nimlgen/tinygrad
1
0
Fork 0
forked from tinygrad/tinygrad
Code Pull Requests Activity
5,693 Commits 334 Branches 15 Tags
911bf7216c3c17407fa30a336b1ffeb8f2bb9d68
Commit Graph
842 Commits
Author SHA1 Message Date
George HotzandGitHub 911bf7216c remove unused match rules [run_process_replay] (#6217) 2024-08-21 00:16:04 -07:00
George HotzandGitHub 2c42e9c2c6 faster rewrite, no folder in expand/reduce [run_process_replay] (#6216) 
* faster rewrite, no folder in expand/reduce [run_process_replay]

* is removing the expander there okay

* parens

* don't reconstruct exact match uop

* fast do_reduce

* expand pyint

* most of the parents gains with less lines
 2024-08-20 23:36:58 -07:00
George HotzandGitHub 16f420f7a7 split full_graph_rewrite and linearize_uop [run_process_replay] (#6215) 
* split full_graph_rewrite and linearize_uop

* fix tests

* graph rewrite in test uops

* add types
 2024-08-20 20:12:33 -07:00
George HotzandGitHub a5d79688db fix indexing out of bounds (#6208) 
* fix indeing out of bounds

* 5 ops per access is fine
 2024-08-20 11:34:56 -07:00
qazalandGitHub ee5fe12630 disallow some uops at different levels [run_process_replay] (#6186) 
* assert intermediate ones

* assert low-level uops
 2024-08-19 21:23:44 +03:00
qazalandGitHub 2242ff84be type verify intermediate UOps [run_process_replay] (#6140) 
* type verify intermediate UOps [run_process_replay]

* merge asserts

* variable const
 2024-08-19 20:59:01 +03:00
chenyuandGitHub b36a7273c6 RUF018 assignment-in-assert [run_process_replay] (#6172) 
assertion should not have side effect or `-O` breaks.

initially just wanted to fix the one in rearrange, but it also made some long lines less long
 2024-08-19 00:34:52 -04:00
qazalandGitHub fad1818530 move graph rewrite to ops [run_proess_replay] (#6159) 
* move graph rewrite to ops [run_proess_replay]

* better place
 2024-08-18 20:02:28 +03:00
TimmyGitHubqazal
 		e3d14d1ccc Lowerer Multireduce Grouping (#6097) 
* grouping changes to codegen

* linters + tests

* fix identical store issue on PTX

* comment in grouping multireduce tests

* cleaning up diff

* cleaning up diff

* comments

* linters

* hotfix: dont change kernels

---------

Co-authored-by: qazal <[email protected]>
 2024-08-18 19:57:51 +03:00
chenyuandGitHub f7950fc2b6 add E275 missing-whitespace-after-keyword linting rule (#6149) 
requires space after keywords like `assert`, `not`, `return`, `else`
 2024-08-17 16:44:34 -04:00
George HotzandGitHub 88edc2902d axis_is_masked with graph_rewrite [run_process_replay] (#6144) 2024-08-17 10:28:49 -07:00
qazalandGitHub d1d41130cd use membufs in ImageDType checks [run_process_replay] (#6136) 
* use membufs in ImageDType checks

* set by key [run_process_replay]
 2024-08-17 16:17:46 +03:00
qazalandGitHub 41ac8bdd63 verify_ast prep refactor for intermediate uops type spec (#6135) 
* refactor to ops

* refactor to two functions

* the uop's shape become local_reduce
 2024-08-17 15:34:18 +03:00
qazalandGitHub d9ce664350 add test_verify_ast [run_process_replay] (#6134) 2024-08-17 14:14:30 +03:00
qazalandGitHub 151a62ad32 hotfix: store dtype for ImageDType (#6133) 2024-08-17 13:44:53 +03:00
George HotzandGitHub 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 HotzandGitHub 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 HotzandGitHub 9bc81c6db4 UOps.SHAPETRACKER (#6129) 
* UOps.SHAPETRACKER [run_process_replay]

* no process replay
 2024-08-16 23:26:34 -07:00
George HotzandGitHub 5048066e79 st_arg, never -1 [run_process_replay] (#6128) 2024-08-16 22:46:56 -07:00
geohot 9e6ad4b40f hotfix: free minor speedup 2024-08-16 21:08:03 -07:00
George HotzandGitHub 912f01ed4b UOpGraph -> linearize_uop [run_process_replay] (#6119) 2024-08-16 19:48:39 -07:00
George HotzandGitHub 7cae152aa2 move uop logic into shapetracker [run_process_replay] (#6118) 2024-08-16 17:47:15 -07:00
George HotzandGitHub 89c7989659 no shapetracker in ops [run_process_replay] (#6117) 2024-08-16 17:23:27 -07:00
George HotzandGitHub 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
qazalGitHubchenyu
 		28c75bf2a6 merge uops with ops (#6111) 
Co-authored-by: chenyu <[email protected]>
 2024-08-16 18:17:57 -04:00
qazalandGitHub 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 HotzandGitHub 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
CaltropHungertonGitHubGeorge Hotz
 		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 <[email protected]>
 2024-08-16 09:19:21 -07:00
George HotzandGitHub f82ecd8802 remove uop symobilc rendering [run_process_replay] (#6108) 2024-08-16 09:02:15 -07:00
chenyuandGitHub e5da88873b enable UOP_IS_SYMBOLIC (#5954) 2024-08-16 00:15:46 -04:00
George HotzandGitHub c850e03758 new test for e2e compile failures (#6101) 
* new test for e2e compile failures

* fix bug
 2024-08-15 18:56:22 -07:00
chenyuandGitHub 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
qazalandGitHub 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
chenyuandGitHub 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
qazalandGitHub 25dffb2079 kernel.py more typing [run_process_replay] (#6092) 2024-08-15 17:59:24 +03:00
qazalandGitHub 4d38fec8c1 rename lazyops to parents [run_process_replay] (#6091) 2024-08-15 17:27:32 +03:00
chenyuandGitHub 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
chenyuandGitHub df03dca6e3 move % inside UOp mod_folding and remove deprecated tests (#6085) 
[run_process_replay]
 2024-08-14 23:25:10 -04:00
chenyuandGitHub 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
chenyuandGitHub a61cb1ff7c move mod mod pattern into generic mod folding (#6077) 2024-08-14 16:24:21 -04:00
chenyuandGitHub de773b593e remove redundant div gcd patterns [run_process_replay] (#6076) 
covered by generic div_folding
 2024-08-14 13:18:28 -04:00
chenyuandGitHub 1782e4f64d use div folding to do lt folding (#6065) 2024-08-13 16:59:05 -04:00
qazalandGitHub 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
andredapratoandGitHub 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
chenyuandGitHub 45bd667a78 rewrite pyint after first rewrite [run_process_replay] (#6059) 2024-08-12 19:18:13 -04:00
qazalandGitHub 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
chenyuandGitHub 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
chenyuandGitHub 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
chenyuandGitHub 7ce716b3a0 bigint -> pyint [run_process_replay] (#6040) 
it's a python int. priority should be  higher than bool, but we are not using it in type promo now.
 2024-08-12 09:12:23 -04:00
qazalandGitHub 059dd35985 minor UOps.RANGE ordering cleanup [run_process_replay] (#6039) 
* range srcs has an extra phi filter

* inline comments _tend_ to be harder to read
 2024-08-12 15:33:26 +03:00