Skip to main content

Huawei Ascend 910B

Overview

Huawei Ascend 910B is part of the Ascend series of AI training chips, based on the Da Vinci architecture, entering mass production in 2022-2023. Under US export controls, it has become the mainstream NVIDIA alternative in the Chinese market. Equipped with 64GB HBM3 memory and 320 TFLOPS FP16 compute, it has been adopted by major Chinese AI projects at Baidu, Alibaba, Tencent, and others.

Core Specifications

ItemSpec
ArchitectureDa Vinci (Huawei proprietary)
ProcessTSMC 7nm+ (including SMIC localization efforts)
Memory64 GB HBM3
Memory Bandwidth1,224 GB/s
FP3264 TFLOPS
FP16320 TFLOPS
INT8640 TOPS
TDP310 W
InterconnectHCCS (Huawei proprietary)
Form FactorPCIe half-height half-length

Vendor Information

ItemDetails
ManufacturerHuawei Technologies Co., Ltd.
Websitehttps://www.hiascend.com
Product Pagehttps://www.hiascend.com/en/hardware/ascend-910-b
CANN Software Stackhttps://www.hiascend.com/en/software/cann
MindSporehttps://www.mindspore.cn
Driver Downloadshttps://www.hiascend.com/developer/download

Key Features

  • HCCS High-Speed Interconnect: NVLink alternative
  • CANN Heterogeneous Compute Architecture: CUDA-like
  • MindSpore Framework: Huawei's proprietary AI framework
  • Domestic Ecosystem: Kunpeng + Ascend + MindSpore complete stack

Use Cases

  • LLM training (tens of billions of parameters)
  • Domestic replacement in the Chinese market
  • Government and state-owned enterprise AI projects
  • Large model inference