Commit Graph

1516 Commits

Author SHA1 Message Date
George Hotz
92cb8b6776 tests pass 2026-01-02 16:43:03 -08:00
George Hotz
c416b20668 failures 2026-01-02 15:54:02 -08:00
George Hotz
415b83ba18 tests pass 2026-01-02 15:47:39 -08:00
George Hotz
8c7eacea59 getting close 2026-01-02 15:25:18 -08:00
George Hotz
81542699f8 work 2026-01-02 14:39:52 -08:00
George Hotz
79f55a5d5e test_snop is correct 2026-01-02 12:01:08 -08:00
George Hotz
37518fb236 start with nop 2026-01-02 11:40:08 -08:00
George Hotz
672008ccab framework 2026-01-02 11:31:41 -08:00
George Hotz
849af761a4 simpler 2026-01-02 11:10:40 -08:00
George Hotz
ab46b3d8d3 origin/master 2026-01-02 10:47:00 -08:00
George Hotz
df20197bfb rever emu to master 2026-01-02 10:46:46 -08:00
George Hotz
2b56c264d5 compare tests 2026-01-02 10:39:07 -08:00
George Hotz
c7e5c2f996 Merge origin/master, remove deleted test_emu.py 2026-01-02 09:41:34 -08:00
George Hotz
0e282025ff assembly/amd: split test_emu into hw tests (#13966)
* assmebly/amd: split test_emu into hw tests

* hw tests

* bugfixes

* more tests and fix
2026-01-02 08:04:56 -08:00
chenyu
2e2b5fed12 fix misspellings (#13976) 2026-01-02 10:37:38 -05:00
nietras
f49e4714af Fix spelling errors in README for AMD assembly (#13975) 2026-01-02 10:15:20 -05:00
George Hotz
659aa14043 orks 2026-01-02 05:29:48 -08:00
qazal
5f52266225 mi350x gemm: use Tensor.custom_kernel in asm test (#13969)
* mi350x gemm: use Tensor.custom_kernel in asm test

* A @ B for baseline
2026-01-02 18:30:50 +09:00
George Hotz
21ffa1a86b 64 nops 2026-01-02 00:38:27 -05:00
George Hotz
29f3fb7af3 still stable 2026-01-01 23:45:19 -05:00
George Hotz
1edc7fc519 stable 2026-01-01 23:43:43 -05:00
George Hotz
c9a3ac988c cleanest 2026-01-01 23:18:19 -05:00
George Hotz
5a1a561e0f assembly/amd: rdna4 autogen (#13967)
* assembly/amd: add pcode ds ops

* refactors

* fix ds op

* update autogen

* fix flat bug

* more tests

* fix emu test

* that's a hack

* generic

* fix all tests

* two tests

* fix test failure

* better

* remove __all__

* assembly/amd: fix autogen for RDNA4
2026-01-01 23:12:18 -05:00
George Hotz
77d96acbe3 clean 2026-01-01 22:59:07 -05:00
George Hotz
660ecf272b work 2026-01-01 22:50:50 -05:00
George Hotz
267bbb163e progress 2026-01-01 21:11:29 -05:00
wozeparrot
b27527f05a fix: missed inner tracked range (#13964) 2026-01-01 18:09:57 -08:00
wozeparrot
ecbac8a338 tk: fa cleanups + causal test (#13963) 2026-01-01 18:05:00 -08:00
George Hotz
de29a49ea3 all the ones i can find 2026-01-01 20:56:30 -05:00
George Hotz
742e10a572 remove fake ones 2026-01-01 20:26:53 -05:00
George Hotz
447fe8907b more 2026-01-01 20:22:52 -05:00
George Hotz
b0cfcec183 good 2026-01-01 20:12:20 -05:00
George Hotz
1726084b2a filt 2026-01-01 19:40:43 -05:00
George Hotz
de069a4876 many 2026-01-01 19:21:46 -05:00
George Hotz
4573e91e61 more 2026-01-01 18:51:31 -05:00
George Hotz
8d43212bc6 assembly/amd: start work on SQTT parsing/emulation 2026-01-01 18:40:58 -05:00
George Hotz
dfb813b760 assembly/amd: add pcode ds ops (#13939)
* assembly/amd: add pcode ds ops

* refactors

* fix ds op

* update autogen

* fix flat bug

* more tests

* fix emu test

* that's a hack

* generic

* fix all tests

* two tests

* fix test failure

* better

* remove __all__
2026-01-01 16:24:13 -05:00
George Hotz
a8bea4ec52 remove __all__ 2026-01-01 16:14:15 -05:00
George Hotz
729bb04d8c fix test failure 2026-01-01 13:21:55 -05:00
George Hotz
a5959ef0f1 fix all tests 2026-01-01 13:11:51 -05:00
George Hotz
5ba06892c0 generic 2026-01-01 12:46:08 -05:00
George Hotz
469efe313d that's a hack 2026-01-01 12:40:14 -05:00
George Hotz
e3b3cb163d fix emu test 2026-01-01 12:12:47 -05:00
George Hotz
3e32185faf more tests 2026-01-01 12:04:41 -05:00
George Hotz
5328913d2b fix flat bug 2026-01-01 11:51:10 -05:00
George Hotz
9c49ec1cc1 update autogen 2026-01-01 11:36:33 -05:00
George Hotz
000d4a125b fix ds op 2026-01-01 10:36:37 -05:00
b1tg
24723327ac fix tc_up in search (#13438)
* tensor_core is missing from Scheduler

* test upcast max

---------

Co-authored-by: chenyu <chenyu@fastmail.com>
2026-01-01 10:25:08 -05:00
qazal
9726500de8 enable using assembly in Tensor.custom_kernel (#13895) 2026-01-02 00:12:01 +09:00
qazal
c0f52c9dcb split assembly gemm to per arch directory (#13953) 2026-01-02 00:10:22 +09:00