Cambricon将其下一代人工智能产品授权NetSpeed Fabric IP
San Jose, Calif. -- June 12, 2018 -- NetSpeed Systems, Inc. today announced that Cambricon Technologies, a leader in China’s AI market, has licensed NetSpeed’s Interconnect IP for use in its next generation system-on-chips (SoCs). Cambricon’s chips are designed specifically for artificial intelligence (AI) applications and are used in data center, security surveillance, and autonomous driving devices.
New AI-enabled applications are demanding new SoC architectures and interconnect implementations are becoming far more important to design success. AI applications tend to have many accelerator cores all bursting large blocks of data simultaneously, easily overwhelming traditional interconnect schemes. The SoCs used in AI applications demand unprecedented performance, sophisticated functionality and ultra-low power.
Cambricon needed an interconnect solution that could meet the performance requirements for its next-generation chip and new features that would enable them to achieve their frequency targets. After careful analysis and evaluation of the available options, Cambricon chose NetSpeed’s physically-aware interconnect IP.
“Most NoCs incorporate concepts of packet switching, dynamic priority, virtual channels, and more to achieve better interconnect bandwidth and latency, said Mike Demler, senior analyst at The Linley Group. “However, automation of the architecture and design process using machine learning is a new frontier for interconnect technology being pioneered by NetSpeed.”
“NetSpeed is the unquestionable leader in providing a high performance interconnect solution for the AI market segment,” said Tianshi Chen, CEO of Cambricon. “The reason we choose NetSpeed is the scalability of the IP and the ability to configure sophisticated topologies for high performance required by AI applications with minimal effort. Hence, we are choosing NetSpeed’s IP with its advanced AI extensions for our next-gen SoC designs.”
"We are pleased to announce our collaboration with Cambricon, a leader and pioneer in designing SoCs targeted for the AI market," said Anush Mohandass, Vice president of marketing and business development at NetSpeed. "Cambricon’s usage of our Orion-AI IP is a reflection of the strength of our technology. It reinforces NetSpeed's leadership in the AI market, both for training and edge computing devices."
About NetSpeed Systems
NetSpeed is at the heart of next-gen system-on-chip (SoC) applications that are transforming the way we interact with each other and how we connect with the world. Whether you are a hardware architect looking for cache coherency solutions to realize your ideas into silicon or a SoC designer looking for a high performance and efficient interconnect or a safety manager looking for solutions to build resilient, fault-tolerant systems—NetSpeed has a solution for you. Learn about how NetSpeed is bringing the power of artificial intelligence to SoC design and architecture at www.netspeedsystems.com
Related Semiconductor IP
- Die-to-Die, High Bandwidth Interconnect PHY Ported to TSMC N7 X24
- Die-to-Die, High Bandwidth Interconnect PHY Ported to TSMC N5 X24, North/South (vertical) poly orientation
- Crossbars Interconnect
- Die-to-Die, High Bandwidth Interconnect PHY in TSMC (N7, N5)
- Network-on-Chip (NoC) Interconnect IP
Related News
- Cambricon将Moortec的嵌入式PVT监控子系统IP应用于人工智能(AI)和机器学习芯片
- 寒武纪为其新一代人工智能处理器芯片采用Synopsys的 HAPS产品
- NetSpeed和Esperanto在人工智能SoC领域合作
- Graphcore获得3000万美元风险投资用于加速人工智能开发