Towards General-Purpose Neural Network Computing

DSpace/Manakin Repository

Towards General-Purpose Neural Network Computing

Citable link to this page


Title: Towards General-Purpose Neural Network Computing
Author: Eldridge, Schuyler; Waterland, Amos; Seltzer, Margo I.; Appavoo, Jonathan; Joshi, Ajay

Note: Order does not necessarily reflect citation order of authors.

Citation: Eldridge, Schuyler, Amos Waterland, Margo Seltzer, Jonathan Appavoo, and Ajay Joshi. 2015. "Towards general-purpose neural network computing." In Proceedings of the 2015 International Conference on Parallel Architecture and Compilation (PACT), San Francisco, CA, October 18-21, 2015: 99-112. doi:10.1109/PACT.2015.21
Full Text & Related Files:
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.
Published Version: doi:10.1109/PACT.2015.21
Terms of Use: This article is made available under the terms and conditions applicable to Open Access Policy Articles, as set forth at
Citable link to this page:
Downloads of this work:

Show full Dublin Core record

This item appears in the following Collection(s)


Search DASH

Advanced Search