Tensor Data Scattering and the Impossibility of Slicing Theorem
This paper establishes a broad theoretical framework for tensor data dissemination methods used in various deep learning frameworks. This paper gives a theorem that is very important for performance analysis and accelerator optimization for implementing data scattering. The theorem shows how the impossibility of slicing happens in tenser data scattering. This paper proposes an algorithm called ScatterX and its source code is provided.
READ FULL TEXT