J. Gareth "Curious Kit" Moreton
|
49d66b8f20
* x86: Fixed bug where incorrect SSE/AVX peephole optimisations were performed under -O3 in some situations.
|
2 years ago |
J. Gareth "Curious Kit" Moreton
|
dde19c0144
* Improvement to TEST/JNE/TEST/JNE code to be more accurate where register deallocations are concerned
|
2 years ago |
J. Gareth "Curious Kit" Moreton
|
699db16fe4
* x86: Fixed bug in TEST/JNE/TEST/JNE optimisation that caused bad code to be generated under -O3
|
2 years ago |
florian
|
4096d9b74f
* factor out subreg2opsize
|
2 years ago |
J. Gareth "Curious Kit" Moreton
|
6ffa258abb
* x86: Revamped OptPass2Jcc CMOV code to shrink and reuse registers as much as possible
|
2 years ago |
J. Gareth "Curious Kit" Moreton
|
2a83972db8
* x86: Fixed bug where OptPass2Jcc CMOV optimisation sometimes
|
2 years ago |
florian
|
1e62913183
* check properly for the supported cpu type, resolves #40298
|
2 years ago |
J. Gareth "Curious Kit" Moreton
|
e40996cd2c
* Fixed bug in "JccMovJmpMov2CMovCMov" optimisation where it didn't track registers in references getting changed
|
2 years ago |
florian
|
e40f997a40
* another patch to fix #40223
|
2 years ago |
Pierre Muller
|
644ffa8e7a
Do not always set DEBUG_AOPTCPU
|
2 years ago |
florian
|
6663d5ca63
* do not replace index registers with esp/rsp, resolves #40223
|
2 years ago |
J. Gareth "Curious Kit" Moreton
|
3f25438d35
* x86: TEST/Jcc/TEST optimisations can now look beyond the next instruction under -O3
|
2 years ago |
J. Gareth "Curious Kit" Moreton
|
d372286159
* x86: RegModifiedByInstruction and RegInInstruction
|
3 years ago |
J. Gareth "Curious Kit" Moreton
|
3635f7cd6f
* x86: Fixed oversight in RegModifiedByInstruction not checking W0, W1 and WU-type flags
|
2 years ago |
J. Gareth "Curious Kit" Moreton
|
b637a3a022
* x86: Fix to MOV/CMP register deallocation positioning
|
3 years ago |
J. Gareth "Curious Kit" Moreton
|
77f53ebde3
* x86: The LEA/LEA optimisations can now work with a different
|
2 years ago |
J. Gareth "Curious Kit" Moreton
|
931bda5633
* x86: LeaLea2Lea now handles cases where the second LEA instruction
|
2 years ago |
florian
|
66ff7a928c
+ added debug messages
|
2 years ago |
florian
|
bf8746ed10
* fixed comment
|
2 years ago |
florian
|
ccbdfa9150
+ x86: AND/CMP -> CMP optimiziation
|
2 years ago |
J. Gareth "Curious Kit" Moreton
|
b8933dd267
* x86: Some refactoring to use aoc_ForceNewIteration instead of manually advancing p
|
2 years ago |
J. Gareth "Curious Kit" Moreton
|
ecf2ad3e53
x86: Some oversights fixed where another iteration of pass 1 wasn't performed when it should have been
|
2 years ago |
J. Gareth "Curious Kit" Moreton
|
4d33e5f137
* x86: OptPass1_V_MOVAP now uses GetNextInstructionUsingReg and UpdateUsedRegsBetween
|
3 years ago |
J. Gareth "Curious Kit" Moreton
|
dd7320ec13
* x86: PostPeepholeOptCmp and PostPeepholeOptTestOr
|
2 years ago |
J. Gareth "Curious Kit" Moreton
|
4d676cd6fa
* x86: JccMovJmpMov2CMovCMov will no longer move
|
2 years ago |
J. Gareth "Curious Kit" Moreton
|
4e8ef448ed
* i386: Bug fix where EBP was marked as preserved when it wasn't, causing faulty optimisations
|
2 years ago |
J. Gareth "Curious Kit" Moreton
|
2224305834
* x86: Fixed bad register tracking in OptPass2JMP
|
2 years ago |
J. Gareth "Curious Kit" Moreton
|
33dfb6cb4e
* x86: Converted bit-test optimisations to use
|
2 years ago |
J. Gareth "Curious Kit" Moreton
|
ae47cc2c88
* x86: New debug_hexstr instruction to help produce concise debug comments
|
2 years ago |
J. Gareth "Curious Kit" Moreton
|
f3f9c68ddb
* x86-64: Extended the movl/movq optimisation to cover more distance
|
2 years ago |