Commit Graph
73 Commits
Author SHA1 Message Date
Nitload 55cf3934bb many thing 2026-02-28 00:54:32 +08:00
Youmu Liu a798ab07f1 arrange of proj structure 2026-02-27 17:09:13 +08:00
Youmu Liu 15434ed053 many things 2026-02-26 18:05:35 +08:00
Youmu Liu 1b04196314 many versions of simdid 2026-02-25 18:02:56 +08:00
Nitload b71515b2d4 per thread context loading is ok, working on global context 2026-02-25 00:20:09 +08:00
Youmu Liu 7ee9c749e5 working on per-PoolThread context loading and global context loading 2026-02-24 18:05:16 +08:00
Youmu Liu d62e59cb93 Switch matrix parallel to task stealing, type and wrap are refacored, thread execution core has not yet 2026-02-24 15:12:23 +08:00
Nitload c155cab510 HLSF use long as aloloc size 2026-02-23 12:32:15 +08:00
Youmu Liu f02e55609b solve or inv starts 2026-01-14 18:01:03 +08:00
Youmu Liu f133cc9147 solve or inv starts 2026-01-13 18:25:25 +08:00
Youmu Liu ad3b2212fa tiled fma is ok, mat mul is now available again 2026-01-12 15:09:39 +08:00
Youmu Liu b8bf1e9f08 seems tile_fma kernel has index error and indexer of matrix has error as well 2026-01-11 16:45:38 +08:00
Youmu Liu cd8210d9a1 fixing tile fma 2026-01-11 15:28:30 +08:00
Nitload 4be5c1c7c9 Daily update on 20260111-005714 by Nitload Youmu. Additional Message : Use optimized tile operation to accelerate matrix mul, still has problem
Signed-off-by: Nitload <YoumuLiu_NSI@whv0t.onmicrosoft.com>
2026-01-11 00:57:14 +08:00
Youmu Liu 6827259891 tile fma added 2026-01-09 18:13:46 +08:00
Youmu Liu 88af8d8957 better kernel fma 2026-01-07 18:06:36 +08:00
Youmu Liu 3d488abd2e add simd id and cpu id 2026-01-06 18:04:17 +08:00
Nitload e1d2a8707d add isa check 2026-01-04 07:56:37 +08:00
Nitload 53085d35d2 Merge branch 'giga' of ssh://ssh.github.com:443/Nitload-NSI/CCD_Github into local 2026-01-01 16:05:35 +08:00
Youmu Liu 0e93787fa2 Double add sub mul sc-mul ok 2025-12-31 18:15:43 +08:00
Nitload 5decbd390d Daily update on 20251230-224423 by Nitload Youmu. Additional Message : Adding compute support for mat<double>. Import all opengl core profile fucntions
Signed-off-by: Nitload <YoumuLiu_NSI@whv0t.onmicrosoft.com>
2025-12-30 22:44:23 +08:00
Youmu Liu f9288c1b3d adding generated opengl function binding 2025-12-29 17:06:04 +08:00
Youmu Liu c6d53d97ea add double compute kernel 2025-12-26 17:16:12 +08:00
Youmu Liu e5539bcc6d keep working on PLN facotrize 2025-12-25 11:59:40 +08:00
Nitload cf370ca98a Merge branch 'giga' of ssh://ssh.github.com:443/Nitload-NSI/CCD_Github into local 2025-12-24 23:21:35 +08:00
Youmu Liu 3b3a90a2af keep working on PLN facotrize 2025-12-24 18:09:16 +08:00
Nitload ca5fc9a3f5 remove branch conflict 2025-12-21 23:20:56 +08:00
Youmu Liu b32c1cb4eb redesign matrix design 2025-12-18 18:04:55 +08:00
Nitload cffe44772e Merge branch 'giga' of ssh://ssh.github.com:443/Nitload-NSI/CCD_Github into local 2025-12-17 22:00:44 +08:00
Youmu Liu 688a420574 Working on Factorize 2025-12-17 16:56:13 +08:00
Nitload b13adc1a1b matrix mul matrix is full function 2025-12-16 23:17:30 +08:00
Nitload 6344242b3c merge main branch 2025-12-16 23:16:57 +08:00
Nitload 3486375470 MulAvailable 2025-12-16 23:13:17 +08:00
Youmu Liu 88ed5a95c5 Mat mul mat is now on full function 2025-12-16 16:15:30 +08:00
Youmu Liu 2c7277f3f9 working on matrix mul matrix, rebuilding task model defines in C# 2025-12-12 18:00:49 +08:00
Youmu Liu 9ff438d3b9 working on matrix mul matrix 2025-12-11 18:09:35 +08:00
Youmu Liu 631bc2b6e8 working on matrix mul matrix 2025-12-10 17:52:17 +08:00
Youmu Liu f960982bd3 time service contains bug, it cannot stop after edge 2025-12-08 18:02:09 +08:00
Youmu Liu 588fa867af working on panel building, preparing for panel compute 2025-12-03 18:14:45 +08:00
Youmu Liu 5b09160049 hlsf wrong slicing solving 2025-11-25 20:39:18 +08:00
Youmu Liu b7b960a604 hlsf wrong alloc solved 2025-11-24 17:00:10 +08:00
Nitload c1995d119a Daily update on 20251124-010227 by Nitload Youmu. Additional Message : error in hlsf
Signed-off-by: Nitload <YoumuLiu_NSI@whv0t.onmicrosoft.com>
2025-11-24 01:02:27 +08:00
Youmu Liu 98f47aaa53 add sub and scalar_mul operation 2025-11-20 19:53:54 +08:00
Youmu Liu 28bdc42982 buffer op and parallel framework is now on full complete 2025-11-20 17:50:06 +08:00
Youmu Liu c595076005 buffer op brief ok, but blocks on unkown reason 2025-11-20 16:17:24 +08:00
Youmu Liu a29a442723 add scheduler method; fixing buffer parallel errors 2025-11-19 19:57:29 +08:00
Youmu Liu 04fc55d31e add scheduler method; fixing buffer parallel errors 2025-11-19 18:09:25 +08:00
Youmu Liu ece12f2ea7 new simplified timer. and little other ops 2025-11-18 20:39:03 +08:00
Youmu Liu 8fa1a9749e going on big buffer, need three diff task scheduler 2025-11-17 16:12:50 +08:00
Youmu Liu a8c522ab23 small size buffer op ok 2025-11-14 18:28:15 +08:00