DPLASMA is a highly optimized, accelerator-aware, implementation of a dense linear algebra package for distributed heterogeneous systems. It is designed to deliver sustained performance for distributed systems where each node featuring multiple sockets of multicore processors, and if available, accelerators, using the PaRSEC runtime as a backend.
Other
11
stars
9
forks
source link
When recursive is disabled, first gpu is at index 1 #111
We would skip the warmup of device 1 in some cases.