zpotrf_dtd fixed for the GPU, updated kernels to cublas_v2, although results still suspicious

ICLDisco / dplasma

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

10 stars 8 forks source link

zpotrf_dtd fixed for the GPU, updated kernels to cublas_v2, although results still suspicious #94

Closed BrieucNicolas closed 11 months ago

BrieucNicolas commented 11 months ago

testing_zpotrf_dtd now works with GPU. However, the factorisation and results produced are suspicious

BrieucNicolas commented 11 months ago

This is the continuation of PR #55