Groq develops the Tensor Streaming Processor. TSP houses a single enormous processor that has hundreds of functional units. The architecture reduces instruction-decoding overhead, and handles integer and floating-point data, which delivers better accuracy for inference and training.

Syntiant uses low power semiconductors to move machine learning from the cloud to the edge device enabling artificial intelligence for sensor, voice, and video applications in most battery-powered products. The company has put its technology to work developing more intelligent hearing aids.

ArchiTek is an AI technology company that researches and develops prototype circuits for information technology systems.

Mythic develops a local AI platform, comprised of both hardware and software, that turns devices into secure intelligent assistants. Mythic leverages local AI to enable consumer electronics, wearable and security and monitoring manufacturers to deliver integration and privacy demanded by consumers. Initial targeted markets include smart home, action cameras, healthcare systems, security and monitoring for commercial and home use and drones for industrial applications.

Cerebras is a computer systems company dedicated to accelerating deep learning. The Wafer-Scale Engine (WSE), is at the heart of the deep learning system, the Cerebras CS-1. The WSE delivers more computing more memory, and more communication bandwidth. This enables AI research at high speeds and scale.

Ceremorphic has built an architecture that delivers the performance required for applications such as AI model training, HPC, drug discovery, and metaverse processing. Designed in tune with advanced silicon geometry, its architecture solves high-performance computing needs in reliability, security, and power consumption at scale.