Optimization of Hierarchical Matrix Computation on GPU

摘要

The demand for dense matrix computation in large scale and complex simulations is increasing; however, the memory capacity of current computer system is insufficient for such simulations. Hierarchical matrix method (H-matrices) is attracting attention as a computational method that can reduce the memory requirements of dense matrix computations. However, the computation of H-matrices is more complex than that of dense and sparse matrices; thus, accelerating the H-matrices is required. We focus on H-matrix - vector multiplication (HMVM) on a single NVIDIA Tesla P100 GPU. We implement five GPU kernels and compare execution times among various processors (the Broadwell-EP, Skylake-SP, and Knights Landing) by OpenMP. The results show that, although an HMVM kernel can compute many small GEMV kernels, merging such kernels to a single GPU kernel was the most effective implementation. Moreover, the performance of BATCHED BLAS in the MAGMA library was comparable to that of the manually tuned GPU kernel.