The SLATE (Software for Linear Algebra Targeting Exascale) library is being developed to provide fundamental dense linear algebra capabilities for current and upcoming distributed high-performance systems, both accelerated CPU–GPU based and CPU based. SLATE will provide coverage of existing ScaLAPACK functionality, including the parallel BLAS; linear systems using LU and Cholesky; least squares problems using QR; and eigenvalue and singular value problems. In this respect, it will serve as a replacement for ScaLAPACK, which after two decades of operation, cannot adequately be retrofitted for modern accelerated architectures. SLATE uses modern techniques such as communication-avoiding algorithms, lookahead panels to overlap communication and computation, and task-based scheduling, along with a modern C++ framework. Here we present the design of SLATE and initial reports of several of its components.
Dalal Sukkari received the MSc and Ph.D. degrees in Applied Mathematics and Computational Science from the King Abdullah University of Science and Technology (KAUST), in 2013 and 2019, respectively, where she was a member of the Extreme Computing Research Center (ECRC). She is currently a post-doctoral research associate in the Innovative Computing Laboratory (ICL) at the University of Tennessee, led by Prof. Jack Dongarra. Her work centers on providing more functionality and applying several optimization techniques to the SLATE (Software for Linear Algebra Targeting Exascale) library. Moreover, she is working on a new high-performance implementation to accelerate the stochastic gradient descent (SGD) computations during training a Deep Neural Network.