Earlier this week, Kent Knox of AMD announced the beta release of a new library on their blog.
The clSPARSE library, created by AMD in partnership with Vratis Ltd., is an open source sparse linear algebra library that uses OpenCL(TM) to accelerate performance with GPU Compute. clSPARSE expands upon exiting the clMathLibraries offerings: dense clBLAS (Basic Linear Algebra Subprograms), clFFT (Fast Fourier Transform) and clRNG (random number generator), and adds new sparse operations:
* Sparse matrix – dense vector multiply (SpM-dV)
* Sparse matrix – dense matrix multiply
* Iterative conjugate gradient (CG) solver
* Iterative biconjugate gradient stabilized (BiCGStab) solver
* Dense to Compressed Sparse Row (CSR) conversions (and converse)
* Coordinate list (COO) to CSR conversions (and converse)
* Functions to read matrix market files
clSPARSE contains optimized kernels that compute on matrices represented in CSR (Compressed Sparse Row) format. The library provides conversion routines to and from the CSR compressed matrix format, and is the required sparse matrix format to use the SpM-dV multiply, CG or the BiCGStab solvers. clSPARSE exports a C interface which allows developers to build wrappers around clSPARSE in any language they need. This means users do not have to write sparse OpenCL kernels to gain the performance benefits of sparse GPU acceleration. OpenCL fluency is still required. The implementation is abstracted, allowing you to focus on memory placement and transport.
This new AMD open source library uses the ASFv2 (Apache Software Foundation) license, and uses the CMake build tool.