Buffered compares: Excavating the hidden parallelism inside DRAM architectures with lightweight logic

Jinho Lee, Jung Ho Ahn, Kiyoung Choi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

10 Citations (Scopus)

Abstract

We propose an approach called buffered compares, a less-invasive processing-in-memory solution that can be used with existing processor memory interfaces such as DDR3/4 with minimal changes. The approach is based on the observation that multi-bank architecture, a key feature of modern main memory DRAM devices, can be used to provide huge internal bandwidth without any major modification. We place a small buffer and a simple ALU per bank, define a set of new DRAM commands to fill the buffer and feed data to the ALU, and return the result for a set of commands (not for each command) to the host memory controller. By exploiting the under-utilized internal bandwidth using 'compare-n-op' operations, which are frequently used in many applications, we not only reduce the amount of energy-inefficient processor-memory communication, but also accelerate the computation of big data processing applications by utilizing parallelism of the buffered compare units in DRAM banks. Experimental results show that our solution significantly improves the performance and efficiency of the system on the tested workloads.

Original languageEnglish
Title of host publicationProceedings of the 2016 Design, Automation and Test in Europe Conference and Exhibition, DATE 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1243-1248
Number of pages6
ISBN (Electronic)9783981537062
Publication statusPublished - 2016 Apr 25
Event19th Design, Automation and Test in Europe Conference and Exhibition, DATE 2016 - Dresden, Germany
Duration: 2016 Mar 142016 Mar 18

Publication series

NameProceedings of the 2016 Design, Automation and Test in Europe Conference and Exhibition, DATE 2016

Conference

Conference19th Design, Automation and Test in Europe Conference and Exhibition, DATE 2016
CountryGermany
CityDresden
Period16/3/1416/3/18

Fingerprint

Dynamic random access storage
Data storage equipment
Bandwidth
Interfaces (computer)
Program processors
Controllers
Communication
Processing

All Science Journal Classification (ASJC) codes

  • Hardware and Architecture
  • Safety, Risk, Reliability and Quality

Cite this

Lee, J., Ahn, J. H., & Choi, K. (2016). Buffered compares: Excavating the hidden parallelism inside DRAM architectures with lightweight logic. In Proceedings of the 2016 Design, Automation and Test in Europe Conference and Exhibition, DATE 2016 (pp. 1243-1248). [7459501] (Proceedings of the 2016 Design, Automation and Test in Europe Conference and Exhibition, DATE 2016). Institute of Electrical and Electronics Engineers Inc..
Lee, Jinho ; Ahn, Jung Ho ; Choi, Kiyoung. / Buffered compares : Excavating the hidden parallelism inside DRAM architectures with lightweight logic. Proceedings of the 2016 Design, Automation and Test in Europe Conference and Exhibition, DATE 2016. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 1243-1248 (Proceedings of the 2016 Design, Automation and Test in Europe Conference and Exhibition, DATE 2016).
@inproceedings{1adb7edb191a4b20bd13da1e85b590c1,
title = "Buffered compares: Excavating the hidden parallelism inside DRAM architectures with lightweight logic",
abstract = "We propose an approach called buffered compares, a less-invasive processing-in-memory solution that can be used with existing processor memory interfaces such as DDR3/4 with minimal changes. The approach is based on the observation that multi-bank architecture, a key feature of modern main memory DRAM devices, can be used to provide huge internal bandwidth without any major modification. We place a small buffer and a simple ALU per bank, define a set of new DRAM commands to fill the buffer and feed data to the ALU, and return the result for a set of commands (not for each command) to the host memory controller. By exploiting the under-utilized internal bandwidth using 'compare-n-op' operations, which are frequently used in many applications, we not only reduce the amount of energy-inefficient processor-memory communication, but also accelerate the computation of big data processing applications by utilizing parallelism of the buffered compare units in DRAM banks. Experimental results show that our solution significantly improves the performance and efficiency of the system on the tested workloads.",
author = "Jinho Lee and Ahn, {Jung Ho} and Kiyoung Choi",
year = "2016",
month = "4",
day = "25",
language = "English",
series = "Proceedings of the 2016 Design, Automation and Test in Europe Conference and Exhibition, DATE 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "1243--1248",
booktitle = "Proceedings of the 2016 Design, Automation and Test in Europe Conference and Exhibition, DATE 2016",
address = "United States",

}

Lee, J, Ahn, JH & Choi, K 2016, Buffered compares: Excavating the hidden parallelism inside DRAM architectures with lightweight logic. in Proceedings of the 2016 Design, Automation and Test in Europe Conference and Exhibition, DATE 2016., 7459501, Proceedings of the 2016 Design, Automation and Test in Europe Conference and Exhibition, DATE 2016, Institute of Electrical and Electronics Engineers Inc., pp. 1243-1248, 19th Design, Automation and Test in Europe Conference and Exhibition, DATE 2016, Dresden, Germany, 16/3/14.

Buffered compares : Excavating the hidden parallelism inside DRAM architectures with lightweight logic. / Lee, Jinho; Ahn, Jung Ho; Choi, Kiyoung.

Proceedings of the 2016 Design, Automation and Test in Europe Conference and Exhibition, DATE 2016. Institute of Electrical and Electronics Engineers Inc., 2016. p. 1243-1248 7459501 (Proceedings of the 2016 Design, Automation and Test in Europe Conference and Exhibition, DATE 2016).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Buffered compares

T2 - Excavating the hidden parallelism inside DRAM architectures with lightweight logic

AU - Lee, Jinho

AU - Ahn, Jung Ho

AU - Choi, Kiyoung

PY - 2016/4/25

Y1 - 2016/4/25

N2 - We propose an approach called buffered compares, a less-invasive processing-in-memory solution that can be used with existing processor memory interfaces such as DDR3/4 with minimal changes. The approach is based on the observation that multi-bank architecture, a key feature of modern main memory DRAM devices, can be used to provide huge internal bandwidth without any major modification. We place a small buffer and a simple ALU per bank, define a set of new DRAM commands to fill the buffer and feed data to the ALU, and return the result for a set of commands (not for each command) to the host memory controller. By exploiting the under-utilized internal bandwidth using 'compare-n-op' operations, which are frequently used in many applications, we not only reduce the amount of energy-inefficient processor-memory communication, but also accelerate the computation of big data processing applications by utilizing parallelism of the buffered compare units in DRAM banks. Experimental results show that our solution significantly improves the performance and efficiency of the system on the tested workloads.

AB - We propose an approach called buffered compares, a less-invasive processing-in-memory solution that can be used with existing processor memory interfaces such as DDR3/4 with minimal changes. The approach is based on the observation that multi-bank architecture, a key feature of modern main memory DRAM devices, can be used to provide huge internal bandwidth without any major modification. We place a small buffer and a simple ALU per bank, define a set of new DRAM commands to fill the buffer and feed data to the ALU, and return the result for a set of commands (not for each command) to the host memory controller. By exploiting the under-utilized internal bandwidth using 'compare-n-op' operations, which are frequently used in many applications, we not only reduce the amount of energy-inefficient processor-memory communication, but also accelerate the computation of big data processing applications by utilizing parallelism of the buffered compare units in DRAM banks. Experimental results show that our solution significantly improves the performance and efficiency of the system on the tested workloads.

UR - http://www.scopus.com/inward/record.url?scp=84973662722&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84973662722&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84973662722

T3 - Proceedings of the 2016 Design, Automation and Test in Europe Conference and Exhibition, DATE 2016

SP - 1243

EP - 1248

BT - Proceedings of the 2016 Design, Automation and Test in Europe Conference and Exhibition, DATE 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Lee J, Ahn JH, Choi K. Buffered compares: Excavating the hidden parallelism inside DRAM architectures with lightweight logic. In Proceedings of the 2016 Design, Automation and Test in Europe Conference and Exhibition, DATE 2016. Institute of Electrical and Electronics Engineers Inc. 2016. p. 1243-1248. 7459501. (Proceedings of the 2016 Design, Automation and Test in Europe Conference and Exhibition, DATE 2016).