2006-04-19 |
Chris Lattner | add a note |
tree | commitdiff |
2006-04-19 |
Chris Lattner | Add a note. |
tree | commitdiff |
2006-04-18 |
Evan Cheng | - PEXTRW cannot take a memory location as its first... |
tree | commitdiff |
2006-04-18 |
Evan Cheng | SHUFP{S|D}, PSHUF* encoding bugs. Left out the mask... |
tree | commitdiff |
2006-04-18 |
Evan Cheng | Name change for clarity sake |
tree | commitdiff |
2006-04-18 |
Evan Cheng | Encoding bug: CMPPSrmi, CMPPDrmi dropped operand 2... |
tree | commitdiff |
2006-04-18 |
Evan Cheng | Name change for clarity sake |
tree | commitdiff |
2006-04-18 |
Evan Cheng | Left a pattern out |
tree | commitdiff |
2006-04-18 |
Chris Lattner | These are correctly encoded by the JIT. I checked :) |
tree | commitdiff |
2006-04-18 |
Chris Lattner | add a note |
tree | commitdiff |
2006-04-18 |
Chris Lattner | Fix a crash on: |
tree | commitdiff |
2006-04-18 |
Evan Cheng | Fixed an encoding bug: movd from XMM to R32. |
tree | commitdiff |
2006-04-18 |
Chris Lattner | pretty print node name |
tree | commitdiff |
2006-04-18 |
Chris Lattner | Implement an important entry from README_ALTIVEC: |
tree | commitdiff |
2006-04-18 |
Chris Lattner | move some stuff around, clean things up |
tree | commitdiff |
2006-04-18 |
Chris Lattner | Teach the codegen about instructions used for SSE spill... |
tree | commitdiff |
2006-04-18 |
Chris Lattner | Use vmladduhm to do v8i16 multiplies which is faster... |
tree | commitdiff |
2006-04-18 |
Chris Lattner | Implement v16i8 multiply with this code: |
tree | commitdiff |
2006-04-18 |
Evan Cheng | Correct comments |
tree | commitdiff |
2006-04-18 |
Chris Lattner | Lower v8i16 multiply into this code: |
tree | commitdiff |
2006-04-18 |
Chris Lattner | Custom lower v4i32 multiplies into a cute sequence... |
tree | commitdiff |
2006-04-18 |
Evan Cheng | Another entry |
tree | commitdiff |
2006-04-18 |
Evan Cheng | Another entry. |
tree | commitdiff |
2006-04-17 |
Evan Cheng | Use movss to insert_vector_elt(v, s, 0). |
tree | commitdiff |
2006-04-17 |
Evan Cheng | Use two pinsrw to insert an element into v4i32 / v4f32... |
tree | commitdiff |
2006-04-17 |
Chris Lattner | remove done item |
tree | commitdiff |
2006-04-17 |
Chris Lattner | Don't diddle VRSAVE if no registers need to be added... |
tree | commitdiff |
2006-04-17 |
Evan Cheng | Encoding bug |
tree | commitdiff |
2006-04-17 |
Chris Lattner | Vectors that are known live-in and live-out are clearly... |
tree | commitdiff |
2006-04-17 |
Chris Lattner | Prefer to allocate V2-V5 before V0,V1. This lets us... |
tree | commitdiff |
2006-04-17 |
Chris Lattner | Move some knowledge about registers out of the code... |
tree | commitdiff |
2006-04-17 |
Chris Lattner | Use a small table instead of macros to do this conversion. |
tree | commitdiff |
2006-04-17 |
Evan Cheng | Implement v8i16, v16i8 splat using unpckl + pshufd. |
tree | commitdiff |
2006-04-17 |
Chris Lattner | implement returns of a vector, testcase here: CodeGen... |
tree | commitdiff |
2006-04-17 |
Chris Lattner | Make sure to check splats of every constant we can... |
tree | commitdiff |
2006-04-17 |
Evan Cheng | Incorrect foldMemoryOperand entries |
tree | commitdiff |
2006-04-17 |
Evan Cheng | Errors in patterns preventing load folding |
tree | commitdiff |
2006-04-17 |
Jeff Cohen | Add checks for __OpenBSD__. |
tree | commitdiff |
2006-04-17 |
Chris Lattner | Teach the ppc backend to use rol and vsldoi to generate... |
tree | commitdiff |
2006-04-17 |
Chris Lattner | add a note |
tree | commitdiff |
2006-04-17 |
Evan Cheng | FP SETOLT, SETOLT, SETUGE, SETUGT conditions were imple... |
tree | commitdiff |
2006-04-17 |
Chris Lattner | Make some code more general, adding support for constan... |
tree | commitdiff |
2006-04-17 |
Chris Lattner | Learn how to make odd splatted constants in range ... |
tree | commitdiff |
2006-04-17 |
Chris Lattner | Pull some code out into a helper function. |
tree | commitdiff |
2006-04-17 |
Chris Lattner | Implement a TODO: for any shuffle that can be viewed... |
tree | commitdiff |
2006-04-17 |
Chris Lattner | Regenerate with adjusted costs |
tree | commitdiff |
2006-04-17 |
Chris Lattner | Regenerate with correct offset |
tree | commitdiff |
2006-04-17 |
Chris Lattner | Increase the opcodes by one each to disambiguate COPY... |
tree | commitdiff |
2006-04-17 |
Chris Lattner | Check in a table, generated by llvm-PerfectShuffle... |
tree | commitdiff |
2006-04-16 |
Evan Cheng | movduprm, movshduprm bugs |
tree | commitdiff |
2006-04-16 |
Evan Cheng | Encoding bugs |
tree | commitdiff |
2006-04-16 |
Evan Cheng | Can't fold loads into alias vector SSE ops used for... |
tree | commitdiff |
2006-04-16 |
Chris Lattner | Implement a TODO: have the legalizer canonicalize a... |
tree | commitdiff |
2006-04-16 |
Chris Lattner | Make the BUILD_VECTOR lowering code much more aggressiv... |
tree | commitdiff |
2006-04-15 |
Chris Lattner | Fix a crash when faced with a shuffle vector that has... |
tree | commitdiff |
2006-04-15 |
Chris Lattner | Add patterns for matching vnots with bit converted... |
tree | commitdiff |
2006-04-15 |
Chris Lattner | Add a new vnot_conv predicate for matching vnot's where... |
tree | commitdiff |
2006-04-15 |
Evan Cheng | More encoding bugs |
tree | commitdiff |
2006-04-15 |
Evan Cheng | pslldrm, psrawrm, etc. encoding bug |
tree | commitdiff |
2006-04-15 |
Evan Cheng | hsubp{s|d} encoding bug |
tree | commitdiff |
2006-04-15 |
Evan Cheng | Silly bug |
tree | commitdiff |
2006-04-15 |
Evan Cheng | Do not use movs{h|l}dup for a shuffle with a single... |
tree | commitdiff |
2006-04-14 |
Evan Cheng | Added SSE (and other) entries to foldMemoryOperand(). |
tree | commitdiff |
2006-04-14 |
Evan Cheng | Some clean up |
tree | commitdiff |
2006-04-14 |
Chris Lattner | Allow undef in a shuffle mask |
tree | commitdiff |
2006-04-14 |
Evan Cheng | Last few SSE3 intrinsics. |
tree | commitdiff |
2006-04-14 |
Evan Cheng | Misc. SSE2 intrinsics: clflush, lfench, mfence |
tree | commitdiff |
2006-04-14 |
Evan Cheng | We were not adjusting the frame size to ensure proper... |
tree | commitdiff |
2006-04-14 |
Evan Cheng | New entry |
tree | commitdiff |
2006-04-14 |
Chris Lattner | Move the rest of the PPCTargetLowering::LowerOperation... |
tree | commitdiff |
2006-04-14 |
Chris Lattner | Pull the VECTOR_SHUFFLE and BUILD_VECTOR lowering code... |
tree | commitdiff |
2006-04-14 |
Evan Cheng | pcmpeq* and pcmpgt* intrinsics. |
tree | commitdiff |
2006-04-14 |
Evan Cheng | psll*, psrl*, and psra* intrinsics. |
tree | commitdiff |
2006-04-13 |
Reid Spencer | Remove the .cvsignore file so this directory can be... |
tree | commitdiff |
2006-04-13 |
Reid Spencer | Remove .cvsignore so that this directory can be pruned. |
tree | commitdiff |
2006-04-13 |
Evan Cheng | Doh. PANDrm, etc. are not commutable. |
tree | commitdiff |
2006-04-13 |
Chris Lattner | Force non-darwin targets to use a static relo model... |
tree | commitdiff |
2006-04-13 |
Chris Lattner | add a note, move an altivec todo to the altivec list. |
tree | commitdiff |
2006-04-13 |
Reid Spencer | Add the README files to the distribution. |
tree | commitdiff |
2006-04-13 |
Evan Cheng | psad, pmax, pmin intrinsics. |
tree | commitdiff |
2006-04-13 |
Evan Cheng | Various SSE2 packed integer intrinsics: pmulhuw, pavgw... |
tree | commitdiff |
2006-04-13 |
Evan Cheng | X86 SSE2 supports v8i16 multiplication |
tree | commitdiff |
2006-04-13 |
Evan Cheng | Update |
tree | commitdiff |
2006-04-13 |
Evan Cheng | padds{b|w}, paddus{b|w}, psubs{b|w}, psubus{b|w} intrin... |
tree | commitdiff |
2006-04-13 |
Evan Cheng | Naming inconsistency. |
tree | commitdiff |
2006-04-12 |
Evan Cheng | SSE / SSE2 conversion intrinsics. |
tree | commitdiff |
2006-04-12 |
Evan Cheng | All "integer" logical ops (pand, por, pxor) are now... |
tree | commitdiff |
2006-04-12 |
Chris Lattner | Add a new way to match vector constants, which make... |
tree | commitdiff |
2006-04-12 |
Chris Lattner | Rename get_VSPLI_elt -> get_VSPLTI_elt |
tree | commitdiff |
2006-04-12 |
Evan Cheng | Promote v4i32, v8i16, v16i8 load to v2i64 load. |
tree | commitdiff |
2006-04-12 |
Chris Lattner | Ensure that zero vectors are always v4i32, which forces... |
tree | commitdiff |
2006-04-12 |
Evan Cheng | Various SSE2 conversion intrinsics |
tree | commitdiff |
2006-04-11 |
Evan Cheng | Added __builtin_ia32_storelv4si, __builtin_ia32_movqv4si, |
tree | commitdiff |
2006-04-11 |
Nate Begeman | Fix SingleSource/UnitTests/Vector/sumarray-dbl |
tree | commitdiff |
2006-04-11 |
Nate Begeman | Fix PR727, correctly handling large stack aligments... |
tree | commitdiff |
2006-04-11 |
Chris Lattner | we have a shuffle instr, add an example. |
tree | commitdiff |
2006-04-11 |
Evan Cheng | gcc lower SSE prefetch into generic prefetch intrinsic... |
tree | commitdiff |
2006-04-11 |
Evan Cheng | Misc. intrinsics. |
tree | commitdiff |
2006-04-11 |
Jim Laskey | Suppress debug label when not debug. |
tree | commitdiff |
2006-04-11 |
Evan Cheng | movnt* and maskmovdqu intrinsics |
tree | commitdiff |
next |