ISN France - Intel® HPC

La suite d'outils MPI dédiée aux
clusters hautes performances
Intel® Cluster Studio 2011
(Intel® Cluster Toolkit Compiler Edition)

Obtenez les compilateurs Intel® C++ et Fortran, des librairies optimisées pour la performance, Intel® Trace Analyzer et Collector, Intel® MPI Library,et les benchmarks Intel® MPI en un package tout-en-un pour un développement optimal des applications dédiées à la haute performance.

Buy Try
Boost Scalability with Intel Cluster Studio

Intel® Cluster Studio provides exceptional value at a significantly discounted price for clusters running either Linux* or Windows*. Easy to install and easy to use, this Intel software package helps you develop, analyze, and optimize performance of parallel applications for clusters using Intel® 32- and 64-bit architectures.

Intel® Cluster Studio 2011 includes:

 Benefits:

  • Built-in optimization technologies and multithreading support with Intel® Composer XE 2011 compilers and libraries.

  • Boost application performance on Intel® architecture-based clusters with the Intel® MPI library.

  • Get highly optimized, extensively threaded math routines for science, engineering, and financial applications that require maximum performance with Intel® Math Kernel Library.

  • Accelerate the analysis and tuning cycle of MPI based cluster applications with the capability for analyzing the effect of advanced interconnects on application performance with Intel® Trace Analyzer and Collector.


Click to enlarge

Extensive MPI Cluster Development Toolkit
The Intel® Cluster Studio license provides access and support for the following programs on either Microsoft Windows or on Linux:

Product brief ›
Intel® Trace Analyzer and Collector Intel Trace Analyzer and Collector 8.0 Update 1 is enhanced with new features that accelerate the analysis and tuning cycle of MPI-based cluster applications and enables programmers to analyze the effect of advanced interconnects on application performance. The Intel Trace Analyzer and Collector 8.0 Update 1 load imbalance diagram and the ideal interconnect simulator help MPI programmers identify further optimization opportunities.
Intel® MPI Library Intel® MPI Library 4.0 update 1 provides new levels of performance and flexibility for applications that execute on clusters of Intel® platforms. The library achieves these advantages by improved interconnect support, faster on-node messaging, and an application- tuning capability that adjusts to the cluster architecture and application structure. This library features multirail InfiniBand* (IB) support, and enhancements to the native IB layer for lower communication latencies. In addition, the library maintains compatibility with previous Intel MPI 3.x versions while providing an enhanced library architecture that will enable interconnect vendors and Intel processors to better expose their future maximum performance and functionality.
Intel® Composer XE compilers and libraries

Multicore optimizations - Intel® compilers have built-in optimization technologies and multithreading support that help create code that runs best on the latest Intel® multicore processors. Intel® Fortran Compiler XE 12.0 provides support for CAF on clusters as part of its support of key features of Fortran 2008 standard.

Optimize applications - Intel compilers offer the breadth of advanced optimization, multithreading, and processor support that includes automatic processor dispatch, vectorization, auto- parallelization, data prefetching, and loop unrolling. It is possible to take advantage of hybrid models of parallelism, mixing process, task, data, and vector parallelism with MPI and threading models like OpenMP, Intel® Cilk™ Plus, and Intel® Threading Building Blocks methods to boost application performance on clusters made up of two-, four-, and eight-socket multicore nodes, each node being an SMP.
Intel® Math Kernel Library (Intel® MKL) Intel Math Kernel Library 10.3 (Intel® MKL 10.3) is a library of highly optimized, extensively threaded math routines for science, engineering, and financial applications that require maximum performance. Core math functions include BLAS, LAPACK, ScaLAPACK, Sparse Solvers, Fast Fourier Transforms, Cluster FFTs, Vector Math, and more. Intel MKL version 10.3 is a revision and offers support for Intel® Advanced Vector Extensions (Intel® AVX), C extensions for LAPACK and PARDISO, Summary Statistics Library, and enhancements to several routines like DGEMM, FFTS, and RNGs.
Intel® Integrated Performance Primitives (Intel® IPP) This is an extensive library of multicore-ready, highly optimized software functions for multimedia data processing and communications applications.
Intel® Debugger The debugger improves the efficiency of the debugging process on code that has been optimized for Intel® architecture and includes new threaded code debugging features and a new GUI.

What's new in Intel® Cluster Studio:

Performance and scalability improvements

  • Scaling Intel® MPI up to 50K cores

  • Improved OFA fabric (OFED* verbs) performance

  • Further optimizations to several collective algorithms

Improved Usability

  • Extended process pining control for hybrid applications through the I_MPI_PIN_DOMAIN and I_MPI_PIN_CELL environment variables

Enhancements to Intel® MPI Benchmarks Suite

  • Large buffers support (greater than 2 Gb) for some MPI benchmarks

  • New benchmarks added

Higher scalability for Trace Analyzer

  • New merge separation feature to reduce the trace collection time at application run time

  • Summary data feature for faster trace load time

New Libraries

Here are some of the resources to teach you how-to use the product. Be sure to go to the Intel® Learning Lab Portal for a complete offering of videos, whitepapers, and other resources to learn how to take advantage of this product.

Identify MPI Bottlenecks

 

A short video that shows how Intel® Trace Analyzer and Trace Collector can be used to visualize bottlenecks in MPI traffic that helps the developer tune the code for better performance.


 Flexible MPI Analysis
with Intel® Trace Analyzer Event Timeline

 

The event timeline shows exactly what's going on over time. It displays function events like entering and leaving a function and messages that were exchanged on a timeline. This is useful to diagnose MPI issues.

Dr. Daniel Gruner, Chief Technical Officer - Software, University of Toronto
"We're delighted by the efforts of the Intel cluster tools team in helping us scale our applications to 10s of thousands of cores with Intel(r) MPI Library 4.0. Intel is again raising the performance bar in providing us with the most scalable commercial MPI library for Intel architecture based processors."

Dominic Holland, SDSC
"One can very easily determine the overall expense of communication, and further get a breakdown into the amount of time spent in each MPI routine. The degree and cause of load imbalance is also easily determined at any number of processes. One particularly useful feature is the Message Statistics display, giving an overall view on a grid of which processors are communicating with each other. Another nice feature is the ability to see, and focus on, the amount of time spent in communication mode as the simulation proceeds."

Dr. Takahiro Koishi, Computational Astrophysics Laboratory, RIDEN, Japan
"Intel Trace Analyzer and Collector for Linux helped to drastically improve the performance of RIKEN's molecular dynamics cluster software. We were able to shorten MPI communication time by half by finding and removing bottlenecks with non-blocking communication patterns. Since Intel Trace Analyzer and Collector can embed instrumentation into the program, we can tell the execution time of each function and its load balance, which enabled us to very easily understand where to optimize. Intel's MPI and Cluster tools provide us the best cluster development environment."

Jinwoo Park, Senior System Manager SPCC, University of Seoul, South Korea
"We evaluated the Cluster Tools and concluded that we would get much better performance on the Intel platform with the Intel software tools. For each application, Intel's compiler gave us better performance than before and using the Intel cluster Tools let us know how the cluster system ran and how to improve it."

Dr. Ing. Ulrich Jakobus, Technical Director, EM Software & Systems
"Our FEKO electromagnetics code runs on various parallel environments (e.g., clusters of different sizes, shared memory machines) and utilizes complex numerical algorithms that are non-trivial to parallelize. Intel Trace Analyzer and Collector have proven to be very valuable tools to help understand FEKO parallel communication patterns and consequently in optimizing the message passing call that result in an extremely well performing electromagnetics ISV cluster application."
Intel® Cluster Studio Support

Browse the Intel® Cluster Studio for Linux* Knowledge Base
Browse the Intel® Cluster Studio for Windows* Knowledge Base
Supported Linux* Distributions



Ask Experts Online


Search and post a new question to the Intel® Software Network Forum for Intel® Cluster Studio. The forums allow you to search a growing archive of technical questions and answers from both Intel® experts and our developer community. If an answer can't be found in Search, you can ask a new question. An Intel® Software Development Products Registration Center login will allow you to participate in the Intel® Software Network User Forums without any additional registration.



Get Help from Intel


If you do not find what you need above:
Submit Software Tools bugs through Intel® Premier Support. Registration is required. Click here for more information.