Design and train your network in a familiar tool such as TensorFlow or PyTorch, and the GrAIFlow SDK will translate it into code that can run on our super-efficient hardware.
Process only the information that has changed, which optimizes energy and maximizes efficiency, saving time, money, and vital natural resources.
All numbers are estimated performance based on simulations of GrAI Core; Further optimizations in sparsity and voltage scaling would improve performance Sparsity is the level of correlation between frames. Actual hardware performance may vary.
Life-Ready AI Ecosystem_
Network of partners working together to provide comprehensive audio/video AI processing solutions to our customers.
Commercialization Partners
Alliances
IP Vendors
Education & Research
Coming Soon...
World’s first Dataflow and sparsity-enabled System-On-Chip (SOC) delivering Resnet-50 inferences in less than 1ms with Batch=1