NVIDIA HPC-X Software Toolkit Rev 2.19.0
NVIDIA HPC-X Software Toolkit Rev 2.19.0

EC/CUDA One-shot Kernel with Cooperative Launch

This feature improves GPU collective performance by utilizing the CUDA cooperative launch feature. It enables the use of a single CUDA kernel for CUDA operations in UCC GPU collectives.

This feature can be activated by enabling the UCC environment variable UCC_EC_CUDA_USE_COOPERATIVE_LAUNCH as follows:

Copy
Copied!
            

UCC_EC_CUDA_USE_COOPERATIVE_LAUNCH=1

© Copyright 2024, NVIDIA. Last updated on May 6, 2024.