Integration of Processing-Near-Memory Library Into SYCL

Student: Ilyushin Valentin

Educational Programme: Applied Mathematics and Information Science (Bachelor)

Final Grade: 9

Year of Graduation: 2024

Modern high-loaded pipelines require the use of task-specific hardware for leveraging the ever-growing amount of data. To handle several devices in one system, developers either need to use a separate language for each device or utilize specific tools for heterogeneous computation. One of the most popular such tools is SYCL - domain-specific language, based on C++. Although it supports a lot of devices, new ones should be integrated with it manually. This work aims to explain how to do this, overview the required steps and possible further directions and discuss advantages and disadvantages of each method. As an example of accelerators, we will take Processing-NearMemory devices supported by PNMLibrary.

Full text (added May 20, 2024)

Student Theses at HSE must be completed in accordance with the University Rules and regulations specified by each educational programme.

Summaries of all theses must be published and made freely available on the HSE website.

The full text of a thesis can be published in open access on the HSE website only if the authoring student (copyright holder) agrees, or, if the thesis was written by a team of students, if all the co-authors (copyright holders) agree. After a thesis is published on the HSE website, it obtains the status of an online publication.

Student theses are objects of copyright and their use is subject to limitations in accordance with the Russian Federation’s law on intellectual property.

In the event that a thesis is quoted or otherwise used, reference to the author’s name and the source of quotation is required.

Search all student theses