Write a Blog >>
PLDI 2021
Sun 20 - Sat 26 June 2021 PLDI

My goal in life is to make sequential software rare. Every program should be a parallel program. This is the only way for software to realize the full benefit of modern systems (from CPU to GPU to clusters and onward to the cloud). I’ve tried many approaches over the years with some success, but I have not come even close to achieving my goal.

My next attempt at achieving my goal is to focus on the fundamental data structures of programming. If we exposed them through a high-level API, we could hide the complexity of parallel and distributed computing and parallel programming would become easy. And of the data structures “out there” none is more important than the array.

There are many steps needed to realize this vision with arrays. I will report on two we’ve “completed” so far: GraphBLAS and TileDB. GraphBLAS is an API for expressing Graph algorithms in terms of sparse arrays. TileDB is a storage engine for sparse arrays optimized for use with database applications. I will describe these two projects and how they fit in to my big-picture goal of making software easier to write and routinely parallel.

Bio: Tim Mattson is a parallel programmer obsessed with every variety of science (Ph.D. Chemistry, UCSC, 1985). He is a senior principal engineer in Intel’s parallel computing lab. Tim has been with Intel since 1993 and has worked with brilliant people on great projects including: (1) the first TFLOP computer (ASCI Red), (2) MPI, OpenMP and OpenCL, (3) two different research processors (Intel’s TFLOP chip and the 48 core SCC), (4) Data management systems (Polystore systems and Array-based storage engines), and (5) the GraphBLAS API for expressing graph algorithms as sparse linear algebra. Tim has over 150 publications including five books on different aspects of parallel computing, the latest (Published November 2019) titled The OpenMP Common Core: Making OpenMP Simple Again.

Slides (ARRAY_keynoteFinal.pdf)4.14MiB

Mon 21 Jun

Displayed time zone: Eastern Time (US & Canada) change

13:30 - 16:15
Session 2 (keynote) and 3 (applications)ARRAY at ARRAY
Chair(s): Aggelos Biboudis Swisscom AG, Sandra Catalán
Keynote: Tilting at Windmills with the Humble Array
Tim Mattson Intel, USA
File Attached
Array Languages Make Neural Networks Fast
Artjoms Šinkarovs Heriot-Watt University, UK, Hans-Nikolai Vießmann Radboud University Nijmegen, Netherlands, Sven-Bodo Scholz Radboud University
Acceleration of Lattice Models for Pricing Portfolios of Fixed-Income Derivatives
Wojciech Michal Pawlak University of Copenhagen, Denmark, Marek Hlava Department of Computer Science, University of Copenhagen, Martin Metaksov Department of Computer Science, University of Copenhagen, Cosmin Oancea University of Copenhagen, Denmark