2006-04-20 |
Evan Cheng | Added a virtual method isVectorClearMaskLegal to TLI...
|
commit | commitdiff | tree |
2006-04-20 |
Evan Cheng | Added a test case for , e.g. xform pand <0, 0, -1,...
|
commit | commitdiff | tree |
2006-04-20 |
Evan Cheng | Added a movhlps, movlhps test case.
|
commit | commitdiff | tree |
2006-04-20 |
Evan Cheng | Handle v2i64 BUILD_VECTOR custom lowering correctly...
|
commit | commitdiff | tree |
2006-04-19 |
Evan Cheng | isSplatMask() bug: first element can be an undef.
|
commit | commitdiff | tree |
2006-04-19 |
Evan Cheng | - Added support to do aribitrary 4 wide shuffle with...
|
commit | commitdiff | tree |
2006-04-19 |
Evan Cheng | Prefer {p}unpack* and mov*dup over {p}shuf* as well.
|
commit | commitdiff | tree |
2006-04-19 |
Evan Cheng | Renamed AddedCost to AddedComplexity.
|
commit | commitdiff | tree |
2006-04-19 |
Evan Cheng | - Renamed AddedCost to AddedComplexity.
|
commit | commitdiff | tree |
2006-04-19 |
Evan Cheng | Rename AddedCost to AddedComplexity.
|
commit | commitdiff | tree |
2006-04-19 |
Evan Cheng | Commute vector_shuffle to match more movlhps, movlp...
|
commit | commitdiff | tree |
2006-04-19 |
Evan Cheng | More mov{h|l}p{d|s} patterns.
|
commit | commitdiff | tree |
2006-04-19 |
Evan Cheng | - More mov{h|l}ps patterns.
|
commit | commitdiff | tree |
2006-04-19 |
Evan Cheng | Allow "let AddedCost = n in" to increase pattern complexity.
|
commit | commitdiff | tree |
2006-04-18 |
Evan Cheng | - PEXTRW cannot take a memory location as its first...
|
commit | commitdiff | tree |
2006-04-18 |
Evan Cheng | SHUFP{S|D}, PSHUF* encoding bugs. Left out the mask...
|
commit | commitdiff | tree |
2006-04-18 |
Evan Cheng | Name change for clarity sake
|
commit | commitdiff | tree |
2006-04-18 |
Evan Cheng | Encoding bug: CMPPSrmi, CMPPDrmi dropped operand 2...
|
commit | commitdiff | tree |
2006-04-18 |
Evan Cheng | Name change for clarity sake
|
commit | commitdiff | tree |
2006-04-18 |
Evan Cheng | Left a pattern out
|
commit | commitdiff | tree |
2006-04-18 |
Evan Cheng | Fixed an encoding bug: movd from XMM to R32.
|
commit | commitdiff | tree |
2006-04-18 |
Evan Cheng | Correct comments
|
commit | commitdiff | tree |
2006-04-18 |
Evan Cheng | Another entry
|
commit | commitdiff | tree |
2006-04-18 |
Evan Cheng | Another entry.
|
commit | commitdiff | tree |
2006-04-17 |
Evan Cheng | Use movss to insert_vector_elt(v, s, 0).
|
commit | commitdiff | tree |
2006-04-17 |
Evan Cheng | Use two pinsrw to insert an element into v4i32 / v4f32...
|
commit | commitdiff | tree |
2006-04-17 |
Evan Cheng | Encoding bug
|
commit | commitdiff | tree |
2006-04-17 |
Evan Cheng | Implement v8i16, v16i8 splat using unpckl + pshufd.
|
commit | commitdiff | tree |
2006-04-17 |
Evan Cheng | Incorrect foldMemoryOperand entries
|
commit | commitdiff | tree |
2006-04-17 |
Evan Cheng | Errors in patterns preventing load folding
|
commit | commitdiff | tree |
2006-04-17 |
Evan Cheng | FP SETOLT, SETOLT, SETUGE, SETUGT conditions were implemente...
|
commit | commitdiff | tree |
2006-04-16 |
Evan Cheng | Better way to splat v2f64
|
commit | commitdiff | tree |
2006-04-16 |
Evan Cheng | movduprm, movshduprm bugs
|
commit | commitdiff | tree |
2006-04-16 |
Evan Cheng | Encoding bugs
|
commit | commitdiff | tree |
2006-04-16 |
Evan Cheng | Can't fold loads into alias vector SSE ops used for...
|
commit | commitdiff | tree |
2006-04-15 |
Evan Cheng | More encoding bugs
|
commit | commitdiff | tree |
2006-04-15 |
Evan Cheng | pslldrm, psrawrm, etc. encoding bug
|
commit | commitdiff | tree |
2006-04-15 |
Evan Cheng | hsubp{s|d} encoding bug
|
commit | commitdiff | tree |
2006-04-15 |
Evan Cheng | Silly bug
|
commit | commitdiff | tree |
2006-04-15 |
Evan Cheng | Do not use movs{h|l}dup for a shuffle with a single...
|
commit | commitdiff | tree |
2006-04-14 |
Evan Cheng | Added SSE (and other) entries to foldMemoryOperand().
|
commit | commitdiff | tree |
2006-04-14 |
Evan Cheng | Some clean up
|
commit | commitdiff | tree |
2006-04-14 |
Evan Cheng | Last few SSE3 intrinsics.
|
commit | commitdiff | tree |
2006-04-14 |
Evan Cheng | Misc. SSE2 intrinsics: clflush, lfench, mfence
|
commit | commitdiff | tree |
2006-04-14 |
Evan Cheng | We were not adjusting the frame size to ensure proper...
|
commit | commitdiff | tree |
2006-04-14 |
Evan Cheng | New entry
|
commit | commitdiff | tree |
2006-04-14 |
Evan Cheng | pcmpeq* and pcmpgt* intrinsics.
|
commit | commitdiff | tree |
2006-04-14 |
Evan Cheng | psll*, psrl*, and psra* intrinsics.
|
commit | commitdiff | tree |
2006-04-13 |
Evan Cheng | Doh. PANDrm, etc. are not commutable.
|
commit | commitdiff | tree |
2006-04-13 |
Evan Cheng | psad, pmax, pmin intrinsics.
|
commit | commitdiff | tree |
2006-04-13 |
Evan Cheng | pmin, pmax, and psad intrinsics.
|
commit | commitdiff | tree |
2006-04-13 |
Evan Cheng | Various SSE2 packed integer intrinsics: pmulhuw, pavgw...
|
commit | commitdiff | tree |
2006-04-13 |
Evan Cheng | X86 SSE2 supports v8i16 multiplication
|
commit | commitdiff | tree |
2006-04-13 |
Evan Cheng | Update
|
commit | commitdiff | tree |
2006-04-13 |
Evan Cheng | pmul*, pmadd*, and pavg* intrinsics.
|
commit | commitdiff | tree |
2006-04-13 |
Evan Cheng | padds{b|w}, paddus{b|w}, psubs{b|w}, psubus{b|w} intrinsics.
|
commit | commitdiff | tree |
2006-04-13 |
Evan Cheng | Naming inconsistency.
|
commit | commitdiff | tree |
2006-04-12 |
Evan Cheng | SSE / SSE2 conversion intrinsics.
|
commit | commitdiff | tree |
2006-04-12 |
Evan Cheng | Update my credits. Can I add "Build breaker" to my...
|
commit | commitdiff | tree |
2006-04-12 |
Evan Cheng | All "integer" logical ops (pand, por, pxor) are now...
|
commit | commitdiff | tree |
2006-04-12 |
Evan Cheng | Promote vector AND, OR, and XOR
|
commit | commitdiff | tree |
2006-04-12 |
Evan Cheng | Promote v4i32, v8i16, v16i8 load to v2i64 load.
|
commit | commitdiff | tree |
2006-04-12 |
Evan Cheng | Vector type promotion for ISD::LOAD and ISD::SELECT
|
commit | commitdiff | tree |
2006-04-12 |
Evan Cheng | Various SSE2 conversion intrinsics
|
commit | commitdiff | tree |
2006-04-11 |
Evan Cheng | Added __builtin_ia32_storelv4si, __builtin_ia32_movqv4si,
|
commit | commitdiff | tree |
2006-04-11 |
Evan Cheng | gcc lower SSE prefetch into generic prefetch intrinsic...
|
commit | commitdiff | tree |
2006-04-11 |
Evan Cheng | Misc. intrinsics.
|
commit | commitdiff | tree |
2006-04-11 |
Evan Cheng | movnt* and maskmovdqu intrinsics
|
commit | commitdiff | tree |
2006-04-11 |
Evan Cheng | Only get Tmp2 for cases where number of operands is...
|
commit | commitdiff | tree |
2006-04-11 |
Evan Cheng | Added support for _mm_move_ss and _mm_move_sd.
|
commit | commitdiff | tree |
2006-04-10 |
Evan Cheng | Remove some bogus patterns; clean up.
|
commit | commitdiff | tree |
2006-04-10 |
Evan Cheng | Remove an entry that is now done.
|
commit | commitdiff | tree |
2006-04-10 |
Evan Cheng | Added some missing shuffle patterns.
|
commit | commitdiff | tree |
2006-04-10 |
Evan Cheng | Correct an entry
|
commit | commitdiff | tree |
2006-04-10 |
Evan Cheng | movups / movupd
|
commit | commitdiff | tree |
2006-04-10 |
Evan Cheng | __builtin_ia32_loadup{s|d}, __builtin_ia32_storeup...
|
commit | commitdiff | tree |
2006-04-10 |
Evan Cheng | Missing break
|
commit | commitdiff | tree |
2006-04-10 |
Evan Cheng | Add a vselect test case.
|
commit | commitdiff | tree |
2006-04-10 |
Evan Cheng | Conditional move of vector types.
|
commit | commitdiff | tree |
2006-04-10 |
Evan Cheng | New entries
|
commit | commitdiff | tree |
2006-04-10 |
Evan Cheng | Use movaps to do VR128 reg-to-reg copies for now. It...
|
commit | commitdiff | tree |
2006-04-08 |
Evan Cheng | INSERT_VECTOR_ELT lowering bug:
|
commit | commitdiff | tree |
2006-04-08 |
Evan Cheng | ldmxcsr and stmxcsr.
|
commit | commitdiff | tree |
2006-04-08 |
Evan Cheng | Fix int_x86_sse_stmxcsr and int_x86_sse_ldmxcsr. Not...
|
commit | commitdiff | tree |
2006-04-07 |
Evan Cheng | Code clean up.
|
commit | commitdiff | tree |
2006-04-07 |
Evan Cheng | Doh!
|
commit | commitdiff | tree |
2006-04-07 |
Evan Cheng | Added patterns for MOVHPSmr and MOVLPSmr.
|
commit | commitdiff | tree |
2006-04-07 |
Evan Cheng | Keep track of an Mac OS X / x86 ABI bug.
|
commit | commitdiff | tree |
2006-04-07 |
Evan Cheng | Remove int_x86_sse_storeh_ps and int_x86_sse_storel_ps...
|
commit | commitdiff | tree |
2006-04-07 |
Evan Cheng | A saner workaround. I hope.
|
commit | commitdiff | tree |
2006-04-07 |
Evan Cheng | Temporary workaround for a Mac OSX specific issue.
|
commit | commitdiff | tree |
2006-04-07 |
Evan Cheng | Added more shuffle tests
|
commit | commitdiff | tree |
2006-04-07 |
Evan Cheng | Add code to RemapOperand() to handle Instruction::ExtractEle...
|
commit | commitdiff | tree |
2006-04-06 |
Evan Cheng | A MOVPS2SSmr, i.e. _mm_store_ss, encoding bug.
|
commit | commitdiff | tree |
2006-04-06 |
Evan Cheng | Remove int_x86_sse_loadh_ps and int_x86_sse_loadl_ps...
|
commit | commitdiff | tree |
2006-04-06 |
Evan Cheng | - movlp{s|d} and movhp{s|d} support.
|
commit | commitdiff | tree |
2006-04-06 |
Evan Cheng | New entries.
|
commit | commitdiff | tree |
2006-04-06 |
Evan Cheng | 1. If both vector operands of a vector_shuffle are...
|
commit | commitdiff | tree |
2006-04-06 |
Evan Cheng | POR encoded as PAND, yikes.
|
commit | commitdiff | tree |
2006-04-05 |
Evan Cheng | An entry about comi / ucomi intrinsics.
|
commit | commitdiff | tree |
next |