Benefit of pruning and clustering a neural network for before deploying on Arm Ethos-U NPU
July 24, 2023
Pruning and clustering are optimization techniques:
- Pruning: setting weights to zero
- Clustering: grouping weights together into clusters
These techniques modify the weights of a Machine Learning model. In some cases, they enable:
- Significant speed-up of the inference execution
- Reduction of the memory footprint
- Reduction in the overall power consumption of the system
We assume that you can optimize your workload without loss in accuracy and that you target an Arm® Ethos NPU. You can therefore prune and cluster your neural network before using the Vela compiler and deploying it on the Ethos-U hardware. See below for more information on optimizing your workload.
To read the full article, click here
Related Semiconductor IP
- Flexible Pixel Processor Video IP
- Complex Digital Up Converter
- Bluetooth Low Energy 6.0 Digital IP
- Verification IP for Ultra Ethernet (UEC)
- MIPI SWI3S Manager Core IP
Related Blogs
- Reviewing different Neural Network Models for Multi-Agent games on Arm using Unity
- Neural Network Model quantization on mobile
- Windows on Arm is Ready for Prime Time: Native Chrome Caps Momentum for the Future of Laptop Computing
- New Armv9 CPUs for Accelerating AI on Mobile and Beyond
Latest Blogs
- CNNs and Transformers: Decoding the Titans of AI
- How is RISC-V’s open and customizable design changing embedded systems?
- Imagination GPUs now support Vulkan 1.4 and Android 16
- From "What-If" to "What-Is": Cadence IP Validation for Silicon Platform Success
- Accelerating RTL Design with Agentic AI: A Multi-Agent LLM-Driven Approach