Cadence has announced the Cadence Tensilica Hi-fi iQ DSP IP as the sixth generation of its Hi-fi DSP family, introducing a new architecture that is purpose-built for next-generation voice Artificial Intelligence and emerging immersive audio applications. The company is targeting use cases across home entertainment, automotive infotainment and smartphone markets, where demand for more sophisticated audio and voice experiences is growing rapidly. The Hi-fi iQ DSP is designed to provide the performance and energy efficiency needed to meet increasingly intensive system on chip computational requirements in these segments.
Compared to the industry-leading Tensilica Hi-fi 5s DSP, the Hi-fi iQ DSP offers 2X greater compute performance, 8X higher Artificial Intelligence performance and more than 25% energy savings for most workloads, while it is delivering over 40% performance uplift on numerous audio codecs. This set of improvements is intended to let chip designers handle more advanced audio processing and Artificial Intelligence workloads without a proportional increase in power consumption. The new architecture aims to support both traditional audio codecs and emerging voice and language models within a single, efficient digital signal processing core.
Industry analyst Anshel Sag, VP and principal analyst at Moor Insights and Strategy, said that with the increased growth of Artificial Intelligence across virtually every facet of the industry, audio and language have become critical interfaces for users. Sag stated that the Artificial Intelligence performance and energy savings with Cadence’s new flagship Tensilica Hi-fi iQ DSP position it to enable future Artificial Intelligence enhanced applications and to offload processing from other intellectual property blocks in a system on chip. Cadence is positioning the Hi-fi iQ DSP IP as a central enabler for next-generation, voice-centric and immersive audio products that need higher performance within strict power budgets.
