@article {1266, title = {Accelerating the SVD Bi-Diagonalization of a Batch of Small Matrices using GPUs}, journal = {Journal of Computational Science}, volume = {26}, year = {2018}, month = {2018-05}, pages = {237{\textendash}245}, abstract = {The acceleration of many small-sized linear algebra problems has become extremely challenging for current many-core architectures, and in particular GPUs. Standard interfaces have been proposed for some of these problems, called batched problems, so that they get targeted for optimization and used in a standard way in applications, calling them directly from highly optimized, standard numerical libraries, like (batched) BLAS and LAPACK. While most of the developments have been for one-sided factorizations and solvers, many important applications {\textendash} from big data analytics to information retrieval, low-rank approximations for solvers and preconditioners {\textendash} require two-sided factorizations, and most notably the SVD factorization. To address these needs and the parallelization challenges related to them, we developed a number of new batched computing techniques and designed batched Basic Linear Algebra Subroutines (BLAS) routines, and in particular the Level-2 BLAS GEMV and the Level-3 BLAS GEMM routines, to solve them. We propose a device functions-based methodology and big-tile setting techniques in our batched BLAS design. The different optimization techniques result in many software versions that must be tuned, for which we adopt an auto-tuning strategy to automatically derive the optimized instances of the routines. We illustrate our batched BLAS approach to optimize batched SVD bi-diagonalization progressively on GPUs. The progression is illustrated on an NVIDIA K40c GPU, and also, ported and presented on AMD Fiji Nano GPU, using AMD{\textquoteright}s Heterogeneous{\textendash}Compute Interface for Portability (HIP) C++ runtime API. We demonstrate achieving 80\% of the theoretically achievable peak performance for the overall algorithm, and significant acceleration of the Level-2 BLAS GEMV and Level-3 BLAS GEMM needed compared to vendor-optimized libraries on GPUs and multicore CPUs. The optimization techniques in this paper are applicable to the other two-sided factorizations as well.}, keywords = {Batched, Eigenvalue and singular value problems, hardware accelerators, numerical linear algebra, Two-sided factorization algorithms}, doi = {https://doi.org/10.1016/j.jocs.2018.01.007}, author = {Tingxing Dong and Azzam Haidar and Stanimire Tomov and Jack Dongarra} }