Is there a way to achieve cross-node point-to-point communication without consuming SM (Streaming Multiprocessor) resources?
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| What is the setting to enable NVSHMEM on multi-node multi-GPU platform with IB | 7 | 507 | January 2, 2025 | |
| NVSHMEM on multi-node GPUs | 8 | 3089 | January 18, 2024 | |
| NVSHMEM node exchange performance dropping when going above 4 GPUs per node | 1 | 81 | September 2, 2025 | |
| NVSHMEM on multi-node GPUs failed . My gpu is A5000 | 5 | 1200 | April 1, 2024 | |
| NVSHMEM without mpi, 1 thread for each GPU on a node- howto initialize? | 1 | 909 | April 18, 2022 | |
| NVSHMEM on 2 node GPUs, small size msg latency is very high | 0 | 90 | February 26, 2025 | |
| Enhancing Application Portability and Compatibility across New Platforms Using NVIDIA Magnum IO NVSHMEM 3.0 | 1 | 49 | September 6, 2024 | |
| Improving Network Performance of HPC Systems Using NVIDIA Magnum IO NVSHMEM and GPUDirect Async | 3 | 731 | March 10, 2025 | |
| Single process with multiple threads pure RDMA data transfer on multiple nodes | 0 | 55 | December 19, 2025 | |
| What is the NVSHMEM configuration setting to achieve optimal performance on multi-node HPC cluster | 3 | 183 | January 2, 2025 |