Imagination and PaddlePaddle announce collaboration to grow the ecosystem for artificial intelligence (AI) for developers worldwide
London, UK and Beijing, China; 1st February 2021 – 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 run AI applications inside heterogeneous systems, such as those containing CPUs, GPUs and NNAs, more easily.
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."
About PaddlePaddle
PaddlePaddle, on top of Baidu's years of efforts on research, development and commercialization of deep learning technologies, has been open-sourced to professional communities as China's first self-developed industrial deep learning platform, providing rich features that include core training and inference frameworks, application-based model banks, end-to-end development kits, and various kinds of toolkits from visualization purpose to 3rd party model hub. Up to now, PaddlePaddle has over 2.65 million developers around the world, serving 100,000+ enterprises, and more than 340,000 models have been created accordingly. PaddlePaddle can help developers realize deep learning related ideas and launch AI businesses in a faster manner and is now empowering an increasing number of industries in commercializing AI technologies and accomplishing intelligent transformation.
About Imagination Technologies
Imagination is a UK-based company that creates silicon and software IP (intellectual property) designed to give its customers an edge in competitive global technology markets. Its graphics, compute, vision and AI technologies enable outstanding power, performance and area (PPA), fast time-to-market and lower total cost of ownership. Products based on Imagination IP are used by billions of people across the globe in their smartphones, cars, homes, and workplaces.
See www.imgtec.com.
|
Imagination Technologies Group plc Hot IP
Related News
- UMC Expects AI to Grow to $3 Billion Business
- BittWare selects EdgeCortix's SAKURA-I AI Processors as its Edge Focused Artificial Intelligence Acceleration Solution
- Imagination Joins Baidu PaddlePaddle "Hardware Ecosystem Co-Creation Program"
- Arteris IP FlexNoc Interconnect and Resilience Package Licensed by Hailo for Artificial Intelligence (AI) Chip
- RIOS Laboratory and Imagination announce partnership to grow the RISC-V ecosystem
Breaking News
- Frontgrade Gaisler Unveils GR716B, a New Standard in Space-Grade Microcontrollers
- Blueshift Memory launches BlueFive processor, accelerating computation by up to 50 times and saving up to 65% energy
- Eliyan Ports Industry's Highest Performing PHY to Samsung Foundry SF4X Process Node, Achieving up to 40 Gbps Bandwidth at Unprecedented Power Levels with UCIe-Compliant Chiplet Interconnect Technology
- CXL Fabless Startup Panmnesia Secures Over $60M in Series A Funding, Aiming to Lead the CXL Switch Silicon Chip and CXL IP
- Cadence Unveils Arm-Based System Chiplet
Most Popular
- Cadence Unveils Arm-Based System Chiplet
- CXL Fabless Startup Panmnesia Secures Over $60M in Series A Funding, Aiming to Lead the CXL Switch Silicon Chip and CXL IP
- Esperanto Technologies and NEC Cooperate on Initiative to Advance Next Generation RISC-V Chips and Software Solutions for HPC
- Eliyan Ports Industry's Highest Performing PHY to Samsung Foundry SF4X Process Node, Achieving up to 40 Gbps Bandwidth at Unprecedented Power Levels with UCIe-Compliant Chiplet Interconnect Technology
- Arteris Selected by GigaDevice for Development in Next-Generation Automotive SoC With Enhanced FuSa Standards
E-mail This Article | Printer-Friendly Page |