Repository navigation
Fix the OpenCL CPU compiler crash in the one-work-group radix sort #3191
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
base: master
Are you sure you want to change the base?
Changes from all commits
File filter
Filter by extension
Conversations
Jump to
Diff view
Diff view
There are no files selected for viewing
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -412,3 +412,33 @@ def test_radix_argsort_size_1_axis(): | |
| x4 = dpt.reshape(dpt.arange(10, dtype="i1"), (1, 10)) | ||
| r4 = dpt.argsort(x4, axis=0, kind="radixsort") | ||
| assert dpt.asnumpy(r4 == 0).all() | ||
|
|
||
|
|
||
| # rows of every size class of the one-work-group radix sort above 256; on the | ||
| # CPU device int8 argsort came out unstable and some data types crashed the | ||
| # compiler at block sizes of 16 and more | ||
| @pytest.mark.parametrize("n", [257, 1025, 2049, 4096, 8193, 16384]) | ||
| @pytest.mark.parametrize("dtype", ["?", "i1", "u1", "i2", "i4", "i8"]) | ||
|
Comment on lines
+420
to
+421
Contributor
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. This misses two size classes: 513..1024 and 4097..8192 (2049 and 4096 share one, 8193 and 16384 another). On master, int8 rows of 8192 crash the CPU compiler too. |
||
| @pytest.mark.parametrize("descending", [False, True]) | ||
| def test_radix_sort_one_work_group(n, dtype, descending): | ||
| q = get_queue_or_skip() | ||
| skip_if_dtype_not_supported(dtype, q) | ||
|
|
||
| rng = np.random.default_rng(42) | ||
| if dtype == "?": | ||
| x_np = rng.integers(0, 2, size=(2, n)).astype(dtype) | ||
| else: | ||
| info = np.iinfo(dtype) | ||
| x_np = rng.integers(info.min, info.max, size=(2, n), dtype=dtype) | ||
| x = dpt.asarray(x_np, sycl_queue=q) | ||
|
|
||
| # stable in either order: ties keep the order of the input | ||
| _, ranks = np.unique(x_np, return_inverse=True) | ||
| ranks = ranks.reshape(x_np.shape) | ||
| expected_inds = np.argsort(-ranks if descending else ranks, kind="stable") | ||
| expected = np.take_along_axis(x_np, expected_inds, axis=-1) | ||
|
|
||
| s = dpt.sort(x, descending=descending, kind="radixsort") | ||
| assert_array_equal(dpt.asnumpy(s), expected) | ||
| inds = dpt.argsort(x, descending=descending, kind="radixsort") | ||
| assert_array_equal(dpt.asnumpy(inds), expected_inds) | ||
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Is it the same as CMPLRLLVM-79305?