Task Parallelism-Aware Deep Neural Network Scheduling on Multiple Hybrid Memory Cube-Based Processing-in-Memory

Task Parallelism-Aware Deep Neural Network Scheduling on Multiple Hybrid Memory Cube-Based Processing-in-Memory

Processing-in-memory (PIM) comprises computational logic in the memory domain. It is the most promising solution to alleviate the memory bandwidth problem in deep neural network (DNN) processing. The hybrid memory cube (HMC), a 3D stacked memory structure, can efficiently implement the PIM architect...

Full description

Bibliographic Details
Main Authors: Young Sik Lee, Tae Hee Han
Format: Article
Language:English
Published: IEEE 2021-01-01
Series:IEEE Access
Subjects:
Processing-in-memory
hybrid memory cube
deep neural network
task scheduling
parallel computing
Online Access:https://ieeexplore.ieee.org/document/9422695/

Internet

https://ieeexplore.ieee.org/document/9422695/

Similar Items