@conference {895, title = {Batched Matrix Computations on Hardware Accelerators Based on GPUs}, booktitle = {2015 SIAM Conference on Applied Linear Algebra (SIAM LA)}, year = {2015}, month = {2015-10}, publisher = {SIAM}, organization = {SIAM}, address = {Atlanta, GA}, abstract = {We will present techniques for small matrix computations on GPUs and their use for energy efficient, high-performance solvers. Work on small problems delivers high performance through improved data reuse. Many numerical libraries and applications need this functionality further developed. We describe the main factorizations LU, QR, and Cholesky for a set of small dense matrices in parallel. We achieve significant acceleration and reduced energy consumption against other solutions. Our techniques are of interest to GPU application developers in general.}, author = {Azzam Haidar and Ahmad Abdelfattah and Stanimire Tomov and Jack Dongarra} }