An Improved Magma Gemm For Fermi Graphics Processing Units
University of Tennassee, USA
International Journal of High Performance Computing Applications, Vol. 24, No. 4. (1 November 2010), pp. 511-515
@article{nath2010improved,
title={An Improved Magma Gemm For Fermi Graphics Processing Units},
author={Nath, R. and Tomov, S. and Dongarra, J.},
journal={International Journal of High Performance Computing Applications},
volume={24},
number={4},
pages={511},
issn={1094-3420},
year={2010},
publisher={SAGE Publications}
}
We present an improved matrix-matrix multiplication routine (General Matrix Multiply [GEMM]) in the MAGMA BLAS library that targets the NVIDIA Fermi graphics processing units (GPUs) using Compute Unified Data Architecture (CUDA). We show how to modify the previous MAGMA GEMM kernels in order to make a more efficient use of the Fermi’s new architectural features, most notably their extended memory hierarchy and memory sizes. The improved kernels run at up to 300 GFlop/s in double precision and up to 645 GFlop/s in single precision arithmetic (on a C2050), which is correspondingly 58% and 63% of the theoretical peak. We compare the improved kernels with the currently available version in CUBLAS 3.1. Further, we show the effect of the new kernels on higher-level dense linear algebra (DLA) routines such as the one-sided matrix factorizations, and compare their performances with corresponding, currently available routines running on homogeneous multicore systems.
January 23, 2011 by hgpu
