github/tinygrad
1
1
Fork 0
mirror of https://github.com/tinygrad/tinygrad.git synced 2026-01-24 14:28:09 -05:00
Code Issues Packages Projects Releases Wiki Activity
5,638 Commits 205 Branches 14 Tags
4df4845b4714e9c2cf538aaaeca57d37b559dfd2
Commit Graph

5638 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
George Hotz
4df4845b47 cache is_int [run_process_replay] (#6131) 
* cache is_int [run_process_replay]

* functools.cached_property is pretty slow
 2024-08-17 00:19:03 -07:00
George Hotz
3a2d724cb2 extra matcher from renderer [run_process_replay] (#6130) 
* extra matcher from renderer

* cache_pm [run_process_replay]
 2024-08-16 23:53:11 -07:00
George Hotz
9bc81c6db4 UOps.SHAPETRACKER (#6129) 
* UOps.SHAPETRACKER [run_process_replay]

* no process replay
 2024-08-16 23:26:34 -07:00
George Hotz
5048066e79 st_arg, never -1 [run_process_replay] (#6128) 2024-08-16 22:46:56 -07:00
George Hotz
9e6ad4b40f hotfix: free minor speedup 2024-08-16 21:08:03 -07:00
George Hotz
d9cb45af09 only axis is masked [run_process_replay] (#6123) 2024-08-16 21:01:17 -07:00
George Hotz
94aa5f11b5 Revert "use vmax for real_size [run_process_replay] (#6120)" (#6122) 
This reverts commit a6e3211444.
 2024-08-16 20:33:19 -07:00
George Hotz
a6e3211444 use vmax for real_size [run_process_replay] (#6120) 
* use vmax for real_size [run_process_replay]

* axis is masked
 2024-08-16 20:17:23 -07:00
George Hotz
912f01ed4b UOpGraph -> linearize_uop [run_process_replay] (#6119) 2024-08-16 19:48:39 -07:00
George Hotz
7cae152aa2 move uop logic into shapetracker [run_process_replay] (#6118) 2024-08-16 17:47:15 -07:00
George Hotz
89c7989659 no shapetracker in ops [run_process_replay] (#6117) 2024-08-16 17:23:27 -07:00
George Hotz
74ee9febec remove iter from uopgraph (#6110) 
* remove iter from uopgraph

* linearize returns uops

* fix tests

* linearize in linearize

* tests fix

* touchup

* test failures
 2024-08-16 15:58:29 -07:00
qazal
28c75bf2a6 merge uops with ops (#6111) 
Co-authored-by: chenyu <chenyu@fastmail.com>
 2024-08-16 18:17:57 -04:00
chenyu
379d080e74 tqdm touchup (#6113) 
more precise names and don't repeat set_description
 2024-08-16 17:34:21 -04:00
nimlgen
5f1554b574 amd fix uaf in program (#6114) 
* amd fix uaf in program

* keep it align

* sync before free
 2024-08-17 00:22:46 +03:00
qazal
d5e3217076 hotfix: scheduler differ (#6115) 
* hotfix: scheduler differ

* add the test back

* track keys
 2024-08-16 23:34:49 +03:00
qazal
c23d44c779 AST is UOp (#6030) 
* most of the work from the uops2 branch

* schedule

* realize

* kernel

* lowerer

* search

* green

* merge uops with ops

* Revert "merge uops with ops"

This reverts commit 1408a59f12.

* fix benchmark

* remove extra dedup
 2024-08-16 22:09:00 +03:00
George Hotz
d6f64c0c1f do better image indexing [run_process_replay] (#6109) 
* do better image indexing [run_process_replay]

* fix tests
 2024-08-16 09:55:22 -07:00
CaltropHungerton
38fb1e14a2 Intel XMX Tensor Core Support (#5622) 
* fixed xmx demo

* i think i'm invoking the DPAS but it's slow

* compiler build arg to stop register spilling, indicated where to fix flop counter

* don't mind this

* do NOT mind me

* do not mind me

* do not view

* i will add bf16 later

* in process of figuring out tc fields

* we figured out the fields!!!

* added check for cl device vendor, added seperate IntelRenderer

* remove tc thread_local_aliases

* cleaning debris before draft pr

* edits for linter

* deduping and checking device extensions

* i will find more line reductions in other places

* before merge upstream

* double grf size in compiler to fix register spilling (bandaid), device checking changes

* tc python emulation

* fixed emulation

* tests for emulated intel tensor core

* TC=0, 1 working on upstream, fixed perf

* test

* debris

* check for specialized cl device when we canonicalize device

* bf16 support, tc=3 test added

* address tests

* revert half2 loads on intel tc, cleanup

* linter

* fold_expanded revert

* lint, whitespace fix

* cuda bf16 (only one with bf16) is skipped in test tensor cores, so i will skip for intel bf16 too

* make line shorter, no need for noqa E501

* removed device intel

* fix python emulation

---------

Co-authored-by: George Hotz <72895+geohot@users.noreply.github.com>
 2024-08-16 09:19:21 -07:00
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