Sam Wu
5168be1867
* update documentation
add version number to documentation
rename .sphinx/.doxygen to sphinx/doxygen
enable htmlzip, pdf, epub formats when publishing on Read the Docs
* add noCI label for dependabot PRs
since RTD CI is separate from math lib CI
* update rocm-docs-core to v0.13.4
* update README with link to rocm.docs.amd.com
[ROCm/rccl commit: c3f47853bd]
12 linhas
1007 B
ReStructuredText
12 linhas
1007 B
ReStructuredText
****
|
|
RCCL
|
|
****
|
|
|
|
The ROCm Collective Communication Library (RCCL) is a stand-alone library which provides multi-GPU and multi-node collective communication primitives optimized for AMD GPUs.
|
|
|
|
RCCL (pronounced “Rickel”) implements routines such as all-reduce, all-gather, reduce, broadcast, reduce-scatter, gather, scatter, all-to-allv, and all-to-all as well as direct point-to-point (GPU-to-GPU) send and receive operations.
|
|
|
|
The provided collective communication routines are implemented using Ring and Tree algorithms. They are optimized to achieve high bandwidth and low latency by leveraging topology awareness, high-speed interconnects, RDMA based collectives. RCCL utilizes PCIe and xGMI high-speed interconnects for intra-node communication as well as InfiniBand, RoCE, and TCP/IP for inter-node communication.
|
|
|
|
RCCL supports an arbitrary number of GPUs installed in a single-node or multi-node platform. It can be easily integrated into either single- or multi-process (e.g., MPI) applications.
|