Is this your business? Claim it to manage your IP and profile
The SAKURA-II AI Accelerator from EdgeCortix is a sophisticated solution designed to propel generative AI to new frontiers with impressive energy efficiency. This advanced accelerator provides unparalleled performance with high flexibility for a wide variety of applications, leveraging EdgeCortix's dedicated Dynamic Neural Accelerator architecture. SAKURA-II is optimized for real-time, low-latency AI inference on the edge, tackling demanding generative AI tasks efficiently in constrained environments. The accelerator boasts up to 60 TOPS (Tera Operations Per Second) INT8 performance, allowing it to process large neural networks with complex parameters such as Llama 2 and Stable Diffusion effectively. It supports applications across vision, language, audio, and beyond, by utilizing robust DRAM capabilities and enhanced data throughput. This allows it to outperform other solutions while maintaining a low power consumption profile typically around 8 watts. Designed for integration into small silicon spaces, SAKURA-II caters to the needs of highly efficient AI models, providing dynamic capabilities to meet the stringent requirements of next-gen applications. Thus, the SAKURA-II AI Accelerator stands out as a top choice for developers seeking seamless deployment of cutting-edge AI applications at the edge, underscoring EdgeCortix's leadership in energy-efficient AI processing.
Dynamic Neural Accelerator II (DNA-II) by EdgeCortix enhances the processing capabilities of AI hardware through its state-of-the-art, reconfigurable architecture. This versatile IP core is tailored for edge applications, enabling seamless execution of complex AI tasks both in convolutional and transformer network contexts. With runtime configurability, DNA-II offers unparalleled efficiency, allowing optimized interconnects between compute units to maximize parallel processing. The DNA-II architecture leverages proprietary technologies to reconfigure data paths dynamically, thereby reducing on-chip memory bandwidth and achieving higher operability than standard approaches. Designed to be interfaced with various host processors, DNA-II is adaptable for multiple system-on-chip (SoC) implementations demanding high parallelism and low latency. It's a pivotal part of the SAKURA-II ecosystem, contributing significantly to its generative AI capabilities. A key advantage of DNA-II is its support for scaling up performance starting with 1K MACs, which facilitates customization across different application scales and requirements. Supported by the MERA software stack, DNA-II optimizes computation and resource allocation efficiently, making it ideal for any developer looking to enhance edge AI solutions with powerful, innovative IP.
The MERA Compiler and Software Framework is an industry-leading platform developed by EdgeCortix to streamline the deployment of AI inference applications across various hardware systems. It provides an all-encompassing software environment that supports pre-trained neural network integration into current infrastructures. With a focus on compatibility, MERA is engineered to work with leading ML frameworks, including PyTorch, TensorFlow Lite, and ONNX, ensuring flexibility and ease of use for developers. MERA facilitates the entire cycle of AI model deployment, from compilation to runtime execution, utilizing EdgeCortix's Dynamic Neural Accelerator (DNA) core technology. It’s especially tailored for handling challenging generative AI applications, making it a pivotal component in creating new content in vision, language, and audio tasks. The framework offers tools and APIs that simplify the optimization and runtime configuration of neural networks, enhancing the capability to adapt multiple models concurrently. Another advantage of MERA is the support for model calibration and quantization, making it essential for achieving high precision in deployed models. With an open-source front end leveraging Apache TVM and MLIR functionalities, MERA encourages collaboration and development across ecosystems, enabling faster time-to-market for AI innovations.
Explore the breakthrough collaboration between EdgeCortix and Renesas with their RUHMI Framework, simplifying AI deployment on MCUs and MPUs. Read more
EdgeCortix to advance the NovaEdge AI chiplet with NEDO funding for energy-efficient edge solutions in AI, set to revolutionize multiple tech sectors. Read more
Join the world's most advanced semiconductor IP marketplace!
It's free, and you'll get all the tools you need to discover IP, meet vendors and manage your IP workflow!
Join the world's most advanced AI-powered semiconductor IP marketplace!
It's free, and you'll get all the tools you need to advertise and discover semiconductor IP, keep up-to-date with the latest semiconductor news and more!
Plus we'll send you our free weekly report on the semiconductor industry and the latest IP launches!
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.
