#1064809 libhipsparse0-tests: csr2bsr test failures

Package:
libhipsparse0-tests
Source:
libhipsparse0-tests
Description:
portable interface for sparse linear algebra on the GPU - tests
Submitter:
Cordell Bloor
Date:
2024-02-26 10:51:03 UTC
Severity:
normal
#1064809#5
Date:
2024-02-26 06:23:27 UTC
From:
To:
Dear Maintainer,

The update of rocsparse 5.5.1 to 5.7.1 seems to have caused a regression
in hipsparse. Although, it's also possible that this problem was because
rocsparse was therefore rebuilt with the updated rocprim 5.7.1.

The failing tests are:

[  FAILED  ] 128 tests, listed below:
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float/86, where GetParam() = (0, 0, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float/87, where GetParam() = (0, 0, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float/100, where GetParam() = (0, 623, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float/101, where GetParam() = (0, 623, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float/114, where GetParam() = (0, 12766, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float/115, where GetParam() = (0, 12766, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float/128, where GetParam() = (0, 29285, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float/129, where GetParam() = (0, 29285, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float/156, where GetParam() = (872, 0, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float/157, where GetParam() = (872, 0, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float/170, where GetParam() = (872, 623, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float/171, where GetParam() = (872, 623, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float/184, where GetParam() = (872, 12766, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float/185, where GetParam() = (872, 12766, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float/198, where GetParam() = (872, 29285, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float/199, where GetParam() = (872, 29285, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float/226, where GetParam() = (13095, 0, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float/227, where GetParam() = (13095, 0, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float/240, where GetParam() = (13095, 623, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float/241, where GetParam() = (13095, 623, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float/254, where GetParam() = (13095, 12766, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float/255, where GetParam() = (13095, 12766, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float/268, where GetParam() = (13095, 29285, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float/269, where GetParam() = (13095, 29285, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float/296, where GetParam() = (21453, 0, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float/297, where GetParam() = (21453, 0, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float/310, where GetParam() = (21453, 623, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float/311, where GetParam() = (21453, 623, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float/324, where GetParam() = (21453, 12766, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float/325, where GetParam() = (21453, 12766, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float/338, where GetParam() = (21453, 29285, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float/339, where GetParam() = (21453, 29285, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double/86, where GetParam() = (0, 0, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double/87, where GetParam() = (0, 0, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double/100, where GetParam() = (0, 623, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double/101, where GetParam() = (0, 623, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double/114, where GetParam() = (0, 12766, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double/115, where GetParam() = (0, 12766, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double/128, where GetParam() = (0, 29285, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double/129, where GetParam() = (0, 29285, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double/156, where GetParam() = (872, 0, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double/157, where GetParam() = (872, 0, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double/170, where GetParam() = (872, 623, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double/171, where GetParam() = (872, 623, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double/184, where GetParam() = (872, 12766, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double/185, where GetParam() = (872, 12766, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double/198, where GetParam() = (872, 29285, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double/199, where GetParam() = (872, 29285, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double/226, where GetParam() = (13095, 0, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double/227, where GetParam() = (13095, 0, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double/240, where GetParam() = (13095, 623, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double/241, where GetParam() = (13095, 623, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double/254, where GetParam() = (13095, 12766, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double/255, where GetParam() = (13095, 12766, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double/268, where GetParam() = (13095, 29285, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double/269, where GetParam() = (13095, 29285, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double/296, where GetParam() = (21453, 0, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double/297, where GetParam() = (21453, 0, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double/310, where GetParam() = (21453, 623, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double/311, where GetParam() = (21453, 623, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double/324, where GetParam() = (21453, 12766, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double/325, where GetParam() = (21453, 12766, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double/338, where GetParam() = (21453, 29285, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double/339, where GetParam() = (21453, 29285, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float_complex/86, where GetParam() = (0, 0, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float_complex/87, where GetParam() = (0, 0, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float_complex/100, where GetParam() = (0, 623, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float_complex/101, where GetParam() = (0, 623, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float_complex/114, where GetParam() = (0, 12766, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float_complex/115, where GetParam() = (0, 12766, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float_complex/128, where GetParam() = (0, 29285, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float_complex/129, where GetParam() = (0, 29285, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float_complex/156, where GetParam() = (872, 0, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float_complex/157, where GetParam() = (872, 0, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float_complex/170, where GetParam() = (872, 623, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float_complex/171, where GetParam() = (872, 623, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float_complex/184, where GetParam() = (872, 12766, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float_complex/185, where GetParam() = (872, 12766, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float_complex/198, where GetParam() = (872, 29285, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float_complex/199, where GetParam() = (872, 29285, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float_complex/226, where GetParam() = (13095, 0, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float_complex/227, where GetParam() = (13095, 0, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float_complex/240, where GetParam() = (13095, 623, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float_complex/241, where GetParam() = (13095, 623, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float_complex/254, where GetParam() = (13095, 12766, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float_complex/255, where GetParam() = (13095, 12766, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float_complex/268, where GetParam() = (13095, 29285, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float_complex/269, where GetParam() = (13095, 29285, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float_complex/296, where GetParam() = (21453, 0, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float_complex/297, where GetParam() = (21453, 0, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float_complex/310, where GetParam() = (21453, 623, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float_complex/311, where GetParam() = (21453, 623, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float_complex/324, where GetParam() = (21453, 12766, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float_complex/325, where GetParam() = (21453, 12766, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float_complex/338, where GetParam() = (21453, 29285, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_float_complex/339, where GetParam() = (21453, 29285, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double_complex/86, where GetParam() = (0, 0, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double_complex/87, where GetParam() = (0, 0, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double_complex/100, where GetParam() = (0, 623, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double_complex/101, where GetParam() = (0, 623, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double_complex/114, where GetParam() = (0, 12766, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double_complex/115, where GetParam() = (0, 12766, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double_complex/128, where GetParam() = (0, 29285, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double_complex/129, where GetParam() = (0, 29285, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double_complex/156, where GetParam() = (872, 0, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double_complex/157, where GetParam() = (872, 0, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double_complex/170, where GetParam() = (872, 623, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double_complex/171, where GetParam() = (872, 623, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double_complex/184, where GetParam() = (872, 12766, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double_complex/185, where GetParam() = (872, 12766, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double_complex/198, where GetParam() = (872, 29285, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double_complex/199, where GetParam() = (872, 29285, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double_complex/226, where GetParam() = (13095, 0, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double_complex/227, where GetParam() = (13095, 0, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double_complex/240, where GetParam() = (13095, 623, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double_complex/241, where GetParam() = (13095, 623, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double_complex/254, where GetParam() = (13095, 12766, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double_complex/255, where GetParam() = (13095, 12766, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double_complex/268, where GetParam() = (13095, 29285, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double_complex/269, where GetParam() = (13095, 29285, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double_complex/296, where GetParam() = (21453, 0, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double_complex/297, where GetParam() = (21453, 0, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double_complex/310, where GetParam() = (21453, 623, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double_complex/311, where GetParam() = (21453, 623, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double_complex/324, where GetParam() = (21453, 12766, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double_complex/325, where GetParam() = (21453, 12766, 0, 0, 1, 1)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double_complex/338, where GetParam() = (21453, 29285, 0, 0, 1, 0)
[  FAILED  ] csr2bsr/parameterized_csr2bsr.csr2bsr_double_complex/339, where GetParam() = (21453, 29285, 0, 0, 1, 1)
#1064809#10
Date:
2024-02-26 07:05:34 UTC
From:
To:
Interestingly, this passed on gfx900 [1].

(I checked a small sample of tests to check that they weren't just
being skipped)

[1]: https://ci.rocm.debian.net/packages/h/hipsparse/unstable/amd64+gfx900/
#1064809#15
Date:
2024-02-26 10:49:15 UTC
From:
To:
This one looks a bit tricky as it also seems to be GPU-arch dependent.

The following is all going by the logs of gfx1034 [1]:

One issue is that the test suite is often aborted early, so the csr2bsr
tests (from this bug) don't even get run. From the tail of the latest
log in experimental [2]:

The last fully completed run (no abort) was on 2024-01-27 [3], with a
runtime of 3m38s. And then the rocsparse-5.7.1 upgrade happens, and
indeed, after that update, no other successful completion can be seen,
suggesting that this might be a factor.

But, within the preceding 24hrs, we had two other test runs [4,5] abort
early -- with rocsparse=5.5.1-2.

Some of the earlier logs have more informative error messages prior to
the abort, eg:

I think these tests were all in VMs, I'll try to reproduce them on bare
metal just to be sure.

And to make things even more interesting, the test history of gfx1030
[6] suggests that rocsparse indeed was a factor. Tests on gfx1030 passed
until rocsparse=5.7.1-2, then failed, and now pass again with
hipsparse=5.7.1-1~exp1.

Best,
Christian

[1]: https://ci.rocm.debian.net/packages/h/hipsparse/unstable/amd64+gfx1034/
[2]: https://ci.rocm.debian.net/data/autopkgtest/unstable/amd64+gfx1034/h/hipsparse/7767/log.gz
[3]: https://ci.rocm.debian.net/data/autopkgtest/unstable/amd64+gfx1034/h/hipsparse/5234/log.gz
[4]: https://ci.rocm.debian.net/data/autopkgtest/unstable/amd64+gfx1034/h/hipsparse/5075/log.gz
[5]: https://ci.rocm.debian.net/data/autopkgtest/unstable/amd64+gfx1034/h/hipsparse/5003/log.gz