{"id":97,"date":"2014-11-28T17:53:16","date_gmt":"2014-11-28T16:53:16","guid":{"rendered":"https:\/\/project.inria.fr\/chameleon\/?page_id=97"},"modified":"2023-08-31T17:17:16","modified_gmt":"2023-08-31T15:17:16","slug":"links","status":"publish","type":"page","link":"https:\/\/project.inria.fr\/chameleon\/test-posts\/links\/","title":{"rendered":"Related libraries"},"content":{"rendered":"<p>To run Chameleon software binaries you will need to install dependencies, mainly :<\/p>\n<ol>\n<li>CPU\/GPU kernels (BLAS\/LAPACK, cuBLAS\/hipBLAS)<\/li>\n<li>A Runtime system (e.g. StarPU)<\/li>\n<li>Parallelization frameworks: pthread, MPI (optional) and CUDA\/ROCm (optional)<\/li>\n<\/ol>\n<p>Here is a list of links to dependencies :<\/p>\n<p align=\"justify\"><strong>1. CPU\/GPU kernels (BLAS\/LAPACK, cuBLAS\/hipBLAS):<\/strong><\/p>\n<ul>\n<li><b><u>BLAS\/LAPACK (with C interfaces cblas and lapacke enabled):<\/u><\/b> <a href=\"http:\/\/www.openblas.net\/\" target=\"_blank\" rel=\"noopener\">OpenBLAS<\/a>, <a href=\"https:\/\/github.com\/flame\/blis\">BLIS<\/a>\/<a href=\"https:\/\/github.com\/flame\/libflame\">FLAME<\/a>, <a href=\"https:\/\/software.intel.com\/en-us\/intel-mkl\" target=\"_blank\" rel=\"noopener\">Intel MKL<\/a>,\u00a0<a href=\"https:\/\/h41374.www4.hpe.com\/docs\/csml\/cray_libsci.html\">Cray libsci<\/a>, <a href=\"https:\/\/www.ibm.com\/docs\/en\/essl?topic=SSFHY8\/essl_content.htm\">IBM libessl<\/a>, <a href=\"https:\/\/www.netlib.org\/lapack\/\" target=\"_blank\" rel=\"noopener\">Reference BLAS\/LAPACK<\/a><\/li>\n<li><b><u>cuBLAS\/hipBLAS (optional)<\/u><\/b>: <a href=\"https:\/\/developer.nvidia.com\/cublas\" target=\"_blank\" rel=\"noopener\">NVIDIA cublas<\/a>, or <a href=\"https:\/\/github.com\/ROCmSoftwarePlatform\/hipBLAS\">ROCm hipBLAS<\/a><\/li>\n<\/ul>\n<p><strong>2. A Runtime system (at least one):<\/strong><\/p>\n<ul>\n<li><b><u>StarPU and dependencies<\/u><\/b>: <a href=\"http:\/\/runtime.bordeaux.inria.fr\/StarPU\/files\" target=\"_blank\" rel=\"noopener\">StarPU from Inria<\/a>, <a href=\"http:\/\/www.open-mpi.org\/projects\/hwloc\/\" target=\"_blank\" rel=\"noopener\">Portable Hardware Locality (hwloc)<\/a>, <a href=\"http:\/\/download.savannah.gnu.org\/releases\/fkt\/\" target=\"_blank\" rel=\"noopener\">FxT<\/a><\/li>\n<li><b><u>OpenMP:<\/u><\/b> <a href=\"https:\/\/www.openmp.org\/\">OpenMP<\/a><\/li>\n<li><b><u>QUARK<\/u><\/b>: <a href=\"http:\/\/icl.cs.utk.edu\/quark\/software\" target=\"_blank\" rel=\"noopener\">QUARK from ICL<\/a>, is also embedded in <a href=\"http:\/\/icl.cs.utk.edu\/plasma\/software\" target=\"_blank\" rel=\"noopener\">PLASMA<\/a><\/li>\n<\/ul>\n<p><strong>3. Parallelization frameworks:<\/strong><\/p>\n<ul>\n<li><b><u>POSIX Threads<\/u><\/b>:<a href=\"https:\/\/computing.llnl.gov\/tutorials\/pthreads\" target=\"_blank\" rel=\"noopener\"> POSIX Threads Programming<\/a>, should be installed in your system<\/li>\n<li><b><u>MPI (optional)<\/u><\/b>: <a href=\"http:\/\/www.open-mpi.org\" target=\"_blank\" rel=\"noopener\">OpenMPI<\/a>, <a href=\"https:\/\/www.mpich.org\/\" target=\"_blank\" rel=\"noopener\">MPICH<\/a>, <a href=\"https:\/\/software.intel.com\/en-us\/intel-mpi-library\" target=\"_blank\" rel=\"noopener\">Intel MPI<\/a>, etc<\/li>\n<li><b><u>CUDA\/ROCm (optional)<\/u><\/b>: <a href=\"https:\/\/developer.nvidia.com\/cuda-downloads\" target=\"_blank\" rel=\"noopener\">NVIDIA CUDA Toolkit<\/a>, or <a href=\"https:\/\/www.amd.com\/fr\/graphics\/servers-solutions-rocm\">AMD ROCm<\/a><\/li>\n<\/ul>\n\n\n<p><\/p>\n","protected":false},"excerpt":{"rendered":"<p>To run Chameleon software binaries you will need to install dependencies, mainly : CPU\/GPU kernels (BLAS\/LAPACK, cuBLAS\/hipBLAS) A Runtime system (e.g. StarPU) Parallelization frameworks: pthread, MPI (optional) and CUDA\/ROCm (optional) Here is a list of links to dependencies : 1. CPU\/GPU kernels (BLAS\/LAPACK, cuBLAS\/hipBLAS): BLAS\/LAPACK (with C interfaces cblas and lapacke enabled): OpenBLAS, BLIS\/FLAME, Intel &hellip; <\/p>\n<p><a class=\"more-link btn\" href=\"https:\/\/project.inria.fr\/chameleon\/test-posts\/links\/\">Continue reading<\/a><\/p>\n","protected":false},"author":582,"featured_media":0,"parent":126,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-97","page","type-page","status-publish","hentry","nodate","item-wrap"],"_links":{"self":[{"href":"https:\/\/project.inria.fr\/chameleon\/wp-json\/wp\/v2\/pages\/97","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/project.inria.fr\/chameleon\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/project.inria.fr\/chameleon\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/project.inria.fr\/chameleon\/wp-json\/wp\/v2\/users\/582"}],"replies":[{"embeddable":true,"href":"https:\/\/project.inria.fr\/chameleon\/wp-json\/wp\/v2\/comments?post=97"}],"version-history":[{"count":14,"href":"https:\/\/project.inria.fr\/chameleon\/wp-json\/wp\/v2\/pages\/97\/revisions"}],"predecessor-version":[{"id":273,"href":"https:\/\/project.inria.fr\/chameleon\/wp-json\/wp\/v2\/pages\/97\/revisions\/273"}],"up":[{"embeddable":true,"href":"https:\/\/project.inria.fr\/chameleon\/wp-json\/wp\/v2\/pages\/126"}],"wp:attachment":[{"href":"https:\/\/project.inria.fr\/chameleon\/wp-json\/wp\/v2\/media?parent=97"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}