Affiliation:
1. University of Tennessee, USA
2. NVIDIA, USA
3. University of Tennessee, Oak Ridge National Laboratory, and University of Manchester, USA
4. University of Manchester, UK
5. AMD, USA
6. NAG Ltd., UK
Abstract
This article describes a standard API for a set of Batched Basic Linear Algebra Subprograms (Batched BLAS or BBLAS). The focus is on many independent BLAS operations on small matrices that are grouped together and processed by a single routine, called a Batched BLAS routine. The matrices are grouped together in uniformly sized groups, with just one group if all the matrices are of equal size. The aim is to provide more efficient, but portable, implementations of algorithms on high-performance many-core platforms. These include multicore and many-core CPU processors, GPUs and coprocessors, and other hardware accelerators with floating-point compute facility. As well as the standard types of single and double precision, we also include half and quadruple precision in the standard. In particular, half precision is used in many very large scale applications, such as those associated with machine learning.
Funder
National Science Foundation
Russian Science Foundation
European Union Horizon 2020
Publisher
Association for Computing Machinery (ACM)
Subject
Applied Mathematics,Software
Cited by
16 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. GPU-based LU Factorization and Solve on Batches of Matrices with Band Structure;Proceedings of the SC '23 Workshops of The International Conference on High Performance Computing, Network, Storage, and Analysis;2023-11-12
2. Porting Batched Iterative Solvers onto Intel GPUs with SYCL;Proceedings of the SC '23 Workshops of The International Conference on High Performance Computing, Network, Storage, and Analysis;2023-11-12
3. Integrating batched sparse iterative solvers for the collision operator in fusion plasma simulations on GPUs;Journal of Parallel and Distributed Computing;2023-08
4. Vectorization of a Thread-Parallel Jacobi Singular Value Decomposition Method;SIAM Journal on Scientific Computing;2023-06-02
5. LBBGEMM: A Load-balanced Batch GEMM Framework on ARM CPU s;2022 IEEE 24th Int Conf on High Performance Computing & Communications; 8th Int Conf on Data Science & Systems; 20th Int Conf on Smart City; 8th Int Conf on Dependability in Sensor, Cloud & Big Data Systems & Application (HPCC/DSS/SmartCity/DependSys);2022-12