Is this your business? Claim it to manage your IP and profile
The BAT audio platform from Dolphin Design is an advanced IP suite tailored for the creation of high-performance audio solutions. Catering mainly to smart speakers, hearables, and IoT applications, BAT encompasses a set of high-fidelity analog-to-digital and digital-to-analog converters (ADC/DAC) along with advanced audio codecs that exceed traditional power and performance metrics. BAT features integrated Voice Activity Detection (VAD) capabilities, distinguishing it as a suitable technology for applications demanding always-on audio processing. With a focus on configurable and adaptable digital processing mechanisms, BAT ensures seamless integration and assembly of audio devices yielding shortened time-to-market cycles and fortified performance robustness. Its configurability extends to supporting varied applications, encouraging limitless customization for reduced component power consumption while preserving sound quality at its peak. Whether it is a MEMS microphone, digital signal processing, or supporting analog and digital microphone inputs, BAT's suite is equipped with tailored solutions for a variety of audio-related challenges.
CHAMELEON is a one-stop MCU subsystem platform developed with a focus on enabling ultra-low power operations for intelligent IoT and sensor-centric devices. The platform's architecture is uniquely event-based, supporting versatile data processing at ultra-low power levels, while allowing flexibility to switch or handle multiple CPU cores effectively. Central to its design is the integration of a fine-grained power management unit and a machine learning booster, facilitating energy-saving operation modes while still ensuring robust performance for edge AI applications. This allows CHAMELEON to serve sectors where efficient data handling and energy conservation are paramount. With readily available pre-verified architectures and compatibility with multiple cores including Cortex M-series processors, CHAMELEON is configured for seamless interoperability with Dolphin Design’s SPIDER power management systems. Its design toolchain supports the quick adaptation and customization according to specific application needs, thereby reducing both development costs and time-to-market latency.
RAPTOR is a Neural Processing Unit (NPU) designed specifically for energy-efficient AI and Machine Learning applications. Capable of executing deep neural networks with impressive efficiency, RAPTOR is suited for far-edge AI systems that require low power but high-performance computational capabilities. This IP features a flexible architecture accommodating up to 128 processing units, optimizing computing at the smallest power consumption threshold. RAPTOR includes a robust AI stack, facilitating the deployment of neural networks with minimized inference latency and power draw, catering particularly to artificial intelligence vis-a-vis data processing tasks. Additionally, RAPTOR is equipped with advanced SDK tools to speed up the transition from designed models in data science programs to functional applications on physical devices. Its well-engineered integration support ensures it meets diverse market demands while maintaining optimal energy parameters.
The SPIDER Power Management IP platform is an advanced solution designed to streamline the creation of energy-efficient power networks for SoCs. SPIDER offers a comprehensive suite of voltage regulators, monitors, and power controllers that redefine the way energy is managed across circuits. Notably, it integrates an innovative controller generator which aids in optimizing energy distribution, and adds efficiency to the system's power functions. This platform stands out for promoting energy efficiency as a central theme in IC design by addressing the needs for smart SoC architectures. With its turnkey approach, SPIDER accelerates time-to-market, achieving power network design, verification, and integration within a mere few weeks. Its design methodology ensures predictability and standardization, which are crucial in preventing silicon failures and enhancing design efficacy. Furthermore, SPIDER supports a wide range of process nodes, allowing for personalized application configurations via a system-level power architecture utility. The platform's robust PMU design capabilities are key in adapting to diverse SoC complexities, making it the ideal choice for designers seeking maximal energy effectiveness and minimized design latency.
PANTHER is an adaptable Digital Signal Processing (DSP) platform, uniquely engineered for balancing massive data processing needs with the lowest possible power consumption rates. Utilizing a scalable architecture, PANTHER is capable of supporting a wide array of AI-driven and traditional DSP tasks with its multi-core processing capabilities. PANTHER stands out for its ability to execute multi-threaded processing tasks efficiently, enabled by a RISC-V based architecture. This setup includes a complete software development ecosystem with extensive libraries and toolsets that facilitate the integration and deployment of versatile applications. Applications range from audio processing, including keyword spotting and scene classification, to critical industrial monitoring tasks. Its adaptability ensures it effectively manages computational tasks without exceeding energy budgets, making it indispensable for devices focusing on data-intensive applications.
Join the world's most advanced semiconductor IP marketplace!
It's free, and you'll get all the tools you need to evaluate IP, download trial versions and datasheets, and manage your evaluation workflow!
To evaluate IP you need to be logged into a buyer profile. Select a profile below, or create a new buyer profile for your company.
