Software Architecture

Built upon mainstream recommendation frameworks, CANN, and diverse hardware and network architectures, Rec SDK TensorFlow addresses the specific requirements of search, recommendation, and advertising model training. It provides high-performance, streamlined APIs designed for ease of use, enabling Ascend AI Processor to achieve highly efficient training for search, recommendation, and advertising models.

**Table 1** Architecture modules
Rec SDK TensorFlow Module	Description
API layer	Provides easy-to-use APIs to simplify customer access and support service growth.
Recommendation function layer	Provides core capabilities to meet customer requirements.
Recommendation acceleration layer	Provides core components to build performance competitiveness and offer superb performance for the entire system.
Sparse storage layer	Supports large-scale sparse table storage of more than 10 TB.

Parent topic: Introduction