Commit graph

11,769 commits

Author SHA1 Message Date
George Hotz
2f85319722 Merge remote-tracking branch 'origin/master' into amd_sqtt
# Conflicts:
#	extra/assembly/amd/emu.py
#	extra/assembly/amd/sqtt.py
2026-01-12 05:42:04 +09:00
George Hotz
44135e2e84
assembly/amd: always use v_nop in test for rocprof-trace-decoder (#14100)
* assembly/amd: always use v_nop in test for rocprof-trace-decoder

* test touchups
2026-01-12 05:31:58 +09:00
George Hotz
8b1b15aec0
assembly/amd: SQTT support (#14099)
* assembly/amd: SQTT support

* simpler

* cmp wave

* instruction compare

* rocprof decode

* simpler

* no llvm

* no strcmp
2026-01-12 05:07:17 +09:00
George Hotz
d9f0e9c40c something 2026-01-12 02:26:31 +09:00
nimlgen
8b5ff403fa
am: flag successful finalization (#14097)
* am: flag successful finalization

* import
2026-01-11 16:24:53 +03:00
qazal
d8aba24967
amd: use kernel descriptor struct in AMDProgram (#14096) 2026-01-11 18:25:16 +09:00
George Hotz
3dcffbea25 NO SLOT 2026-01-11 17:31:50 +09:00
George Hotz
41c5368266 close 2026-01-11 17:26:20 +09:00
George Hotz
4598a21f94 rdna3 timing 2026-01-11 07:14:39 +00:00
George Hotz
27084cd618 some 2026-01-11 16:12:16 +09:00
George Hotz
d2616e5daf weird forward beavhior 2026-01-11 16:00:21 +09:00
George Hotz
3130c53f85 strange hardware behavior 2026-01-11 15:53:40 +09:00
George Hotz
1c66e41383 new test 2026-01-11 15:23:37 +09:00
George Hotz
93823b272c DEBUG=3 is pretty 2026-01-11 15:05:29 +09:00
George Hotz
1c6147e9bf better 2026-01-11 14:55:41 +09:00
George Hotz
7f5656d236 cold chain 2026-01-11 14:33:39 +09:00
George Hotz
5f55a61700 dumb 2026-01-11 13:22:39 +09:00
George Hotz
ed097df864 cleaner 2026-01-11 13:14:10 +09:00
George Hotz
a83c97f17e sqtt correct 2026-01-11 13:12:51 +09:00
George Hotz
c793076fb6 add s_delay_alu tests 2026-01-11 11:28:21 +09:00
George Hotz
1f45601a97 tests with early nops 2026-01-11 11:16:25 +09:00
George Hotz
14c4989f65 pipeline exec 2026-01-11 11:11:52 +09:00
George Hotz
31b38640ac nop anomaly 2026-01-11 10:41:13 +09:00
George Hotz
fe770e822c pats 2026-01-11 09:56:05 +09:00
George Hotz
768231c065 lat tests 2026-01-11 09:54:32 +09:00
George Hotz
4165594b30 first cycle lat 2026-01-11 09:48:04 +09:00
George Hotz
c03b7b0da1 gap5 anomaly 2026-01-11 09:13:51 +09:00
George Hotz
66249836c0 good test 2026-01-11 09:11:36 +09:00
George Hotz
a0d6ed9914 a couple more 2026-01-11 09:06:32 +09:00
George Hotz
99fcfc0e97 cleaner 2026-01-11 08:57:19 +09:00
George Hotz
cf8bb15aef padding 2026-01-11 08:55:51 +09:00
George Hotz
32dfc9b1d0 another test 2026-01-11 08:49:20 +09:00
chenyu
9973a81356
add channels_last to QLinearGlobalAveragePool (#14094)
and other minor cleanups
2026-01-10 18:38:19 -05:00
George Hotz
9803e389fe good tests 2026-01-11 08:29:39 +09:00
George Hotz
1f893b65cc new hw free test 2026-01-11 07:49:50 +09:00
chenyu
c5492f8f75
cstyle cleanup [pr] (#14093) 2026-01-10 09:44:50 -05:00
nimlgen
d5f954858d
viz: show precise timings (#14092) 2026-01-10 16:21:08 +03:00
nimlgen
3e2c05ee9f
hevc: decoder as iterator (#14091) 2026-01-10 14:57:56 +03:00
chenyu
35c9701df0
update outdated tests and comments (#14090) 2026-01-10 01:00:48 -05:00
chenyu
92246ea731
update tests, WEBGPU=1 pytest . passes (#14089)
* update tests, `WEBGPU=1 pytest .` passes

* minor update
2026-01-10 00:03:02 -05:00
George Hotz
35f5f05ad5 multiwave 2026-01-09 21:01:26 -08:00
George Hotz
b9f08ad18a fix multiwave 2026-01-09 21:01:26 -08:00
George Hotz
222ae38aa4 fix multiwave 2026-01-09 21:01:26 -08:00
George Hotz
f0bf20d7b2 structuring 2026-01-09 21:01:26 -08:00
George Hotz
85ef097da6 snop passes 2026-01-09 21:01:26 -08:00
chenyu
c34c6d9468
fix wgsl packed_store can drop valid (#14088)
* fix wgsl packed_store can drop valid

* fix
2026-01-09 15:22:06 -05:00
chenyu
eacccc5ace
more disk assign tests (#14087)
covers more edge cases
2026-01-09 14:14:52 -05:00
chenyu
ed295e74dc
don't skip gguf test if ggml is not installed (#14086)
* don't skip gguf test if ggml is not installed

should just let it fail

* fix
2026-01-09 12:05:58 -05:00
chenyu
cff33c8d78
add some disk assign tests (#14085) 2026-01-09 11:50:59 -05:00
chenyu
74fa3c7d09
decomp pow for LVP (#14084)
test failed due to undefined behavior, so use decomp instead
2026-01-09 10:50:28 -05:00