2007-10-23 |
Evan Cheng | Temporary solution: added a different set of BCTRL_Mach... |
blob | commitdiff | raw |
2007-10-10 |
Dale Johannesen | Next PPC long double bits: ppcf128->i32 conversion. |
blob | commitdiff | raw | diff to current |
2007-09-11 |
Evan Cheng | Remove (somewhat confusing) Imp<> helper, use let Defs... |
blob | commitdiff | raw | diff to current |
2007-08-01 |
Evan Cheng | Some out operands were incorrectly specified as input... |
blob | commitdiff | raw | diff to current |
2007-07-21 |
Evan Cheng | No more noResults. |
blob | commitdiff | raw | diff to current |
2007-07-20 |
Evan Cheng | Oops. These stores actually produce results. |
blob | commitdiff | raw | diff to current |
2007-07-19 |
Evan Cheng | Change instruction description to split OperandList... |
blob | commitdiff | raw | diff to current |
2007-07-06 |
Evan Cheng | Do away with ImmutablePredicateOperand. |
blob | commitdiff | raw | diff to current |
2007-07-05 |
Evan Cheng | PPC conditional branch predicate does not change after... |
blob | commitdiff | raw | diff to current |
2007-05-08 |
Evan Cheng | PredicateOperand can be used as a normal operand for... |
blob | commitdiff | raw | diff to current |
2007-04-03 |
Nicolas Geoffray | The ELF ABI specifies F1-F8 registers as argument regis... |
blob | commitdiff | raw | diff to current |
2007-02-27 |
Nicolas Geoffray | Differentiate between the MachO and the ELF ABI the... |
blob | commitdiff | raw | diff to current |
2007-02-26 |
Chris Lattner | always lower to RETFLAG, never leave it as just ret. |
blob | commitdiff | raw | diff to current |
2007-02-25 |
Chris Lattner | one important bugfix: PPC32 didn't have both elf and... |
blob | commitdiff | raw | diff to current |
2007-02-25 |
Chris Lattner | implement support for the linux/ppc function call ABI... |
blob | commitdiff | raw | diff to current |
2007-01-26 |
Jim Laskey | Make LABEL a builtin opcode. |
blob | commitdiff | raw | diff to current |
2006-11-18 |
Chris Lattner | Rewrite the branch selector to be correct in the face... |
blob | commitdiff | raw | diff to current |
2006-11-17 |
Chris Lattner | add encoding for BCC, after finally wrestling strange... |
blob | commitdiff | raw | diff to current |
2006-11-17 |
Chris Lattner | convert PPC::BCC to use the 'pred' operand instead... |
blob | commitdiff | raw | diff to current |
2006-11-17 |
Chris Lattner | rename PPC::COND_BRANCH to PPC::BCC |
blob | commitdiff | raw | diff to current |
2006-11-17 |
Chris Lattner | start using PPC predicates more consistently. |
blob | commitdiff | raw | diff to current |
2006-11-16 |
Jim Laskey | This is a general clean up of the PowerPC ABI. Address... |
blob | commitdiff | raw | diff to current |
2006-11-16 |
Chris Lattner | fix broken encoding |
blob | commitdiff | raw | diff to current |
2006-11-16 |
Chris Lattner | add patterns for ppc32 preinc stores. ppc64 next. |
blob | commitdiff | raw | diff to current |
2006-11-16 |
Chris Lattner | switch these back to the 'bad old way' |
blob | commitdiff | raw | diff to current |
2006-11-15 |
Chris Lattner | Stop using isTwoAddress, switching to operand constrain... |
blob | commitdiff | raw | diff to current |
2006-11-15 |
Chris Lattner | fix ldu/stu jit encoding. Swith 64-bit preinc load... |
blob | commitdiff | raw | diff to current |
2006-11-15 |
Chris Lattner | Switch loads over to use memri as the operand instead... |
blob | commitdiff | raw | diff to current |
2006-11-14 |
Chris Lattner | group load and store instructions together. No functio... |
blob | commitdiff | raw | diff to current |
2006-11-14 |
Chris Lattner | Rework PPC64 calls. Now we have a LR8/CTR8 register... |
blob | commitdiff | raw | diff to current |
2006-11-11 |
Chris Lattner | Mark operands as symbol lo instead of imm32 so that... |
blob | commitdiff | raw | diff to current |
2006-11-10 |
Chris Lattner | dform 8/9 are identical to dform 1 |
blob | commitdiff | raw | diff to current |
2006-11-10 |
Chris Lattner | add an initial cut at preinc loads for ppc32. This... |
blob | commitdiff | raw | diff to current |
2006-11-08 |
Chris Lattner | correct the (currently unused) pattern for lwzu. |
blob | commitdiff | raw | diff to current |
2006-11-04 |
Chris Lattner | encode BLR predicate info for the JIT |
blob | commitdiff | raw | diff to current |
2006-11-04 |
Chris Lattner | Go through all kinds of trouble to mark 'blr' as having... |
blob | commitdiff | raw | diff to current |
2006-11-03 |
Chris Lattner | Describe PPC predicates, which are a pair of CR# and... |
blob | commitdiff | raw | diff to current |
2006-11-03 |
Chris Lattner | remove dead vars |
blob | commitdiff | raw | diff to current |
2006-10-24 |
Chris Lattner | Add intrinsics for the rest of the DCB* instructions. |
blob | commitdiff | raw | diff to current |
2006-10-13 |
Evan Cheng | Merge ISD::TRUNCSTORE to ISD::STORE. Switch to using... |
blob | commitdiff | raw | diff to current |
2006-10-13 |
Chris Lattner | set isBarrier correctly |
blob | commitdiff | raw | diff to current |
2006-10-12 |
Chris Lattner | mark adjcallstack up/down as clobbering and using the SP |
blob | commitdiff | raw | diff to current |
2006-10-11 |
Evan Cheng | Add properties to ComplexPattern. |
blob | commitdiff | raw | diff to current |
2006-10-09 |
Evan Cheng | Reflects ISD::LOAD / ISD::LOADX / LoadSDNode changes. |
blob | commitdiff | raw | diff to current |
2006-09-27 |
Chris Lattner | Use abstract private/comment directives, to increase... |
blob | commitdiff | raw | diff to current |
2006-09-22 |
Nate Begeman | Fold AND and ROTL more often |
blob | commitdiff | raw | diff to current |
2006-08-11 |
Evan Cheng | CALLSEQ_* produces chain even if that's not needed. |
blob | commitdiff | raw | diff to current |
2006-07-19 |
Chris Lattner | bswapped load/store instructions are only availble... |
blob | commitdiff | raw | diff to current |
2006-07-18 |
Chris Lattner | Make the implicit def instructions look like other... |
blob | commitdiff | raw | diff to current |
2006-07-10 |
Chris Lattner | Implement Regression/CodeGen/PowerPC/bswap-load-store... |
blob | commitdiff | raw | diff to current |
2006-06-27 |
Chris Lattner | Add 64-bit MTCTR so that indirect calls work. |
blob | commitdiff | raw | diff to current |
2006-06-27 |
Chris Lattner | Implement 64-bit undef, sub, shl/shr, srem/urem |
blob | commitdiff | raw | diff to current |
2006-06-27 |
Chris Lattner | Implement a bunch of 64-bit cleanliness work. With... |
blob | commitdiff | raw | diff to current |
2006-06-26 |
Chris Lattner | Remove two more definitions |
blob | commitdiff | raw | diff to current |
2006-06-26 |
Chris Lattner | remove two unused instructions. |
blob | commitdiff | raw | diff to current |
2006-06-20 |
Chris Lattner | Make these predicates correct in 64-bit mode too. |
blob | commitdiff | raw | diff to current |
2006-06-20 |
Chris Lattner | Rename OR4 -> OR. Move some PPC64-specific stuff to... |
blob | commitdiff | raw | diff to current |
2006-06-20 |
Chris Lattner | remove unused flag |
blob | commitdiff | raw | diff to current |
2006-06-20 |
Chris Lattner | remove some unused patterns |
blob | commitdiff | raw | diff to current |
2006-06-20 |
Chris Lattner | Add some 64-bit logical ops. |
blob | commitdiff | raw | diff to current |
2006-06-20 |
Chris Lattner | 64-bit bugfix: 0xFFFF0000 cannot be formed with a singl... |
blob | commitdiff | raw | diff to current |
2006-06-20 |
Chris Lattner | Remove some now-unneeded casts from instruction pattern... |
blob | commitdiff | raw | diff to current |
2006-06-16 |
Chris Lattner | In 64-bit mode, addr mode operands use G8RC instead... |
blob | commitdiff | raw | diff to current |
2006-06-16 |
Chris Lattner | fix some assumptions that pointers can only be 32-bits... |
blob | commitdiff | raw | diff to current |
2006-06-16 |
Chris Lattner | Split 64-bit instructions out into a separate .td file |
blob | commitdiff | raw | diff to current |
2006-06-10 |
Chris Lattner | Fix a problem exposed by the local allocator. CALL... |
blob | commitdiff | raw | diff to current |
2006-06-06 |
Chris Lattner | Add PowerPC intrinsics to support dcbz[l] |
blob | commitdiff | raw | diff to current |
2006-05-17 |
Chris Lattner | Make PPC call lowering more aggressive, making the... |
blob | commitdiff | raw | diff to current |
2006-05-17 |
Chris Lattner | Switch PPC over to a call-selection model where the... |
blob | commitdiff | raw | diff to current |
2006-04-22 |
Nate Begeman | JumpTable support! What this represents is working... |
blob | commitdiff | raw | diff to current |
2006-04-18 |
Chris Lattner | These are correctly encoded by the JIT. I checked :) |
blob | commitdiff | raw | diff to current |
2006-04-18 |
Chris Lattner | Implement an important entry from README_ALTIVEC: |
blob | commitdiff | raw | diff to current |
2006-04-08 |
Chris Lattner | Add VRRC select support |
blob | commitdiff | raw | diff to current |
2006-03-31 |
Chris Lattner | Lower vector compares to VCMP nodes, just like we lower... |
blob | commitdiff | raw | diff to current |
2006-03-28 |
Chris Lattner | Use normal lvx for scalar_to_vector instead of lve... |
blob | commitdiff | raw | diff to current |
2006-03-26 |
Chris Lattner | Codegen vector predicate compares. |
blob | commitdiff | raw | diff to current |
2006-03-25 |
Chris Lattner | Move all Altivec stuff out into a new PPCInstrAltivec... |
blob | commitdiff | raw | diff to current |
2006-03-25 |
Chris Lattner | Add some basic patterns for other datatypes |
blob | commitdiff | raw | diff to current |
2006-03-25 |
Chris Lattner | Add support for __builtin_altivec_vnmsubfp /vmaddfp |
blob | commitdiff | raw | diff to current |
2006-03-25 |
Chris Lattner | Codegen things like: |
blob | commitdiff | raw | diff to current |
2006-03-24 |
Chris Lattner | Fix a bad JIT encoding of VPERM. Why is VPERM D,A... |
blob | commitdiff | raw | diff to current |
2006-03-24 |
Chris Lattner | add support for using vxor to build zero vectors. ... |
blob | commitdiff | raw | diff to current |
2006-03-24 |
Chris Lattner | Gabor points out that we can't spell. :) |
blob | commitdiff | raw | diff to current |
2006-03-23 |
Chris Lattner | Add PPC vector bit-convert support |
blob | commitdiff | raw | diff to current |
2006-03-22 |
Chris Lattner | When possible, custom lower 32-bit SINT_TO_FP to this: |
blob | commitdiff | raw | diff to current |
2006-03-22 |
Chris Lattner | Fix the JIT encoding of the VAForm_1 instructions,... |
blob | commitdiff | raw | diff to current |
2006-03-21 |
Chris Lattner | When codegen'ing vector MUL using VFMADD, *add* the... |
blob | commitdiff | raw | diff to current |
2006-03-20 |
Chris Lattner | Fix a couple of bugs in permute/splat generate, thanks... |
blob | commitdiff | raw | diff to current |
2006-03-20 |
Chris Lattner | Fix the pattern for VADDUWM, add i32 splat |
blob | commitdiff | raw | diff to current |
2006-03-20 |
Evan Cheng | Use tblgen'd VECTOR_SHUFFLE selection code. |
blob | commitdiff | raw | diff to current |
2006-03-20 |
Chris Lattner | Add support for generating vspltw, instead of a vperm... |
blob | commitdiff | raw | diff to current |
2006-03-20 |
Chris Lattner | Check in some intermediate code that adds a skeleton... |
blob | commitdiff | raw | diff to current |
2006-03-20 |
Chris Lattner | fix typo |
blob | commitdiff | raw | diff to current |
2006-03-20 |
Chris Lattner | add vsplat instructions, fix sched description for... |
blob | commitdiff | raw | diff to current |
2006-03-20 |
Chris Lattner | Custom lower arbitrary VECTOR_SHUFFLE's to VPERM. |
blob | commitdiff | raw | diff to current |
2006-03-20 |
Chris Lattner | add the vperm instruction |
blob | commitdiff | raw | diff to current |
2006-03-19 |
Chris Lattner | Custom lower SCALAR_TO_VECTOR into lve*x. |
blob | commitdiff | raw | diff to current |
2006-03-19 |
Chris Lattner | add support for vector undef |
blob | commitdiff | raw | diff to current |
2006-03-19 |
Chris Lattner | minor fixes |
blob | commitdiff | raw | diff to current |
2006-03-19 |
Chris Lattner | we don't use lmw/stmw. When we want them they are... |
blob | commitdiff | raw | diff to current |
next |