github/tinygrad
1
1
Fork 0
mirror of https://github.com/tinygrad/tinygrad.git synced 2026-01-26 07:18:40 -05:00
Code Issues Packages Projects Releases Wiki Activity
3,328 Commits 206 Branches 14 Tags
v0.8.0
Commit Graph

57 Commits

Author SHA1 Message Date
chenyu
1d730b8853 remove ACCUM_FP32 in simple_matmul.py (#3045) 
* remove ACCUM_FP32 in simple_matmul.py

accumate for half inputs is always in float

* move test llama compile speed to metal
 2024-01-08 17:37:57 -05:00
George Hotz
a280cfe169 move dtypes to dtype.py (#2964) 
* move dtypes to dtype.py

* fix urllib
 2024-01-01 14:58:48 -08:00
George Hotz
c81ce9643d move globalcounters to ops (#2960) 
* move globalcounters to ops

* missed a few

* sick of that failing
 2024-01-01 14:21:02 -08:00
George Hotz
7da2325dc7 get_lazyops() -> lazyops (#2884) 
* get_lazyops() -> lazyops

* don't compare empty mem
 2023-12-20 18:04:49 -08:00
Rory Clear
f409b57854 update metal matmul and matvec for new device style (#2732) 
* update for new device style

* create device before compile

---------

Co-authored-by: chenyu <chenyu@fastmail.com>
 2023-12-17 16:15:07 -05:00
Nguyen Nguyen Phuong
07cf45e133 fix cuda matmul (#2725) 2023-12-12 07:59:31 -08:00
George Hotz
b5fd160b39 hotfix: increase rtol on simple_matmul 2023-12-11 10:10:29 -08:00
George Hotz
a73579919f mlx benchmark, a lil slower than tg 2023-12-05 19:00:43 -08:00
George Hotz
0be5d16950 only 62 gflops (#2629) 2023-12-05 13:28:24 -08:00
Yixiang Gao
fde44aed76 update hip_matmul with new abstraction (#2605) 2023-12-04 13:37:10 -08:00
Jake
5588922884 Update cuda_matmul.py (#2495) 2023-11-28 19:46:01 -08:00
George Hotz
3f137b134a jax parallel matmul example 2023-11-28 13:48:11 -08:00
Davi Silva
186ac77ec3 Update hip_matmul.py (#2480) 2023-11-27 18:36:19 -08:00
George Hotz
9e07824542 move device to device.py (#2466) 
* move device to device.py

* pylint test --disable R,C,W,E --enable E0611

* fix tests
 2023-11-27 11:34:37 -08:00
George Hotz
0cbf6c1811 move things, clean up extra (#2292) 
* move things

* idk why pylint needs that now

* delete unused
 2023-11-13 20:18:40 -08:00
Rory Clear
553688f12a update metal matmul and matvec for compile api (#2238) 2023-11-08 08:08:35 -08:00
George Hotz
2f7aab3d13 move optimize_local_size (#2221) 
* move optimize_local_size

* interpret_ast
 2023-11-05 21:00:52 -08:00
George Hotz
5472a14544 openpilot compile2 (#1977) 
* start compile2

* tweak

* why are there two more kernels?

* minor cleanups

* don't break onnx tests

* add __metadata__ support to safetensors

* no early realize in onnx

* cleanups

* bugfix

* clean up image type, add optimize

* opt to match old

* try that

* opt work

* run compile2

* optimizer

* prt more

* prerealize

* imp

* NOLOCALS works

* no locals means no locals

* support fractional globals

* all locals welcome

* int that

* cleanups

* show gemv regression

* clean up diff

* use idx for the cond

* nolocals

---------

Co-authored-by: Comma Device <device@comma.ai>
 2023-10-15 20:39:46 -07:00
George Hotz
8db92bd060 fix tvm gemm example 2023-10-08 05:57:41 -07:00
Francis Lam
dece9958f8 wmma: clean up to make WMMA arg order consistent (#2014) 
also add cache defeat to extra/gemm/simple_matmul.py
 2023-10-07 17:45:40 -07:00
Francis Lam
0ba75c4370 optimizer: add matvec optimizations (#1972) 
* optimizer: add matvec optimizations

* renderer: fix alignment of shared memory in opencl
 2023-10-04 14:16:27 -07:00
George Hotz
717451a244 Revert "optimizer: add matvec optimizations (#1753)" (#1959) 
This reverts commit f520323054.
 2023-10-03 00:28:42 -07:00
Francis Lam
f520323054 optimizer: add matvec optimizations (#1753) 
* optimizer: add matvec optimizations

* Update optimizer.py

---------

Co-authored-by: George Hotz <72895+geohot@users.noreply.github.com>
 2023-10-03 00:01:59 -07:00
Francis Lam
f445e056ed wmma: add test and tensor core shape (#1925) 2023-09-28 18:04:28 -07:00
George Hotz
c36d0e3bd8 tvm import hook 2023-09-28 09:24:32 -07:00
qazal
d0e752003d fixes (#1893) 2023-09-22 07:20:27 +08:00
George Hotz
4613c9e77c add tvm example, formatting (#1813) 
* add tvm example

* no realize
 2023-09-07 11:50:41 -07:00
Pavol Rusnak
52a92bf95d use class Foo: instead of class Foo(): (#1797) 
* use class Foo: instead of class Foo():

* add ruff linter, copy settings from .flake8 to ruff.toml
 2023-09-06 12:20:25 -07:00
George Hotz
a6d842af7a move device to ops (#1646) 
* move device to ops

* mlops types

* 2 lines
 2023-08-23 08:30:17 -07:00
George Hotz
e464442adf WMMA for 7900XTX (#1563) 
* go

* hip no LRU

* work

* works

* 16 TFLOPS

* 29 TFLOPS

* 30 TFLOPS

* never mind, it's 60 TFLOPS

* fix metal WMMA

* put hip alloc back
 2023-08-19 09:07:23 -07:00
George Hotz
c417cd3c97 fast HIP gemm -> 100 TFLOPS (#1476) 
* fast HIP gemm

* wmma

* correct b

* fix spilling

* 60 TFLOPS

* 64 TFLOPS

* 65 TFLOPS
 2023-08-09 06:54:15 -07:00
David Hou
3300d0aeaf syncthreads before wmma (#1389) 
(venv) chaos@tiny3:~/tinygrad$ KX=2 KY=2 N=2048 python extra/gemm/hip_matmul.py
   4194304    289.60 us, would be  59322.55 GFLOPS matmul, 173.80 GB/s
 2023-07-31 17:05:49 -07:00
George Hotz
37fa7e96fb Revert "update editorconfig, enforce via CI (#1343)" (#1380) 
This reverts commit da2efecbe2.
 2023-07-31 10:35:50 -07:00
Pavol Rusnak
da2efecbe2 update editorconfig, enforce via CI (#1343) 
* update editorconfig to set unix-style newlines and trim whitespace

* add editorconfig github action to the CI

* fix whitespace
 2023-07-30 18:44:30 -07:00
George Hotz
67e34b356a good stuff from tensor cores branch (#1199) 2023-07-08 16:58:26 -07:00
George Hotz
b8dfbba703 hip_matmul: f16 gemm 2048x2048 gets 36 TFLOPS 2023-07-08 00:35:45 +00:00
George Hotz
e234bf2298 hip matmul : add K support 2023-06-28 19:54:33 +00:00
George Hotz
0e93b9642a hip matmul 2023-06-28 19:21:01 +00:00
Casey Primozic
805eef10dd Add tensorflow GEMM benchmark script (#1000) 
* Modelled closely after the existing torch benchmark script but just adapted slightly for tensorflow
 2023-06-18 10:57:45 -07:00
George Hotz
fe71282ba1 faster RDNA assembly backend (#990) 
* fast asm

* torch gemm
 2023-06-16 12:06:38 -07:00
George Hotz
90fff82c8a Rdna (#776) 
* assembler maybe

* custom asm

* rdna3 on quiet

* trigger crashes

* fixed notes

* non-fatal rdna2 crash

* Crash4

* improve rdna sniffer

* comments

* improve sniffer

* asm

* 131 TFLOPS RDNA3

* opt simple matmul

* todos
 2023-05-16 05:33:57 -07:00
George Hotz
59d0d168cd FLOAT16 off works 2023-04-19 15:34:56 -07:00
George Hotz
3d15769a8f 50 TFLOPS cuda matmul 2023-04-19 14:38:24 -07:00
George Hotz
0b5a0b9ba4 winograd comment 2023-04-16 03:36:51 -07:00
George Hotz
8b777af571 metal_conv gets over 10.4 TFLOPS... 2023-04-15 03:31:22 -07:00
George Hotz
d66e682205 metal matmul from tcores branch 2023-04-14 23:29:29 -07:00
George Hotz
68e45fca18 metal_matmul: bw and torch sync 2023-03-23 08:02:04 -07:00
George Hotz
bd6c3c31a9 compare to torch 2023-03-22 23:58:37 -07:00
George Hotz
c3a3db75c7 fix metal matmul example 2023-03-22 23:42:51 -07:00
George Hotz
1a039306d2 good changes from llama branch (#671) 
* good changes from llama

* transpose behavior changed
 2023-03-09 20:51:22 -08:00