Extending Amdahl's Law for Heterogeneous Computing

Marowka, Ami

doi:10.1109/ispa.2012.47

Cited by 20 publications

(18 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…According to Amdahl's law, such large improvement can be achieved only by subsequently shaving off the largest cost factors in the task [9]. Only pre-calculating the bits during permutation brings ~30% performance improvement.…”

Section: Performancementioning

confidence: 99%

Implementation of a New Cipher in OpenSSL Environment the Case of INDECT Block Cipher

Jurkiewicz¹,

Niemiec²

2016

IJCCE

View full text Add to dashboard Cite

Implementation of a new cipher in the popular cryptographic library is a convenient way of deploying it for wide usage. In this article we described the process of integration of a new cipher with the OpenSSL libraries. In this case it is the INDECT Block Cipher (IBC), a new symmetric block cipher based on a substitution-permutation network. However, this work is more universal because it is possible in the same way to integrate any symmetric cipher in the OpenSSL environment. The goal of the implementation is to enable usage of a new cipher in applications using OpenSSL libraries, especially to encrypt data in SSL/TLS connections. The article contains general descriptions of OpenSSL, SSL/TLS protocol and the IBC algorithm. Also, the integration process was described in detail. Particular attention is paid to binary compatibility issues. Additionally, results of various tests of the modified libraries were presented.

show abstract

Section: Performancementioning

confidence: 99%

Implementation of a New Cipher in OpenSSL Environment the Case of INDECT Block Cipher

Jurkiewicz¹,

Niemiec²

2016

IJCCE

View full text Add to dashboard Cite

show abstract

“…In these publications, there is no limitation on power consumption to restrict number of baseline cores. Power consumption, performance, and power/energy trade-offs is added to the Amdahl's law for heterogeneous architectures in [11,12]. Memory wall problem is taken into consideration in [13] and a new formulation for speedup is introduced in which Amdahl and Gustafson's laws are combined together.…”

Section: Related Workmentioning

confidence: 99%

Voltage scaling and dark silicon in symmetric multicore processors

Nejatollahi

Salehi

2015

J Supercomput

View full text Add to dashboard Cite

As technology scales further, multicore and many-core processors emerge as an alternative to keep up with performance demands. However, because of power and thermal constraints, we are obliged to power off remarkable area of chip. Many innovative techniques have been presented to improve energy efficiency and maintain utilization at the highest level. In this paper, we discuss different models and methods of exploiting dark silicon, and by using dynamic voltage and frequency scaling in Amdahl's law and considering memory overheads, we attempt to decrease amount of dark silicon and improve performance and performance per watt/joule. We propose high-performance and energy-efficient multicore architectures for variety of parallelisms and memory-intensities in workloads. According to the results, by voltage scaling, for a highly parallel CPU-intensive workload, we reach improvements of approximately 5.2× and 3.78× in performance per watt and performance per joule, respectively, while about 27 % reduction of performance should be tolerated. For memory-intensive applications, a negligible change in speedup is detected by scaling, while performance per watt and performance per joule for both serial and parallel applications lead to around 6× enhancements.

show abstract

“…One of the simple analytical model that can applied is Amdahl's Law. Previous studies have extended the Amdahl's Law into the heterogeneous computing era [30,31]. The future computer will integration various unconventional computing units (GPGPUs, FPGAs, and ASICs) as suggested by the measurements and predictions [30].…”

Section: B-1mentioning

confidence: 99%

“…The second mode schedules different programs onto CPUs and GPUs which computes simultaneously. Amdahl's Law is revised to capture the system configuration leading to the optimal speedup [31]. The study is based on the structure that CPU and GPU share the same memory space.…”

Section: B-1mentioning

confidence: 99%

“…Similar to the definition in previous work [31], the total numbers of CPUs and GPUs are denoted by c and g. However, due to the power constraint which is measured by a single CPU power consumption, the number of GPUs is limited by (P B − c)/w g , where P B is the power budget and w g is the power ratio between GPU and CPU. Assume the portion of the program can be paralleled is f and the portion of parallel program running on multi-cores is α. β is the execution timing ratio of GPU to CPU.…”

Section: B-1mentioning

confidence: 99%

See 1 more Smart Citation

Heterogeneous architecture design with emerging 3D and non-volatile memory technologies

Zou

Poremba

Rui

et al. 2015

The 20th Asia and South Pacific Design Automation Conference

View full text Add to dashboard Cite

Energy becomes the primary concern in nowadays multi-core architecture designs. Moore's law predicts that the exponentially increasing number of cores can be packed into a single chip every two years, however, the increasing power density is the obstacle to continuous performance gains. Recent studies show that heterogeneous multi-core is a competitive promising solution to optimize performance per watt. In this paper, different types of heterogeneous architecture are discussed. For each type, current challenges and latest solutions are briefly introduced. Preliminary analyses are performed to illustrate the scalability of the heterogeneous system and the potential benefits towards future application requirements. Moreover, we demonstrate the advantages of leveraging three-dimensional (3D) integration on heterogeneous architectures. With 3D die stacking, disparate technologies can be integrated on the same chip, such as the CMOS logic and emerging non-volatile memory, enabling a new paradigm of architecture design. 1 9B-1

show abstract

Extending Amdahl's Law for Heterogeneous Computing

Cited by 20 publications

References 10 publications

Implementation of a New Cipher in OpenSSL Environment the Case of INDECT Block Cipher

Implementation of a New Cipher in OpenSSL Environment the Case of INDECT Block Cipher

Voltage scaling and dark silicon in symmetric multicore processors

Heterogeneous architecture design with emerging 3D and non-volatile memory technologies

Contact Info

Product

Resources

About