@article {,
title = {A Set of Batched Basic Linear Algebra Subprograms and LAPACK Routines},
journal = {ACM Transactions on Mathematical Software (TOMS)},
volume = {47},
number = {3},
year = {2021},
pages = {1{\textendash}23},
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.},
keywords = {Computations on matrices, Mathematical analysis, Mathematics of computing, Numerical analysis},
doi = {10.1145/3431921},
author = {Abdelfattah, Ahmad and Costa, Timothy and Dongarra, Jack and Mark Gates and Haidar, Azzam and Hammarling, Sven and Higham, Nicholas J and Kurzak, Jakub and Luszczek, Piotr and Tomov, Stanimire and others}
}