How to measure, present, and compare parallel performance

Crowl, Lawrence A.

doi:10.1109/88.281869

Cited by 27 publications

(19 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many factors affect the parallel algorithms' performance. Such factors include the structure of the algorithm implemented on the parallel machine, the programming system, the actual platform, and the run time [21]. The parallel implementations need, in general, less operation time than the sequential ones.…”

Section: Mults Adds Divs Sqrtsmentioning

confidence: 99%

See 1 more Smart Citation

Optimal seismic deconvolution: distributed algorithms

Plataniotis¹,

Katsikas

Lainiotis

et al. 1998

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

Abstract-Deconvolution is one of the most important aspects of seismic signal processing. The objective of the deconvolution procedure is to remove the obscuring effect of the wavelet's replica making up the seismic trace and therefore obtain an estimate of the reflection coefficient sequence. This paper introduces a new deconvolution algorithm. Optimal distributed estimators and smoothers are utilized in the proposed solution. The new distributed methodology, perfectly suitable for a multisensor environment, such as the seismic signal processing, is compared to the centralized approach, with respect to computational complexity and architectural efficiency. It is shown that the distributed approach greatly outperforms the currently used centralized methodology offering flexibility in the design of the data fusion network.

show abstract

Section: Mults Adds Divs Sqrtsmentioning

confidence: 99%

“…This situation is of course outside the scope of the present paper, since it heavily depends on the specific configuration of the computing platform. It is assumed here that, in all parallel machines used, the operating system provides the same CPU time to all processes running in parallel [21].…”

Section: Mults Adds Divs Sqrtsmentioning

confidence: 99%

Optimal seismic deconvolution: distributed algorithms

Plataniotis¹,

Katsikas

Lainiotis

et al. 1998

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Good references on parallel computing performance include [7,8]. Gustafson [9] discusses the impact of architecture on performance and speedup.…”

Section: Related Literaturementioning

confidence: 99%

“…Note Compiling with the Intel 10.1 compiler (-fast option) and using (8,4,47) as the parameters for (B, K, θ), the 2.3G E5345 processes the SANBI10000 set in 18.8s. Compare this to the 362s that the Xeon 2.4GHz/stepping 7 (gcc 4.1.1 -O2) takes with parameters (10,1,40).…”

Section: Compiler Effectsmentioning

confidence: 99%

Truth in advertising: Reporting performance of computer programs, algorithms and the impact of architecture

Hazelhurst¹

2010

SACJ

View full text Add to dashboard Cite

The level of detail and precision that appears in the experimental methodology section computer science papers is usually much less than in natural science disciplines. This is partially justified by different nature of experiments. The experimental evidence presented here shows that the time taken by the same algorithm varies so significantly on different CPUs that without knowing the exact model of CPU, it is difficult to compare the results. This is placed in context by analysing a cross-section of experimental results reported in the literature. The reporting of experimental results is sometimes insufficient to allow experiments to be replicated, and in some case is insufficient to support the claims made for the algorithms. New standards for reporting on algorithms results are suggested.

show abstract

“…In some cases, however, speedup can be misleading because it may give a distorted picture. The one metrics that almost all agree on is the elapsed time (response time) [4]. Elapsed time is directly measured for the application and it encapsulates all affecting attributes such as system time and communication time.…”

Section: The Performance Modelmentioning

confidence: 99%