GPU Algorithms

Scalable Methods for Multivariate Normal Probability Estimation with Applications in Confidence Region Detection, Transport Phenomena, and Parallel Computing Using RCOMPSs

Xiran Zhang, Ph.D. Student, Statistics

May 14, 15:00 - 17:00

B2 R5209

geospatial statistics spatio-temporal statistics High Performance Computing HPC multivariate statistics GPU Algorithms

This thesis addresses computing high-dimensional multivariate normal (MVN) probabilities in environmental and geospatial applications by combining high-performance computing, numerical approximation, and transport-based covariance modeling to make several important spatial procedures usable at larger scales.

Distributed multi-GPU Algorithms for Hierarchical Matrices

George Turkiyyah, Research Professor, Applied Mathematics and Computational Science

Oct 18, 12:00 - 13:00

B9 L2 R2322

GPU Algorithms hierarchical matrices

In this talk, we show that, besides their optimal O(N) algorithmic complexity, hierarchical matrix operations also benefit from parallel scalability on distributed machines with extremely large core counts. In particular, we describe high-performance, distributed-memory, GPU-accelerated algorithms for matrix-vector multiplication and other operations on hierarchical matrices in the H^2 format.