2397 Commits

Author	SHA1	Message	Date
J. Gareth "Curious Kit" Moreton	a70e4ed9be	* x86: "OptPass2ADD" and "OptPass2SUB" now force another iteration if "OptPass2MOV" returned True	2025-03-02 14:00:57 +00:00
J. Gareth "Curious Kit" Moreton	f85aa24ad0	* x86: Refactoring register update code in "OptPass2ADD" and "OptPass2SUB"	2025-03-02 14:00:57 +00:00
J. Gareth "Curious Kit" Moreton	b2dd980329	* x86: Fixed bug where flags register wasn't tracked during ... long-range "AddMov2LeaAdd" and "SubMov2LeaSub" optimisations	2025-03-02 14:00:57 +00:00
J. Gareth "Curious Kit" Moreton	83c9b17ec5	* x86: Fixed oversight in LeaLea2LeaLea optimisations where bad code is ... generated if the intermediate register appears in the first reference	2025-02-27 21:25:23 +00:00
J. Gareth "Curious Kit" Moreton	4648f967bd	* x86: Fixed bug in "MovMovMov2MovMovMov" optimisation where a register wasn't properly tracked	2025-02-24 15:32:21 +00:00
florian	9a223100d1	+ x86: proper flag (de)alloc in a_bit_scan	2025-02-15 22:19:05 +01:00
florian	29b3b09251	* allow absolutes on open arrays (use of this is doubtful though), resolves #41147	2025-02-11 22:45:56 +01:00
Rika Ichinose	d1ba97d462	Make use of not_zero in x86 bitscans.	2025-02-09 21:01:43 +00:00
florian	b2f6214b33	+ a_bit_scan_reg_reg gets a flag if src cannot be zero: this simplifies the generated code	2025-02-08 14:27:48 +01:00
florian	125da5f10a	* SubLea2Lea has to check both times for equal super registers, resolves the second part of #41126	2025-02-03 22:19:25 +01:00
florian	f75de6c340	* check for 64 bit registers in TX86AsmOptimizer.RegReadByInstruction as well for sanity reasons	2025-02-02 22:12:06 +01:00
florian	9355e703d7	* change some getglobaldatalabel into getlocaldatalabel to simplify code if pic is used	2025-01-13 22:34:31 +01:00
florian	5b54ab2040	+ zen5 architecture for completeness	2024-12-07 22:23:35 +01:00
User Muller	f689746372	cmpxchg16b instruction uses no size suffix in ATT syntax	2024-12-06 14:45:44 +01:00
J. Gareth "Curious Kit" Moreton	36f771a312	* x86: Modification to PostPeepholeOptShr to skip over MOV instructions if they don't modify the current register	2024-11-30 12:51:07 +00:00
florian	42c5e368bd	* formatting/readability	2024-11-10 09:33:51 +01:00
J. Gareth "Curious Kit" Moreton	43bdd8c07e	* x86: Refactor of a DeepMOVOpt call to make use of a while loop and aoc_ForceNewIteration to increase compiler speed and efficiency.	2024-11-10 08:23:02 +00:00
J. Gareth "Curious Kit" Moreton	8520dabebb	* x86: New RET/lbl/RET optimisation	2024-10-27 08:17:10 +00:00
J. Gareth "Curious Kit" Moreton	8bb3367a49	* x86: Refactored SetCC optimisations to better ... spot label clusters and alignment hints.	2024-10-27 08:17:10 +00:00
florian	5d4bb6db9b	* patch by lag programming to replace bitcnt by popcnt, resolves #40962	2024-10-22 22:54:57 +02:00
J. Gareth "Curious Kit" Moreton	80f1d55822	- MovOp2Op optimisation upgraded.	2024-10-20 12:43:52 +00:00
J. Gareth "Curious Kit" Moreton	85ee93c2c5	- MovLea2Add optimisation upgraded.	2024-10-20 12:43:52 +00:00
J. Gareth "Curious Kit" Moreton	1bc0ae3d18	- Mov2Nop 5a and Mov2Nop 5b optimisations upgraded.	2024-10-20 12:43:52 +00:00
J. Gareth "Curious Kit" Moreton	f36fbd17b1	- 32-to-64-bit zero extension optimisations upgraded.	2024-10-20 12:43:52 +00:00
J. Gareth "Curious Kit" Moreton	b1a76314ae	- Const and ref merge optimisations upgraded.	2024-10-20 12:43:52 +00:00
J. Gareth "Curious Kit" Moreton	65f2dd2337	- OR and extension optimisations upgraded.	2024-10-20 12:43:52 +00:00
J. Gareth "Curious Kit" Moreton	6dfe323e6f	- AND and DeepMovOpt optimisations upgraded.	2024-10-20 12:43:52 +00:00
J. Gareth "Curious Kit" Moreton	e187d49590	* x86: New reference support methods to detect modification	2024-10-20 12:43:52 +00:00
J. Gareth "Curious Kit" Moreton	d0c7838eec	* x86: CheckMovMov2MovMov2 now sets "Force New Iteration" if it optimises	2024-10-20 12:43:52 +00:00
J. Gareth "Curious Kit" Moreton	d5c6286852	* x86: Bug fix in OptPass1MOV long-range optimisations where ... the wrong register was checked to see if had changed.	2024-10-20 12:43:52 +00:00
florian	210cb8cb74	* load 64 bit constants through a register into memory to avoid store-forwarding stalls, resolves #40945	2024-10-12 21:19:14 +02:00
florian	23bbf87c10	* accidentally committed with a set debug define	2024-10-08 23:13:53 +02:00
florian	e91c8040ea	* do not generate lea with 16 bit references on x86-64, resolves #40936	2024-10-07 22:53:54 +02:00
florian	2f5fe67e56	* FSRM works only with movsb	2024-09-28 21:52:37 +02:00
florian	eb440e0ff1	+ Zen4 for i386	2024-09-22 10:43:26 +02:00
Rika Ichinose	fc1050a834	Make use of CPUX86_HINT_BSX_DEST_UNCHANGED_ON_ZF_1 in Bsf*/Bsr*.	2024-09-22 08:33:44 +00:00
J. Gareth "Curious Kit" Moreton	a06a20f9c0	* x86: Fixed an issue where invalid typecast errors would be raised in the peephole optimizer under -CriotR	2024-07-25 20:35:06 +00:00
florian	f6002d8078	* ensure make_simple_ref is called, resolves #40851	2024-07-10 22:26:09 +02:00
florian	db5e821ead	* more change information updates	2024-07-02 22:21:24 +02:00
florian	9ce7fbeef0	* change information updates	2024-06-28 22:45:00 +02:00
J. Gareth "Curious Kit" Moreton	fb66369a3b	* x86: CheckJumpMovTransferOpt now also copies over register deallocations to allow better optimisations	2024-06-24 20:05:39 +00:00
florian	2fe3955be9	+ more change information	2024-06-11 23:22:21 +02:00
florian	bdb611c925	* small fix of change information	2024-06-10 23:10:48 +02:00
florian	15b3f16646	* use fld1/fchs regardless of pic	2024-06-06 22:36:29 +02:00
florian	aaeefacf85	* also optimize loading of -1.0	2024-06-05 22:56:45 +02:00
florian	8c2aca6ece	* load 2 on x86 stack by fld1/fadd, if pic code is generated. It is more efficient as two memory accesses are saved.	2024-06-04 23:21:26 +02:00
florian	c64fae2f89	* missing AVX-2 change information fixed	2024-06-03 23:29:37 +02:00
florian	73a251410e	+ more change information	2024-06-02 23:11:14 +02:00
florian	8db51a367e	* forgotten part of last commit	2024-06-01 18:53:50 +02:00
florian	055681c8b4	* correct change information for some instructions where the change ... information cannot be modelled in x86ins.dat	2024-06-01 18:46:23 +02:00