[gcc r15-1833] [APX PPX] Avoid generating unmatched pushp/popp in pro/epilogue

2024-07-03 Thread Hongyu Wang via Gcc-cvs
https://gcc.gnu.org/g:8e72b1bb3896f6e8d4f4679cbcfbc2a8212d04f9 commit r15-1833-g8e72b1bb3896f6e8d4f4679cbcfbc2a8212d04f9 Author: Hongyu Wang Date: Wed Feb 7 14:42:58 2024 +0800 [APX PPX] Avoid generating unmatched pushp/popp in pro/epilogue According to APX spec, the pushp/popp pa

[gcc r15-2030] AVX512BF16: Do not allow permutation with vcvtne2ps2bf16 [PR115889]

2024-07-14 Thread Hongyu Wang via Gcc-cvs
https://gcc.gnu.org/g:02a3bf5e2f0c18078bf67fc0002219edba1d76ff commit r15-2030-g02a3bf5e2f0c18078bf67fc0002219edba1d76ff Author: Hongyu Wang Date: Sat Jul 13 11:45:31 2024 +0800 AVX512BF16: Do not allow permutation with vcvtne2ps2bf16 [PR115889] According to the instruction spec o

[gcc r15-2037] [APX NF] Add a pass to convert legacy insn to NF insns

2024-07-15 Thread Hongyu Wang via Gcc-cvs
https://gcc.gnu.org/g:681ff5ccca153864eb86099eed201838d8d98bc2 commit r15-2037-g681ff5ccca153864eb86099eed201838d8d98bc2 Author: Hongyu Wang Date: Thu Apr 18 16:53:26 2024 +0800 [APX NF] Add a pass to convert legacy insn to NF insns For APX ccmp, current infrastructure will always

[gcc r14-9882] [APX] Prohibit SHA/KEYLOCKER usage of EGPR when APX enabled

2024-04-09 Thread Hongyu Wang via Gcc-cvs
https://gcc.gnu.org/g:ea665f90260acb3ffd2e39fcd2e200e702ee0ead commit r14-9882-gea665f90260acb3ffd2e39fcd2e200e702ee0ead Author: Hongyu Wang Date: Tue Apr 9 09:50:11 2024 +0800 [APX] Prohibit SHA/KEYLOCKER usage of EGPR when APX enabled The latest APX spec announced removal of SHA

[gcc r15-2430] i386: Mark target option with optimization when enabled with opt level [PR116065]

2024-07-31 Thread Hongyu Wang via Gcc-cvs
https://gcc.gnu.org/g:a59c4e496fa916cb9a484a649aa1b4cebd6550f2 commit r15-2430-ga59c4e496fa916cb9a484a649aa1b4cebd6550f2 Author: Hongyu Wang Date: Fri Jul 26 08:27:01 2024 +0800 i386: Mark target option with optimization when enabled with opt level [PR116065] When introducing mun

[gcc r15-893] i386: Fix ix86_option override after change [PR 113719]

2024-05-29 Thread Hongyu Wang via Gcc-cvs
https://gcc.gnu.org/g:499d00127d39ba894b0f7216d73660b380bdc325 commit r15-893-g499d00127d39ba894b0f7216d73660b380bdc325 Author: Hongyu Wang Date: Wed May 15 11:24:34 2024 +0800 i386: Fix ix86_option override after change [PR 113719] In ix86_override_options_after_change, calls to

[gcc r14-10262] i386: Fix ix86_option override after change [PR 113719]

2024-05-30 Thread Hongyu Wang via Gcc-cvs
https://gcc.gnu.org/g:cd161b335c2723d0dce1cab00ad216b423ec2767 commit r14-10262-gcd161b335c2723d0dce1cab00ad216b423ec2767 Author: Hongyu Wang Date: Wed May 15 11:24:34 2024 +0800 i386: Fix ix86_option override after change [PR 113719] In ix86_override_options_after_change, calls t

[gcc r13-8811] i386: Fix ix86_option override after change [PR 113719]

2024-05-30 Thread Hongyu Wang via Gcc-cvs
https://gcc.gnu.org/g:173f8763a66622f2a70ad66f60573fcff7d6b49e commit r13-8811-g173f8763a66622f2a70ad66f60573fcff7d6b49e Author: Hongyu Wang Date: Wed May 15 11:24:34 2024 +0800 i386: Fix ix86_option override after change [PR 113719] In ix86_override_options_after_change, calls to

[gcc r15-1057] [APX] Adjust target-support check [PR 115341]

2024-06-06 Thread Hongyu Wang via Gcc-cvs
https://gcc.gnu.org/g:f46d54a2a76acb94356989fb187853e5b58c3098 commit r15-1057-gf46d54a2a76acb94356989fb187853e5b58c3098 Author: Hongyu Wang Date: Thu Jun 6 13:00:26 2024 +0800 [APX] Adjust target-support check [PR 115341] Current target apxf check does not specify sub-features th

[gcc r15-1058] [APX CCMP] Support APX CCMP

2024-06-06 Thread Hongyu Wang via Gcc-cvs
https://gcc.gnu.org/g:c989e59fc99d994159114304d4e715c72bedff0a commit r15-1058-gc989e59fc99d994159114304d4e715c72bedff0a Author: Hongyu Wang Date: Wed Mar 27 10:13:06 2024 +0800 [APX CCMP] Support APX CCMP APX CCMP feature implements conditional compare which executes compare

[gcc r15-1059] [APX CCMP] Adjust startegy for selecting ccmp candidates

2024-06-06 Thread Hongyu Wang via Gcc-cvs
https://gcc.gnu.org/g:23db87301b623ecf162c9df718ce82ed9aa354a8 commit r15-1059-g23db87301b623ecf162c9df718ce82ed9aa354a8 Author: Hongyu Wang Date: Tue Apr 9 16:05:26 2024 +0800 [APX CCMP] Adjust startegy for selecting ccmp candidates For general ccmp scenario, the tree sequence is

[gcc r15-1060] [APX CCMP] Support ccmp for float compare

2024-06-06 Thread Hongyu Wang via Gcc-cvs
https://gcc.gnu.org/g:0b6cea8783b9e1b86c5c7c277c301cb5931bc5e0 commit r15-1060-g0b6cea8783b9e1b86c5c7c277c301cb5931bc5e0 Author: Hongyu Wang Date: Wed May 8 11:08:42 2024 +0800 [APX CCMP] Support ccmp for float compare The ccmp insn itself doesn't support fp compare, but x86 has f

[gcc r15-1242] [APX CCMP] Use ctestcc when comparing to const 0

2024-06-13 Thread Hongyu Wang via Gcc-cvs
https://gcc.gnu.org/g:99e6cf404e37655be303e71f20df03c284c7989e commit r15-1242-g99e6cf404e37655be303e71f20df03c284c7989e Author: Hongyu Wang Date: Thu May 9 10:12:16 2024 +0800 [APX CCMP] Use ctestcc when comparing to const 0 For CTEST, we don't have conditional AND so there's no

[gcc r15-1293] [APX CCMP] Add targetm.have_ccmp hook [PR115370]

2024-06-13 Thread Hongyu Wang via Gcc-cvs
https://gcc.gnu.org/g:83a765768510d1f329887116757d6818d7846717 commit r15-1293-g83a765768510d1f329887116757d6818d7846717 Author: Hongyu Wang Date: Thu Jun 13 00:18:32 2024 +0800 [APX CCMP] Add targetm.have_ccmp hook [PR115370] In cfgexpand, there is an optimization for branch whic

[gcc r15-1469] i386: Fix some ISA bit test in option_override

2024-06-20 Thread Hongyu Wang via Gcc-cvs
https://gcc.gnu.org/g:4867cc815531ede8bc356a2507f1c35ee6e6399c commit r15-1469-g4867cc815531ede8bc356a2507f1c35ee6e6399c Author: Hongyu Wang Date: Mon Jun 17 10:34:01 2024 +0800 i386: Fix some ISA bit test in option_override Adjust several new feature check in ix86_option_override

[gcc r15-4948] i386: Utilize VCOMSBF16 for BF16 Comparisons with AVX10.2

2024-11-04 Thread Hongyu Wang via Gcc-cvs
https://gcc.gnu.org/g:61622cfa463f2ef4fc835ace2ecf5451b232cf4f commit r15-4948-g61622cfa463f2ef4fc835ace2ecf5451b232cf4f Author: Levy Hsu Date: Wed Oct 9 16:38:57 2024 +0800 i386: Utilize VCOMSBF16 for BF16 Comparisons with AVX10.2 This patch enables the use of the VCOMSBF16 instr

[gcc r14-10862] [APX PPX] Avoid generating unmatched pushp/popp in pro/epilogue

2024-10-31 Thread Hongyu Wang via Gcc-cvs
https://gcc.gnu.org/g:df542909224a7ff88b204534ad035a0b216a98bf commit r14-10862-gdf542909224a7ff88b204534ad035a0b216a98bf Author: Hongyu Wang Date: Wed Feb 7 14:42:58 2024 +0800 [APX PPX] Avoid generating unmatched pushp/popp in pro/epilogue According to APX spec, the pushp/popp p

[gcc r15-5007] i386: Support cstorebf4 with native bf16 comi

2024-11-07 Thread Hongyu Wang via Gcc-cvs
https://gcc.gnu.org/g:50ecb6e960e98fa3150239af72cf751f9b644544 commit r15-5007-g50ecb6e960e98fa3150239af72cf751f9b644544 Author: Hongyu Wang Date: Tue Nov 5 17:19:34 2024 +0800 i386: Support cstorebf4 with native bf16 comi We recently supports cbranchbf4 with AVX10_2 native bf16 c

[gcc r15-5225] i386: Fix cstorebf4 fp comparison operand [PR117495]

2024-11-13 Thread Hongyu Wang via Gcc-cvs
https://gcc.gnu.org/g:19b24f4aae6c59d70cc882623b1e9b279b3872f3 commit r15-5225-g19b24f4aae6c59d70cc882623b1e9b279b3872f3 Author: Hongyu Wang Date: Tue Nov 12 13:04:46 2024 +0800 i386: Fix cstorebf4 fp comparison operand [PR117495] For cstorebf4 it uses comparison_operator for BFmo

[gcc r15-7036] i386: Fix wrong insn generated by shld/shrd ndd split [PR118510]

2025-01-19 Thread Hongyu Wang via Gcc-cvs
https://gcc.gnu.org/g:af4fb245e12f2dd8e2c32167c9acfaceb4b6af6a commit r15-7036-gaf4fb245e12f2dd8e2c32167c9acfaceb4b6af6a Author: Hongyu Wang Date: Fri Jan 17 09:04:17 2025 +0800 i386: Fix wrong insn generated by shld/shrd ndd split [PR118510] For shld/shrd_ndd_2 insn, the spiltter

[gcc r15-6679] i386: Add br_mispredict_scale in cost table.

2025-01-07 Thread Hongyu Wang via Gcc-cvs
https://gcc.gnu.org/g:59096f014fedab9bd6787a286acf2afa7ab0fe9e commit r15-6679-g59096f014fedab9bd6787a286acf2afa7ab0fe9e Author: Hongyu Wang Date: Thu Jan 2 10:29:27 2025 +0800 i386: Add br_mispredict_scale in cost table. For later processors, the pipeline went deeper so the penal