Exploring new features of high-bandwidth memory for GPUs

Bingchao Li, Choungki Song, Jizeng Wei, Jung Ho Ahn, Nam Sung Kim

Research output: Contribution to journalLetter

Abstract

Due to the off-chip I/O pin and power constraints of GDDR5, HBM has been proposed to provide higher bandwidth and lower power consumption for GPUs. In this paper, we first provide detailed comparison between HBM and GDDR5 and expose two unique features of HBM: Dualcommand and pseudo channel mode. Second, we analyze the effectiveness of these two features and show that neither notably contributes to performance. However, by combining pseudo channel mode with cache architecture supporting fine-grained cache-line management such as Amoeba cache, we achieve high effciency for applications with irregular memory requests. Our experiment demonstrates that compared with Amoeba caches with legacy mode, Amoeba cache with pseudo channel mode improves GPU performance by 25% and reduces HBM energy consumption by 15%.

Original languageEnglish (US)
JournalIEICE Electronics Express
Volume13
Issue number14
DOIs
StatePublished - Jan 1 2016

Fingerprint

amoeba
bandwidth
Bandwidth
Data storage equipment
Electric power utilization
Energy utilization
energy consumption
Experiments
chips
Graphics processing unit

Keywords

  • Amoeba cache
  • DRAM
  • Energy
  • GPU
  • HBM

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Electrical and Electronic Engineering

Cite this

Exploring new features of high-bandwidth memory for GPUs. / Li, Bingchao; Song, Choungki; Wei, Jizeng; Ahn, Jung Ho; Kim, Nam Sung.

In: IEICE Electronics Express, Vol. 13, No. 14, 01.01.2016.

Research output: Contribution to journalLetter

Li, Bingchao ; Song, Choungki ; Wei, Jizeng ; Ahn, Jung Ho ; Kim, Nam Sung. / Exploring new features of high-bandwidth memory for GPUs. In: IEICE Electronics Express. 2016 ; Vol. 13, No. 14.
@article{5b337be165ac4697a05796d63705f4d9,
title = "Exploring new features of high-bandwidth memory for GPUs",
abstract = "Due to the off-chip I/O pin and power constraints of GDDR5, HBM has been proposed to provide higher bandwidth and lower power consumption for GPUs. In this paper, we first provide detailed comparison between HBM and GDDR5 and expose two unique features of HBM: Dualcommand and pseudo channel mode. Second, we analyze the effectiveness of these two features and show that neither notably contributes to performance. However, by combining pseudo channel mode with cache architecture supporting fine-grained cache-line management such as Amoeba cache, we achieve high effciency for applications with irregular memory requests. Our experiment demonstrates that compared with Amoeba caches with legacy mode, Amoeba cache with pseudo channel mode improves GPU performance by 25{\%} and reduces HBM energy consumption by 15{\%}.",
keywords = "Amoeba cache, DRAM, Energy, GPU, HBM",
author = "Bingchao Li and Choungki Song and Jizeng Wei and Ahn, {Jung Ho} and Kim, {Nam Sung}",
year = "2016",
month = "1",
day = "1",
doi = "10.1587/elex.13.20160527",
language = "English (US)",
volume = "13",
journal = "IEICE Electronics Express",
issn = "1349-2543",
publisher = "The Institute of Electronics, Information and Communication Engineers (IEICE)",
number = "14",

}

TY - JOUR

T1 - Exploring new features of high-bandwidth memory for GPUs

AU - Li, Bingchao

AU - Song, Choungki

AU - Wei, Jizeng

AU - Ahn, Jung Ho

AU - Kim, Nam Sung

PY - 2016/1/1

Y1 - 2016/1/1

N2 - Due to the off-chip I/O pin and power constraints of GDDR5, HBM has been proposed to provide higher bandwidth and lower power consumption for GPUs. In this paper, we first provide detailed comparison between HBM and GDDR5 and expose two unique features of HBM: Dualcommand and pseudo channel mode. Second, we analyze the effectiveness of these two features and show that neither notably contributes to performance. However, by combining pseudo channel mode with cache architecture supporting fine-grained cache-line management such as Amoeba cache, we achieve high effciency for applications with irregular memory requests. Our experiment demonstrates that compared with Amoeba caches with legacy mode, Amoeba cache with pseudo channel mode improves GPU performance by 25% and reduces HBM energy consumption by 15%.

AB - Due to the off-chip I/O pin and power constraints of GDDR5, HBM has been proposed to provide higher bandwidth and lower power consumption for GPUs. In this paper, we first provide detailed comparison between HBM and GDDR5 and expose two unique features of HBM: Dualcommand and pseudo channel mode. Second, we analyze the effectiveness of these two features and show that neither notably contributes to performance. However, by combining pseudo channel mode with cache architecture supporting fine-grained cache-line management such as Amoeba cache, we achieve high effciency for applications with irregular memory requests. Our experiment demonstrates that compared with Amoeba caches with legacy mode, Amoeba cache with pseudo channel mode improves GPU performance by 25% and reduces HBM energy consumption by 15%.

KW - Amoeba cache

KW - DRAM

KW - Energy

KW - GPU

KW - HBM

UR - http://www.scopus.com/inward/record.url?scp=84979555724&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84979555724&partnerID=8YFLogxK

U2 - 10.1587/elex.13.20160527

DO - 10.1587/elex.13.20160527

M3 - Letter

AN - SCOPUS:84979555724

VL - 13

JO - IEICE Electronics Express

JF - IEICE Electronics Express

SN - 1349-2543

IS - 14

ER -