github/tinygrad
1
1
Fork 0
mirror of https://github.com/tinygrad/tinygrad.git synced 2026-04-29 03:00:14 -04:00
Code Issues Packages Projects Releases Wiki Activity
8,167 Commits 248 Branches 14 Tags
cde4fd3be3647104dbacdc488cce0ea746afca4f
Commit Graph

101 Commits

Author SHA1 Message Date
Ignacio Sica
459d0cd14f add arch to AMDRenderer and HIPRenderer (#9431) 2025-03-13 13:06:27 -03:00
chenyu
7ea633f94f remove from __future__ import annotations from runtimes [pr] (#8373) 
it's not needed if we move the Device before Program and Allocator, which need Device.

not updating hcq because it has a lot more stuff, and CLDevice requires CLDevice
 2024-12-21 23:46:07 -05:00
George Hotz
9c77e9f9b7 replace Tuple with tuple [pr] (#8344) 
* replace Tuple with tuple [pr]

* replace List with list [pr]

* replace Dict with dict [pr]

* replace Set with set [pr]
 2024-12-19 21:27:56 -08:00
George Hotz
c5d458ce02 BufferSpec and ProgramSpec [pr] (#7814) 
* BufferSpec and ProgramSpec [pr]

* delete preallocate, it's unused

* Revert "delete preallocate, it's unused"

This reverts commit dcfcfaccde.
 2024-11-21 12:18:05 +08:00
George Hotz
6688539bc9 rename device to dev so Buffer can be Allocator [pr] (#7799) 
* rename device to dev to Buffer can be Allocator [pr]

* missed those

* update the Program classes also

* more renames

* oops
 2024-11-20 15:47:26 +08:00
George Hotz
d71fe7faa5 rename allocator methods to not conflict [pr] (#7788) 
* rename allocator methods to not conflict [pr]

* forgot those

* transfer + offset
 2024-11-20 00:10:29 +08:00
George Hotz
6bb230287b pass the src into Metal [pr] (#7518) 
* pass the src into Metal [pr]

* put that comment back

* keep old functionality

* move all to disassembler

* metal supports parallel beam

* touchups

* comment in correct place
 2024-11-04 12:35:30 +08:00
nimlgen
137ad5519f amd fix cwsr for gfx11 (#6950) 
* amd cwsr

* ()
 2024-10-08 17:44:29 +03:00
chenyu
471b188d79 fix mypy errors in latest mypy (#5794) 
* fix mypy errors in latest mypy

mypy has stricter partial and api arg checks now

* PYTHONPATH="."
 2024-07-29 14:53:30 -04:00
chenyu
9838c1a6ff update import style in runtime (#5735) 2024-07-26 14:00:23 -04:00
George Hotz
5c688560bc move CUDA/HIP compilers to their own files [run_process_replay] (#5732) 2024-07-26 10:00:15 -07:00
nimlgen
7b7b751513 simple hip backend for debugging (#5201) 
* hip backend

* fix mypy

* shorter

* fixes

* tiny changes
 2024-06-30 23:00:11 +03:00
George Hotz
53adcb34f5 remove hip backend (#3783) 
* remove hip backend

* remove unused

* rhip

* more RHIP
 2024-03-17 10:12:16 -07:00
Francis Lam
b6e2495fdd kernel: limit shared memory usage when adding opts (#3705) 
* kernel: limit shared memory usage when adding opts

* search: remove unnecessary limit on search space

apply_opt will do the more correct check
 2024-03-12 17:06:21 -04:00
George Hotz
fe97a85014 the compiler is a driver (#3427) 2024-02-16 10:18:09 +01:00
nimlgen
002bf380b0 hsa runtime (#3382) 
* hsa init

* handles transfer

* linter

* clean up hwqueue

* fix sync freezes

* print errors
 2024-02-15 14:14:34 +01:00
George Hotz
d1fb1e0ba4 full sync to fix HIP memory leak (#3364) 2024-02-10 11:50:27 +01:00
George Hotz
c32ea95d7d Python uop emulator (#3327) 
* start uop emu

* tiny_add passes

* more ops

* emulate the whole warp

* test_gemm passes

* metal gemm test pass

* works on big gemm

* works on big gemm

* more tests pass

* touch ups

* fix mypy

* cleanups

* exp2 mypy

* arch is where it belongs

* actually emulate tensor cores

* fix test

* new style
 2024-02-08 19:24:55 +01:00
qazal
5b46b0ff3d Simple RDNA3 emulator (#2974) 
* mockhip->hipcpu

* allocate buffers

* launch a kernel

read_asm api

* run remu in CI

* remu 0.0.2, real test ops

* simple driver

* 0.0.3, all test_ops

* run the latest emulator

* 9 minutes is way too long, drop backprop in CI

* bring back the backward pass

* Revert "bring back the backward pass"

This reverts commit 3781e1bc56.

* Print slowest tests

* emulated device directly in ops_hip

* fix ruff, override mypy for specific rules

* test in the same code path

- hip backend env variables

- install packages and verify autogen

- run certain tests

- remove the other hip tests path

- verify Device.DEFAULT

* remove the emulated hip in extra

---------

Co-authored-by: George Hotz <72895+geohot@users.noreply.github.com>
 2024-01-30 10:39:28 -08:00
George Hotz
3c728d1082 compiler support (#3260) 
* compiler support

* revert that

* fix tests
 2024-01-26 23:36:40 -08:00
George Hotz
473935125a use comgr to compile (#3248) 
* use comgr to compile

* fast

* bfloat16

* move comgr to it's own file

* cleaner style

* comgr in new place

* comgr free + dtype cleanup
 2024-01-26 18:27:49 -08:00
George Hotz
c4d870db0d fix jit realize issue (#3258) 2024-01-26 18:27:35 -08:00
George Hotz
03a6bc59c1 move autogen to runtime/autogen (#3254) 2024-01-26 12:44:19 -08:00
George Hotz
a3869ffd46 move gpuctypes in tree (#3253) 
* move gpuctypes in tree

* fix mypy

* regex exclude

* autogen sh

* mypy exclude

* does that fix it

* fix mypy

* add hip confirm

* verify all autogens

* build clang2py

* opencl headers

* gpu on 22.04
 2024-01-26 12:25:03 -08:00
George Hotz
7feeb118e6 hip launch speed (#3246) 
* faster HIP kernel launch

* args

* expand compile_hip
 2024-01-25 15:13:55 -08:00
George Hotz
cb372b053f add device speed test (#3244) 2024-01-25 12:01:22 -08:00
George Hotz
a8fbb03438 minor hip cleanups (#3237) 2024-01-24 15:13:38 -08:00
George Hotz
ed8a32722a hip mutex signal (#3234) 
* hip mutex

* hip mutex 2

* sync
 2024-01-24 13:23:09 -08:00
George Hotz
47f9887ce4 hip events work (#3229) 
* hip events work

* event
 2024-01-24 11:49:53 -08:00
George Hotz
e2e4632aea LoadOps SYNC (#3223) 
* LoadOps SYNC and WAIT

* no wait, only sync

* DEBUG >= 1

* track cross device
 2024-01-23 21:59:18 -08:00
George Hotz
23b084e70a add device name to device, all are constructed (#3221) 2024-01-23 20:34:56 -08:00
George Hotz
4a07ea355d buffer options should work (#3211) 
* buffer options should work

* minor

* fix dtype
 2024-01-22 19:23:55 -08:00
George Hotz
c80884884e event driven hip (#3160) 
* event driven hip

* simpler, src makes copy

* pass mypy
 2024-01-18 14:35:18 -08:00
George Hotz
9cc2577a08 use hip events (#3157) 
* use hip events

* cleanup
 2024-01-17 10:39:57 -08:00
nimlgen
81ae4ea179 compile cache for several devices (#3148) 
* compile cache for several devices

* ops_gpu uses hash to not care about sql

* hip rdna test with device

* linter happy

* no device passed where possible

* arch is optional to compile_{hip|cuda}
 2024-01-16 11:45:26 -08:00
George Hotz
120c8b1841 update llvm api + add cache key (#3140) 
* update llvm api + add cache key

* use_xcode is a different function

* types
 2024-01-15 17:25:32 -08:00
nimlgen
cf1d0a6704 no exceptions in __del__ when module creation is failed in hip/cuda (#3107) 2024-01-13 12:03:55 -05:00
chenyu
0fe6904351 use device from LinearizerOptions in kernel search (#3090) 
* use device from LinearizerOptions in kernel search

removed all Device.DEFAULT in search.py

* pass device string for parallel pickle

* device for interpreted backends in LinearizerOptions
 2024-01-11 14:46:03 -05:00
George Hotz
60abc62a3f fast hip read (#3014) 
* fast hip read

* hip read faster

* fix tests

* to_mv

* simplify

* bump to 6k lines
 2024-01-05 10:33:13 -08:00
George Hotz
c2a044ed83 disk_read_speed example 2024-01-04 13:59:43 -08:00
George Hotz
65dc3700b7 hip device is default on supported platforms (#2993) 2024-01-03 13:42:13 -08:00
George Hotz
753a7ecc05 Hip driver (#2992) 
* start hip driver

* fix hip llama

* make HIP default if we can

* don't change those
 2024-01-03 12:53:47 -08:00
George Hotz
56f44bd10e move the compiler cache to be global (#2957) 
* move the compiler cache to be global

* remove non robust test

* remove dead code
 2024-01-01 10:59:56 -08:00
George Hotz
6617dcf095 move graph to runtime, check line count with sz.py (#2842) 
* move graph to runtime, check line count with sz.py

* oops, didn't save

* dtype aliases

* restore comment, REALCOUNT
 2023-12-18 20:30:06 -08:00
George Hotz
6d6eb9302d ruff checks the max line length is 150 (#2734) 
* ruff checks the max line length is 150

* fix tensor.py

* a lot more

* done
 2023-12-12 17:34:47 -08:00
George Hotz
0fd44259cd bf16 fix + cleanups from mixtral (#2698) 
* bf16 fix + cleanups from mixtral

* generic bf16 cast
 2023-12-10 16:31:52 -08:00
George Hotz
4164d0ebbd multitensor start (#2676) 
* multitensor work

* early gen fixes the tests

* atol for flaky test
 2023-12-07 17:07:05 -08:00
George Hotz
41d696145d hotfix: forking works okay in HIP now 2023-12-04 21:59:18 +00:00
George Hotz
09b6e254a3 hip compile speed (#2606) 2023-12-04 13:47:40 -08:00
George Hotz
664475f247 vals is an argument (#2599) 
* vals is an argument

* don't even know how that's legal python
 2023-12-03 21:50:43 -08:00