Class meets TTh 11:00--12:15 in CSIC 3120.
Description (from catalog)
Selected topics in high-performance systems, including contemporary
architectures, interconnection topologies, shared memory and
message-passing systems, multi-threaded kernels, latency avoidance and
hiding techniques, methods for data and workload partitioning,
performance profiling, debugging.
The objective of this course is to study the theory and practice
of high performance parallel and distributed computing. The overall goal is to
expose you to tools and techniques for parallel and/or distributed environments
and to study current trends and technologies.
This course will focus on current practices in high performance computing technologies, including systems, architectures, programming
models, languages and software tools. The course will require students to
produce questions for multiple papers during the semester and complete two introductory and one more extensive
group research project in parallel and/or distributed programming.
Tentative/partial list of topics
Introduction (1 week)
Programming Models (3 weeks)
Parallel Architectures (2 weeks)
Interconnection Networks (1 week)
& Instrumentation (1 week)
Scheduling (1 week)
Tools (2 weeks)
Commercial and Scientific Applications (1 week)