ROC_SHMEM
ROC_SHMEM copied to clipboard
ROC_SHMEM intra-kernel networking runtime for AMD dGPUs on the ROCm platform.
### Problem Description Can you please provide install instructions for frontier machine in OLCF ### Operating System HPE Cray OS ### CPU 4-core AMD “Optimized 3rd Gen EPYC” CPU ###...
Hi team, I require the documentation of your ROC_SHMEM API generated by deoxygen in your repository. I have tried cloning and just generating it but I was unable to do...
I’m testing the roc_shmem using two nodes on frontier. I find that if I did MPI_Init in the code, and then do roc_shmem_init, I’ll get the below error msg. Assertion...
Does ROC_SHMEM have roc_shmem_##TNAME##_wait_util_any? I failed to find it.
Does ROC_SHMEM have a collective launch to avoid potential deadlocks? https://docs.nvidia.com/nvshmem/api/api/launch.html#nvshmemx-collective-launch
Hi, I wonder if ROC_SHMEM can support "put with signal API"(https://docs.nvidia.com/nvshmem/api/gen/api/signal.html#nvshmem-put-signal-nbi). It will speed up the inter-node GPU communication in my experience.
Hi there, How to build the library with only reverse offload? I failed to find the documentation. I want to try ROC_SHMEM on Crusher. However, Crusher doesn't have the InfiniBand...
Fix compilation errors.
Avoid overriding CMAKE_CXX_COMPILER by setting it as the preset path rarely matches installations
### Problem Description Need the documentation for ROCshmem as there is some API difference in nvshmem to ROC_SHMEM, so cant convert directly like HIP. Can you please provide the documentation...