forked from tinygrad/tinygrad
cheeetooandGitHub
a0965ee198
* models matrix * fix typo and install gpu deps * install llvm deps if needed * fix * testops with cuda * remove pip cache since not work * cuda env * install cuda deps * maybe it will work now * i can't read * all tests in matrix * trim down more * opencl stuff in matrix * opencl pip cache * test split * change cuda test exclusion * test * fix cuda maybe * add models * add more n=auto * third thing * fix bug * cache pip more * change name * update tests * try again cause why not * balance * try again... * try apt cache for cuda * try on gpu: * try cuda again * update packages step * replace libz-dev with zlib1g-dev * only cache cuda * why error * fix gpuocelot bug * apt cache err * apt cache to slow? * opt and image in single runner * add a couple n=autos * remove test matrix * try cuda apt cache again * libz-dev -> zlib1g-dev * remove -s since not supported by xdist * the cache takes too long and doesn't work * combine webgpu and metal tests * combine imagenet to c and cpu tests * torch tests with linters * torch back by itself * small windows clang test with torch tests * fix a goofy windows bug * im dumb * bro * clang with linters * fix pylint error * linter not work on windows * try with clang again * clang and imagenet? * install deps * fix * fix quote * clang by itself (windows too slow) * env vars for imagenet * cache pip for metal and webgpu tests * try torch with metal and webgpu * doesn't work, too long * remove -v * try -n=logical * don't use logical * revert accidental thing * remove some prints unless CI * fix print unless CI * ignore speed tests for slow tests * clang windows in matrix (ubuntu being tested in imagenet->c test) * try manual pip cache * fix windows pip cache path * all manual pip cache * fix pip cache dir for macos * print_ci function in helpers * CI as variable, no print_ci * missed one * cuda tests with docker image * remove setup-python action for cuda * python->python3? * remove -s -v * try fix pip cache * maybe fix * try to fix pip cache * is this the path? * maybe cache pip * try again * create wheels dir * ? * cuda pip deps in dockerfile * disable pip cache for clang * image from ghcr instead of docker hub * why is clang like this * fast deps * try use different caches * remove the fast thing * try with lighter image * remove setup python for cuda * small docker and cuda fast deps * ignore a few more tests * cool docker thing (maybe) * oops * quotes * fix docker command * fix bug * ignore train efficientnet test * remove dockerfile (docker stuff takes too long) * remove docker stuff and normal cuda * oops * ignore the tests for cuda * does this work * ignore test_train on slow backends * add space * llvm ignore same tests as cuda * nvm * ignore lr scheduler tests * get some stats * fix ignore bug * remove extra ' * remove and * ignore test for llvm * change ignored tests and durationon all backends * fix * and -> or * ignore some more cuda tests * finally? * does this fix it * remove durations=0 * add some more tests to llvm * make last pytest more readable * fix * don't train efficientnet on cpu * try w/out pip cache * pip cache seems to be generally better * pytest file markers * try apt fast for cuda * use quick install for apt-fast * apt-fast not worth * apt-get to apt * fix typo * suppress warnings * register markers * disable debug on fuzz tests * change marker names * apt update and apt install in one command * update marker names in test.yml * webgpu pytest marker
71 lines
2.1 KiB
Python
71 lines
2.1 KiB
Python
#!/usr/bin/env python
|
|
import unittest
|
|
import numpy as np
|
|
from tinygrad.tensor import Tensor
|
|
from tinygrad.lazy import LAZY
|
|
from tinygrad.ops import GlobalCounters
|
|
from tinygrad.graph import nm
|
|
import pytest
|
|
|
|
pytestmark = pytest.mark.webgpu
|
|
|
|
N = 200 # has to be bigger than the cache to fail
|
|
|
|
class TestAssign(unittest.TestCase):
|
|
def test_simple_assignment(self):
|
|
a = Tensor(np.arange(N*N, dtype=np.float32)).reshape(N,N)
|
|
b = Tensor(np.arange(N*N, dtype=np.float32)).reshape(N,N)
|
|
a.realize()
|
|
b.realize()
|
|
ba1 = a.lazydata.realized
|
|
bb1 = b.lazydata.realized
|
|
a += b
|
|
a.realize()
|
|
ba2 = a.lazydata.realized
|
|
if LAZY: assert ba1 == ba2 and ba1 != bb1
|
|
np.testing.assert_allclose(a.numpy(), (np.arange(N*N)*2).reshape((N,N)))
|
|
|
|
def test_permuted_assignment(self):
|
|
a = Tensor(np.arange(N*N, dtype=np.float32)).reshape(N,N)
|
|
b = Tensor(np.arange(N*N, dtype=np.float32)).reshape(N,N)
|
|
a.realize()
|
|
b.realize()
|
|
ba1 = a.lazydata.realized
|
|
bb1 = b.lazydata.realized
|
|
a = a.permute(1,0)
|
|
a += b
|
|
a.realize()
|
|
ba2 = a.lazydata.realized
|
|
assert ba1 != ba2 and ba1 != bb1
|
|
np.testing.assert_allclose(a.numpy(), np.arange(N*N).reshape((N,N)) + np.arange(N*N).reshape((N,N)).transpose(1,0))
|
|
|
|
def test_post_permuted_assignment(self):
|
|
a = Tensor(np.arange(N*N, dtype=np.float32)).reshape(N,N)
|
|
b = Tensor(np.arange(N*N, dtype=np.float32)).reshape(N,N)
|
|
a.realize()
|
|
b.realize()
|
|
#GlobalCounters.cache = []
|
|
ba1 = a.lazydata.realized
|
|
bb1 = b.lazydata.realized
|
|
a.assign(a.permute(1,0) + b) # this should not work!
|
|
a.realize()
|
|
ba2 = a.lazydata.realized
|
|
# NOTE: don't test that it's assigned
|
|
#assert ba1 == ba2 and ba1 != bb1
|
|
|
|
"""
|
|
if len(GlobalCounters.cache):
|
|
runner, args = GlobalCounters.cache[0]
|
|
b0, b1, b2 = args
|
|
print(nm(b0), id(b0.cl))
|
|
print(nm(b1), id(b1.cl))
|
|
print(nm(b2), id(b2.cl))
|
|
"""
|
|
|
|
np.testing.assert_allclose(a.numpy(), np.arange(N*N).reshape((N,N)) + np.arange(N*N).reshape((N,N)).transpose(1,0))
|
|
|
|
# TODO: is there a way to sneak in a permute such that it returns the wrong answer?
|
|
|
|
if __name__ == "__main__":
|
|
unittest.main()
|