We offer an array of products and services to fit partners' development needs. Partners have a variety of applications and requirements, and we offer the flexibility to select what's needed to get the job done.
Drive algorithm-to-silicon system design with our model-hardware co-design tools. Work in PyTorch or Tensorflow while our tools do the low level work to ensure models make best use of the target hardware.
Quickly evaluate and deploy with access to our repository of pre-trained, pre-optimized neural network models. Customize and fine-tune these models for a specific application and hardware configuration.
Accurately estimate power, performance, area, and other key performance metrics for your system before deploying to an FPGA, IP or ASIC. Our hardware simulation tools enable rapid iteration of model and hardware configuration for a quick and agile system design process.
Rapidly prototype systems and applications with our fully customizable FPGA prototype platform. Take a model and map it to an FPGA prototype of an efficient embedded hardware design to assess real-world performance.
Tailor the hardware to your particular applications and system. Our architecture is designed for maximum scalability. Alternatively, simply choose from one of our pre-optimized ready-to-deploy hardware designs for your SoC.
Tell us about your application and we will design a fully optimized solution from concept to ASIC. We also provide consultation and support from start to finish to ensure any design is running as efficiently as possible.
Evaluate prospective deployments with Femtosense technology at low risk. We provide software tools and support for partners to benchmark models targeting Femtosense hardware. We can also take a partner-defined task and design, train, and benchmark reference models.
Prototype real-time deployments with Femtosense development kits to test our complete technology stack. We provide materials to prototype in-house. We can also take care of the whole project and everything needed to prepare and verify the stack for deployment.
Deploy the full technology stack according to partner specifications. We provide ASICs or IP blocks, the software to run them, and ongoing support.