Source: rocblas Section: devel Homepage: https://github.com/rocmsoftwareplatform/rocblas Priority: optional Standards-Version: 4.6.2 Vcs-Git: https://salsa.debian.org/rocm-team/rocblas.git Vcs-Browser: https://salsa.debian.org/rocm-team/rocblas Maintainer: Debian ROCm Team Uploaders: Maxime Chambonnet , Cordell Bloor , Christian Kastner , Build-Depends: debhelper-compat (= 13), cmake, gfortran, python3-venv, python3-yaml, python3-msgpack, hipcc (>= 5.6.1~), libamd-comgr-dev (>= 6.0~), libhsa-runtime-dev (>= 5.7.1~), llvm-17, rocm-cmake (>= 5.3.0), libmsgpack-cxx-dev, libblas-dev , libgtest-dev Build-Depends-Indep: dh-sequence-sphinxdoc , doxygen , python3-breathe , python3-sphinx , python3-sphinx-rtd-theme , libjs-jquery , libjs-mathjax , libjs-sphinxdoc , libjs-underscore Rules-Requires-Root: no Package: librocblas0 Section: libs Architecture: amd64 arm64 ppc64el Depends: ${misc:Depends}, ${shlibs:Depends}, Description: ROCm library for basic linear algebra - library rocBLAS is a library for performing basic linear algebra routines on AMD GPUs. It provides implementations of BLAS operations such as dot product (DOT), general matrix multiplication (GEMM), triangular matrix multiplication (TRMM), and many others. It is built on the AMD ROCm platform and optimized for discrete AMD GPUs. The rocBLAS library is implemented in the HIP programming language and is supplemented by tuned assembly kernels. . rocBLAS provides a C99 interface and supports operations on matrices of half-, single- or double-precision floating point numbers. The library provides variants for its routines that efficiently operate on batches of matrices and that support a variety of data layouts. . This package provides the AMD ROCm rocBLAS library. Package: librocblas-dev Section: libdevel Architecture: amd64 arm64 ppc64el Depends: librocblas0 (= ${binary:Version}),${misc:Depends}, ${shlibs:Depends}, libamdhip64-dev, Suggests: librocblas-doc Description: ROCm library for basic linear algebra - headers rocBLAS is a library for performing basic linear algebra routines on AMD GPUs. It provides implementations of BLAS operations such as dot product (DOT), general matrix multiplication (GEMM), triangular matrix multiplication (TRMM), and many others. It is built on the AMD ROCm platform and optimized for discrete AMD GPUs. The rocBLAS library is implemented in the HIP programming language and is supplemented by tuned assembly kernels. . rocBLAS provides a C99 interface and supports operations on matrices of half-, single- or double-precision floating point numbers. The library provides variants for its routines that efficiently operate on batches of matrices and that support a variety of data layouts. . This package provides the AMD ROCm rocBLAS development headers. Package: librocblas0-tests Section: libdevel Architecture: amd64 arm64 ppc64el Depends: librocblas0 (= ${binary:Version}),${misc:Depends}, ${shlibs:Depends}, librocblas0-tests-data Build-Profiles: Description: ROCm library for basic linear algebra - tests rocBLAS is a library for performing basic linear algebra routines on AMD GPUs. It provides implementations of BLAS operations such as dot product (DOT), general matrix multiplication (GEMM), triangular matrix multiplication (TRMM), and many others. It is built on the AMD ROCm platform and optimized for discrete AMD GPUs. The rocBLAS library is implemented in the HIP programming language and is supplemented by tuned assembly kernels. . rocBLAS provides a C99 interface and supports operations on matrices of half-, single- or double-precision floating point numbers. The library provides variants for its routines that efficiently operate on batches of matrices and that support a variety of data layouts. . This package provides the AMD ROCm rocBLAS test binaries used for verifying that the library is functioning correctly. These binaries are only used to check whether rocBLAS works correctly on a given GPU, so generally speaking, users probably don't need this package. Package: librocblas0-tests-data Section: libdevel Architecture: all Depends: ${misc:Depends}, Build-Profiles: Description: ROCm library for basic linear algebra - test data rocBLAS is a library for performing basic linear algebra routines on AMD GPUs. It provides implementations of BLAS operations such as dot product (DOT), general matrix multiplication (GEMM), triangular matrix multiplication (TRMM), and many others. It is built on the AMD ROCm platform and optimized for discrete AMD GPUs. The rocBLAS library is implemented in the HIP programming language and is supplemented by tuned assembly kernels. . rocBLAS provides a C99 interface and supports operations on matrices of half-, single- or double-precision floating point numbers. The library provides variants for its routines that efficiently operate on batches of matrices and that support a variety of data layouts. . This package provides the data files required by the AMD ROCm rocBLAS tests. The tests are only used to check whether rocBLAS works correctly on a given GPU, so generally speaking, users probably don't need this package. Package: librocblas-doc Section: doc Architecture: all Multi-Arch: foreign Build-Profiles: Depends: ${misc:Depends}, ${sphinxdoc:Depends}, libjs-mathjax, Breaks: librocblas-dev (<< 5.5.1+dfsg-5~) Replaces: librocblas-dev (<< 5.5.1+dfsg-5~) Description: ROCm library for basic linear algebra - documentation rocBLAS is a library for performing basic linear algebra routines on AMD GPUs. It provides implementations of BLAS operations such as dot product (DOT), general matrix multiplication (GEMM), triangular matrix multiplication (TRMM), and many others. It is built on the AMD ROCm platform and optimized for discrete AMD GPUs. The rocBLAS library is implemented in the HIP programming language and is supplemented by tuned assembly kernels. . rocBLAS provides a C99 interface and supports operations on matrices of half-, single- or double-precision floating point numbers. The library provides variants for its routines that efficiently operate on batches of matrices and that support a variety of data layouts. . This package provides the AMD ROCm rocBLAS documentation.