Simulation / Modeling / Design

cuSOLVERMp v0.0.1 Now Available: Through Early Access

May 10, 2021

By Matthew Nicely

Discuss (0)

Today, cuSOLVERMp version 0.0.1 is now available at no charge for members of the NVIDIA Developer Program.

Download Now

What’s New

Support for LU solver, with and without pivoting.
The Early Access release targets P9 + IBM’s Spectrum MPI

About cuSOLVERMp

cuSOLVERMp provides a distributed-memory multi-node and multi-GPU solution for solving systems of linear equations at scale! In the future, it will also solve eigenvalue and singular value problems.

Future releases will be hosted in the HPC SDK. It will provide additional functionality and support for x86_64 + OpenMPI.

Learn more:

GTC 2021: S31754 Recent Developments in NVIDIA Math Libraries

GTC 2021: S31286 A Deep Dive into the Latest HPC Software

GTC 2021: CWES1098 Tensor Core-Accelerated Math Libraries for Dense and Sparse Linear Algebra in AI and HPC

Blog post coming soon!

Related resources

DLI course: Speed Up DataFrame Operations With RAPIDS cuDF
GTC session: 1,001 Ways to Write CUDA Kernels in Python
GTC session: Unlock Deep Learning Performance on Blackwell With cuDNN
SDK: cuSOLVERMp
SDK: cuSOLVER
SDK: cuSOLVERMg

Discuss (0)

About the Authors

About Matthew Nicely
Matthew Nicely is a senior product manager over Deep Learning Compilers at NVIDIA, working with cuDNN and CUTLASS. At NVIDIA, he has worked as a public sector solution architect and CUDA Math Libraries product manager. In 2019, he received his Ph.D. in computer engineering, focusing on algorithm optimizations on GPUs.

View all posts by Matthew Nicely