Programming Languages Lunch - Martin Schatz, "A Domain-specific Language for Distributed Tensor Computation"
Talk Audience: UTCS Faculty, Grads, Undergrads, Other Interested Parties
Talk Abstract: Recently, data models have become more complex leading to the need for multi-dimensional representations to express the data in a more meaningful way. Commonly, tensors are used to represent such data. Multi-linear algebra, the math associated with tensors, has become essential for tackling problems in big data and scientific computing. To solve the largest problems of today, libraries designed for supercomputers consisting of thousands of compute nodes connected via a network are utilized. Such compute architectures are referred to as “distributed-memory” architectures. Up to now, the main approach for problems of multi-linear algebra has been based on mapping the multi-linear algebra to linear algebra and rely on highly efficient linear algebra libraries to perform the equivalent computation [5, 21]. Unfortunately, there are inherent inefficiencies associated with this approach. In this proposal, we define a domain-specific language for distributed tensor computation. Additionally, through a process akin to constraint propagation, we show how, using the language, algorithms can be systematically derived, required collective communications can be identified, and approximate cost can be analyzed for the given tensor contraction operation.
Speaker Bio: Martin Schatz a 4th year Ph.D. student supervised by Robert van de Geijn and Tamara G. Kolda focusing on distributed-memory multi-linear algebra.
- Awards & Honors
- About Us
- Student Engagement and Support
- Masters Program
- Ph.D. Program
- Financial Information
- Prospective Students
- Incoming Students
- Current Students
- Portfolio Program in Robotics
- Curricular Practical Training
- Grad Student Talks
- UTCS Direct