DocumentCode :
3759119
Title :
Towards General-Purpose Neural Network Computing
Author :
Schuyler Eldridge;Amos Waterland;Margo Seltzer;Jonathan Appavoo;Ajay Joshi
Author_Institution :
Dept. of Electr. &
fYear :
2015
Firstpage :
99
Lastpage :
112
Abstract :
Machine learning is becoming pervasive, decades of research in neural network computation is now being leveraged to learn patterns in data and perform computations that are difficult to express using standard programming approaches. Recent work has demonstrated that custom hardware accelerators for neural network processing can outperform software implementations in both performance and power consumption. However, there is neither an agreed-upon interface to neural network accelerators nor a consensus on neural network hardware implementations. We present a generic set of software/hardware extensions, X-FILES, that allow for the general-purpose integration of feedforward and feedback neural network computation in applications. The interface is independent of the network type, configuration, and implementation. Using these proposed extensions, we demonstrate and evaluate an example dynamically allocated, multi-context neural network accelerator architecture, DANA. We show that the combination of X-FILES and our hardware prototype, DANA, enables generic support and increased throughput for neural-network-based computation in multi-threaded scenarios.
Keywords :
"Artificial neural networks","Hardware","Software","Registers","Standards","Accelerator architectures"
Publisher :
ieee
Conference_Titel :
Parallel Architecture and Compilation (PACT), 2015 International Conference on
ISSN :
1089-795X
Type :
conf
DOI :
10.1109/PACT.2015.21
Filename :
7429298
Link To Document :
بازگشت