cuda-api-wrappers
cuda-api-wrappers copied to clipboard
Should we include support for GPUDirect/RDMA as in NVIDIA's gdrcopy?
A low-latency GPU memory copy library based on NVIDIA GPUDirect RDMA technology. Introduction
While GPUDirect RDMA is meant for direct access to GPU memory from third-party devices, it is possible to use these same APIs to create perfectly valid CPU mappings of the GPU memory.
The advantage of a CPU driven copy is the very small overhead involved. That might be useful when low latencies are required.