Age | Commit message (Expand) | Author | Files | Lines |
2014-04-23 | [X86] Fix missing/wrong scheduling model found by code inspection. | Quentin Colombet | 1 | -1/+2 |
2014-04-17 | [X86] Add disassembler support for the 0x0f 0x7f form of movq %mm, %mm. | Craig Topper | 1 | -0/+5 |
2014-04-04 | Revert r205599, the commit was not intended to have so many changes | Quentin Colombet | 1 | -2/+1 |
2014-04-04 | [RegAllocGreedy][Last Chance Recoloring] Emit diagnostics when last chance | Quentin Colombet | 1 | -1/+2 |
2014-02-18 | Add an x86 prefix encoding for instructions that would decode to a different ... | Craig Topper | 1 | -3/+3 |
2014-01-14 | Separate the concept of 16-bit/32-bit operand size controlled by 0x66 prefix ... | Craig Topper | 1 | -3/+3 |
2013-10-14 | Allow pinsrw/pinsrb/pextrb/pextrw/movmskps/movmskpd/pmovmskb/extractps instru... | Craig Topper | 1 | -9/+10 |
2013-10-09 | Replace a couple instructions with patterns referring to other instructions w... | Craig Topper | 1 | -16/+11 |
2013-10-09 | Add in64BitMode/in32BitMode to the MMX/SSE2/AVX maskmovq/dq instructions. Thi... | Craig Topper | 1 | -4/+4 |
2013-10-08 | Remove unneeded MMX instruction definition by moving pattern to an equivalent... | Craig Topper | 1 | -6/+2 |
2013-09-13 | Adds support for Atom Silvermont (SLM) - -march=slm | Preston Gurd | 1 | -1/+1 |
2013-06-14 | X86: cvtpi2ps is just an SSE instruction with MMX operands. It has no AVX equ... | Benjamin Kramer | 1 | -7/+8 |
2013-05-14 | Reapply "Subtract isn't commutative, fix this for MMX psub." with | Eric Christopher | 1 | -7/+7 |
2013-05-14 | Temporarily revert "Subtract isn't commutative, fix this for MMX psub." | Eric Christopher | 1 | -7/+7 |
2013-05-14 | Subtract isn't commutative, fix this for MMX psub. | Eric Christopher | 1 | -7/+7 |
2013-03-26 | Annotate x87 and mmx instructions with SchedRW lists. | Jakob Stoklund Olesen | 1 | -24/+52 |
2013-03-25 | Remove IIC_DEFAULT from X86Schedule.td | Jakob Stoklund Olesen | 1 | -2/+2 |
2012-10-30 | X86 MMX: optimize transfer from mmx to i32 | Manman Ren | 1 | -2/+8 |
2012-08-30 | Introduce 'UseSSEx' to force SSE legacy encoding | Michael Liao | 1 | -32/+33 |
2012-08-13 | Remove the LowerMMXCONCAT_VECTORS function. It could never execute because th... | Craig Topper | 1 | -14/+0 |
2012-07-30 | Fix patterns for CVTTPS2DQ to specify SSE2 instead of SSE1. | Craig Topper | 1 | -2/+2 |
2012-05-11 | Added X86 Atom latencies to X86InstrMMX.td. | Preston Gurd | 1 | -129/+274 |
2012-02-18 | Emacs-tag and some comment fix for all ARM, CellSPU, Hexagon, MBlaze, MSP430,... | Jia Liu | 1 | -1/+1 |
2012-02-01 | Instruction scheduling itinerary for Intel Atom. | Andrew Trick | 1 | -4/+8 |
2012-01-10 | Instruction selection priority fixes to remove the XMM/XMMInt/orAVX predicate... | Craig Topper | 1 | -20/+20 |
2012-01-09 | Don't disable MMX support when AVX is enabled. Fix predicates for MMX instruc... | Craig Topper | 1 | -24/+24 |
2011-05-05 | PR9848: pandn is not commutative. | Eli Friedman | 1 | -1/+1 |
2010-10-04 | The pshufw instruction came about in MMX2 when SSE was introduced. Don't place | Bill Wendling | 1 | -3/+3 |
2010-10-03 | the immediate field of pshufw is actually an 8-bit field, not a 8-bit field t... | Chris Lattner | 1 | -2/+2 |
2010-10-03 | add support for the prefetch/prefetchw instructions, move femms into | Chris Lattner | 1 | -3/+1 |
2010-10-02 | stub out a header to put 3dNow! instructions into. | Chris Lattner | 1 | -1/+1 |
2010-10-02 | fix a regression introduced in r115243, in which the instruction | Chris Lattner | 1 | -0/+16 |
2010-09-30 | Massive rewrite of MMX: | Dale Johannesen | 1 | -493/+69 |
2010-09-09 | Move remaining MMX instructions from SSE to MMX. | Dale Johannesen | 1 | -62/+44 |
2010-09-09 | Move most MMX instructions (defined as anything that | Dale Johannesen | 1 | -1/+120 |
2010-09-08 | Add intrinsic-based patterns for MMX PINSRW and PEXTRW. | Dale Johannesen | 1 | -0/+19 |
2010-09-08 | Slight cleanup, use only one form of MMXI_binop_rm_int. | Dale Johannesen | 1 | -53/+37 |
2010-09-08 | Add intrinsic forms of mmx<->sse conversions. Notes: | Dale Johannesen | 1 | -0/+51 |
2010-09-07 | Add patterns for MMX that use the new intrinsics. | Dale Johannesen | 1 | -14/+60 |
2010-07-15 | fix the encoding of MMX_MOVFR642Qrr, it starts with 0xF2 not 0xF3, | Chris Lattner | 1 | -1/+1 |
2010-07-05 | rip out even more sporadic v2f32 support. | Chris Lattner | 1 | -14/+0 |
2010-05-24 | Fix an mmx movd encoding. | Dan Gohman | 1 | -4/+4 |
2010-05-20 | Delete MMX_MOVQ64gmr. It was the same as MMX_MOVQ64mr, but it didn't | Dan Gohman | 1 | -3/+0 |
2010-05-03 | Fixed the encoding of two of the X86 movq instuctions. The Move quadword from | Kevin Enderby | 1 | -1/+1 |
2010-04-23 | Add some missing x86 patterns for movdq2q. Fixes two (LLVM-)GCC DejaGNU test... | Stuart Hastings | 1 | -0/+11 |
2010-03-28 | remove a bunch of dead patterns. | Chris Lattner | 1 | -13/+0 |
2010-03-15 | fix a few more ambiguous types. | Chris Lattner | 1 | -2/+2 |
2010-03-08 | fix some more ambiguous patterns, remove another nontemporalstore | Chris Lattner | 1 | -4/+5 |
2010-02-27 | The mayHaveSideEffects flag is no longer used. | Dan Gohman | 1 | -1/+1 |
2010-02-23 | remove a confused pattern that is trying to match an address | Chris Lattner | 1 | -7/+0 |