According to Cisco’s forecast, there will be 850 ZB of data generated by mobile users and IoT devices by 2021. With a surge in data, challenges like latency will emerge. And, if one has to derive intelligence from algorithms in real-time, the traditional systems cannot be trusted for long. Thanks to the efforts of top companies to place supercomputers in the pockets, edge computing systems have garnered significant attention. Over the past couple of years chipmakers have been bullish on developing integrated solutions for edge cases.
As we approach an era of IoT, 5G and portable medical devices, it is crucial to facilitate developers to quickly develop and deploy edge applications.
Companies like Huawei too have been explicit about their AI ambitions. Last year they launched their AI SoC, Ascend 310, which powers Huawei’s developer AI toolkit among other products. The Atlas 200 Developer Kit is a developer board that uses the Atlas 200 AI accelerator module. This developer kit allows developers to leverage the Atlas 200 AI accelerator module easily. For developers looking into R&D related to smart cities, drones and robotics, Atlas 200 DK can come in handy.
What’s In The Box
The Atlas 200 DK developer kit is a high-performance AI application development board that integrates the Ascend 310 AI processor to facilitate quick development and verification, making it an ideal option for scenarios such as developer solution verification, university education, and scientific research. Whereas, the Atlas 200 AI accelerator module performs image and video analysis and inference and has been widely used in intelligent surveillance, robots, drones, and video servers.
Coming to the SoC, the Ascend 310 AI Processor is a chip designed for image recognition, video processing, inference computing, and machine learning. It features high performance and low power consumption. The Ascend 310 chip has two built-in AI cores, supports 128-bit, and delivers computing power of up to 22 TOPS.
Powered by the Huawei Ascend 310 AI processor, the Atlas 200 DK integrates various peripheral interfaces and the Mind Studio, facilitating access to the development environment and enabling quick development.
So, who are these kits designed for?
Huawei’s AI computing platform is for those who are looking for:
- Compute Power
Inspired by Huawei Ascend series AI processors, a single chip delivers 16 TeraOPS (TOPS) of INT8 and supports real-time analytics of 16-channel HD videos with a power consumption of less than 8 Watts.
- Ease of Use
The all-scenario AI infrastructure solution is designed and tuned for device-edge-cloud, fully meeting the AI application scenario requirements in the intelligent era.
Huawei’s AI computing platform supports mainstream frameworks, and provides easy-to-use code porting and model conversion tools, allowing for flexible collaboration with industry ISVs to build an open industry ecosystem.
Along with developer kits, one can also leverage Huawei’s edge and inference servers for solving compute intensive problems with AI.