Chinese chiplet architecture for data centres, automotive

Chinese chiplet architecture for data centres, automotive

Business news |
By Nick Flaherty

Blue Ocean Smart System in China has developed a scalable chiplet architecture for high performance computing, automotive and data centre applications.

The chiplet architecture uses multiple processors from VeriSilicon in China, including the CC8400 General-Purpose Graphics Processor Unit (GPGPU), VIP9400 Neural Network Processor (NPU), and VC8000D Video Processor Unit (VPU).

VeriSilicon’s CC8400 GPGPU supports half-precision 16-bit floating-point and full-precision 32-bit floating-point, as well as 8-bit, 16-bit, and 32-bit fixed-point data precision. The VIP9400 NPU supports AI transformer models for data centre and automotive applications while the multi-format VC8000D VPU can be used for video analytics.

The chiplets are linked via Blue Ocean’s patented BxLink interconnect to reduce product development costs, and shorten development cycles for the markets focused on AI training, inferencing, high-precision computing, large-scale image processing, fluid dynamics, climate science, autonomous driving, advanced robotics, and biomedicine.

The first-generation 12nm Chiplet GPGPU chip, BlueFin, and NPU chip, BlueDanio, are available for customers at the same time.

“The demand for high-performance computing in data center and automotive applications is increasing rapidly. VeriSilicon’s extensive portfolio of high-performance processors and their expertise in chip implementation makes them an excellent partner for our chiplet products’ deployments,” said John Rowland, President of Blue Ocean. “The recent advancements in AI applications, such as ChatGPT, have further fueled the demand for more GPGPU and NPU computing. With the innovative chiplet-based system architecture, we can provide quite a number of unique features and competitive solutions to our customers. The success of shipments of Blue Ocean’s Bx series of chipsets to the market last year has proven this point.”

If you enjoyed this article, you will like the following ones: don't miss them by subscribing to :    eeNews on Google News


Linked Articles