13 research outputs found
How to Choose Processor for Personal Computer Based on Benchmarking and Testing Games
No full textKäesoleva töö eesmärgiks on anda teadmisi, mille põhjal valida protsessorit video renderdamiseks, mängude mängimiseks või mängude streamimiseks. Töös võrreldakse kahe erineva mängu jõudlust, video renderdamise jõudlust ning mängupildi streamimise jõudlust kuuel erinevalt protsessoril. Töö lõpuks leiti, et video renderdamisele ja mängupildi streamimisele aitab põhiliselt kaasa suurem tuumade arv koos suurema lõimede arvuga. Mängude mängimise puhul tuli välja, et suurem tuumade ja lõimede arv ei anna oluliselt jõudlust juurde, kui protsessor on juba vähemalt neljatuumaline. Kui protsessor on juba neljatuumaline, siis põhiline jõudluse kasv saavutatakse kõrgema taktsageduse arvelt.The aim of the thesis to give knowledge about selecting processor for video rendering or playing games and streaming them to online. The main contribution of the thesis is to compare two game benchmarks, video rendering benchmark and video streaming benchmark on six different processors. It was found that for a video rendering and a video streaming benchmark the processor’s clock speed doesn’t matter so much and main performance boost is gained by higher core and thread count. For the games benchmarks, it was found that after four cores additional cores and threads do not increase performance and the main factor that helps to get a higher framerate is the clock speed
Software used in: Neural networks and adjoints for parameter identification in systems modeled by differential equations
No full text<p>Software for the Octave environment to perform parameter identification for the simple harmonic oscillator and for Chua's circuit by using the method of adjoints and by using neural networks</p>Tested using Octave version 4.4.
The flow in a cylindrical container with a rotating end wall at small but finite Reynolds number
No full textReproducibility in Benchmarking Parallel Fast Fourier Transform based Applications
No full textAn overview of concerns observed in allowing for reproducibility in parallel applications that heavily depend on the three dimensional distributed memory fast Fourier transform are summarized. Suggestions for reproducibility categories for benchmark results are given.We thank all the authors of [2] and those who have given a presentation on their use of the FFT in the ongoing discussion at www.fft.report. We also thank Robert Henschel for an overview of the SPEC benchmarking process at the benchmarking in the data center workshop at HPC Asia 2019. We thank RIKEN for the use of the K computer, HLRS for the use of Kabuki and Hazelhen, and the KAUST Supercomputing Laboratory for the use of Shaheen II. B.K.M. was partially supported by HPC Europa 3 (INFRAIA-2016-1-730897). B.K.M. thanks H. Berger, A. Chepstov, J. Gracia and A. Jocksch for helpful hints and discussions
An Open Source System for Crowd Sourcing an African Language Short Story Corpus
No full textMany African languages are under resourced in having open access corpora for use in developing technological applications such as grammar checkers, spell checkers, speech to text, text to speech and machine translation tools. This may lead to a decline in all cultural traits associated with the peoples that speak these languages. To enable collection of textual corpora and long term preservation of positive cultural characteristics, the design considerations and implementation of an open source online short story competition collection and evaluation system are described. The system is written in PHP and can be relatively cheaply deployed on shared hosting servers available from many African hosting providers. This allows for the possibility of a decentralized collection of stories, as well as adaptation and improvements of the software to different types of short story competitions. The software has been used for two short story competitions across the African continent with the aim of providing stories suitable for children. Holding the competition online has enabled participation from a wide variety of locations, but most of the submissions have came from African countries with relatively good information technology infrastructure. Preparation for a third competition is in progress
Fully implicit time stepping can be efficient on parallel computers
No full textBenchmarks in high performance computing often involve a single component used in the full solution of a computational problem, such as the solution of a linear system of equations. In many cases, the choice of algorithm, which can determine the components used, is also important when solving a full problem. Numerical evidence suggests that for the Taylor-Green vortex problem at a Reynolds number of 1600, a second order implicit midpoint rule method can require less computational time than the often used linearly implicit Carpenter-Kennedy method for solving the equations of incompressible fluid dynamics for moderate levels of accuracy at the beginning of the flow evolution. The primary reason is that even though the implicit midpoint rule is fully implicit, it can use a small number of iterations per time step, and thus require less computational work per time step than the Carpenter-Kennedy method. For the same number of timesteps, the Carpenter-Kennedy method is more accurate since it uses a higher order timestepping method.We thank the reviewers for their constructive comments, and Koen Hillewaert and David Ketcheson for helpful advice. We thank the participants of the 2013 HiOCFD workshop [12] for feedback on an earlier version of this work that enabled greater examination of the numerical results. BKM thanks Arieh Iserles for pointing out the geometric properties of the implicit midpoint rule and Charles Doering, José Gracia, Hans Johnston, Ning Li, Peter Van Keken, Divakar Viswanath and Jared Whitehead for helpful discussion. BKM was partially supported by HPC Europa 3 (INFRAIA-2016-1-730897)
Silo Music and Silo Quake: Granular Flow-Induced Vibration
No full textAcceleration and sound measurements during granular discharge from silos are used to show that silo music is a sound resonance produced by silo quake. In tall and narrow silos, the latter is produced by stickslip friction between the wall and the granular material. For the discharge rates studied, the occurrence of flow pulsations is determined primarily by the surface properties of the granular material and the silo wall. The measurements show that the pulsating motion ofthe granular material drives the oscillatory motion of the silo
Data for figures in "Reproducibility in Benchmarking Parallel Fast Fourier Transform based Applications"
No full textFFT benchmark data and Python plotting programs</p
Data for figures in "Reproducibility in Benchmarking Parallel Fast Fourier Transform based Applications"
No full textFFT benchmark data and Python plotting programs</p
