Convert SHUFPD with the same register for both sources to PSHUFD if it would prevent...
[oota-llvm.git] / lib / Target / X86 / X86InstrSSE.td
2012-01-13 Craig TopperConvert SHUFPD with the same register for both sources...
2012-01-13 Craig TopperMake X86 instruction selection use 256-bit VPXOR for...
2012-01-13 Craig TopperAdd patterns for v16i16 and v32i8 immAllZerosV to selec...
2012-01-10 Chad RosierAdd missing VEX predicates to VMOVSDto64rr/VMOVSDto64mr...
2012-01-10 Craig TopperInstruction selection priority fixes to remove the...
2012-01-09 Craig TopperAdd HasAVX predicate to some of the AVX patterns.
2012-01-09 Craig TopperReorder a bunch of patterns to put the AVX version...
2012-01-09 Craig TopperClean up patterns for MOVNT*. Not sure why there were...
2012-01-09 Craig TopperMark MOVNTI as being supported in SSE2 OR AVX mode...
2012-01-09 Craig TopperMove SSE2 logical operations PAND/POR/PXOR/PANDN above...
2012-01-03 Chad RosierEnhance DAGCombine for transforming 128->256 casts...
2012-01-02 Craig TopperMake CanXFormVExtractWithShuffleIntoLoad reject loads...
2012-01-01 Craig TopperFix sfence, lfence, mfence, and clflush to be able...
2011-12-31 Craig TopperMerge X86 SHUFPS and SHUFPD node types.
2011-12-31 Craig TopperAdd patterns for integer forms of SHUFPD/VSHUFPD with...
2011-12-31 Craig TopperFix typo in a SHUFPD and VSHUFPD pattern that prevented...
2011-12-29 Craig TopperRemove the separate explicit AES instruction patterns...
2011-12-21 Chad RosierFix 80-column violations.
2011-12-20 Elena DemikhovskyThis is the second fix related to VZEXT_MOVL node.
2011-12-15 Eli FriedmanMake sure we correctly note the existence of an i8...
2011-12-15 Chad RosierAdd missing zmovl AVX patterns which were causing crashes.
2011-12-09 Benjamin KramerX86: Add patterns for the various rounding ops for...
2011-12-09 Benjamin KramerX86: Split (v)rounds[sd] into a normal and an intrinsic...
2011-12-08 Evan ChengAdd 256-bit variant vmovss and vmovsd patterns. rdar...
2011-12-08 Evan ChengAdd various missing AVX patterns which was causing...
2011-12-08 Evan ChengMany of the SSE patterns should not be selected when...
2011-12-07 Craig TopperFix a bunch of SSE/AVX patterns to use proper memop...
2011-12-06 Craig TopperFix a bunch of SSE/AVX patterns to use v2i64/v4i64...
2011-12-06 Craig TopperMerge floating point and integer UNPCK X86ISD node...
2011-11-30 Craig TopperMerge VPERM2F128/VPERM2I128 ISD node types.
2011-11-30 Craig TopperMerge decoding of VPERMILPD and VPERMILPS shuffle masks...
2011-11-29 Evan ChengAdd another missing pattern. llvm-gcc likes f64 but...
2011-11-29 Jakob Stoklund OlesenMake X86::FsFLD0SS / FsFLD0SD real pseudo-instructions.
2011-11-29 Elena DemikhovskyFixed vsqrt.ss intrinsic usage - order of input operand...
2011-11-29 Craig TopperFix issues in shuffle decoding around VPERM* instructio...
2011-11-29 Craig TopperFix VINSERTF128/VEXTRACTF128 to be marked as FP instruc...
2011-11-29 Craig TopperCorrectly mark VPERM2F128 as being an FP instruction...
2011-11-28 Evan ChengAdd missing avx pattern.
2011-11-28 Craig TopperAdd X86 instruction selection for VPERM2I128 when AVX2...
2011-11-26 Craig TopperMerge 128-bit and 256-bit X86ISD node types for VPERMIL...
2011-11-26 Craig TopperCollapse X86ISD node types for PUNPCKH*, PUNPCKL*,...
2011-11-24 Craig TopperRemove 256-bit specific node types for UNPCKHPS/D and...
2011-11-24 Craig TopperRemove AVX2 specific X86ISD node types for PUNPCKH...
2011-11-21 Craig TopperLowering for v32i8 to VPUNPCKLBW/VPUNPCKHBW when AVX2...
2011-11-21 Craig TopperAdd support for lowering 256-bit shuffles to VPUNPCKL...
2011-11-20 Craig TopperAdd code for lowering v32i8 shifts by a splat to AVX2...
2011-11-19 Craig TopperUse 256-bit vcmpeqd for creating an all ones vector...
2011-11-19 Craig TopperRemove some of the special classes that worked around...
2011-11-19 Craig TopperCustom lower AVX2 variable shift intrinsics to shl...
2011-11-19 Craig TopperSynthesize SSSE3/AVX 128-bit horizontal integer add...
2011-11-19 Craig TopperCollapse X86 PSIGNB/PSIGNW/PSIGND node types.
2011-11-19 Craig TopperExtend VPBLENDVB and VPSIGN lowering to work for AVX2.
2011-11-19 Craig TopperRemove unused parameters from the AVX maskmov classes.
2011-11-18 Nadav RotemAdd AVX2 vpbroadcast support
2011-11-17 Craig TopperFix SSE/AVX integer comparison patterns to understand...
2011-11-17 Craig TopperRemove seemingly unnecessary duplicate VROUND definitions.
2011-11-16 Evan ChengAnother missing X86ISD::MOVLPD pattern. rdar://10450317
2011-11-16 Craig TopperFix the execution domain on a bunch of SSE/AVX instruct...
2011-11-14 Evan ChengAdd a missing pattern for X86ISD::MOVLPD. rdar://10436044
2011-11-14 Craig TopperAdd neverHasSideEffects, mayLoad, and mayStore to many...
2011-11-12 Craig TopperAdd more AVX2 shift lowering support. Move AVX2 variabl...
2011-11-11 Craig TopperAdd lowering for AVX2 shift instructions.
2011-11-10 Nadav RotemAVX2: Add variable shift from memory.
2011-11-09 Nadav RotemAVX2: Add patterns for variable shift operations
2011-11-09 Nadav RotemAdd AVX2 support for vselect of v32i8
2011-11-09 Craig TopperAdd instruction selection for AVX2 integer comparisons.
2011-11-08 Evan ChengAdd x86 isel logic and patterns to match movlps from...
2011-11-07 Craig TopperAdd AVX2 variable shift instructions and intrinsics.
2011-11-07 Craig TopperAdd AVX2 VPMOVMASK instructions and intrinsics.
2011-11-07 Craig TopperAdd AVX2 VEXTRACTI128 and VINSERTI128 instructions...
2011-11-06 Craig TopperMore AVX2 instructions and their intrinsics.
2011-11-06 Craig TopperAdd more AVX2 instructions and intrinsics.
2011-11-04 Craig TopperAdd intrinsics for X86 vcvtps2ph and vcvtph2ps instructions
2011-11-03 Craig TopperAdd new X86 AVX2 VBROADCAST instructions.
2011-11-02 Craig TopperMore AVX2 instructions and intrinsics.
2011-11-02 Craig TopperAdd a bunch more X86 AVX2 instructions and their corres...
2011-10-31 Craig TopperBegin adding AVX2 instructions. No selection support...
2011-10-14 Jakob Stoklund OlesenV_SET0 has no side effects.
2011-10-13 Craig TopperAdd 'implicit EFLAGS' to patterns for popcnt and lzcnt
2011-10-11 Craig TopperAdd HasPOPCNT predicate to the POPCNT instructions...
2011-10-11 Craig TopperMake Ivy Bridge 16-bit floating point conversion instru...
2011-10-09 Craig TopperAdd Ivy Bridge 16-bit floating point conversion instruc...
2011-10-04 Craig TopperAdd support in the disassembler for ignoring the L...
2011-10-03 Craig TopperAdd support for MOVBE and RDRAND instructions for the...
2011-09-29 Jakob Stoklund OlesenExpand the x86 V_SET0* pseudos right after register...
2011-09-23 Duncan SandsImplement Chris's suggestion of legalizing the various...
2011-09-22 Duncan SandsSynthesize SSE3/AVX 128 bit horizontal add/sub instruct...
2011-09-20 Bruno Cardoso LopesRevert r140097, working on a better approach
2011-09-20 Bruno Cardoso LopesThe wrong relocation was being emitted for several...
2011-09-19 Bruno Cardoso LopesFix PR10949. Fix the encoding of VMOVPQIto64rr.
2011-09-19 Bruno Cardoso LopesBased on the small opt Zvi's patch was trying to achiev...
2011-09-19 Bruno Cardoso LopesMatch X86ISD::FSETCCsd and X86ISD::FSETCCss while in...
2011-09-16 Bruno Cardoso LopesDescribe more AVX 128-bit convert instructions without...
2011-09-16 Bruno Cardoso LopesAdd mayLoad attribute to AVX convert instructions,...
2011-09-14 Craig TopperFix mem type for VEX.128 form of VROUNDP*. Remove filte...
2011-09-14 Bruno Cardoso LopesTeach the foldable tables about 128-bit AVX instruction...
2011-09-13 Nadav Rotemswap vselect operand order - pr10907
2011-09-13 Bruno Cardoso LopesAdd versions 256-bit versions of alignedstore and align...
2011-09-13 Craig TopperRemove filter that was preventing MOVDQU/MOVDQA and...
2011-09-13 Craig TopperFix encoding of VMOVDQU to not simultaneously be 'TB...
next