Hua Xia GPT (hxGPT), China's leading licensor of customisable processor IP cores, has developed a family of scalable, programmable AI accelerators. The cores range from handset to edge processing for a wide range of applications including the Internet of Things (IoT), Advanced Driver Assistance Systems (ADAS), Self-driving Cars, Robotics, Surveillance, and Machine Vision.
The "Song" AI core is a highly configurable IP block that provides for efficient implementations of CNN's. Running at up to 1GHz in 28nm technology, each accelerator core contains 288 MAC units scalable to beyond 2 TFLOPS. Performance, power, and size can be optimised for low power embedded IoT devices and edge processing designs.
Accuracy can be optimised using built-in 16-bit integer or floating point operations. Support for compressed 8-bit data is provided. Extended precision intermediate results reduce errors in both regression and classification workloads.
Targeting inference applications, the AI accelerator supports multi-dimensional tensor processing. The design provides direct support for convolution, pooling, dropout, padding, and programmable activation functions. A library of popular CNN networks is provided with general framework support such as Tensorflow and Caffee is in development.
Previously hxGPT announced availability and licensing of the Changcheng out-of-order superscalar CPU. This has been tested in TSMC's 28nm process, the core is configurable providing for multiple performance levels based on customer requirements. Memories, caches, and out-of-order features (issue window, ROB, rename, etc.) can all be customised. Depending upon technology selection the core can run up to 3GHz at very low power.
The Song AI core integrates with the Changcheng CPU for ease of programming. Both are programmed using the same proprietary processor programming environment.
WuxiDSP, hxGPT's customer of both the Changcheng core and Song AI core, has used them for silicon that is scheduled to sample later this year targeting edge IoT processing, says Xiaodong Zhang, Chief Engineer of WuxiDSP.
hxGPT is the only IC design house in China with a portfolio of proprietary intellectual property for CPU, DSP, GPU and AI accelerators targeted at high-end SoC designs for heterogeneous computing. The company has 8 issued patents and more than 90 pending world-wide patents covering the core architecture and implementations of the next generation processor design. It has operations in New York, Beijing, and Shanghai.
www.GeneralProcessorTech.com
Targeting inference applications, the AI accelerator supports multi-dimensional tensor processing. The design provides direct support for convolution, pooling, dropout, padding, and programmable activation functions. A library of popular CNN networks is provided with general framework support such as Tensorflow and Caffee is in development.
Previously hxGPT announced availability and licensing of the Changcheng out-of-order superscalar CPU. This has been tested in TSMC's 28nm process, the core is configurable providing for multiple performance levels based on customer requirements. Memories, caches, and out-of-order features (issue window, ROB, rename, etc.) can all be customised. Depending upon technology selection the core can run up to 3GHz at very low power.
The Song AI core integrates with the Changcheng CPU for ease of programming. Both are programmed using the same proprietary processor programming environment.
WuxiDSP, hxGPT's customer of both the Changcheng core and Song AI core, has used them for silicon that is scheduled to sample later this year targeting edge IoT processing, says Xiaodong Zhang, Chief Engineer of WuxiDSP.
hxGPT is the only IC design house in China with a portfolio of proprietary intellectual property for CPU, DSP, GPU and AI accelerators targeted at high-end SoC designs for heterogeneous computing. The company has 8 issued patents and more than 90 pending world-wide patents covering the core architecture and implementations of the next generation processor design. It has operations in New York, Beijing, and Shanghai.
www.GeneralProcessorTech.com
Related stories:
- CEVA launches AI cores for edge processing
- Qualcomm pushes on-chip AI with SenseTime deal
- Another startup aims for embedded AI
- Qualcomm boosts its embedded AI development with Scyfer buy
- ARM takes aim at embedded AI
- NVIDIA pushes artificial intelligence into embedded designs with Jetson TX2
- Xilinx pushes machine learning and AI to the edge for embedded applications
- Startup aims to bring artificial intelligence to IoT nodes
No comments:
Post a Comment