パッケージ: libgloo-cuda-0 (0.0~git20230519.597accf-3 など) [contrib]
libgloo-cuda-0 に関するリンク
Debian の資源:
gloo-cuda ソースパッケージをダウンロード:
- [gloo-cuda_0.0~git20230519.597accf-3.dsc]
- [gloo-cuda_0.0~git20230519.597accf.orig.tar.xz]
- [gloo-cuda_0.0~git20230519.597accf-3.debian.tar.xz]
メンテナ:
外部の資源:
- ホームページ [github.com]
類似のパッケージ:
Collective communications library (shared object)
Gloo is a collective communications library. It comes with a number of collective algorithms useful for machine learning applications. These include a barrier, broadcast, and allreduce.
Transport of data between participating machines is abstracted so that IP can be used at all times, or InifiniBand (or RoCE) when available. In the latter case, if the InfiniBand transport is used, GPUDirect can be used to accelerate cross machine GPU-to-GPU memory transfers.
Where applicable, algorithms have an implementation that works with system memory buffers, and one that works with NVIDIA GPU memory buffers. In the latter case, it is not necessary to copy memory between host and device; this is taken care of by the algorithm implementations.
This package ships the shared object for Gloo.
その他の libgloo-cuda-0 関連パッケージ
|
|
|
|
-
- dep: libc6 (>= 2.34)
- GNU C ライブラリ: 共有ライブラリ
以下のパッケージによって提供される仮想パッケージでもあります: libc6-udeb
-
- dep: libcudart12
- NVIDIA CUDA Runtime Library
-
- dep: libgcc-s1 (>= 3.0)
- GCC 共有ライブラリ
-
- dep: libhiredis0.14 (>= 0.14.0) [amd64 以外]
- minimalistic C client library for Redis
-
- dep: libhiredis1.1.0 (>= 1.2.0) [amd64]
- minimalistic C client library for Redis
-
- dep: libibverbs1 (>= 1.1.6)
- Library for direct userspace use of RDMA (InfiniBand/iWARP)
-
- dep: libnccl2 (>= 2.16.5)
- NVIDIA Optimized primitives for inter-GPU communication
-
- dep: libopenmpi3 (>= 4.1.5) [amd64 以外]
- high performance message passing library -- shared library
-
- dep: libopenmpi3t64 (>= 4.1.6) [amd64]
- high performance message passing library -- shared library
-
- dep: libstdc++6 (>= 12)
- GNU 標準 C++ ライブラリ v3