f MSU Cloud HPC Cluster

hpc.usm.md

52 x 2.2 GHz CPU (AMD), 68 GB RAM
OpenMPI, OpenMP, MPI, C, C++, F77, F90, ScaLAPACK, PETSc, Mathematica, Grid mathematica

hpc2.usm.md

100 x 2.6 GHz CPU (Intel), 272 GB RAM
OpenMPI, OpenMP, MPI, C, C++, F77, F90, Python, NumPy, ScaLAPACK, PETSc

24/7 Support

boris.hancu @ gmail.com
elena.calmis @ gmail.com

HPC Lab

About MSU
HPC Cluster

At the moment, the HPC laboratory is equipped with parallel computing systems for the training and research process, such as:

- The HPC Cluster (hpc.usm.md) – involved since 2007 in the training and research process of the Faculty of Mathematics and Informatics. The cluster has a total of 52 x 2.2 GHz CPU (AMD) and 68 GB RAM.
- Cloud HPC Cluster (hpc2.usm.md) – launched in 2022 within the research project "Investigation and development of the integrated infrastructure of the unified Cloud Computing environment to support open science", project director Hâncu Boris, associate professor. The cluster has a total of 100 x 2.6 GHz CPU (Intel) and 272 GB RAM.
- Workstations – 18 modern PCs for teachers and students.
- Interactive whiteboard for video conferencing

Read more
about

HPC software for

PARALLEL COMPUTING

libraries and routines for linear algebra, partial differential equations, technical computing, message passing interface and more...

SCALAPACK

ScaLAPACK (Scalable Linear Algebra PACKage) is a library of high-performance linear algebra routines for parallel distributed memory machines.

PETSc

Portable, Extensible Toolkit for Scientific Computing - a suite of data structures and routines for parallel solutions of partial differential equations.

Mathematica

Wolfram Mathematica provides a single integrated, continually expanding system that covers the breadth and depth of technical computing.

MPI

The message passing interface (MPI) is a standardized means of exchanging messages between multiple computers running a parallel program across distributed memory. The term itself typically refers to the sending of a message to an object, parallel process, subroutine, function or thread, used to start another process.

OpenMP

OpenMP is an application programming interface (API) that supports multi-platform shared-memory multiprocessing programming in C, C++ and Fortran, on many platforms and operating systems. It consists of a set of compiler directives, library routines, and environment variables that influence run-time behavior.

MPI for Python

MPI for Python provides Python bindings for the Message Passing Interface (MPI) standard, allowing programmers to exploit multiple processor computing systems. NumPy offers comprehensive mathematical functions, random number generators, linear algebra routines, Fourier transforms, and more.

HPC Courses

PARALLEL AND DISTRIBUTED PROGRAMMING

parallel algorithms on distributed and shared memory systems

MPI programming

parallel algorithms on distributed memory systems

Parallel computing systems

Parallel programming models

MPI on distributed memory computing systems

Dynamic generation of MPI processes

12 lessons

Acces the course

OpenMP programming

parallel algorithms on shared memory systems

OpenMP directives

Data management in OpenMP

Mixed MPI-OpenMP programming

Summa and Canon algorithm

5 lessons

Acces the course

ScaLAPACK programming


Data Distributions and Software Conventions

Basic BLACS communication routine

Using PDGEADD for Data Paralization

Parallel Basic Linear Algebra Subprograms

10 lessons

Acces the course
work

Our projects

The last project "Investigation and elaboration the integrated infrastructure of the unified environment “cloud computing” to support open science" will allow to create a Cloud service oriented on variety types of jobs and suitable for the support of open science using multiprocessor clusters of the MSU, RENAM and the Institute of Mathematics and Informatics. For more information click HERE.

1

PROJECTS COMPLETED

1

AWARDS

1

CUSTOMER ACTIVE

1

GOOD REVIEWS

NEWS

The new project Investigation and elaboration of the integrated infrastructure of the unified environment “cloud computing” to support open science will allow to create a Cloud service oriented on variety types of jobs suitable for the support of open science.

testimonial
Cloud Computing Project

June 6 2022

The EYR@EaP Call for Participation is open for Eastern Partnership Countries including for Moldova. Individual researchers and research teams are invited to submit their research project proposal. Winning applicants will get free participation at..

testimonial
Enlighten Your Research

July 25 2018

A new interactive training course “Parallel algorithms for linear models using ScaLAPACK” package is available to students! The course includes all the necessary information so that at the end of the course the students will be able to..

testimonial
ScaLAPACK online course

September 01 2015

The Center for Education and Research in Mathematics and Computer Science (CERIM) is equipped with a HPC Cluster that is involved in educational and research process. More info about HPC and software available for parallel computing you can find on HPC website.

testimonial

Welcome to HPC Lab

January 10 2007

Contact us

contact
Address

Mateevici 60 str., 4th block, cab. 239, Moldova State University, Chisinau, MD-2002

Phone

(+373) 67 560 048

Email

boris.hancu @ gmail.com

Open

10:00 - 16:00

MSU Cloud HPC Cluster

HPC Lab, Faculty of Mathematics and Computer Science, Moldova State University

Quick Links

About

Courses

Projects

Contact

Useful Links

MSU HPC

Math & IT

MSU

Ganglia

Location

MSU Cloud HPC Cluster © 2024