Ubuntu
rocsparse package

rocsparse 5.5.1-1 source package in Ubuntu

Changelog

rocsparse (5.5.1-1) unstable; urgency=medium

  * New upstream version 5.5.1
  * d/rules: drop gfx1011 architecture from librocsparse0.
    The HIP runtime will fall back to using gfx1010.
  * d/rules: use compressed DWARF 5 debug symbols
  * Fix FTBFS with Sphinx 7.1 by specifying full filepath to local
    copy of MathJax.js (Closes: #1042702).

 -- Cordell Bloor <email address hidden>  Sun, 30 Jul 2023 20:18:24 -0600

Upload details

Uploaded by:
Debian Deep Learning Team
Uploaded to:
Sid
Original maintainer:
Debian Deep Learning Team
Architectures:
amd64 arm64 ppc64el all
Section:
misc
Urgency:
Medium Urgency

See full publishing history Publishing

Series Pocket Published Component Section
Mantic release universe misc

Downloads

File Size SHA-256 Checksum
rocsparse_5.5.1-1.dsc 2.8 KiB c0fa90adcc561012b37e742f3ad82be305ce2360da907751a1a9ca552bc739fc
rocsparse_5.5.1.orig.tar.gz 1.1 MiB 1dd2d18898dfebdf898e8fe7d1c1198e8f8451fd70ff12a1990ec1419cf359e1
rocsparse_5.5.1-1.debian.tar.xz 10.3 KiB 198cc57dba1e6fa65660da94a07aad0c89536beed10e2c1548b59f126a319364

Available diffs

No changes file available.

Binary packages built by this source

librocsparse-dev: ROCm library for sparse linear algebra - headers

 rocSPARSE is a library that implements BLAS operations for sparse data
 structures. It is built on the AMD ROCm platform and optimized for
 discrete AMD GPUs.
 .
 rocSPARSE provides a C99 API containing sparse level 1, sparse level 2 and
 sparse level 3 BLAS functions, as well as general matrix multiplication
 between dense and sparse matricies (GEMMI), sparse preconditioner functions,
 sparse matrix format conversion functions, and sparse matrix reordering
 functions.
 .
 It supports a variety of sparse matrix formats, including coordinate list
 in either array of structure form (COO) or structure of array form (COO SOA),
 compressed sparse row (CSR) or column (CSC), block compressed sparse row
 (BSR), general block compressed sparse row (GEBSR), and the ELLPACK-ITPACK
 format (ELL).
 .
 This package provides the AMD ROCm rocSPARSE development headers.

librocsparse-doc: ROCm library for sparse linear algebra - documentation

 rocSPARSE is a library that implements BLAS operations for sparse data
 structures. It is built on the AMD ROCm platform and optimized for
 discrete AMD GPUs.
 .
 rocSPARSE provides a C99 API containing sparse level 1, sparse level 2 and
 sparse level 3 BLAS functions, as well as general matrix multiplication
 between dense and sparse matricies (GEMMI), sparse preconditioner functions,
 sparse matrix format conversion functions, and sparse matrix reordering
 functions.
 .
 It supports a variety of sparse matrix formats, including coordinate list
 in either array of structure form (COO) or structure of array form (COO SOA),
 compressed sparse row (CSR) or column (CSC), block compressed sparse row
 (BSR), general block compressed sparse row (GEBSR), and the ELLPACK-ITPACK
 format (ELL).
 .
 This package provides the AMD ROCm rocSPARSE documentation.

librocsparse0: ROCm library for sparse linear algebra - library

 rocSPARSE is a library that implements BLAS operations for sparse data
 structures. It is built on the AMD ROCm platform and optimized for
 discrete AMD GPUs.
 .
 rocSPARSE provides a C99 API containing sparse level 1, sparse level 2 and
 sparse level 3 BLAS functions, as well as general matrix multiplication
 between dense and sparse matricies (GEMMI), sparse preconditioner functions,
 sparse matrix format conversion functions, and sparse matrix reordering
 functions.
 .
 It supports a variety of sparse matrix formats, including coordinate list
 in either array of structure form (COO) or structure of array form (COO SOA),
 compressed sparse row (CSR) or column (CSC), block compressed sparse row
 (BSR), general block compressed sparse row (GEBSR), and the ELLPACK-ITPACK
 format (ELL).
 .
 This package provides the AMD ROCm rocSPARSE library.

librocsparse0-dbgsym: debug symbols for librocsparse0
librocsparse0-tests: ROCm library for sparse linear algebra - tests

 rocSPARSE is a library that implements BLAS operations for sparse data
 structures. It is built on the AMD ROCm platform and optimized for
 discrete AMD GPUs.
 .
 rocSPARSE provides a C99 API containing sparse level 1, sparse level 2 and
 sparse level 3 BLAS functions, as well as general matrix multiplication
 between dense and sparse matricies (GEMMI), sparse preconditioner functions,
 sparse matrix format conversion functions, and sparse matrix reordering
 functions.
 .
 It supports a variety of sparse matrix formats, including coordinate list
 in either array of structure form (COO) or structure of array form (COO SOA),
 compressed sparse row (CSR) or column (CSC), block compressed sparse row
 (BSR), general block compressed sparse row (GEBSR), and the ELLPACK-ITPACK
 format (ELL).
 .
 This package provides the AMD ROCm rocSPARSE test binaries used for verifying
 that the library is functioning correctly. These binaries are only used to
 check whether rocSPARSE works correctly on a given GPU, so generally speaking,
 users probably don't need this package.

librocsparse0-tests-data: ROCm library for sparse linear algebra - test data

 rocSPARSE is a library that implements BLAS operations for sparse data
 structures. It is built on the AMD ROCm platform and optimized for
 discrete AMD GPUs.
 .
 rocSPARSE provides a C99 API containing sparse level 1, sparse level 2 and
 sparse level 3 BLAS functions, as well as general matrix multiplication
 between dense and sparse matricies (GEMMI), sparse preconditioner functions,
 sparse matrix format conversion functions, and sparse matrix reordering
 functions.
 .
 It supports a variety of sparse matrix formats, including coordinate list
 in either array of structure form (COO) or structure of array form (COO SOA),
 compressed sparse row (CSR) or column (CSC), block compressed sparse row
 (BSR), general block compressed sparse row (GEBSR), and the ELLPACK-ITPACK
 format (ELL).
 .
 This package provides the data files required by the AMD ROCm rocSPARSE tests.
 The tests are only used to check whether rocSPARSE works correctly on a given
 GPU, so generally speaking, users probably don't need this package.

librocsparse0-tests-dbgsym: debug symbols for librocsparse0-tests