Convolution engine

Author:

Qadeer Wajahat1,Hameed Rehan1,Shacham Ofer1,Venkatesan Preethi1,Kozyrakis Christos1,Horowitz Mark A.1

Affiliation:

1. Stanford University, California

Abstract

This paper focuses on the trade-off between flexibility and efficiency in specialized computing. We observe that specialized units achieve most of their efficiency gains by tuning data storage and compute structures and their connectivity to the data-flow and data-locality patterns in the kernels. Hence, by identifying key data-flow patterns used in a domain, we can create efficient engines that can be programmed and reused across a wide range of applications. We present an example, the Convolution Engine (CE), specialized for the convolution-like data-flow that is common in computational photography, image processing, and video processing applications. CE achieves energy efficiency by capturing data reuse patterns, eliminating data transfer overheads, and enabling a large number of operations per memory access. We quantify the tradeoffs in efficiency and flexibility and demonstrate that CE is within a factor of 2-3x of the energy and area efficiency of custom units optimized for a single kernel. CE improves energy and area efficiency by 8-15x over a SIMD engine for most applications.

Funder

Defense Advanced Research Projects Agency

Publisher

Association for Computing Machinery (ACM)

Reference31 articles.

1. Digic Processors Canon Inc. http://learn.usa.canon.com/resources-/articles/2012/digic_processors.htmlp. Digic Processors Canon Inc. http://learn.usa.canon.com/resources-/articles/2012/digic_processors.htmlp.

2. Omap 5 platform texas instruments www.ti.com/omap. Omap 5 platform texas instruments www.ti.com/omap.

3. Snapdragon Processors Qualcomm Inc. http://www.qualcomm.com/snapdragon/processors. Snapdragon Processors Qualcomm Inc. http://www.qualcomm.com/snapdragon/processors.

4. Tegra processors. NVIDIA Corporation. Tegra processors. NVIDIA Corporation.

5. The Frankencamera

Cited by 16 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Hardware-Software Co-Design of a Collaborative DNN Accelerator for 3D Stacked Memories with Multi-Channel Data;2024 29th Asia and South Pacific Design Automation Conference (ASP-DAC);2024-01-22

2. Design and Implementation of 2D Convolution on x86/x64 Processors;IEEE Transactions on Parallel and Distributed Systems;2022-12-01

3. Crescent;Proceedings of the 49th Annual International Symposium on Computer Architecture;2022-06-11

4. Sanger: A Co-Design Framework for Enabling Sparse Attention using Reconfigurable Architecture;MICRO-54: 54th Annual IEEE/ACM International Symposium on Microarchitecture;2021-10-17

5. Evaluating the Impact of Fault-Tolerance Capability of Deep Neural Networks Caused by Faults;2021 IEEE 34th International System-on-Chip Conference (SOCC);2021-09-14

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3