Ceva-TeakLite-4 is a low-power, native 32-bit, variable 10-stage pipeline, fixed-point DSP architecture framework. The Ceva-TeakLite-4 is a fully synthesizable, process-independent design that allows the SoC designer to select the optimal implementation in terms of silicon area, power consumption, and operating frequency.
Ranging from dual 16x16-bit MAC and single 32x32-bit MAC to quad 16x16-bit MAC and dual 32x32-bit MAC, The Ceva-TeakLite-4 DSP family includes the deeply embedded Ceva-TL410 and Ceva-TL411, along with the cache enabled Ceva-TL420 and Ceva-TL421 DSP cores, that are all fully compatible. The four cores enable much needed scalability and are also backward compatible with previous generation cores of the Ceva-TeakLite family.
Thanks to its scalability, the Ceva-TeakLite-4 DSP family is efficiently handling most demanding audio, voice, sensor fusion and wireless connectivity use-cases, whether targeting ultra-low-power always-on voice control, advanced multi-microphone noise reduction and voice processing, VoLTE or high-performance multichannel audio processing and post-processing. Ceva-TeakLite-4 cores are adopted by mobile, home, IoT and automotive chip vendors, for use in the smallest, lowest-power audio CODEC, audio DSP, voice activation and sensor hub chips, through Baseband, Application Processors and connectivity chips, and up to high-end multi-channel audio such as wireless speakers, digital televisions (DTVs), set-top boxes (STBs), game consoles, and more.
Combined with the Ceva-Bluetooth hardware and software, the Ceva-TeakLite-4 further enables a wide range of wireless applications from Bluetooth Smart (a.k.a. single mode Bluetooth Low Energy or BLE) to Bluetooth Smart Ready (a.k.a. dual mode Bluetooth Low Energy) and wireless audio.
Multifunctional DSP Architecture for High-Performance, Low-Power Audio/Voice/Sensing and Wireless Communication Applications
Overview
Key Features
- Small size and ultra-low-power
- 90K gates area optimized
- High-performance
- Up to 1.5 GHz @ 28nm HPM
- Native 32-bit, Harvard/SIMD architecture DSP with multiple options:
- 1/2/4 32x32-bit multipliers
- 2/4 16x16-bit multipliers
- 32-bit register file
- Automatic 32-bit saturation
- 64-bit and 72-bit MAC accumulation for wide dynamic range
- Optional tightly-coupled instruction sets
- Easy software development
- Optimizing C compiler
- Cycle-accurate simulation and graphical profiling of the entire DSP sub-system
- Macro assembler, linker, and GUI debugger and IDE
- Tight MATLAB bi-directional connectivity
Benefits
- CEVA-TeakLite-4 DSP cores can be used for applications that are highly sensitive to die-area and power consumption
- CEVA-TeakLite-4 DSP cores support the toughest HD-audio and HD-voice use cases with fully certified codecs available
- CEVA-TeakLite-4 supports a wide range of wireless connectivity and wireless audio applications, including a full Bluetooth solution available
- Smooth C-level software development and easy integration into target SoC reduces risk and time-to-market
Block Diagram
Video
CEVA offers an optimized solution for integrating sensor hub and connectivity functionality into this new generation of products. Based on our CEVA-TeakLite-4 DSP platform and the CEVA-Bluetooth solution, while leveraging software capabilities from a host
CEVA offers an optimized solution for integrating sensor hub and connectivity functionality into this new generation of products. Based on our CEVA-TeakLite-4 DSP platform and the CEVA-Bluetooth solution, while leveraging software capabilities from a host of ecosystem partners, CEVA delivers the low power and performance needed to efficiently process multiple types of user and environmental inputs, and be always connected. In this demonstration we'll see how the CEVA-TeakLite-4 DSP is used as a sensor hub for always on voice activation, face activation and motion detection, as well as wirelessly streaming audio to a Bluetooth speaker. All this is done while operating with extremely low power -- down to 150 micro-Watt in standby mode for Bluetooth LE and multiple always-on sensing capabilities in a 28-nanometer process.
Applications
- Voice assistants
- Voice control
- Headsets
- Mobile audio
- Wearables
Technical Specifications
Related IPs
- Highly powerful and scalable multi-mode communication processor for IoT wireless applications
- Modern Audio DSP, designed for battery operated, high-performance, audio and voice applications
- Low-power, low-gate-count, highly-configurable DSP core for audio and control processing
- High-performance Processor for Real-time and Linux Applications
- Highly powerful, multi-mode communication processor for IoT wireless applications
- High-performance, low-power 2D composition IP core for embedded devices