Production high-performance computing (HPC) systems are adopting and integrating GPUs into their design to accommodate artificial intelligence (AI), machine learning, and data visualization workloads. To aid with the design and operations of new and existing GPU-based large-scale systems, we provide a detailed characterization of system operations, job characteristics, user behavior, and trends on a contemporary GPU-accelerated production HPC system. Our insights indicate that the pre-mature phases in modern AI workflow take up significant GPU hours while underutilizing GPUs, which opens up the opportunity for a multi-tier system. Finally, we provide various potential recommendations and areas for future investment for system architects, operators, and users.

Little attention has been given to language support for block-based compression algorithms, despite their high implementation complexity. Current implementations have to deal with both the intricacies of the algorithm itself, as well as the low-level optimizations necessary for generating fast code. However, many block-based compression algorithms share a common structure in terms of their data representations, data partitioning operations, and data traversals. In this work, we propose a set of high-level language abstractions that can succinctly capture this structure. These abstractions provide the building blocks for the development of a domain-specific language and an associated optimizing compiler. With compression-specific language support, researchers can focus on algorithm development rather than the low-level implementation details.

This Work-In-Progress paper details the process and lessons learned when converting a hands-on engineering mini-course to a scalable, self-paced Massively Open Online Course (MOOC). Online courseware has been part of academic and industry training and learning for decades. Learning activities in online courses strive to mimic in-person delivery by including lectures, homework assignments, software exercises and exams. While these instructional activities provide “theory and practice” for many disciplines, engineering courses often require hands-on activities with physical tools, devices and equipment. To accommodate the need for this type of learning, MIT Lincoln Laboratory's “Build A Small Radar” (BSR) course was used to explore teaching and learning strategies that support the inclusion of physical construction and real world data collection in a MOOC. These tasks are encountered across a range of engineering disciplines and the methods illustrated here are easily generalized to the learning experiences in engineering and science disciplines.

A crucial element of large web companies is their ability to collect and analyze massive amounts of data. Tuple store databases are a key enabling technology employed by many of these companies (e.g., Google Big Table and Amazon Dynamo). Tuple stores are highly scalable and run on commodity clusters, but lack interfaces to support efficient development of mathematically based analytics. D4M (Dynamic Distributed Dimensional Data Model) has been developed to provide a mathematically rich interface to tuple stores (and structured query language “SQL” databases). D4M allows linear algebra to be readily applied to databases. Using D4M, it is possible to create composable analytics with significantly less effort than using traditional approaches. This work describes the D4M technology and its application and performance.

MATLAB® is one of the most commonly used languages for scientific computing with approximately one million users worldwide. At MIT Lincoln Laboratory, MATLAB is used by technical staff to develop sensor processing algorithms. MATLAB's popularity is based on availability of high-level abstractions leading to reduced code development time. Due to the compute intensive nature of scientific computing, these applications often require long running times and would benefit greatly from increased performance offered by parallel computing. pMatlab (www.ll.mit.edu/pMatlab) implements partitioned global address space (PGAS) support via standard operator overloading techniques. The core data structures in pMatlab are distributed arrays and maps, which simplify parallel programming by removing the need for explicit message passing. This paper presents the pMatlab design and results for the HPC Challenge benchmark suite. Additionally, two case studies of pMatlab use are described.