Peer-to-Peer Memory Access
Direct GPU-to-GPU copies over NVLink.
The Slow Detour
Moving data from one GPU to another usually bounces through the CPU's memory first. That round trip is slow and wastes the host's bandwidth.
GPUs Talking Directly
Modern GPUs can skip the CPU entirely. Peer-to-peer access lets one GPU read and write another's memory over a direct link.
All lessons in this course
- Enumerating and Selecting Devices
- Partitioning Work Across GPUs
- Peer-to-Peer Memory Access
- Multi-GPU with NCCL