010-05-24 Dan GohmanFix an mmx movd encoding.
2010-05-20 Dan GohmanDelete MMX_MOVQ64gmr. It was the same as MMX_MOVQ64mr...
2010-05-03 Kevin EnderbyFixed the encoding of two of the X86 movq instuctions...
2010-04-23 Stuart HastingsAdd some missing x86 patterns for movdq2q. Fixes two...
2010-03-28 Chris Lattnerremove a bunch of dead patterns.
2010-03-15 Chris Lattnerfix a few more ambiguous types.
2010-03-08 Chris Lattnerfix some more ambiguous patterns, remove another nontem...
2010-02-27 Dan GohmanThe mayHaveSideEffects flag is no longer used.
2010-02-23 Chris Lattnerremove a confused pattern that is trying to match an...
2010-02-23 Chris LattnerX86InstrInfoSSE.td declares PINSRW as having type v8i16,
2010-02-09 David GreeneTableGen fragment refactoring.
2010-02-05 Chris Lattnerlower the last of the MRMInitReg instructions in MCInst...
2010-01-24 Mon P WangImproved widening loads by adding support for wider...
2009-12-18 Sean CallananInstruction fixes, added instructions, and AsmString...
2009-10-29 Dan GohmanRename usesCustomDAGSchedInserter to usesCustomInserter...
2009-08-11 Daniel DunbarAdd 'isCodeGenOnly' bit to Instruction .td records.
2009-08-10 Eric ChristopherWhitespace, 80-column, and isTwoAddress -> Constraints...
2009-08-03 Evan ChengRemove neverHasSideEffects on MMX_MOVD64rrv164 since...
2009-08-03 Rafael EspindolaUse movd instead of movq
2009-08-03 Rafael EspindolaFix the instruction encoding.
2009-08-03 Rafael EspindolaUse movq to move 64 bits in and out of mmx registers.
2009-07-22 Eli FriedmanAdd support for MMX VSETCC.
2009-07-09 Eli FriedmanMisc encoding fixes; reported on llvmdev.
2009-06-23 Bill Wendling"The MMX_MASKMOVQ and MMX_MASKMOVQ64 instructions are...
2009-06-06 Eli FriedmanGet rid of some bogus patterns for X86vzmovl. Don...
2009-06-06 Eli FriedmanGet rid of a bogus pattern that interferes with optimiz...
2009-06-03 Stuart HastingsEvan says it's wrong; back out 72808.
2009-06-03 Stuart HastingsRecognize another euphemism for MOVDQ2Q.
2009-05-28 Bill Wendling"The instructions MMX_PSADBWrm and MMX_PSADBWrr have...
2009-04-27 Nate Begeman2nd attempt, fixing SSE4.1 issues and implementing...
2009-04-24 Rafael EspindolaRevert 69952. Causes testsuite failures on linux x86-64.
2009-04-24 Nate BegemanPR2957
2009-02-23 Evan ChengOnly v1i16 (i.e. _m64) is returned via RAX / RDX.
2008-12-12 Mon P WangAdded support for SELECT v8i8 v4i16 for X86 (MMX)
2008-12-03 Evan ChengUse mmx (punpckldq VR64, (mmx_v_set0)) to clear high...
2008-12-03 Dan GohmanRename isSimpleLoad to canFoldAsLoad, to better reflect...
2008-11-05 Evan ChengAdd more vector move low and zero-extend patterns.
2008-08-27 Bill WendlingMake "movdq2q" and "movq2dq" dependent upon having...
2008-08-25 Bill WendlingNevermind. This broke the bootstrap (?!).
2008-08-25 Bill WendlingMOVQ2DQ and MOVQ2DQ use SSE2. We should conditionalize...
2008-08-23 Anton KorobeynikovProvide a 64 bit variant of mmx.maskmovq intrinsic...
2008-07-25 Nate BegemanRemove dead PatLeaf; there are a number of issues aroun...
2008-06-24 Dale JohannesenAdd v2f32 (MMX) type to X86. Support is primitive:
2008-05-29 Evan ChengImplement vector shift up / down and insert zero with...
2008-05-09 Evan ChengHandle a few more cases of folding load i64 into xmm...
2008-05-08 Evan ChengHandle vector move / load which zero the destination...
2008-05-03 Evan ChengAdd separate intrinsics for MMX / SSE shifts with i32...
2008-04-25 Evan ChengFix illegal MMX_MOVDQ2Qrr pattern. vector_extract resul...
2008-04-25 Evan ChengSpecial handling for MMX values being passed in either...
2008-04-25 Evan ChengFix MMX_MOVQ2DQrr pattern. It's illegal to do a bitconv...
2008-04-21 Dan GohmanFix the encoding of the MMX movd that moves from MMX...
2008-04-15 Dan GohmanAdd movd instructions to move from MMX registers
2008-03-21 Evan ChengUndo 48570. Correctly match mmx shift instructions...
2008-03-19 Evan ChengAdd intrinsics to match mmx shift builtin's with immedi...
2008-03-15 Evan ChengReplace all target specific implicit def instructions...
2008-03-12 Evan ChengClean up my own mess.
2008-02-29 Anders CarlssonUse the correct instruction encodings for the 64-bit...
2008-02-18 Evan Cheng- When DAG combiner is folding a bit convert into a...
2008-01-10 Chris LattnerStart inferring side effect information more aggressive...
2008-01-10 Chris Lattnerremove explicit sets of 'neverHasSideEffects' that...
2008-01-06 Chris Lattnerrename isLoad -> isSimpleLoad due to evan's desire...
2007-12-29 Chris LattnerRemove attribution from file headers, per discussion...
2007-12-17 Bill WendlingAdd "mayHaveSideEffects" and "neverHasSideEffects"...
2007-12-12 Evan ChengImplicit def instructions, e.g. X86::IMPLICIT_DEF_GR32...
next