Cadence Releases New Version of Tensilica Systems
Cadence Design Systems has launched the Cadence Tensilica HiFi 3z DSP IP core for system-on-chip (SoC) designs targeted for the latest mobile and home entertainment applications, including smartphones, augmented reality (AR)/3D goggles, digital TVs and set-top boxes. The new HiFi 3z architecture offers more than 1.3 times better voice and audio processing performance than its predecessor, the HiFi 3 DSP.
Higher voice sample rates require more complex voice pre-processing. Enhanced Voice Services (EVS), the latest mobile voice codec supporting voice over LTE (VoLTE), supports up to a 48kHz sample rate, compared to 16kHz for the previous AMR-WB codec.
The HiFi 3z DSP offers a number of architecture and instruction set architecture improvements over the earlier HiFi 3 DSP, including the following:
- Dual load/store;
- Advanced FLIX bundling (multiple-base ISA operations per cycle);
- Double the MACs for 16x16 (octal MAC);
- Enhanced ISA for accelerating FFTs, FIRs and IIRs;
- New instruction extensions to improve codec (especially EVS) performance for mobile;
- 4-way, 8-bit load for improved voice trigger performance; and
- 8-way, 8-bit load for reduced neural network memory usage.
"In pursuit of better consumer experiences, new audio and voice codecs and pre- and post-processing functions have emerged that significantly increase the signal processing and control code workloads," stated Larry Przywara, group director of marketing, audio/voice IP at Cadence, in a statement. "We've designed the HiFi 3z DSP to efficiently support these new audio and voice compute requirements."
Tensilica HiFi DSP audio/voice/speech processors support more than 200 software packages and more than 95 software partners in the Tensilica Xtensions partner program. More than 75 semiconductor companies and system manufacturers have selected Tensilica HiFi DSPs for their audio, voice and speech products.
Cadence's Tensilica Fusion F1 DSP will power Fortemedia's always-on smart microphone processor for voice trigger capabilities.