20.500.12556/RUL-95091 Prenos orodja SYCL-GTX na operacijski sistem Linux in koprocesor Xeon Phi Migrating SYCL-GTX to Linux and Xeon Phi coprocessor 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. 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. SYCL OpenCL heterogeno programiranje vzporedno programiranje SYCL OpenCL heterogeneous programming parallel programming true false false Slovenski jezik Angleški jezik Diplomsko delo/naloga 2017-09-14 10:44:51 2017-09-14 10:44:52 2022-08-10 02:15:57 0000-00-00 00:00:00 2017 0 0 0000-00-00 NiDoloceno NiDoloceno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 1970-01-01 19944 Jesensek_Jure_-_Prenos_orodja_SYCL-GTX_na_operacijski_sistem_Linux_in_koprocesor_Xeon_Phi.pdf Jesensek_Jure_-_Prenos_orodja_SYCL-GTX_na_operacijski_sistem_Linux_in_koprocesor_Xeon_Phi.pdf 1 B03BE21A44D6130B890836B44409B207 3edd66057ef2b09d5cea1dad0f0fa93bbd63bec5409742b133d9261fc3e0edf2 acae8540-a1b3-11eb-a523-00155dcfd717 20.500.12556/rul/05bc887e-22f9-4f66-bb7b-8b38e2a2f0c5 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=103618 Fakulteta za računalništvo in informatiko 0 0 0