An Efficient Live Process Migration Approach for High Performance Cluster Computing Systems

2011 ◽  
pp. 362-373 ◽  
Author(s):  
Ehsan Mousavi Khaneghah ◽  
Najmeh Osouli Nezhad ◽  
Seyedeh Leili Mirtaheri ◽  
Mohsen Sharifi ◽  
Ashakan Shirpour
Keyword(s):  
High Performance ◽  
Cluster Computing ◽  
Process Migration ◽  
Computing Systems

scholarly journals Using Intel Xeon Phi coprocessors for execution of natural join on compressed data

2015 ◽  
pp. 534-542
Author(s):  
Е.В. Иванова ◽  
Л.Б. Соколинский
Keyword(s):  
High Performance ◽  
Data Exchange ◽  
Cluster Computing ◽  
Xeon Phi ◽  
Intel Xeon Phi ◽  
Computing Systems ◽  
Parallel Decomposition ◽  
Many Core ◽  
Compressed Data ◽  
Intel Xeon

В статье описывается сопроцессор баз данных для высокопроизводительных кластерных вычислительных систем с многоядерными ускорителями, использующий распределенные колоночные индексы с интервальной фрагментацией. Работа сопроцессора рассматривается на примере выполнения операции естественного соединения. Параллельная декомпозиция естественного соединения выполняется на основе использования распределенных колоночных индексов. Предложенный подход позволяет выполнять реляционные операции на кластерных вычислительных системах без массовых обменов данными. Приводятся результаты вычислительных экспериментов с использованием сопроцессоров Intel Xeon Phi, подтверждающие эффективность разработанных методов и алгоритмов. A database coprocessor for high-performance cluster computing systems with many-core accelerators is described. This coprocessor uses distributed columnar indexes with interval fragmentation. The operation of the coprocessor engine is considered by an example of natural join processing. The parallel decomposition of natural join operator is performed using distributed columnar indexes. The proposed approach allow one to perform relational operators on computing clusters without massive data exchange. The results of computational experiments on Intel Xeon Phi confirm the efficiency of the developed methods and algorithms.

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