Koç University Research Hub

Welcome to the Koç University Institutional Academic Repository

The Koç University Institutional Academic Repository (KUHub Research) is a state-of-the-art academic repository that consolidates all academic outputs—such as articles, conference proceedings, theses, research data, and more—produced by the university since its establishment in 1993.

KUHub Research adheres to the principles of Open Access and FAIR (Findable, Accessible, Interoperable, Reusable), providing access to the bibliographic records, research data, and full texts of research outputs. Equipped with innovative features such as Author Profile pages and enhanced tools, KUHub Research aims to enhance the visibility of researchers both nationally and internationally. KUHub Research aims to preserve and maintain Koç University's valuable academic legacy for future generations while also serving the needs of today’s researchers.

For more information or inquiries please contact openaccess@ku.edu.tr

To learn how to deposit your publications in your KUHub Research profile, watch our video guide: “How to Deposit Publications into KUHub Research?”

Supported by ©SelenSoft Yazılım

Communities in DSpace

Select a community to browse its collections.

Now showing 1 - 2 of 2

Academic Entities 8079
Research Outputs 26508

Recent Submissions

Access status: Metadata only ,
The landscape of GPU-Centric communication
(Association for Computing Machinery, 2026-09-22)
Sağbili, Doğan
;
Turimbetov, İlyas
;
Graduate School of Sciences and Engineering
;
Department of Computer Engineering
;
Yes
In recent years, GPUs have become the preferred accelerators for HPC and ML applications due to their parallelism and high memory bandwidth. While GPUs boost computation, inter-GPU communication can create scalability bottlenecks, especially as the number of GPUs per node and cluster grows. Traditionally, the CPU managed multi-GPU communication, but advancements in GPU-centric communication now challenge this CPU dominance by reducing its involvement, granting GPUs more autonomy in communication tasks, and addressing mismatches in multi-GPU communication and computation. This article provides a landscape of GPU-centric communication, focusing on vendor mechanisms and user-level library supports. It aims to clarify the complexities and diverse options in this field, define the terminology, and categorize existing approaches within and across nodes. The article discusses vendor-provided mechanisms for communication and memory management in multi-GPU execution and reviews major communication libraries, their benefits, challenges, and performance insights. Then, it explores key research paradigms, future outlooks, and open research questions. By extensively describing GPU-centric communication techniques across the software and hardware stacks, we provide researchers, programmers, engineers, and library designers insights on how to exploit multi-GPU systems at their best.
Mahmoudi Azar, Sepehr
PhD Student
Yaşar, İrem
Undergraduate Student
Morkavuk, Şevket Barış
Doctor
Kadiroğulları, Hazar
Undergraduate Student