Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Dataflow accelerator architecture for general matrix-matrix multiplication and tensor computation in deep learning

Dataflow accelerator architecture for general matrix-matrix multiplication and tensor computation in deep learning

US Patent 12164593 · Granted Dec 10, 2024

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Methods for crystal growth by replacing a sublimated target source material with2025
Cache-coherent interconnect based near-data-processing accelerator2025
Coordinated in-module RAS features for synchronous DDR compatible memory2025
Hybrid memory management systems and methods with in-storage processing and attr2025
Systems and methods for scalable and coherent memory devices2025
Coherent memory system2025
High bandwidth memory system2025
High bandwidth memory system2025
High bandwidth memory system2025
Adjustable function-in-memory computation system2025
In-memory computing with cache coherent protocol2025
Two-dimensional processing array with a vertically stacked memory tile array2025