Some of the flagship DAWN projects include:
MacroBase is a new analytic monitoring engine designed to prioritize human attention in large-scale datasets and data streams. Unlike a traditional analytics engine, MacroBase is specialized for one task: finding and explaining unusual or interesting trends in data.
Snorkel is a system for rapidly creating, modeling, and managing training data, currently focused on accelerating the development of structured or “dark” data extraction applications for domains in which large labeled training sets are not available or easy to obtain.
Spatial is a new Domain Specific Language for programming reconfigurable hardware from a parameterized, high level abstraction.
Weld is a runtime for improving the performance of data-intensive applications. It optimizes across libraries and functions by expressing the core computations in libraries using a small common intermediate representation, similar to CUDA and OpenCL.
NoScope is a system for querying videos at scale using neural networks and for accelerating neural network inference by over 1000x by exploiting model specialization and dynamic cascades.
DAWNBench is a benchmark suite for end-to-end deep learning training and inference.