2010-09-07 |
Chris Lattner | add missing cmov aliases, this resolves rdar://8208499 |
tree | commitdiff |
2010-09-06 |
Chris Lattner | remove duplicated entry |
tree | commitdiff |
2010-09-06 |
Chris Lattner | "sldt <mem>" is ambiguous in 64-bit mode, but should |
tree | commitdiff |
2010-09-06 |
Chris Lattner | fix rdar://8017621 - llvm-mc can't guess encoding for... |
tree | commitdiff |
2010-09-06 |
Chris Lattner | fix the operand constraints of the immediate form of... |
tree | commitdiff |
2010-09-06 |
Chris Lattner | in the case where an instruction only has one implement... |
tree | commitdiff |
2010-09-06 |
Chris Lattner | Now that we know if we had a total fail on the instruct... |
tree | commitdiff |
2010-09-06 |
Chris Lattner | simplify the hacks around jrcxz. |
tree | commitdiff |
2010-09-06 |
Chris Lattner | have tblgen detect when an instruction would have match... |
tree | commitdiff |
2010-09-06 |
Chris Lattner | change MatchInstructionImpl to return an enum instead... |
tree | commitdiff |
2010-09-06 |
Chris Lattner | have AsmMatcherEmitter.cpp produce the hunk of code... |
tree | commitdiff |
2010-09-06 |
Roman Divacky | Redefine LOOP* instructions from I to Ii8PCRel as they... |
tree | commitdiff |
2010-09-06 |
Chris Lattner | random cleanups |
tree | commitdiff |
2010-09-05 |
Chris Lattner | update this. |
tree | commitdiff |
2010-09-05 |
Chris Lattner | implement rdar://6653118 - fastisel should fold loads... |
tree | commitdiff |
2010-09-04 |
Chris Lattner | zap dead code. |
tree | commitdiff |
2010-09-04 |
Bruno Cardoso Lopes | Remove the last bit of isShuffleMaskLegal checks and... |
tree | commitdiff |
2010-09-04 |
Bruno Cardoso Lopes | make explicit that we not handle several mmx shuffles |
tree | commitdiff |
2010-09-04 |
Bruno Cardoso Lopes | Emit target specific nodes to handle palignr. Do not... |
tree | commitdiff |
2010-09-04 |
Bruno Cardoso Lopes | Emit target specific nodes to handle splats starting... |
tree | commitdiff |
2010-09-04 |
Bruno Cardoso Lopes | Emit target specific nodes for isPSHUFHWMask and isPSHU... |
tree | commitdiff |
2010-09-04 |
Bruno Cardoso Lopes | Emit target specific nodes for isSHUFPMask |
tree | commitdiff |
2010-09-04 |
Bruno Cardoso Lopes | Previous isMOVLMask matching already emits targets... |
tree | commitdiff |
2010-09-04 |
Bruno Cardoso Lopes | One more check from the original isShuffleMaskLegal... |
tree | commitdiff |
2010-09-04 |
Bruno Cardoso Lopes | Remove a duplicated but useless check that i've inserte... |
tree | commitdiff |
2010-09-04 |
Bruno Cardoso Lopes | Refactor some code and remove the extra checks for... |
tree | commitdiff |
2010-09-03 |
Bruno Cardoso Lopes | Remove check for unpckh mask |
tree | commitdiff |
2010-09-03 |
Bruno Cardoso Lopes | Remove check for unpckl mask |
tree | commitdiff |
2010-09-03 |
Bruno Cardoso Lopes | Inline isShuffleMaskLegal into LowerVECTOR_SHUFFLE... |
tree | commitdiff |
2010-09-03 |
Bruno Cardoso Lopes | Reapply considered harmfull part of rr112934 and r112942. |
tree | commitdiff |
2010-09-03 |
Dale Johannesen | Remove the rest of the nonexistent 64-bit AVX instructions. |
tree | commitdiff |
2010-09-03 |
Bruno Cardoso Lopes | Reapply last harmless part of r112934, the pattern... |
tree | commitdiff |
2010-09-03 |
Bruno Cardoso Lopes | Reintroduce a simple function refactoring done in r1129... |
tree | commitdiff |
2010-09-03 |
Bruno Cardoso Lopes | Reapply piecies of r112942 and r112934 which don't do |
tree | commitdiff |
2010-09-03 |
Bruno Cardoso Lopes | Reapply Fix comment |
tree | commitdiff |
2010-09-03 |
Daniel Dunbar | Revert r112934, "- Use specific nodes to match unpckl... |
tree | commitdiff |
2010-09-03 |
Daniel Dunbar | Revert r112938 "Fix comment", which depends on r112934... |
tree | commitdiff |
2010-09-03 |
Daniel Dunbar | Revert r112942, "Use punpckh and unpckh family of nodes... |
tree | commitdiff |
2010-09-03 |
Bruno Cardoso Lopes | AVX doesn't support mm operations neither its instrinsics. |
tree | commitdiff |
2010-09-03 |
Bruno Cardoso Lopes | Use punpckh and unpckh family of nodes instead of using... |
tree | commitdiff |
2010-09-03 |
Bruno Cardoso Lopes | Fix comment |
tree | commitdiff |
2010-09-03 |
Bruno Cardoso Lopes | - Use specific nodes to match unpckl masks. |
tree | commitdiff |
2010-09-03 |
Jakob Stoklund Olesen | Don't call Predicate_* from X86 target. |
tree | commitdiff |
2010-09-02 |
Anton Korobeynikov | Properly emit __chkstk call instead of __alloca on... |
tree | commitdiff |
2010-09-02 |
Bruno Cardoso Lopes | Move insertps mask decoding to header file |
tree | commitdiff |
2010-09-02 |
Anton Korobeynikov | Revert win64 changes. They seem to be incomplete |
tree | commitdiff |
2010-09-02 |
Anton Korobeynikov | Properly allocate win64 shadow reg area. |
tree | commitdiff |
2010-09-02 |
Bruno Cardoso Lopes | Move decoding of insertps back to avoid unused warnings... |
tree | commitdiff |
2010-09-02 |
Dan Gohman | Don't narrow the load and store in a load+twiddle+store... |
tree | commitdiff |
2010-09-02 |
Bruno Cardoso Lopes | Move x86 specific shuffle mask decoding to its own... |
tree | commitdiff |
2010-09-02 |
Bruno Cardoso Lopes | Replace unpckl_undef and unpckh_undef matching with... |
tree | commitdiff |
2010-09-02 |
Bruno Cardoso Lopes | Move condition out to prepare for more matching |
tree | commitdiff |
2010-09-02 |
Bruno Cardoso Lopes | Remove checking for isUNPCKL_v_undef_Mask, the specific... |
tree | commitdiff |
2010-09-02 |
Bruno Cardoso Lopes | become more strict about when it's safe to use X86ISD... |
tree | commitdiff |
2010-09-01 |
Bruno Cardoso Lopes | Revert r112689, avoid those kind of checks cause they... |
tree | commitdiff |
2010-09-01 |
Bruno Cardoso Lopes | Using target specific nodes for shuffle nodes makes... |
tree | commitdiff |
2010-09-01 |
Bruno Cardoso Lopes | Use movlps, movlpd, movss and movsd specific nodes... |
tree | commitdiff |
2010-09-01 |
Bruno Cardoso Lopes | minor change, simplify some logic |
tree | commitdiff |
2010-09-01 |
Bruno Cardoso Lopes | Move some functions around so they can be used for... |
tree | commitdiff |
2010-08-31 |
Bruno Cardoso Lopes | Use x86 specific MOVSLDUP node, add more patterns to... |
tree | commitdiff |
2010-08-31 |
Bruno Cardoso Lopes | Use x86 specific MOVSHDUP node and add more patterns... |
tree | commitdiff |
2010-08-31 |
Jakob Stoklund Olesen | Make %EFLAGS unallocatable. |
tree | commitdiff |
2010-08-31 |
Bruno Cardoso Lopes | Use MOVHLPS node instead of matching using movhlps... |
tree | commitdiff |
2010-08-31 |
Bruno Cardoso Lopes | Use MOVLHPS and MOVHLPS x86 nodes whenever possible... |
tree | commitdiff |
2010-08-31 |
Bruno Cardoso Lopes | Use X86ISD::MOVSS and MOVSD to represent the movl mask... |
tree | commitdiff |
2010-08-29 |
Eli Friedman | A couple of small missed optimizations. |
tree | commitdiff |
2010-08-29 |
Chris Lattner | add a bunch more common shuffles to the instprinter. |
tree | commitdiff |
2010-08-28 |
Chris Lattner | I have manually decoded the imm field of an insertps... |
tree | commitdiff |
2010-08-28 |
Chris Lattner | fix the buildvector->insertp[sd] logic to not always... |
tree | commitdiff |
2010-08-28 |
Chris Lattner | fix the BuildVector -> unpcklps logic to not do pointle... |
tree | commitdiff |
2010-08-28 |
Chris Lattner | improve comments in the unpcklps generating logic,... |
tree | commitdiff |
2010-08-28 |
Bruno Cardoso Lopes | Clean up the logic of vector shuffles -> vector shifts. |
tree | commitdiff |
2010-08-27 |
Anton Korobeynikov | Properly handle passing of FP stuff to varargs function... |
tree | commitdiff |
2010-08-27 |
Daniel Dunbar | X86: Fix an encoding issue with LOCK_ADD64mr, which... |
tree | commitdiff |
2010-08-26 |
Jim Grosbach | Simplify eliminateFrameIndex() interface back down... |
tree | commitdiff |
2010-08-26 |
Bruno Cardoso Lopes | zap the now unused MVT::getIntVectorWithNumElements |
tree | commitdiff |
2010-08-26 |
Bob Wilson | Fix comment typos. |
tree | commitdiff |
2010-08-26 |
Chris Lattner | implement SplitVecOp_CONCAT_VECTORS, fixing the include... |
tree | commitdiff |
2010-08-26 |
Chris Lattner | fix sse1 only codegen in x86-64 mode, which is something we |
tree | commitdiff |
2010-08-26 |
Bruno Cardoso Lopes | Fix PR7748 without using microsoft extensions |
tree | commitdiff |
2010-08-25 |
Chris Lattner | we should pattern match the SSE complex arithmetic... |
tree | commitdiff |
2010-08-25 |
Bruno Cardoso Lopes | Revert this for now, PUNPCKLDQ dont operate on v4f32 |
tree | commitdiff |
2010-08-25 |
Daniel Dunbar | X86: Fix misencode of RI64mi8. This fixes OpenSSL ... |
tree | commitdiff |
2010-08-25 |
Benjamin Kramer | Remove dead recursive function. Yay for clang -Wunused... |
tree | commitdiff |
2010-08-25 |
Anton Korobeynikov | Fix nasty mingw32 bug, which e.g. prevented llvm-gcc... |
tree | commitdiff |
2010-08-25 |
Bruno Cardoso Lopes | PUNPCKLDQ should also be used for v4f32 |
tree | commitdiff |
2010-08-25 |
Bruno Cardoso Lopes | teach lowering to get target specific nodes for pshufd... |
tree | commitdiff |
2010-08-24 |
Daniel Dunbar | MC/X86: Tweak imul recognition, previous hack only... |
tree | commitdiff |
2010-08-24 |
Daniel Dunbar | MC/X86: Add custom hack for recognizing "imul $12,... |
tree | commitdiff |
2010-08-24 |
Daniel Dunbar | MC/X86: Warn on scale factors > 1 without index registe... |
tree | commitdiff |
2010-08-24 |
Dan Gohman | Fix X86's isLegalAddressingMode to recognize that stati... |
tree | commitdiff |
2010-08-24 |
Bruno Cardoso Lopes | Use pshufhw and pshuflw in more cases and fix getTarget... |
tree | commitdiff |
2010-08-23 |
Bruno Cardoso Lopes | Start using target speficic nodes for shuffles: pshufhw... |
tree | commitdiff |
2010-08-23 |
Gabor Greif | tyops |
tree | commitdiff |
2010-08-23 |
Chris Lattner | Add a new llvm.x86.int intrinsic, allowing access to the |
tree | commitdiff |
2010-08-23 |
Chris Lattner | random improvement for variable shift codegen. |
tree | commitdiff |
2010-08-23 |
Anton Korobeynikov | Revert invalid r111792. Jump tables are not broken... |
tree | commitdiff |
2010-08-23 |
Michael J. Spencer | Workaround broken jump tables on x86-64 COFF. |
tree | commitdiff |
2010-08-21 |
Anton Korobeynikov | Use rip-rel addressing on win64 by default. For this... |
tree | commitdiff |
2010-08-21 |
Michael J. Spencer | MC: Add partial x86-64 support to COFF. |
tree | commitdiff |
next |