@inproceedings{8fae0292cbc7422598101aa4244ab11f,
title = "Fast development of dense linear algebra codes on graphics processors",
abstract = "We present an application programming interface (API) for the C programming language that facilitates the development of dense linear algebra algorithms on graphics processors applying the FLAME methodology. The interface, built on top of the NVIDIA CUBLAS library, implements all the computational functionality of the FLAME/C interface. In addition, the API includes data transference routines to explicitly handle communication between the CPU and GPU memory spaces. The flexibility and simplicity-of-use of this tool are illustrated using a complex operation of dense linear algebra: the Cholesky factorization. For this operation, we implement and evaluate all existing variants on an NVIDIA G80 processor, attaining speed-ups 7× compared with the CPU implementations.",
keywords = "FLAME, Graphics processors, High performance, High-level APIs, Linear algebra",
author = "Zafont, {M. Jes{\'u}s} and Alberto Mart{\'i}n and Francisco Igual and Quintana-Ort{\'i}, {Enrique S.}",
year = "2009",
doi = "10.1109/IPDPS.2009.5160940",
language = "English",
isbn = "9781424437504",
series = "IPDPS 2009 - Proceedings of the 2009 IEEE International Parallel and Distributed Processing Symposium",
booktitle = "IPDPS 2009 - Proceedings of the 2009 IEEE International Parallel and Distributed Processing Symposium",
note = "23rd IEEE International Parallel and Distributed Processing Symposium, IPDPS 2009 ; Conference date: 23-05-2009 Through 29-05-2009",
}