Reduced Operation Set Computing (ROSC) for Flexible, Future-Proof, High-Performance Inference
The versatility and power of deep learning means that modern neural networks have found myriad applications in areas as diverse as machine translation, action recognition, task planning, sentiment analysis and image processing. This is inevitable as the field matures, and there is a high and growing degree of specialisation, which is an accelerating trend. This makes it a challenge to keep with the current state of the art, let alone predict the future compute needs of neural networks.
Designers of neural network accelerator (NNA) IP have a Herculean task on their hands: making sure that their product is sufficiently general to apply to a very wide range of current and future applications, whilst guaranteeing high performance. In the mobile, automotive, data centre and embedded spaces targeted by Imagination’s cutting-edge IMG Series4 NNAs, there are even more stringent constraints on bandwidth, area and power consumption. The engineers at Imagination have found innovative ways to address these daunting challenges and deliver ultra-high-performance and future-proof IP.
To read the full article, click here
Related Semiconductor IP
- DSP-Based 112G SerDes
- XTAL oscillator in TSMC-7nm
- GPU
- V-by-One Verification IP
- AI model compression IP
Related Blogs
- Global semicon market set for slowdown due to deteriorating business climate!
- Bluetooth set as short range wireless standard for smart energy!
- ARM Eyes Computing
- Moore's Law Continues, but Needs Help from Heterogeneous Computing
Latest Blogs
- Embedded Security explained: Secure boot for embedded systems
- World's First Standards-Compliant 112G PHY IP for Linear Optics: A Turning Point for AI Interconnects
- One Key for Every Door: How Aliro Extends the UWB Digital Key Beyond the Car
- Reprogrammable Post-Quantum Security for SoCs: Why Crypto-Agility Matters
- Designing the Beam Steering Core for a C-Band AESA: A Look at VSI's VBF0644 GaAs Beamformer IC