寒武纪590
Search documents
国产AI芯片厂商竞争格局、产品力与市场情况
2025-11-24 01:46
国产 AI 芯片厂商竞争格局、产品力与市场情况 20251123 摘要 国产 AI 芯片在部分模型性能上可达英伟达 A100 的 50%-100%,推理 侧华为、寒武纪、昆仑芯达 H100 的 50%-70%,但尚无芯片达到 H100 水平。受美国限制,国产芯片依赖海外产能,少数如华为可获国 内 7 纳米(N+2)产能,多数厂商仅能获得 12 纳米(N+1)制程。 国内 AI 芯片厂商计划在 2026 年 Q1-Q3 量产新一代全国产 12 纳米 (N+1)制程芯片,华为、寒武纪、海光预计上半年实现 7 纳米 (N+2)制程量产,但这些产品多为上一代加强版。华为和寒武纪已开 发出基于光电直连的新型互联方式,部分超越英伟达 NVLink 技术。 二三线 AI 芯片设计公司采用迷你超节点技术,通过定制高速网卡连接 32-64 张 GPU 卡以提高性能。百度昆仑已完成万卡集群调试,并开发 类似平头哥超节点系统,通过与上下游合作提升竞争力。 2025 年 Smith N+2 芯片月产量 4,000-5,000 片晶圆,良率接近 40%,预计 2026 年产量增至每月超 1 万片,但不超 1.5 万片,良率上 限 50 ...
国产GPU的性能PK
傅里叶的猫· 2025-05-08 14:11
Core Viewpoint - The article discusses the performance of domestic GPUs, highlighting the competitive landscape and the impact of sanctions on production capabilities. It emphasizes that while the BR100 from Birun is the most powerful, it cannot be mass-produced due to sanctions, leaving Huawei's 910C as the strongest available option [1][2]. Performance Comparison - The performance ranking of GPUs indicates that the Huawei 910C leads, followed by the Haiguang BW100, with the latter achieving approximately 87% of its potential performance. The Cambrian 590's performance is uncertain, potentially reaching 80% [2]. - The Haiguang BW100 has a deep computing capability of over 400T, which is about 50% of the H800's performance, while the 910C reaches approximately 60% of the H800's performance [1][2]. Memory and Bandwidth - Most domestic GPUs utilize HBM2e memory due to sanctions preventing the use of HBM3e. Sufficient memory is crucial for initiating inference tasks, as insufficient memory can hinder model startup [3]. - Huawei leads significantly in memory bandwidth, which is a critical factor for performance [4]. Pricing Insights - Current market prices for GPUs are as follows: Haiguang BW100 at approximately 100,000 yuan, Huawei 910B at around 70,000 yuan, and 910C at about 180,000 yuan. The Cambrian 590 has seen a price drop from 80,000-85,000 yuan to between 60,000-70,000 yuan [2]. Technical Specifications - A table summarizes key specifications of various GPUs, including memory type, bandwidth, capacity, and arithmetic intensity. For instance, the Huawei 910C features HBM2e with a bandwidth of 3.2 TB/s and a memory capacity of 64 GB [5].