HCCL
The collective communication library for Huawei's Ascend platform, analogous to NVIDIA's NCCL. It supports distributed communication primitives such as AllReduce and AlltoAll across Ascend NPUs.
Timeline (last 90 days)
GPU clusters rely on NVLink and InfiniBand for high-bandwidth, low-latency communication, with the NCCL library deeply optimized for this; the interconnect topologies of NPU devices are often different, such as Huawei Ascend's HCCL or the TPU's ICI.
The Ascend version of DeepEP uses HCCL, with UB within a node, HCCL/HCCN's URMA engine across nodes, and kernels written in Ascend C.
CANN includes the operator development framework (TBE/DSL), graph compilation engine (ATC/GE), runtime (ACL), communication library (HCCL, corresponding to NCCL), and model conversion and tuning toolchain.
All Facts (3)
GPU clusters rely on NVLink and InfiniBand for high-bandwidth, low-latency communication, with the NCCL library deeply optimized for this; the interconnect topologies of NPU devices are often different, such as Huawei Ascend's HCCL or the TPU's ICI.
50%UnverifiedThe Ascend version of DeepEP uses HCCL, with UB within a node, HCCL/HCCN's URMA engine across nodes, and kernels written in Ascend C.
50%UnverifiedCANN includes the operator development framework (TBE/DSL), graph compilation engine (ATC/GE), runtime (ACL), communication library (HCCL, corresponding to NCCL), and model conversion and tuning toolchain.
50%