In a collaboration between Imagination Technologies and PaddlePaddle, Imagination’s IMGDNN API has been integrated into Paddle-Lite, growing the artificial intelligence (AI) ecosystem for developers worldwide.
Paddle-Lite is part of Baidu’s deep learning framework PaddlePaddle (Parallel Distributed Deep Learning), and the IMGDNN API enables developers to target PowerVR-architecture-based graphics processing units (GPUs) and neural network accelerators (NNAs) to achieve maximum performance for their applications. At present, the NNA has been integrated into the Paddle-Lite framework through this interface. The move increases the number of frameworks supported by Imagination’s hardware platforms and enables developers to more easily run AI applications inside heterogeneous systems, such as those containing CPUs, GPUs and NNAs.
For example, the ‘Imagination NNA + CPU’ heterogeneous computing system can be established so developers can make the best use of the NNA and CPU.
Developers can now take advantage of the full PaddlePaddle toolset, including PaddleSlim, a compression tool for optimising pre-trained neural network models and converting them so they are suitable for execution on Imagination’s NNA. The code has already been merged into the PaddlePaddle’s development branch and will appear in the next major stable release V2.8.
Yunkai Wang, Ecosystem Product Owner, PaddlePaddle, says; “It is exciting to be collaborating with Imagination in the AI space. PaddlePaddle’s Paddle-Lite inferencing engine can support multiple types of hardware, operating systems, and AI models comprehensively and the successful integration with Imagination’s hardware enriches our ecosystem further. We look forward to working with Imagination in the future to accelerate AI innovation.”
Imagination’s award-winning NNA IP is highly-scalable and specifically designed to accelerate machine learning workloads at the edge. It is silicon proven and has been licensed into markets including automotive, mobile, AIoT and datacentre/desktop. Featuring ultra-high performance per mm2 the new IMG Series4 multi-core is highly power efficient and can scale to 500 TOPS and beyond. Architectural highlights include Imagination Tensor Tiling to reduce bandwidth needs as well as mature software and tools.
IMG Series4 recently won two awards; the Best Automotive Technology award from the World Intelligent Vehicle Conference and the Most Potential Enterprise award at the Elecfans IoT Conference.
Andrew Grant, Senior Director, Artificial Intelligence, Imagination Technologies, says; “We are honoured to join PaddlePaddle’s hardware ecosystem and will support PaddlePaddle’s team in technology and the ecosystem. Imagination NNA can support all mainstream AI frameworks at present and the support for Paddle Lite engine means our ability in this area continues to strengthen.”