2022-02-20 21:51:11 +01:00
|
|
|
ViennaCL is a free open-source linear algebra library for computations on
|
|
|
|
|
many-core architectures (GPUs, MIC) and multi-core CPUs. The library is
|
|
|
|
|
written in C++ and supports CUDA, OpenCL, and OpenMP (including switches
|
2017-06-03 16:18:18 +02:00
|
|
|
at runtime).
|
|
|
|
|
|
|
|
|
|
The highlights of the latest 1.7.x release family are:
|
|
|
|
|
|
|
|
|
|
* Fast sparse matrix-matrix multiplications, outperforming CUBLAS and MKL.
|
2022-02-20 21:51:11 +01:00
|
|
|
* Fine-grained parallel algebraic multigrid preconditioners for CPUs, Xeon
|
2017-06-03 16:18:18 +02:00
|
|
|
Phis, and GPUs.
|
2022-02-20 21:51:11 +01:00
|
|
|
* Fine-grained parallel incomplete LU factorization preconditioners for
|
2017-06-03 16:18:18 +02:00
|
|
|
CPUs, Xeon Phis, and GPUs.
|
