Cycle-Accurate full system simulation for CPU+GPU+HBM computing platform

Yoonah Paik, Miseon Han, Kyu Hyun Choi, Minseong Kim, Seon Wook Kim

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

Abstract

Nowadays GPUS have evolved into a general purpose computing platform that can handle large amounts of data, and they began to be integrated with CPUs in one chip to avoid data transfer bottleneck and reduce its required energy. Furthermore, HBM works with the integrated CPU and GPU for providing high memory throughput from lower-level memories while preserving energy efficiency for data transfer. In order to study and develop such systems in academia and industry, their cycle-Accurate full system simulators became necessary, but they are not available in public. In this paper, we introduce the simulator that is adapted and integrated from several well-known simulators, i.e., PTLSim for CPU, GPGPU-Sim for GPU and DRAMSim2 for HBM. Our evaluation result showed that our simulation speed reaches 72.76% of the GPU+HBMsimulator.

Original languageEnglish
Title of host publicationInternational Conference on Electronics, Information and Communication, ICEIC 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1-2
Number of pages2
Volume2018-January
ISBN (Electronic)9781538647547
DOIs
Publication statusPublished - 2018 Apr 2
Event17th International Conference on Electronics, Information and Communication, ICEIC 2018 - Honolulu, United States
Duration: 2018 Jan 242018 Jan 27

Other

Other17th International Conference on Electronics, Information and Communication, ICEIC 2018
CountryUnited States
CityHonolulu
Period18/1/2418/1/27

Fingerprint

Program processors
Simulators
Data transfer
Data storage equipment
Energy efficiency
Throughput
Graphics processing unit
Industry

Keywords

  • CPU+GPU+HBM
  • Cycle-Accurate simulation
  • DRAMSim2
  • GPGPU-Sim
  • PTLSim

ASJC Scopus subject areas

  • Information Systems
  • Computer Networks and Communications
  • Computer Science Applications
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Paik, Y., Han, M., Choi, K. H., Kim, M., & Kim, S. W. (2018). Cycle-Accurate full system simulation for CPU+GPU+HBM computing platform. In International Conference on Electronics, Information and Communication, ICEIC 2018 (Vol. 2018-January, pp. 1-2). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.23919/ELINFOCOM.2018.8330603

Cycle-Accurate full system simulation for CPU+GPU+HBM computing platform. / Paik, Yoonah; Han, Miseon; Choi, Kyu Hyun; Kim, Minseong; Kim, Seon Wook.

International Conference on Electronics, Information and Communication, ICEIC 2018. Vol. 2018-January Institute of Electrical and Electronics Engineers Inc., 2018. p. 1-2.

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

Paik, Y, Han, M, Choi, KH, Kim, M & Kim, SW 2018, Cycle-Accurate full system simulation for CPU+GPU+HBM computing platform. in International Conference on Electronics, Information and Communication, ICEIC 2018. vol. 2018-January, Institute of Electrical and Electronics Engineers Inc., pp. 1-2, 17th International Conference on Electronics, Information and Communication, ICEIC 2018, Honolulu, United States, 18/1/24. https://doi.org/10.23919/ELINFOCOM.2018.8330603
Paik Y, Han M, Choi KH, Kim M, Kim SW. Cycle-Accurate full system simulation for CPU+GPU+HBM computing platform. In International Conference on Electronics, Information and Communication, ICEIC 2018. Vol. 2018-January. Institute of Electrical and Electronics Engineers Inc. 2018. p. 1-2 https://doi.org/10.23919/ELINFOCOM.2018.8330603
Paik, Yoonah ; Han, Miseon ; Choi, Kyu Hyun ; Kim, Minseong ; Kim, Seon Wook. / Cycle-Accurate full system simulation for CPU+GPU+HBM computing platform. International Conference on Electronics, Information and Communication, ICEIC 2018. Vol. 2018-January Institute of Electrical and Electronics Engineers Inc., 2018. pp. 1-2
@inproceedings{3d9608c66da54f48884e2cb6170ce99c,
title = "Cycle-Accurate full system simulation for CPU+GPU+HBM computing platform",
abstract = "Nowadays GPUS have evolved into a general purpose computing platform that can handle large amounts of data, and they began to be integrated with CPUs in one chip to avoid data transfer bottleneck and reduce its required energy. Furthermore, HBM works with the integrated CPU and GPU for providing high memory throughput from lower-level memories while preserving energy efficiency for data transfer. In order to study and develop such systems in academia and industry, their cycle-Accurate full system simulators became necessary, but they are not available in public. In this paper, we introduce the simulator that is adapted and integrated from several well-known simulators, i.e., PTLSim for CPU, GPGPU-Sim for GPU and DRAMSim2 for HBM. Our evaluation result showed that our simulation speed reaches 72.76{\%} of the GPU+HBMsimulator.",
keywords = "CPU+GPU+HBM, Cycle-Accurate simulation, DRAMSim2, GPGPU-Sim, PTLSim",
author = "Yoonah Paik and Miseon Han and Choi, {Kyu Hyun} and Minseong Kim and Kim, {Seon Wook}",
year = "2018",
month = "4",
day = "2",
doi = "10.23919/ELINFOCOM.2018.8330603",
language = "English",
volume = "2018-January",
pages = "1--2",
booktitle = "International Conference on Electronics, Information and Communication, ICEIC 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Cycle-Accurate full system simulation for CPU+GPU+HBM computing platform

AU - Paik, Yoonah

AU - Han, Miseon

AU - Choi, Kyu Hyun

AU - Kim, Minseong

AU - Kim, Seon Wook

PY - 2018/4/2

Y1 - 2018/4/2

N2 - Nowadays GPUS have evolved into a general purpose computing platform that can handle large amounts of data, and they began to be integrated with CPUs in one chip to avoid data transfer bottleneck and reduce its required energy. Furthermore, HBM works with the integrated CPU and GPU for providing high memory throughput from lower-level memories while preserving energy efficiency for data transfer. In order to study and develop such systems in academia and industry, their cycle-Accurate full system simulators became necessary, but they are not available in public. In this paper, we introduce the simulator that is adapted and integrated from several well-known simulators, i.e., PTLSim for CPU, GPGPU-Sim for GPU and DRAMSim2 for HBM. Our evaluation result showed that our simulation speed reaches 72.76% of the GPU+HBMsimulator.

AB - Nowadays GPUS have evolved into a general purpose computing platform that can handle large amounts of data, and they began to be integrated with CPUs in one chip to avoid data transfer bottleneck and reduce its required energy. Furthermore, HBM works with the integrated CPU and GPU for providing high memory throughput from lower-level memories while preserving energy efficiency for data transfer. In order to study and develop such systems in academia and industry, their cycle-Accurate full system simulators became necessary, but they are not available in public. In this paper, we introduce the simulator that is adapted and integrated from several well-known simulators, i.e., PTLSim for CPU, GPGPU-Sim for GPU and DRAMSim2 for HBM. Our evaluation result showed that our simulation speed reaches 72.76% of the GPU+HBMsimulator.

KW - CPU+GPU+HBM

KW - Cycle-Accurate simulation

KW - DRAMSim2

KW - GPGPU-Sim

KW - PTLSim

UR - http://www.scopus.com/inward/record.url?scp=85048543407&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85048543407&partnerID=8YFLogxK

U2 - 10.23919/ELINFOCOM.2018.8330603

DO - 10.23919/ELINFOCOM.2018.8330603

M3 - Conference contribution

AN - SCOPUS:85048543407

VL - 2018-January

SP - 1

EP - 2

BT - International Conference on Electronics, Information and Communication, ICEIC 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -