Batched matrix computations on hardware accelerators based on GPUs

Contributors: Dongarra, Jack [Univ. of Tennessee, Knoxville, TN (United States); Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States); Univ. of Manchester (United Kingdom)]

Source: International Journal of High Performance Computing Applications; 29; 2

File Description: Medium: ED; Size: p. 193-208

Access URL: http://www.osti.gov/scitech/servlets/purl/1361289

High-performance Cholesky factorization for GPU-only execution

Authors: Haidar, Azzam, Abdelfatah, Ahmad, Tomov, Stanimire, Dongarra, Jack

Source: Proceedings of the General Purpose GPUs. :42-52

Availability: http://dl.acm.org/doi/10.1145/3038228.3038237

Optimization for performance and energy for batched matrix computations on GPUs

Authors: Haidar, Azzam, Dong, Tingxing, Luszczek, Piotr, Tomov, Stanimire, Dongarra, Jack

Source: Proceedings of the 8th Workshop on General Purpose Processing using GPUs. :59-69

Availability: http://dl.acm.org/doi/10.1145/2716282.2716288

RETRACTED: Batched matrix computations on hardware accelerators based on GPUs

Authors: Haidar, Azzam, Dong, Tingxing, Luszczek, Piotr, Tomov, Stanimire, Dongarra, Jack

Source: Haidar, A, Dong, T, Luszczek, P, Tomov, S & Dongarra, J 2015, 'Batched matrix computations on hardware accelerators based on GPUs', International Journal of High Performance Computing Applications, vol. 29, no. 2, pp. 193-208. https://doi.org/10.1177/1094342014567546

Subject Terms: one-sided factorization algorithms, numerical linear algebra, 0202 electrical engineering, electronic engineering, information engineering, Batched factorization, 02 engineering and technology, numerical software libraries, hardware accelerators, 7. Clean energy

Access URL: https://www.osti.gov/biblio/1361289
https://research.manchester.ac.uk/en/publications/3b928883-2575-424b-9c5c-93c76c117dd7
https://doi.org/10.1177/1094342014567546
https://research.manchester.ac.uk/en/publications/3b928883-2575-424b-9c5c-93c76c117dd7
https://doi.org/10.1177/1094342014567546
http://www.scopus.com/inward/record.url?scp=84930795358&partnerID=8YFLogxK

Towards batched linear solvers on accelerated hardware platforms

Authors: Haidar, Azzam, Dong, Tingxing, Luszczek, Piotr, Tomov, Stanimire, Dongarra, Jack

Source: Proceedings of the 20th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming. :261-262

Availability: http://dl.acm.org/doi/10.1145/2688500.2688534