github/tinygrad
1
1
Fork 0
mirror of https://github.com/tinygrad/tinygrad.git synced 2026-02-17 10:02:00 -05:00
Code Issues Packages Projects Releases Wiki Activity
6,030 Commits 227 Branches 14 Tags
46e360fdc0a5ff715fee50d8484f09bc56dfaf79
Commit Graph

2555 Commits

Author SHA1 Message Date
wozeparrot
46e360fdc0 check bfloat16 range with threefry (#6660) 2024-09-23 10:48:44 +08:00
qazal
d24e4b1042 viz more kernel view work (#6659) 2024-09-23 10:48:35 +08:00
qazal
6be1bf09f1 hotfix: bring COMPARE_SCHEDULE=0 back (#6657) 2024-09-23 10:39:43 +08:00
George Hotz
e945fa9c5c put local on the PtrDtype [run_process_replay] (#6656) 
* put local on the PtrDtype [run_process_replay]

* those are local too
 2024-09-23 10:29:17 +08:00
chenyu
90c1ccc402 simpler drop valid check in simplify_valid_image_load (#6653) 
* simpler drop valid check in simplify_valid_image_load

* update tests
 2024-09-22 21:46:39 -04:00
qazal
6b65d8c461 more process replay tracing work [run_process_replay] (#6650) 2024-09-22 16:16:58 +08:00
qazal
5bafed2f88 process replay traceback (#6642) 2024-09-21 16:53:34 +08:00
qazal
982086f54c UOps.VALID try 2 (#6623) 
* make UOps.VALID compile

* fixable tests

* bufs dedup

* cleanup the CONST spec

* regenerate dataset with graph_rewrite

```py
def rewrite_const(const:UOp, st_src:UOp) -> UOp:
  st: ShapeTracker = st_src.arg
  return UOp(UOps.VALID, dtypes.bool, (st.to_uop(),)).where(UOp.const(const.dtype, const.arg), UOp.const(const.dtype, 0))
pm = PatternMatcher([(UPat(UOps.CONST, name="const", src=(UPat(UOps.SHAPETRACKER, name="st_src"),)), rewrite_const)])
```

* rm arg

* remove arg

* revert arg removal

This reverts commit 2c35c75c95.

* red test_pickle_define_var
 2024-09-21 14:19:25 +08:00
qazal
d2351af019 fixup non-void SINKs in tests [run_process_replay] (#6624) 2024-09-21 13:29:18 +08:00
qazal
391d14438e DEFINE_VAR prereqs for VALID [run_process_replay] (#6637) 2024-09-21 13:28:39 +08:00
nimlgen
053c4dee55 qcom test for image pitch (#6621) 
* qcom test for image pitch

* comment
 2024-09-20 18:13:48 +08:00
chenyu
acef3e67fa add an example that idx is const and valid cannot be removed (#6625) 
very weird
 2024-09-20 05:46:27 -04:00
chenyu
5707503048 x//a<b -> x <a*b for positive a (#6622) 
openpilot valids 47 -> 37
 2024-09-20 04:38:47 -04:00
chenyu
b14c1bc417 UOps.RANGE is_increasing (#6615) 
* UOps.RANGE is_increasing

283 -> 47 valids

* test
 2024-09-20 03:14:52 -04:00
chenyu
036c2f5b26 validhack use the new style ge for upper bound valid (#6612) 
also relaxed the bound check to check vmin/vmax instead just const.
valids 482 -> 283
 2024-09-19 23:45:42 -04:00
chenyu
a37e92081a fix unrolled arange folding (#6606) 
* fix unrolled arange folding

also added flop test to test_arange to make sure it's 0 flop

* skip PTX
 2024-09-19 09:03:01 -04:00
George Hotz
a1a882b006 arange folding with new ge (#6604) 
* arange folding with new ge

* bump allowed gated

* bump allowed speed
 2024-09-19 18:01:28 +08:00
chenyu
d148a62f8d more generic simplify_valid_image_load (#6603) 
use graph_rewrite to simplify the expression with narrowed variables, and check boundry conditions on monotonically increasing function to drop valid.
 2024-09-19 05:33:37 -04:00
chenyu
eeee032b14 tiny cleanup of test_image_valid (#6597) 
* tiny cleanup of test_image_valid

Sepcial and Variable to setup UOp

* typo
 2024-09-19 03:09:47 -04:00
George Hotz
012a2c449a fix lt_folding VCONST issue [run_process_replay] (#6424) 
* le and ge [run_process_replay]

* bugfix

* fix divides bug

* fix lt_folding issue
 2024-09-19 14:59:20 +08:00
qazal
309ea63c03 include cached replaces in VIZ=1 (#6596) 
* pick some work from vizmore branch

* fix the ctx location

* fix that loc
 2024-09-19 14:48:31 +08:00
qazal
44c18a39a5 fix upat .location for the type verifier (#6592) 
* fix upat .location for the type verifier

* get the last tinygrad file
 2024-09-19 14:13:12 +08:00
chenyu
496806ce75 another example of openpilot conv with valid (#6595) 2024-09-19 01:54:01 -04:00
chenyu
7f9fd556b0 _min_max for WHERE (#6564) 
prereq to gated load simplification

just for int
 2024-09-18 23:47:48 -04:00
chenyu
1b6eee02ad failed test case for openpilot validhack conv (#6590) 
* failed test case for openpilot validhack conv

can save 2ms once this is fixed

* fix order
 2024-09-18 23:12:30 -04:00
George Hotz
e015b41ce9 remove e( function just alu( [run_process_replay] (#6589) 
* remove e( function just alu( [run_process_replay]

* missed two
 2024-09-19 10:24:02 +08:00
George Hotz
fa0f678d5a use the PatternMatcher to validate UOps type [run_process_replay] (#6583) 
* use the PatternMatcher to validate UOps type [run_process_replay]

* type check tests pass

* DEFINE_VAR

* fix precommit

* fix tests

* ptx

* type check tests pass

* ptx test

* int64

* ptx barrier

* delete old stuff
 2024-09-19 09:59:06 +08:00
chenyu
bd40a26b8b image valid test case that current approach does not work (#6584) 2024-09-18 06:06:03 -04:00
George Hotz
d02bb270b7 add copyin copyout for image on GPU [run_process_replay] (#6580) 
* add copyin copyout for image on GPU [run_process_replay]

* add timing

* enqueue vs total run

* it's failing but that's fine
 2024-09-18 16:06:20 +08:00
chenyu
162ead02a9 remove LOAD where valid is an empty set (#6579) 
356 -> 354 valids
 2024-09-18 03:49:41 -04:00
George Hotz
d4b662c318 new openpilot compile (#6573) 
* new openpilot compile

* note, copyout doesn't work for images
 2024-09-18 14:22:50 +08:00
chenyu
c3a70dbf0d 20 jitted steps in openpilot benchmark (#6577) 2024-09-18 02:15:16 -04:00
chenyu
a72d51e277 brute force VALIDHACK matching (#6575) 
* brute force VALIDHACK matching

* cleanup

* 9700
 2024-09-18 01:59:50 -04:00
qazal
d8e5d5c663 move VIZ=1 tests to fuzzers (#6574) 2024-09-18 12:12:03 +08:00
George Hotz
28e565dc0d prune independent kernels for openpilot [run_process_replay] (#6569) 
* prune independent kernels for openpilot [run_process_replay]

* new pruning

* prune first, then memory plan
 2024-09-17 20:02:38 +08:00
qazal
9295bc0189 viz more work [run_process_replay] (#6568) 
* infra

* found it

* real work

* bring those back

* cleanup test_viz

* comment that out
 2024-09-17 19:27:09 +08:00
qazal
455a27dd43 start viz unittests (#6550) 
* test_viz

* more tests
 2024-09-17 18:58:23 +08:00
George Hotz
67a03e72bb remove expr_idxs [run_process_replay] (#6567) 
* remove expr_idxs [run_process_replay]

* goodbye that test
 2024-09-17 18:34:51 +08:00
chenyu
b947db3de1 don't fold mul mod for common factor (#6566) 
it makes valid pattern more annoying
 2024-09-17 06:01:27 -04:00
Gaétan Lepage
f214bb140d test: relax tolerance of test_broadcastdot (#6560) 2024-09-17 03:26:39 -04:00
chenyu
5fb877c78c generic valid match criteria of #6552 (#6558) 
455 -> 364 valids.
generalize `idx < image bound` to `idx < image bound + c` for some `c`
 2024-09-17 02:40:36 -04:00
George Hotz
0ab06d5840 push geps through wmma (#6559) 
* push geps through wmma

* update tests
 2024-09-17 14:38:40 +08:00
George Hotz
ffce3ed896 add some new rules (#6555) 
* add some new rules

* fix that

* non controversial
 2024-09-17 13:59:55 +08:00
chenyu
c62b6fd8f0 match any statement in valid for simplification (#6554) 2024-09-17 01:39:47 -04:00
George Hotz
a2239c812e minimum new style expand (#6534) 
* minimum new style expand [run_process_replay]

* float4 folding works

* fix uop graph

* if means or

* dype.count idx overload

* fix test arange

* expand nope

* fix expand contract

* fix amd tensor core

* oh, that's a good test with a real failure

* remove prints

* early reduce

* tomorrow, we remove sorted on expand args

* fix wmma issue

* that makes test_arange pass

* vectorized folding

* no check

* broadcast

* fix clang with self assign rule
 2024-09-17 13:02:41 +08:00
kormann
f5dd25d376 enable whisper batch for long sequences (#6458) 
* long batch +test

* long batch +test

* cleanup

* rollback syntactic changes

---------

Co-authored-by: chenyu <chenyu@fastmail.com>
 2024-09-17 00:42:10 -04:00
chenyu
7c942418a1 other side of simple out of bound valid case (#6552) 
462 -> 455
 2024-09-16 23:57:15 -04:00
chenyu
aeaf7894a7 more generic version of #6548 (#6549) 
x*(-1)<0 can be generalized to x*(-1)<c, 473 -> 462 valids
 2024-09-16 23:17:16 -04:00
chenyu
596f41eb46 simple drop image valid case (#6548) 
* simple drop image valid case

started unit test, 530 -> 473 valids

* cleanup
 2024-09-16 22:54:07 -04:00
George Hotz
42ba887daa remove logic to vectorize reduces (#6536) 
* remove logic to vectorize reduces

* fix tests
 2024-09-16 14:04:48 +08:00