A multithreaded CUDA and OpenMP based power‐aware programming framework for multi‐node GPU systems
P Czarnul - Concurrency and Computation: Practice and …, 2023 - Wiley Online Library
In the article, we have proposed a framework that allows programming a parallel application
for a multi‐node system, with one or more graphical processing units (GPUs) per node …
for a multi‐node system, with one or more graphical processing units (GPUs) per node …
[HTML][HTML] NGS: A network GPGPU system for orchestrating remote and virtual accelerators
Abstract In General-Purpose computing on Graphics Processing Unit (GPGPU), the use of
CPUs is combined with that of GPUs. CPUs are used for sequential code, while GPUs are …
CPUs is combined with that of GPUs. CPUs are used for sequential code, while GPUs are …
PoCL-R: A scalable low latency distributed OpenCL runtime
J Solanti, M Babej, J Ikkala… - … on Embedded Computer …, 2021 - Springer
Offloading the most demanding parts of applications to an edge GPU server cluster to save
power or improve the result quality is a solution that becomes increasingly realistic with new …
power or improve the result quality is a solution that becomes increasingly realistic with new …
Hybrid-Smash: a heterogeneous CPU-GPU compression library
Compression algorithms are widely used to reduce data size and improve application
performance. Nevertheless, data compression has a computational cost which can limit its …
performance. Nevertheless, data compression has a computational cost which can limit its …
Hybrid-Smash: a heterogeneous CPU-GPU compression library
[EN] Compression algorithms are widely used to reduce data size and improve application
performance. Nevertheless, data compression has a computational cost which can limit its …
performance. Nevertheless, data compression has a computational cost which can limit its …
gVMP: A multi-objective joint VM and vGPU placement heuristic for API remoting-based GPU virtualization and disaggregation in cloud data centers
A Siavashi, M Momtazpour - Journal of Parallel and Distributed Computing, 2023 - Elsevier
The diverse needs of customers drive cloud providers to incorporate more GPU-enabled
services. It is known that users barely utilize GPUs. Hence, GPU virtualization techniques …
services. It is known that users barely utilize GPUs. Hence, GPU virtualization techniques …
[HTML][HTML] Programming Optimization of Move with Interleaving Transform
Computer resources and programming solutions have always been utilised with the aim of
improving efficiency; consequently, many optimisations have been developed in the past …
improving efficiency; consequently, many optimisations have been developed in the past …
Enabling the CUDA Unified Memory model in Edge, Cloud and HPC offloaded GPU kernels
The use of hardware accelerators, based on code and data offloading devoted to
overcoming the CPU limitations in cores, is one of the main distinctive trends in high-end …
overcoming the CPU limitations in cores, is one of the main distinctive trends in high-end …
On Move with Interleaving (MwI) Implementation
Various implementations of the Move with Interleaving transform are discussed in this paper,
with the transformation itself explained briefly at first. The transform has an expected time …
with the transformation itself explained briefly at first. The transform has an expected time …
GPU Acceleration in Unikernels Using Cricket GPU Virtualization
Today, large compute clusters increasingly move towards heterogeneous architectures by
employing accelerators, such as GPUs, to realize ever-increasing performance. To achieve …
employing accelerators, such as GPUs, to realize ever-increasing performance. To achieve …