Traditional TCP/IP communication in GPGPU virtualization suffers from high context switch overhead. Our RDMA communicator for GVirtuS reduces voluntary context switches by 90%, slashing execution time for Matrix Multiplication and SAXPY algorithms. The future of low-latency HPC is here.
🌟 Follow us on LinkedIn! https://www.linkedin.com/company/clever-project/?viewAsMember=true
🌟 Check the updates from the website: www.cleverproject.eu
🌟 Full paper in: https://zenodo.org/records/14717622