hierarchical matrices

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.

Wajih Halim Boukaram

Ph.D. Student, Computer Science

kblas hierarchical matrices High Performance Computing GPU Computing batched linear algebra

Wajih Halim Boukaram is a PhD candidate in Computer Science. He is studying under the supervision of Professor David E. Keyes.