scholarly journals A study of implementation methods for the Sobel filter on reconfigurable computing systems

2018 ◽  
pp. 379-389
Author(s):  
Е.Е. Таратута
Keyword(s):  
Programming Language ◽  
Reconfigurable Computing ◽  
High Performance ◽  
Computing Systems ◽  
Main Motivation ◽  
C Programming Language ◽  
Software Model ◽  
C Programming ◽  
Performance Computing ◽  
Efficient Software

Основной мотивацией для данной статьи послужила растущая популярность реконфигурируемых ПЛИС (программируемых логических интегральных схем) в области высокопроизводительных вычислений, а также необходимость исследовать особенности написания эффективных программ с использованием инструмента Altera SDK for OpenCL, позволяющего писать приложения для ПЛИС с помощью языка программирования Си++ и стандарта OpenCL. В статье рассмотрены особенности программной модели OpenCL и представлено исследование производительности и особенностей различных реализаций фильтра Собеля с использованием указанного инструмента. The main motivation is the growing popularity of reconfigurable FPGAs in the field of high-performance computing as well as the need to study the features of writing efficient software using the Altera SDK for OpenCL tool, which allows one to implement applications for FPGA using the C++ programming language and the OpenCL standard. The paper discusses the features of the OpenCL software model and presents a study of the performance and features of various Sobel filter implementations using the mentioned tool.

GPU-accelerated molecular dynamics: State-of-art software performance and porting from Nvidia CUDA to AMD HIP

2021 ◽  
pp. 109434202110082
Author(s):  
Nikolay Kondratyuk ◽  
Vsevolod Nikolskiy ◽  
Daniil Pavlov ◽  
Vladimir Stegailov
Keyword(s):  
Molecular Dynamics ◽  
High Performance ◽  
Software Performance ◽  
Computing Systems ◽  
Accelerated Molecular Dynamics ◽  
Nvidia Cuda ◽  
Software And Hardware ◽  
Management Capabilities ◽  
Utilization Time ◽  
Performance Computing

Classical molecular dynamics (MD) calculations represent a significant part of the utilization time of high-performance computing systems. As usual, the efficiency of such calculations is based on an interplay of software and hardware that are nowadays moving to hybrid GPU-based technologies. Several well-developed open-source MD codes focused on GPUs differ both in their data management capabilities and in performance. In this work, we analyze the performance of LAMMPS, GROMACS and OpenMM MD packages with different GPU backends on Nvidia Volta and AMD Vega20 GPUs. We consider the efficiency of solving two identical MD models (generic for material science and biomolecular studies) using different software and hardware combinations. We describe our experience in porting the CUDA backend of LAMMPS to ROCm HIP that shows considerable benefits for AMD GPUs comparatively to the OpenCL backend.

Sign in / Sign up

Export Citation Format

Share Document