Jack Dongarra

DOE Advanced Scientific Computing Advisory Subcommittee (ASCAC) Report: Top Ten Exascale Research Challenges

Exascale computing systems are essential for the scientific fields that will transform the 21st century global economy, including energy, biotechnology, nanotechnology, and materials science. Progress in these fields is predicated on the ability to perform advanced scientific and engineering simulations, and analyze the deluge of data. On July 29, 2013, ASCAC was charged by Patricia Dehmer, the Acting Director of the Office of Science, to assemble a subcommittee to provide advice on exascale computing. This subcommittee was directed to return a list of no more than ten technical approaches (hardware and software) that will enable the development of a system that achieves the Departments goals for exascale computing. Numerous reports over the past few years have documented the technical challenges and the non¬-viability of simply scaling existing computer designs to reach exascale. The technical challenges revolve around energy consumption, memory performance, resilience, extreme concurrency, and big data. Drawing from these reports and more recent experience, this ASCAC subcommittee has identified the top ten computing technology advancements that are critical to making a capable, economically viable, exascale system.

LAPACK: A Linear Algebra Library for High-Performance Computers

This talk outlines the computational package called LAPACK. LAPACK is a collection of Fortran 77 subroutines for the analysis and solution of various systems of simultaneous linear algebraic equations, linear least squares problems, and matrix eigenvalue problems. Such computations form the core of perhaps the majority of statistical methods.

Matrix Algebra for GPU and Multicore Architectures (MAGMA) for Large Petascale Systems

The goal of the MAGMA project is to create a new generation of linear algebra libraries that achieve the fastest possible time to an accurate solution on hybrid Multicore+GPU-based systems, using all the processing power that future high-end systems can make available within given energy constraints. Our efforts at the University of Tennessee achieved the goals set in all of the five areas identified in the proposal: 1. Communication optimal algorithms; 2. Autotuning for GPU and hybrid processors; 3. Scheduling and memory management techniques for heterogeneity and scale; 4. Fault tolerance and robustness for large scale systems; 5. Building energy efficiency into software foundations. The University of Tennessee’s main contributions, as proposed, were the research and software development of new algorithms for hybrid multi/many-core CPUs and GPUs, as related to two-sided factorizations and complete eigenproblem solvers, hybrid BLAS, and energy efficiency for dense, as well as sparse, operations. Furthermore, as proposed, we investigated and experimented with various techniques targeting the five main areas outlined.

Changes in Dense Linear Algebra Kernels: Decades-Long Perspective

Over the years, computational physics and chemistry served as an ongoing 5 source of problems that demanded the ever increasing performance from 6 hardware as well as the software that ran on top of it. Most of these 7 problems could be translated into solutions for systems of linear equa8 tions: the very topic of numerical linear algebra. Seemingly then, a set of 9 efficient linear solvers could be solving important scientific problems for 10 years to come. We argue that dramatic changes in hardware designs pre11 cipitated by the shifting nature of the marketplace of computer hardware 12 had a continuous effect on the software for numerical linear algebra. The 13 extraction of high percentages of peak performance continues to require 14 adaptation of software. If the past history of this adaptive nature of linear 15 algebra software is any guide then the future theme will feature changes 16 as well — changes aimed at harnessing the incredible advances of the 17 evolving hardware infrastructure. 18