Digital Signal Processors (DSPs) are a key part of any battery-powered device offering a way to process audio data with a very low power consumption. Increasingly these DSPs are also being used to run neural networks such as wake-word detection, speech recognition, and noise suppression. Cadence is developing a highly optimized software library, called NeuralNet library (NNLIB), that leverages the SIMD and VLIW capabilities of their low-power HiFi DSP.

3m read timeFrom blog.tensorflow.org
Post cover image
Table of contents
Google and Cadence – A Multi-Year Partnership for Enabling AI at the EdgePerformance ImprovementsHow to use these optimizationsLooking AheadAcknowledgements

Sort: