github/tinygrad
1
1
Fork 0
mirror of https://github.com/tinygrad/tinygrad.git synced 2026-01-25 06:48:22 -05:00
Code Issues Packages Projects Releases Wiki Activity
5,619 Commits 205 Branches 14 Tags
f82ecd8802010c75cffcef71b4ffcfaff9d96587
Commit Graph

5619 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
George Hotz
f82ecd8802 remove uop symobilc rendering [run_process_replay] (#6108) 2024-08-16 09:02:15 -07:00
George Hotz
e8ae9af962 bump line count to 9000. we should be here a while 2024-08-16 08:46:36 -07:00
chenyu
7d46fb0c83 load balance NV benchmark ci (#6107) 2024-08-16 10:08:08 -04:00
qazal
1ff6c7c519 add more types to search [run_process_replay] (#6096) 
* add more types to search [run_process_replay]

* bufs_from_lin
 2024-08-16 13:19:25 +03:00
chenyu
e5da88873b enable UOP_IS_SYMBOLIC (#5954) 2024-08-16 00:15:46 -04:00
George Hotz
553ae9ebc0 bilinear interp uint8 fails (#6103) 
* new test for e2e compile failures

* fix bug

* bilinear interp uint8 fails

* better tests
 2024-08-15 19:34:39 -07:00
George Hotz
c850e03758 new test for e2e compile failures (#6101) 
* new test for e2e compile failures

* fix bug
 2024-08-15 18:56:22 -07:00
chenyu
e4a7869893 move cancel mod pattern into mod_folding (#6100) 
changed some kernel in a good way because x does not go through add chain
 2024-08-15 19:04:18 -04:00
qazal
11d62668a3 refactor ast ops dtype access [run_process_replay] (#6093) 
* refactor ast ops dtype access [run_process_replay]

* fix assert message
 2024-08-15 19:13:33 +03:00
chenyu
9ef82e1f2b UOp pattern DEFINE_VAR with min==max is also CONST (#6095) 
* UOp pattern DEFINE_VAR with min==max is also CONST

* fix tests
 2024-08-15 12:09:44 -04:00
chenyu
a41c9dd12c test py.typed as a package (#6094) 
* test py.typed as a package

* try this?

* and this

* try that?

* add this back

* cleanup
 2024-08-15 11:19:08 -04:00
qazal
25dffb2079 kernel.py more typing [run_process_replay] (#6092) 2024-08-15 17:59:24 +03:00
qazal
4d38fec8c1 rename lazyops to parents [run_process_replay] (#6091) 2024-08-15 17:27:32 +03:00
chenyu
5accfe26a0 rewrite bool ADD to OR and MUL to AND (#6084) 
* rewrite bool ADD to OR and MUL to AND

fixed running `tinyphysics.onnx`, which contains a getitem from a boolean tensor.

only can repro through BEAM_COMPARE, which i think is a different bug in test_linearizer_failure

* fold those, and fix tests

* only for bool

* move dtypes.bool
 2024-08-15 10:11:57 -04:00
nimlgen
b765996d54 hcq remove offset from progs (#6090) 2024-08-15 17:02:54 +03:00
chenyu
df03dca6e3 move % inside UOp mod_folding and remove deprecated tests (#6085) 
[run_process_replay]
 2024-08-14 23:25:10 -04:00
George Hotz
c6e117c899 add a single py.typed (#6083) 2024-08-14 17:31:46 -07:00
qazal
2bf7b56485 minor test fixups from the AST is UOp diff (#6081) 
* add assert_equiv_uops cache

* dont expect lowering and schedule errors
 2024-08-14 23:58:04 +03:00
chenyu
95aa6d8ccd remove redundant x/c pattern [run_process_replay] (#6082) 
there's no div and 1/c is const folded
 2024-08-14 16:57:39 -04:00
chenyu
a61cb1ff7c move mod mod pattern into generic mod folding (#6077) 2024-08-14 16:24:21 -04:00
George Hotz
64563abc90 add LSTMCell to nn (#6080) 
* add LSTMCell to nn

* lstmcell works with no input on first

* fix no bias 0

* simpler
 2024-08-14 12:08:42 -07:00
chenyu
6b3112d525 fix qcom process_replay for kernel diff (#6079) 
* debug why qcom process_replay does not run

skipping the wrong exception?

* um-hum

* get_step_times was parsed incorrectly

* cleanup
 2024-08-14 15:05:49 -04:00
chenyu
2fe9d62451 increase test_recursive_add time from 1s to 2s (#6078) 
flaky https://github.com/chenyuxyz/tinygrad/actions/runs/10392144818/job/28776666700
 2024-08-14 13:52:02 -04:00
nimlgen
7ab531aede autogen cleanup (#6064) 
* start autogen cleanup

* nvgpu

* better?

* better

* amd part

* gpu regen

* fix mockgpu amd

* nv

* amd fix linter

* remove import

* ugh

* nv on master

* amd on master
 2024-08-14 20:20:35 +03:00
chenyu
de773b593e remove redundant div gcd patterns [run_process_replay] (#6076) 
covered by generic div_folding
 2024-08-14 13:18:28 -04:00
samm393
2dc586ffe5 Shape change bitcast for more dtypes (#6047) 
* bitcast & tests

* use to_dtype

* put disk tensor tests back

* tests

* bitmask

* no bitmask

---------

Co-authored-by: George Hotz <72895+geohot@users.noreply.github.com>
 2024-08-14 10:03:34 -07:00
qazal
83a2543c74 spec for in order LOAD/STORE indexing (#6073) 
* test_unaligns_idxs

* spec for in order LOAD/STORE indexing

* test UOps.SPECIAL

* check for supports_float4
 2024-08-14 19:18:00 +03:00
chenyu
5048f9a4d5 test linearizer failure 49 (#6074) 
with UOP_IS_SYMBOLIC=1, on METAL it breaks store fusion and have A+B and B+A being two different UOp
 2024-08-14 11:29:10 -04:00
qazal
30035df5a4 add metal process replay back (#6068) 
test this new one
 2024-08-14 12:29:56 +03:00
wozeparrot
518c022c29 feat: tag 0.9.2 (#6067) v0.9.2 2024-08-13 16:15:36 -07:00
George Hotz
97c3563109 hotfix: clamp in docs 2024-08-13 16:06:30 -07:00
George Hotz
e039b2a920 add Tensor.clamp and fix bool loading (#6069) 2024-08-13 15:26:40 -07:00
chenyu
1782e4f64d use div folding to do lt folding (#6065) 2024-08-13 16:59:05 -04:00
chenyu
e3af273fa1 touchup cl_errors (#6058) 
* touchup cl_errors

* update test
 2024-08-13 13:06:59 -04:00
qazal
9145ad52ff revert UOps eq, this needs to be isolated in realize.py (#6063) 
This reverts commit dccca7f227.
 2024-08-13 18:02:34 +03:00
nimlgen
fa84e6ec48 init hcq args state (#6046) 
* init hcq args state

* cleaner

* amd

* fillargs

* fixes

* myoy

* docs

* fix

* not needed

* spacing
 2024-08-13 17:11:58 +03:00
qazal
9d2ea94fe9 temp: disable process replay on metal (#6062) 2024-08-13 16:31:55 +03:00
andredaprato
18192079a9 Apply transcendental rewrite rules only if required by backend (#6061) 
* Apply transcendental folding for missing ops

* Remove comments

* Remove Final type
 2024-08-12 22:38:45 -07:00
Tobias Fischer
6e3eb50fd1 added fix and reg tests (#6060) 2024-08-12 21:00:48 -04:00
chenyu
45bd667a78 rewrite pyint after first rewrite [run_process_replay] (#6059) 2024-08-12 19:18:13 -04:00
qazal
2ac80576e4 remove BufferOps from log_lazybuffer (#6057) 
this is fine because lazy.py doesn't create BufferOps.
 2024-08-13 02:06:47 +03:00
qazal
dccca7f227 test: uop and lazyop have the same compare (#6053) 
* test: uop and lazyop have the same compare

* typings

* self.assert_equiv_uops -> assertEqual

* hash dtype

* test nop too

* TestPatternMatcher never used this compare anyway

* nop eq and ne tests
 2024-08-13 00:33:19 +03:00
qazal
8c501272f3 proposal: MetaOps.EXT (#6054) 
`MetaOps.CUSTOM, MetaOps.COPY, MetaOps.EMPTY, MetaOps.VIEW` don't fit into any of our existing UOps.

MetaOps.KERNEL and MetaOps.EXT can be the two paths in realize.py

after AST is UOp:
MetaOps.KERNEL -> UOps.SINK
MetaOps.EXT -> UOps.EXT
 2024-08-13 00:29:29 +03:00
wozeparrot
059cf2a90d feat: autogen from kernel register offset headers (#6056) 2024-08-12 14:08:35 -07:00
chenyu
3f2d24a6ec test_failure_48 for wrong truncation in idx on NV (#6055) 
also added `RAWAST` to print pre-modified AST in DEBUG=3
 2024-08-12 16:17:42 -04:00
chenyu
6ed9711898 UOps pattern (x%c)+(x//c)*c = x (#6051) 
pretty cool that this is very easy to write now
 2024-08-12 14:58:48 -04:00
qazal
71c5901fc1 refactor ast arg and op [compare_schedule] (#6052) 2024-08-12 21:51:00 +03:00
wozeparrot
dc2617bffd feat: use more correct reg for local dims (#6048) 2024-08-12 11:15:37 -07:00
qazal
529832d223 refactor ast creation [compare_schedule] (#6050) 
* refactor scheduler lazyop creation [compare_schedule]

* helpful prints

* this will become the default
 2024-08-12 21:15:11 +03:00
nimlgen
8f787785d9 fix openpilot benchmark (#6049) 2024-08-12 21:12:32 +03:00