Programming

Programming graphics processors with extensible languages

A. V. Adinetz<sup>ab

a</sup> Joint Institute for Nuclear Research, Dubna, Moskovskaya obl.
^b Scientific-Research Computing Centre at the M.V. Lomonosov State University

Abstract: This paper presents a GPU programming system, NUDA, built on top of an extensilbe language, Nemerle. NUDA provides control over porting application to GPU, while making the compiler do the mechanical work. Macros and annotations simplify the porting process, and increase efficiency without sacrificing code size and readability. On a number of problems and architectures, use of NUDA increased performance several times compared to initial implementation.

Keywords: programming languages, Parallel programming, Extensible programming, metaprogramming, GPU, GPGPU.

UDC: 004.432.2, 004.435, 004.422.837

Received: 02.03.2011