Intel Cluster Studio XE



MPI hybrid development suite for developers on high-performance clusters
Intel® Cluster Studio XE 2012

Get Intel® C++ and Fortran compilers, optimized performance libraries, Intel® Trace Analyzer and Collector, Intel® MPI Library, Intel® MPI Benchmarks, Intel® VTune™ Amplifier XE and Intel® Inspector XE in a single package for comprehensive MPI hybrid cluster application development.


Also available without Intel® VTune™ Amplifier XE and Intel® Inspector XE in Intel® Cluster Studio 2012 (comparison table).

Buy Try

Intel® Cluster Studio XE scales forward and scales faster to meet evolving HPC compute capacity. Software tools must scale for multicore processors today and many-core tomorrow. Intel® Cluster Studio XE is the first HPC development suite that unites Intel's leading analysis tools for MPI use with Intel's leading MPI libraries, compilers, libraries, and programming models.

Intel® Cluster Studio XE cluster tools include:

Benefits:

 

Intel Composer XE Capabilities
Click to enlarge

Extensive MPI Cluster Development Suite
The Intel® Cluster Studio XE cluster software license provides access and support on either Microsoft Windows or on Linux. Below is a partial list of highlighted software tools in the suite. Please refer to the Product Brief for a complete list of tools contained in the suite:

Intel Cluster Studio XE Product brief ›

Intel® MPI Library

Intel MPI Library provides new levels of performance, scalability and flexibility for applications that execute on clusters of Intel® platforms.
  • Interconnect Independence
  • Runtime Fabric Selection
  • Application Tuning Capability
  • Multirail InfiniBand Support
  • Compatible with Previous Intel® MPI 3.x versions
Intel Composer XE Capabilities
Click to enlarge

 

Intel® Trace Analyzer and Collector

Intel Trace Analyzer and Collector is a powerful tool for understanding MPI application correctness and behavior.
  • Visualize and understand parallel applications behavior
  • Evaluate profiling statistics and load balancing
  • Analyze performance of subroutines or code blocks
  • Learn communications patterns and identify hotspots
  • Decrease time to workload
Intel Composer XE Capabilities
Click to enlarge

 

Intel® Composer XE compilers and libraries

Intel® C++ and Fortran compilers have built-in optimization technologies and multithreading support that help create code that runs best on the latest Intel® multicore processors.
  • Multicore Optimizations
  • Support for distributed memory CAF
  • Advanced optimization, multithreading, and processor support
  • Support for hybrid models of parallelism with MPI and threading models like OpenMP, Intel Cilk Plus, and Intel TBB methods to boost application performance on clusters

Intel Composer XE Capabilities
Click to enlarge

Intel® VTune™ Amplifier XE

(Cluster Studio XE only)
Intel VTune Amplifier XE is a powerful performance profiling tool to quickly find, and provide greater insights into, multicore performance bottlenecks
  • Performance profiling now MPI enabled at every node of the cluster
  • Hotspot analysis finds functions using the most time
  • Identify locks and waits degrading parallel performance
  • Map results back to source code
  • Visualize threading timeline of running, waiting, and transitions
  • Develop and fine-tune code for optimal performance, ensuring all cores are fully exploited and new processor capabilities are supported to the fullest

Intel Composer XE Capabilities
Click to enlarge

Intel® Inspector XE

(Cluster Studio XE only)
Intel® Inspector XE enhances developer productivity and facilitates application reliability by effectively finding crucial memory and threading defects early in the development cycle.
  • Static and dynamic code analysis with threading and memory correctness checker now MPI enabled at every node of the cluster
  • Finds latent, intermittent and non-deterministic threading errors
  • Map errors to the source code line and call stack
  • Develop highly robust, secure, and highly optimized parallel or hybrid applications on either shared and distributed memory

Intel Composer XE Capabilities
Click to enlarge

What's new in Intel® Cluster Studio XE:

Performance and scalability improvements for Intel® MPI Library

  • MPI Latency - 6.5X as fast as alternative MPI libraries
  • MPI Scalability - New architecture provides industry-leading performance and sustainable scalability beyond 90K cores
  • Improved Job Manager Integration - Hydra process manager is now default with tight integration with the Simple Linux Utility for Resource Management (SLURM*)

Performance improvements for Intel® Composer XE

  • More performance – Additional optimizations through memory, auto-parallelization, and vectorization
    • C/C++ compiler is now up to 47% faster than the nearest competitor
    • Fortran compiler is now up to 24% faster than the nearest competitor
  • Expanded IEEE Support - Intel Compiler 12.1 the first compiler for IA to support IEEE 754-2008 standard for Binary and Decimal floating point

Higher scalability for Intel® Trace Analyzer and Collector

  • File descriptor virtualization
  • Experimental scalable trace file format
  • Advanced aggregation
  • Seek and jump function

MPI enabled node level performance profiling with Intel® VTune Amplifier XE

  • MPI Enabled – Supports profiling of MPI enabled applications at every node of the cluster
  • Project Explorer - New Project explorer feature helps manage results in a standalone GUI
  • Process Attachment - Attach to a running process available for both Windows* and Linux

MPI enabled node level memory, threading and correctness checking with Intel® Inspector XE

  • MPI Enabled – Supports profiling of MPI enabled applications at every node of the cluster
  • Improved performance – Improved memory & threading checking
  • Project Explorer - New Project explorer feature helps manage results in a standalone GUI

New Libraries

Review the resources below to learn how to use the Intel cluster suite. 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 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 library 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 XE and 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, including Intel cluster software and other cluster tools, from both Intel® experts and our developer community. If an answer cannot be found in Search, you can ask a new cluster development 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 the cluster software information you need above:
Submit Software Tools bugs through Intel® Premier Support. Registration is required.