An automatic OpenCL compute kernel generator for basic linear algebra operations

Authors:
Philippe Tillet;Karl Rupp;Siegfried Selberherr
Affiliations:
Institute for Microelectronics, TU Wien, Wien, Austria;Institute for Microelectronics, TU Wien, Wien, Austria and Institute for Analysis and Scientific Computing, TU Wien Wiedner, Wien, Austria;Institute for Microelectronics, TU Wien, Wien, Austria
Venue:
Proceedings of the 2012 Symposium on High Performance Computing
Year:
2012

Citing 6
Cited 0

BI-CGSTAB: a fast and smoothly converging variant of BI-CG for the solution of nonsymmetric linear systems

SIAM Journal on Scientific and Statistical Computing
Modern C++ design: generic programming and design patterns applied

Modern C++ design: generic programming and design patterns applied
Iterative Methods for Sparse Linear Systems

Iterative Methods for Sparse Linear Systems
An Improved Magma Gemm For Fermi Graphics Processing Units

International Journal of High Performance Computing Applications
Implementing Domain-Specific Languages for Heterogeneous Parallel Computing

IEEE Micro
PyCUDA and PyOpenCL: A scripting-based approach to GPU run-time code generation

Parallel Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

An automatic OpenCL compute kernel generator framework for linear algebra operations is presented. It allows for specifying matrix and vector operations in high-level C++ code, while the low-level details of OpenCL compute kernel generation and handling are dealt with in the background. Our approach releases users from considerable additional effort required for learning the details of programming graphics processing units (GPUs), and we demonstrate that higher performance than for a fixed, predefined set of OpenCL compute kernels is obtained due to the minimization of launch overhead. The generator is made available in the Vienna Computing Library (ViennaCL) and is demonstrated here with the stabilized bi-conjugate gradient algorithm, for which performance gains up to 40 percent are observed.