izpis_h1_title_alt

Prenos orodja SYCL-GTX na operacijski sistem Linux in koprocesor Xeon Phi
ID Jesenšek, Jure (Author), ID Slivnik, Boštjan (Mentor) More about this mentor... This link opens in a new window

.pdfPDF - Presentation file, Download (1,56 MB)
MD5: B03BE21A44D6130B890836B44409B207
PID: 20.500.12556/rul/05bc887e-22f9-4f66-bb7b-8b38e2a2f0c5

Abstract
V zadnjem času je poleg računanja na večjedrnih centralnih procesnih enotah (CPE), postalo pogosto tudi računanje na vedno zmogljivejših grafičnih procesnih enotah (GPE). Tak način računanja, ki mu pravimo heterogeno programiranje, pa prinaša probleme pri prenosljivosti programske opreme. Ena izmed rešitev je uporaba OpenCL, ki poveča prenosljivost napisane programske kode, ampak ni najbolj preprost za uporabo. Za rešitev teh problemov je bil izdan nov soroden standard SYCL, ki prinaša mnoge poenostavitve v primerjavi z OpenCL. Naloga opiše standarda OpenCL in SYCL ter ju primerja med seboj. Predstavi odprtokodno implementacijo standarda z imenom sycl-gtx in nato nadaljuje z opisom rezultatov testiranj na različnih tipih strojne opreme. Testiranje se izvaja na CPE in GPE različnih zmogljivosti, kot tudi na Intelovem koprocesorju Xeon Phi. Naloga se konča s komentarjem in primerjavo dobljenih rezultatov testiranj z že obstoječimi testiranji, ki jih je izvedel avtor sycl-gtx.

Language:Slovenian
Keywords:SYCL, OpenCL, heterogeno programiranje, vzporedno programiranje
Work type:Bachelor thesis/paper
Organization:FRI - Faculty of Computer and Information Science
Year:2017
PID:20.500.12556/RUL-95091 This link opens in a new window
Publication date in RUL:14.09.2017
Views:1149
Downloads:332
Metadata:XML DC-XML DC-RDF
:
Copy citation
Share:Bookmark and Share

Secondary language

Language:English
Title:Migrating SYCL-GTX to Linux and Xeon Phi coprocessor
Abstract:
Besides the use of multi-core central processing units (CPUs) there has been an increase in use of evermore powerful graphics processing units (GPUs) for the purpose of parallel computing. But this kind of simultaneous computing on different types of processing units, called heterogeneous programming, brings on a new set of challenges, especially those concerning software portability. One of the more commonly used solutions to this problem is OpenCL framework, which is aimed at maximising portability across platforms, but is not the easiest to use. To solve this and other issues, a new standard, named SYCL, that aims to simplify heterogenous programming was released. This thesis describes and compares the OpenCL and SYCL standards. It introduces an open-source implementation of the SYCL standard called sycl-gtx and continues with the presentation of test results on different kinds of hardware, from CPUs and GPUs with different levels of performance, to the Intel's manycore processor Xeon Phi. Finally, the results are compared to those obtained by the original author of sycl-gtx and a conclusion is presented.

Keywords:SYCL, OpenCL, heterogeneous programming, parallel programming

Similar documents

Similar works from RUL:
Similar works from other Slovenian collections:

Back