Simultaneous multithreading technology (SMT) can effectively improve the overall throughput and fairness through improving the resources usage efficiency of processors. Traditional works have proposed some metrics for evaluation in real systems, each of which strikes a trade-off between fairness and throughput. How to choose an appropriate metric to meet the demand is still controversial. Therefore, we put forward suggestions on how to select the appropriate metrics through analyzing and comparing the characteristics of each metric. In addition, for the new application scenario of cloud computing, the data centers have high demand for the quality of service for killer applications, which bring new challenges to SMT in terms of performance guarantees. Therefore, we propose a new metric P-slowdown to evaluate the quality of performance guarantees. Based on experimental data, we show the feasibility of P-slowdown on performance evaluation. We also demonstrate the benefit of P-slowdown through two use cases, in which we not only improve the performance guarantee level of SMT processors through the cooperation of P-slowdown and resources allocation strategy, but also use P-slowdown to predict the occurrence of abnormal behavior against security attacks.
Xin JIN
Xi'an University of Technology
Ningmei YU
Xi'an University of Technology
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Xin JIN, Ningmei YU, "Which Metric Is Suitable for Evaluating Your Multi-Threading Processors? In Terms of Throughput, Fairness, and Predictability" in IEICE TRANSACTIONS on Fundamentals,
vol. E103-A, no. 9, pp. 1127-1132, September 2020, doi: 10.1587/transfun.2019EAL2155.
Abstract: Simultaneous multithreading technology (SMT) can effectively improve the overall throughput and fairness through improving the resources usage efficiency of processors. Traditional works have proposed some metrics for evaluation in real systems, each of which strikes a trade-off between fairness and throughput. How to choose an appropriate metric to meet the demand is still controversial. Therefore, we put forward suggestions on how to select the appropriate metrics through analyzing and comparing the characteristics of each metric. In addition, for the new application scenario of cloud computing, the data centers have high demand for the quality of service for killer applications, which bring new challenges to SMT in terms of performance guarantees. Therefore, we propose a new metric P-slowdown to evaluate the quality of performance guarantees. Based on experimental data, we show the feasibility of P-slowdown on performance evaluation. We also demonstrate the benefit of P-slowdown through two use cases, in which we not only improve the performance guarantee level of SMT processors through the cooperation of P-slowdown and resources allocation strategy, but also use P-slowdown to predict the occurrence of abnormal behavior against security attacks.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.2019EAL2155/_p
Copy
@ARTICLE{e103-a_9_1127,
author={Xin JIN, Ningmei YU, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Which Metric Is Suitable for Evaluating Your Multi-Threading Processors? In Terms of Throughput, Fairness, and Predictability},
year={2020},
volume={E103-A},
number={9},
pages={1127-1132},
abstract={Simultaneous multithreading technology (SMT) can effectively improve the overall throughput and fairness through improving the resources usage efficiency of processors. Traditional works have proposed some metrics for evaluation in real systems, each of which strikes a trade-off between fairness and throughput. How to choose an appropriate metric to meet the demand is still controversial. Therefore, we put forward suggestions on how to select the appropriate metrics through analyzing and comparing the characteristics of each metric. In addition, for the new application scenario of cloud computing, the data centers have high demand for the quality of service for killer applications, which bring new challenges to SMT in terms of performance guarantees. Therefore, we propose a new metric P-slowdown to evaluate the quality of performance guarantees. Based on experimental data, we show the feasibility of P-slowdown on performance evaluation. We also demonstrate the benefit of P-slowdown through two use cases, in which we not only improve the performance guarantee level of SMT processors through the cooperation of P-slowdown and resources allocation strategy, but also use P-slowdown to predict the occurrence of abnormal behavior against security attacks.},
keywords={},
doi={10.1587/transfun.2019EAL2155},
ISSN={1745-1337},
month={September},}
Copy
TY - JOUR
TI - Which Metric Is Suitable for Evaluating Your Multi-Threading Processors? In Terms of Throughput, Fairness, and Predictability
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1127
EP - 1132
AU - Xin JIN
AU - Ningmei YU
PY - 2020
DO - 10.1587/transfun.2019EAL2155
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E103-A
IS - 9
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - September 2020
AB - Simultaneous multithreading technology (SMT) can effectively improve the overall throughput and fairness through improving the resources usage efficiency of processors. Traditional works have proposed some metrics for evaluation in real systems, each of which strikes a trade-off between fairness and throughput. How to choose an appropriate metric to meet the demand is still controversial. Therefore, we put forward suggestions on how to select the appropriate metrics through analyzing and comparing the characteristics of each metric. In addition, for the new application scenario of cloud computing, the data centers have high demand for the quality of service for killer applications, which bring new challenges to SMT in terms of performance guarantees. Therefore, we propose a new metric P-slowdown to evaluate the quality of performance guarantees. Based on experimental data, we show the feasibility of P-slowdown on performance evaluation. We also demonstrate the benefit of P-slowdown through two use cases, in which we not only improve the performance guarantee level of SMT processors through the cooperation of P-slowdown and resources allocation strategy, but also use P-slowdown to predict the occurrence of abnormal behavior against security attacks.
ER -