Security and Performance Trade-off in PerfCloud

Author(s):  
Valentina Casola ◽  
Antonio Cuomo ◽  
Massimiliano Rak ◽  
Umberto Villano
Keyword(s):  
2021 ◽  
Vol 18 (2) ◽  
pp. 1-24
Author(s):  
Nhut-Minh Ho ◽  
Himeshi De silva ◽  
Weng-Fai Wong

This article presents GRAM (<underline>G</underline>PU-based <underline>R</underline>untime <underline>A</underline>daption for <underline>M</underline>ixed-precision) a framework for the effective use of mixed precision arithmetic for CUDA programs. Our method provides a fine-grain tradeoff between output error and performance. It can create many variants that satisfy different accuracy requirements by assigning different groups of threads to different precision levels adaptively at runtime . To widen the range of applications that can benefit from its approximation, GRAM comes with an optional half-precision approximate math library. Using GRAM, we can trade off precision for any performance improvement of up to 540%, depending on the application and accuracy requirement.


2021 ◽  
Vol 34 (5) ◽  
pp. 303-318
Author(s):  
Maarten Baele ◽  
An Vermeulen ◽  
Dimitri Adons ◽  
Roos Peeters ◽  
Angelique Vandemoortele ◽  
...  

Author(s):  
Harold O. Fried ◽  
Loren W. Tauer

This article explores how well an individual manages his or her own talent to achieve high performance in an individual sport. Its setting is the Ladies Professional Golf Association (LPGA). The order-m approach is explained. Additionally, the data and the empirical findings are presented. The inputs measure fundamental golfing athletic ability. The output measures success on the LPGA tour. The correlation coefficient between earnings per event and the ability to perform under pressure is 0.48. The careers of golfers occur on the front end of the age distribution. There is a classic trade-off between the inevitable deterioration in the mental ability to handle the pressure and experience gained with time. The ability to perform under pressure peaks at age 37.


2021 ◽  
Vol 5 (1) ◽  
pp. 15-21
Author(s):  
Bruno Elmôr Duarte ◽  
Ricardo Pereira Câmara Leal

This article analyzes conflicts between principals that led to activism by one large Brazilian government-owned investor as a minority shareholder and verifies the antecedents, means employed, apparent motivations, and effectiveness of its reactions (Goranova & Ryan, 2014). It examines the cases of three large high ownership concentration listed companies using solely public sources. Poor performance was a frequent conflict antecedent. No evident trade-off between activism and corporate governance (CG) practices emerged. High ownership concentration influenced the way the investor reacted and its success because opposition through internal CG mechanisms was usually not successful and led to legal proceedings. The limitations of the regulatory framework became evident from the mixed outcomes of these proceedings. The investor was not exclusively financially motivated and it occasionally opposed the interests of other minority shareholders to follow government policy. These findings illustrated how high ownership concentration rendered difficult the mitigation of principal-principal conflicts even for a large government-owned investor and help explain the failure of previous econometric studies to relate activism, quality of CG practices and performance (Young, Peng, Ahlstrom, Bruton, & Jiang, 2008)


Author(s):  
Miguel Bordallo López

Computer vision can be used to increase the interactivity of existing and new camera-based applications. It can be used to build novel interaction methods and user interfaces. The computing and sensing needs of this kind of applications require a careful balance between quality and performance, a practical trade-off. This chapter shows the importance of using all the available resources to hide application latency and maximize computational throughput. The experience gained during the developing of interactive applications is utilized to characterize the constraints imposed by the mobile environment, discussing the most important design goals: high performance and low power consumption. In addition, this chapter discusses the use of heterogeneous computing via asymmetric multiprocessing to improve the throughput and energy efficiency of interactive vision-based applications.


Electronics ◽  
2020 ◽  
Vol 9 (4) ◽  
pp. 629 ◽  
Author(s):  
Junaid Arshad ◽  
Muhammad Ajmal Azad ◽  
Roohi Amad ◽  
Khaled Salah ◽  
Mamoun Alazab ◽  
...  

Internet of Things (IoT) forms the foundation of next generation infrastructures, enabling development of future cities that are inherently sustainable. Intrusion detection for such paradigms is a non-trivial challenge which has attracted further significance due to extraordinary growth in the volume and variety of security threats for such systems. However, due to unique characteristics of such systems i.e., battery power, bandwidth and processor overheads and network dynamics, intrusion detection for IoT is a challenge, which requires taking into account the trade-off between detection accuracy and performance overheads. In this context, we are focused at highlighting this trade-off and its significance to achieve effective intrusion detection for IoT. Specifically, this paper presents a comprehensive study of existing intrusion detection systems for IoT systems in three aspects: computational overhead, energy consumption and privacy implications. Through extensive study of existing intrusion detection approaches, we have identified open challenges to achieve effective intrusion detection for IoT infrastructures. These include resource constraints, attack complexity, experimentation rigor and unavailability of relevant security data. Further, this paper is envisaged to highlight contributions and limitations of the state-of-the-art within intrusion detection for IoT, and aid the research community to advance it by identifying significant research directions.


Sign in / Sign up

Export Citation Format

Share Document