Intel® Cluster Studio XE 2013 Release Notes

 

 

Document number: 327992-001US

28 September 2012

 

Contents

Introduction
Product Contents

What's New

System Requirements
Installation Notes

Documentation
Issues and Limitations
Technical Support
Disclaimer and Legal Information

 

Introduction

Intel® Cluster Studio XE 2013 for Linux* OS and Windows* OS accelerates parallel software development on cluster systems based on IA-32 and Intel® 64 architectures, as well as Intel® Many Integrated Core Architecture (Intel® MIC Architecture) on Linux* OS. For Intel® MIC Architecture, only Intel® Xeon Phi™ coprocessor (codename: Knights Corner) is supported.

 

Intel® Cluster Studio XE 2013 provides a software tools environment for hybrid parallel programming (message passing and threading). In terms of the Intel® Cluster Studio XE software for Windows* OS, consider references within this document to Microsoft* Windows* HPC Server 2008 OS and Microsoft* Windows* HPC Server 2008 R2 OS as interchangeable. The Microsoft Windows HPC Server 2008 and Microsoft Windows HPC Server 2008 R2 operating systems support only Intel® 64 architecture.

 

Intel® Cluster Studio XE 2013 supports hybrid-parallel-programming application development using Intel® MPI Library with optimized parallel libraries, performance analysis, and benchmarks. Intel® Cluster Studio XE 2013 saves software developers time and improves performance on distributed computing systems.

 

Intel® Cluster Studio XE 2013 for Linux OS and Windows* OS supports critical parts of the message-passing interface (MPI) application development process including:

 

·         Compiler support through Intel® C++ Compiler XE 13.0 Update 1 and Intel® Fortran Compiler XE 13.0 Update 1. Intel® C++ Compiler XE 13.0 Update 1 and Intel® Fortran Compiler XE 13.0 Update 1 for Linux* OS provide support for Intel® Many Integrated Core Architecture (Intel® MIC Architecture).

·         Parallel Debugging with Intel® Debugger 13.0 Update 1 on Linux OS. Parallel debugging with Intel® Debugger on Windows OS has been discontinued beginning with the 3.2 release of Intel® Cluster Toolkit and Intel® Cluster Toolkit Compiler Edition. Intel® Cluster Studio XE supports parallel debugging on Linux OS.

·         Intel® MPI Library 4.1, which implements the Message Passing Interface 2.2 Standard (MPI-2.2). Intel MPI library enables multiple interconnect solutions with a single implementation. Intel seeks to be a software leader in MPI and open standards. Intel® MPI Library 4.1 for Linux* OS supports Intel® Many Integrated Core Architecture (Intel® MIC Architecture).

·         Intel® Trace Analyzer and Collector 8.1

o        Intel® Trace Collector 8.1 provides event-based tracing in cluster applications through an instrumentation library that ensures low overhead in execution. The trace information provides performance data, statistics, multi-threaded events, and automatic instrumentation of user binaries on IA-32 architecture.

o        Intel® Trace Analyzer 8.1 provides visual analysis of application activities gathered by the Intel Trace Collector.

o        A message checking component of the Intel Trace Collector provides a novel MPI correctness technology that detects errors with data types, buffers, communicators, point-to-point messages and collective operations, deadlocks, and data corruption.

·            Application tuning with optimized mathematical library functions from Intel® Math Kernel Library (Intel® MKL) 11.0 Update 1 that includes ScaLAPACK* solvers and Cluster DFTs (Discrete Fourier Transforms). Intel® MKL 11.0 Update 1 for Linux* OS supports Intel® Many Integrated Core Architecture (Intel® MIC Architecture).

·            Intel® MPI Benchmarks 3.2.4 that makes it easy to gather performance information about a cluster system.

 

On completing the Intel® Cluster Studio XE 2013 installation process, locate a file called Doc_Index.htm in the doc folder on the master node of the cluster. This file is a documentation map to navigate to various information resources of the Intel® Cluster Studio XE. See the Installation Notes section of these Release Notes for additional information about the exact location of Doc_Index.htm and its content.

 

Back to Top

 

Product Contents

The table below lists the product components and related documentation.

 

Component

Version

Documentation

Intel® Advisor XE

2013 Update 1

documentation_advisor.htm

Intel® C++ Compiler XE

13.0 Update 1

get_started_wc.htm for Windows* OS

get_started_lc.htm for Linux* OS

Intel® Debugger (Linux* OS only)

13.0 Update 1

debugger_documentation.htm

Intel® Fortran Compiler XE

13.0 Update 1

get_started_wf.htm for Windows* OS

get_started_lf.htm for Linux* OS

Intel® Inspector XE

2013 Update 2

documentation_inspector_xe.htm

Intel® Integrated Performance Primitives (Intel® IPP)

7.1 Update 1

ipp_documentation.htm

Intel® Math Kernel Library (Intel® MKL)

11.0 Update 1

mkl_documentation.htm

Intel® MPI Benchmarks

3.2 Update 4

IMB_Users_Guide.htm

Readme_Addendum_for_MIC_Architecture.txt (Linux* OS only)

Intel® MPI Library

4.1

Doc_Index.html for Linux* OS and Doc_Index.htm for Windows* OS

Release_Notes_Addendum_for_MIC_Architecture.txt (Linux* OS only)

Intel® Threading Building Blocks (Intel® TBB)

4.1 Update 1

tbb_documentation.htm

Intel® Trace Analyzer and Collector

8.1

ITA_Reference_Guide.htm

ITC_Reference_Guide.htm

Release_Notes_Addendum_for_MIC_Architecture.txt (Linux* OS only)

Intel® VTuneTM Amplifier XE

2013 Update 2

documentation_amplifier.htm

 

Back to Top

 

What’s New

Intel® Cluster Studio XE 2013

·      Within one installation session, the Intel® Cluster Studio XE installer on Linux* OS or Windows* OS installs:

o      Intel® C++ Compiler XE 13.0 Update 1

o      Intel® Debugger 13.0 Update 1 (For Linux* OS only)

o      Intel® Fortran Compiler XE 13.0 Update 1

o      Intel® Inspector XE 2013 Update 2

o      Intel® Integrated Performance Primitives 7.1 Update 1

o      Intel® MKL 11.0 Update 1

o      Intel® MPI Benchmarks 3.2 Update 4

o      Intel® MPI Library 4.1

o      Intel® Advisor XE 2013 Update 1

o      Intel® Threading Building Blocks 4.1 Update 1

o      Intel® Trace Analyzer and Collector 8.1

o      Intel® VTuneTM Amplifier XE 2013 Update 2

o      Microsoft* Visual Studio* Shell for Intel® Visual Fortran (For Windows* OS; installs only on the master node). Intel® Cluster Studio XE 2013 for Windows* OS provides Microsoft Visual Studio 2010 Shell. As a prerequisite, if you install the included Microsoft Visual Studio 2010 Shell, additional Microsoft software may be required to be installed prior to beginning the installation of the Intel® Cluster Studio XE 2013. Microsoft .NET* 4.0 Framework is required for Microsoft* Visual Studio* 2010 Shell. If you do not have this framework installed already, you can download the installer from:
http://www.microsoft.com/en-us/download/details.aspx?id=17851

 

·      As with Intel® Cluster Studio XE 2012, the topic Integrated Development Environments (IDEs) can be found both for Linux* OS and Windows* OS in the Getting Started Guide for the Intel® Cluster Studio XE.

·      The topic Using Intel® MPI Library on Intel® Many Integrated Cores Architecture (Intel® MIC Architecture) can be found in the Getting Started Guide for applications running on Linux* OS.

·      The topic Using Intel® Trace Analyzer and Collector on Intel® Many Integrated Cores Architecture (Intel® MIC Architecture) can be found in the Getting Started Guide for MPI applications running on Linux* OS.

·      The topic Using Intel® MPI Benchmarks on Intel® Many Integrated Core Architecture (Intel® MIC Architecture) can be found in the Getting Started Guide for the Intel® MPI Benchmark 3.2.4 applications running on Linux* OS

·      The topic Using Intel® Advisor XE for non-MPI C/C++ or non-MPI Fortran Software Applications of the Getting Started Guide provides simple steps for using Intel® Advisor XE for a Fortran or C/C++ application that is a candidate for threading.

Intel® MPI Library 4.1 for Linux* OS

Intel® MPI Library 4.1 for Linux* OS includes the following new features compared to the Intel® MPI Library 4.0 Update 3 (see the product documentation for more details):

·         Support for the MPI-2.2 standard

·         Backward compatibility with Intel MPI Library 4.0.x based applications

·         Support for clusters with different Intel® Architecture Processors

·         Intel® Many Integrated Core Architecture (Intel® MIC Architecture) support

·         Support for the PBS Pro* job management system

·         Support for Intel® Composer XE 2013

·         New documentation in the HTML-based format

Intel® MPI Library 4.1 for Windows* OS

Intel® MPI Library 4.1 for Windows* OS includes the following new features compared to the Intel® MPI Library 4.0 Update 3 (see the product documentation for more details):

·         Support for the MPI-2.2 standard

·         Extended interoperability

·         Intel® Composer XE 2013 support

·         New documentation in the HTML-based format

 

Intel® Math Kernel Library (Intel® MKL) 11.0 Update 1

 

Intel MKL now has support for the Intel® Many Integrated Core Architecture (Intel® MIC Architecture) on Linux* OS. Most of Intel MKL has been ported to run natively on processors based on this architecture. A smaller number of functions have been optimized to automatically divide their computational work between the host CPU and Intel® Xeon Phi™ coprocessors, a feature called automatic offload (AO). Read the Intel MKL User’s Guide for more information. The following describes the parts of Intel MKL currently supported and optimized.

o    The following components are tuned for the Intel MIC Architecture:

§  BLAS

·         AO: ?TRMM, ?TRSM, ?GEMM

·         native: Level 3 BLAS and key functions from Level 1 and 2 BLAS

§  Sparse BLAS

·         native: ?CSRMV, ?CSRMM

§  LAPACK

·         native: LU, Cholesky, and QR factorization

§  FFTS

·         native: Single- and double-precision real-to-complex and complex-to-complex one-, two-, and three-dimensional fast Fourier transforms

§  VML

·         native: real functions

§  Random number generators

·         native: MT19937, MT2203, MRG32k3a BRNGs, and discrete Uniform and Geometric RNGs

o    Most standard Intel MKL functions run on coprocessors based on Intel MIC Architecture with the following exceptions:

§  ScaLAPACK and cluster FFTs

§  Poisson library, iterative sparse solvers, and trust region solvers

o    Only static native libraries

·         Conditional Numerical Reproducibility (CNR): New functionality in Intel MKL now allows you to balance performance with reproducible results by allowing greater flexibility in code branch choice and by ensuring algorithms are deterministic. See the Intel® MKL User’s Guide for more information. All of Intel MKL supports this new capability except the following: ScaLAPACK, cluster FFTs, data fitting functions, summary statistics functions, and the vsRngBeta random number generator on 32-bit operating systems.

·         Intel MKL also introduces optimizations using the new Intel® Advanced Vector Extensions 2 (Intel® AVX2) including the new FMA3 instructions. The following parts of Intel MKL have been optimized:

o    BLAS

o    FFTs

o    Vector math functions

o    Data fitting functions

o    Random number generators

o    Summary statistics functions

·         Other new features

o    FFT: Completed support for real-to-complex transforms with sizes given by 64-bit integers

o    Random number generators: Added support for a non-deterministic random number generator (VSL_BRNG_NONDETERM) based on the RdRand instruction

·         Intel® Xeon® processor optimizations

o    Improved ?CSRMM algorithm by improving scalability on all multicore processors

o    Improved Geometric RNG performance on Intel® Core™ i7-2600 and Intel® Xeon® E7-4870 processors

o    Improved data fitting Integrate1D function performance on Intel® Core™ i7-2600 and Intel® Xeon® E7-4870 processors

·         Documentation

o    Intel MKL Reference Manual in HTML format is no longer available with the product but accessible online. For Windows OS, Intel MKL Reference manual in HTML-based format is delivered with the product and integrates into Microsoft* Visual Studio 2008, 2010, and 2012.

o    Man pages and Eclipse help integration are no longer provided

·         Other changes

o    Removed Intel MKL GNU Multiple Precision* (GMP) function interfaces

o    Disabled timing function mkl_set_cpu_frequency() to perform useful work – use mkl_get_max_cpu_frequency(), mkl_get_clocks_frequency(), and mkl_get_cpu_frequency() as described in the Intel MKL Reference Manual.

o    Removed MKL_PARDISO constant – used MKL_DOMAIN_PARDISO to specify the PARDISO domain with the mkl_domain_set_num_threads() function

o    Removed special backward compatibility functions for convolution and correlation functions in Intel MKL 10.2 update 4

o    Removed the OpenMP* static runtime library from the Windows* version of Intel MKL and Intel® compilers.

Intel® Trace Analyzer and Collector 8.1

·         Usability improvements

o      New interactive help system with support for non-ASCII installation path

o      New documentation in the HTML-based format

·         Intel® Many Integrated Core Architecture (Intel® MIC Architecture) support for Linux* OS

·         Extended interoperability

o        Intel® Composer XE 2013 support

Intel® MPI Benchmarks 3.2 Update 4

·         Intel® MPI Benchmarks on Linux* OS now supports Intel® Many Integrated Core Architecture (Intel® MIC Architecture)

·         New documentation in HTML-based format.

 

Back to Top

 

 

System Requirements

Processor Requirements

 

Systems based on IA-32 architecture:

A system based on the Intel® Pentium® 4 processor or higher

Intel® Core® i7 processor recommended

 

Systems based on Intel® 64 architecture:

Intel® Core™ processor family or higher

Intel® Xeon® 5500 processor series recommended

 

Note:    It is assumed that the processors listed above are configured into homogeneous clusters. For the Microsoft Windows HPC Server* 2008 operating system, only processors based on the Intel® 64 architecture are supported.

 

Back to Top

 

Disk Space Requirements

 

100 GB of disk space (minimum)

 

Note:    During the installation process, the installer may need up to 12 GB of temporary disk storage to manage the intermediate installation files.

 

Back to Top

 

Operating System Requirements

 

OS Distributions

IA-32 Architecture

Intel® 64 Architecture

32-Bit Applications

64-Bit Applications

Intel® Cluster Ready1

N/A

N/A

S

Red Hat Enterprise Linux* 5.0

S

S

S

Red Hat Enterprise Linux* 6.0

S

S

S

SUSE Linux Enterprise Server* 11

S

S

S

Microsoft* Windows* HPC Server 2008

N/A

S

S

Microsoft* Windows* HPC Server 2008 R2

N/A

S

S

 

S = Supported

 

1 Intel® Cluster Ready is an applications platform architecture standard for Linux* OS clusters. Please convey to your users the Linux* OS platform needed for your MPI application with:

 

This application has been verified to run correctly on Linux* OS clusters that conform to the Intel® Cluster Ready platform architecture. Each Intel® Cluster Ready system is shipped and tested with a diagnostic tool: Intel® Cluster Checker. Intel® Cluster Checker is used to validate operability and compliance, as well as overall system health. On an Intel® Cluster Ready system, start with these commands to easily view diagnostic logs:

 

$ . /opt/intel/clck/<version>/clckvars.sh

$ cluster-check --report

 

For more information on Intel® Cluster Ready and on the alliance of partner vendors, please visit http://www.intel.com/go/cluster.

 

Back to Top

 

Memory Requirements

 

2 GB RAM (minimum)

 

Back to Top

 

Intel® Professional Edition C++ Compiler and Intel® Fortran Compilers

 

For all of the Intel® architectures, the version number on the Intel compilers should be 11.1 or higher.

 

Back to Top

 

Adobe* Reader*

 

There are certain documents within the Intel® Cluster Studio XE that require Adobe Reader for viewing. You can download Adobe Reader onto your system from http://get.adobe.com/reader/.

 

 

Back to Top

 

Installation Notes

 

For instructions on installing and uninstalling the Intel® Cluster Studio XE 2013 on Linux* OS and Windows* OS, see the Installation Guide.

 

Back to Top

 

 

Documentation

The documentation index file Doc_Index.htm provides hyperlinks to the Intel® Cluster Studio XE documentation

 

Back to Top

 

Issues and Limitations

1.   When trying to install the Intel® Cluster Studio or Intel® Cluster Studio XE product via the “activate by using a license manager” option, you may experience delays of up to 10 minutes.  Do not immediately shut down the install in such cases but wait for the installer to  complete.  If you experience delays exponentially longer than this, contact Intel® Premier Support at http://premier.intel.com

2.   There have been situations where during the installation process, /tmp has been filled up. We recommend that you have at least 12 GB of free space in /tmp when installing the Intel® Cluster Studio XE. Also, the installer script install.sh has the command-line options:

 

-t [FOLDER]

 

or

 

--tmp-dir [FOLDER]

 

where [FOLDER]  is a directory path, which can direct the use of intermediate storage to another disk partition referenced by [FOLDER]. [FOLDER]  should be a non-shared storage location on each node of the cluster. Note that [FOLDER] should also contain at least 12 GB of free space.

3.      On Linux* OS, if any software component of the Intel® Cluster Studio XE is detected as pre-installed on the head node, that software component will not be processed by the Intel Cluster Studio installer. There is a similar problem on Windows* OS in the ‘Modify’ mode. For Windows* OS, if some software component of the Intel® Cluster Studio XE is pre-installed on the head node using the Intel Cluster Studio installer, that software component will not be installed on the compute nodes of the cluster. For either Linux* OS or Windows* OS, if you already installed some of the software components only on the head node, and you want to install them on the other nodes using the Intel Cluster Studio installer, you need to uninstall such components from the head node manually before starting the installer.

4.      For Linux* OS versions of the Intel® Cluster Studio XE, the Java* Runtime Environment is used by the Intel® Debugger graphical environment, which is a Java* application. On Linux* OS, the installer may display the following message with respect to the Java* Runtime Environment (JRE) during installation:

 

Step no: 4 of 6 | Installation configuration > Missing Optional Prerequisite

--------------------------------------------------------------------------------

There is one or more optional unresolved issues. It is highly recommended to fix

them all before you continue the installation. You can fix it without exiting the
installation and re-check. Or you can quit the installation, fix the issues, and

run the installation again.

--------------------------------------------------------------------------------

Missing optional prerequisite

-- No compatible Java* Runtime Environment (JRE) found

--------------------------------------------------------------------------------

1. Skip missing optional prerequisites [default]

2. Show the detailed info about issue(s)

3. Re-check the prerequisites

 

h. Help

b. Back to the previous menu

q. Quit

--------------------------------------------------------------------------------

Please type a selection or press "Enter" to accept default choice [1]:

 

You can resolve this issue by entering value 2 after the prompt message for the installation state shown above. This will generate the following diagnostic information:

 

Step no: 4 of 6 | Installation configuration > Missing Optional Prerequisite

--------------------------------------------------------------------------------

This system does not appear to have a Java* JRE version 5.0 (also referred to as

1.5.0) installed.  This may prevent operation of the Intel(R) Debugger GUI.  For

further details, please refer to the System Requirement section of the product

Release Notes.

--------------------------------------------------------------------------------

1. Finish with prerequisites and continue installation [default]

2. Back to Prerequisite summary dialog

 

h. Help

b. Back to the previous menu

q. Quit

--------------------------------------------------------------------------------

Please type a selection or press "Enter" to accept default choice [1]:

 

The generated instructions indicate that a version of the Java* Runtime Environment is missing from your system. For the prompt message above, enter the character “q” to quit the installation process. Make sure that the Java* Runtime Environment package is installed on your system. The directory path for the Java* Runtime Environment might be:

 

/usr/java

 

If you cannot find the Java* Runtime Environment library on your system, you can download the appropriate version of the Java* Runtime Environment from http://www.java.com/en/download/

 

 

After the download completes, install the Java* Runtime Environment on your system. You may need a system administrator to help you with the installation. The Java* Runtime Environment is used by the Intel® Debugger graphical environment, which is a Java* application.

 

If you have located an existing and compatible Java* Runtime Environment library on your system, or you have proceeded to visit the URL above and completed a download and installation, set your PATH environment variable to include the directory path to the Java* Runtime Environment library. The Bourne* and Korn* Shell syntax for setting the PATH environment variable might be as follows:

 

export PATH=/usr/java/jre1.5.0_22/bin:$PATH

 

For C Shell, the syntax for setting the PATH environment variable might be as follows:

 

setenv PATH /usr/java/jre1.5.0_22/bin:$PATH

 

After setting the PATH environment variable, repeat the installation process. The message regarding the missing Java* Runtime Environment library will disappear.

5.      You may encounter a symbolic links creation error on Linux* OS when  upgrading from Intel® Cluster Studio to Intel® Cluster Studio XE, with the following symptoms:

 

a.  No symbolic links are created in /opt/intel/icsxe/<version>/

b.  Lots of error messages are returned in case of the distributed install, such as:

ln: creating symbolic link `/root/icsxe/2013.0.028/mpi' to `/root/icsxe/impi/4.1.0.008': No such file or directory
ln: creating symbolic link `/root/icsxe/2013.0.028/impi' to `/root/icsxe/impi/4.1.0.008': No such file or directory
ln: creating symbolic link `/root/icsxe/2013.0.028/mpi' to `/root/icsxe/impi/4.1.0.008': No such file or directory
ln: creating symbolic link `/root/icsxe/2013.0.028/impi' to `/root/icsxe/impi/4.1.0.008': No such file or directory

 

The workaround is to put the Intel® Cluster Studio XE license into either /opt/intel/licenses or ${HOME}/intel/licenses before starting the installation procedure described in the Linux* OS installation guide.

6.      If you use the C/C++ memory leak programming example described in the topic Using Intel® Inspector XE of the Intel® Cluster Studio XE 2013 Getting Started Guide and issue the Intel® MPI Library/Intel® Inspector XE command-line:

 

mpiexec -n 4 inspxe-cl -r inspectorxe_results -collect mi1 -- ./a.out

 

You may encounter a message of the following type:

 

Inspector reports 0 issues for all processes

 

Then try running the Intel® Inspector XE with the mi2 collector as follows:

 

mpiexec -n 4 inspxe-cl -r inspectorxe_results -collect mi2 -- ./a.out

 

mi1 is the Intel® Inspector XE collector that detects memory leaks. mi2 is the Intel® Inspector XE collector that detects other memory problems.

7.      If you use the Intel® MPI Library command mpirun with the Intel® Inspector XE as follows:

 

mpirun -f ./mpd.hosts -nolocal -ppn 1 -n 4 inspxe-cl -c ti2 -r r003_{mpirank} `pwd`/inspxe_mpirank.exe inspxe-cl -c mi2 -r r000_{mpirank} `pwd`/inspxe_mpirank.exe

 

where the above command line is collecting two types of instrumentation data (ti2 and mi2), and you encounter a run-time error that may look as follows:

 

HYDU_create_process (./utils/launch/launch.c:94): execvp error on file r000_{mpirank} (No such file or directory)
HYDU_create_process (./utils/launch/launch.c:94): execvp error on file r000_{mpirank} (No such file or directory)
HYDU_create_process (./utils/launch/launch.c:94): execvp error on file r000_{mpirank} (No such file or directory)
HYDU_create_process (./utils/launch/launch.c:94): execvp error on file r000_{mpirank} (No such file or directory)

 

In this case, you can use the mpiexec command in lieu of the mpirun command:

 

mpiexec -nolocal -ppn 1 -n 4 inspxe-cl -c ti2 -r /shared/cluster_common/inspector_test/cluster/r003_{mpirank} `pwd`/inspxe_mpirank.exe inspxe-cl -c mi2 -r r000_{mpirank} inspxe_mpirank.exe

 

where /shared/cluster_common/inspector_test/cluster/r003_{mpirank} is a shared path for collecting ti2 instrumentation data.

 

Alternatively, you can create a Bourne* Shell or C Shell script that contains instrumentation information that may look as follows:

 

inspxe-cl -c ti2 -r /shared/cluster_common/inspector_test/cluster/r003_{mpirank} `pwd`/inspxe_mpirank.exe inspxe-cl -c mi2 -r r000_{mpirank} inspxe_mpirank.exe

      Using Bourne* Shell syntax, the script might be called run.sh, where it is used with the mpirun command in the following manner:

 

mpirun -ppn 1 -n 4 ./run.sh

 

You also need to remove the –nolocal command-line option because the –f <hosts_file> option was not specified, and therefore all processes are started locally.

8.      Intel® Cluster Studio XE 2013 for Windows* OS requires the creation and use of symbolic links for installation of the Intel® software product components. If you have a File Allocation Table (FAT32) file system deployed on your Windows* OS platform, these symbolic links cannot be created and the integrity of the Intel® Cluster Studio XE 2013 installation is compromised.

9.   Intel® Trace Analyzer and Collector 8.1 - itcpin is not supported for Linux* OS kernels version 3.x.

10. Inte MPI Library supports only Inte Xeon Phi™  coprocessor (codename: Knights Corner) based on Inte MIC Architecture.

This release of the Inte
MPI Library 4.1 for Linux* OS does not support certain features for Inte Xeon Phi™  coprocessor:
o MPD process manager
o Checkpoint-Restart Support. See the Checkpoint-Restart Support topic in the Reference Manual for more details.

Inte
MPI Library 4.1 for Linux* OS supports multiple DAPL* providers for communication between host and Inte Xeon Phi™  coprocessor and between several Inte Xeon Phi™  coprocessors inside one node.
Currently supported providers are DAPL over InfiniBand* Architecture and DAPL over Symmetric Communications Interface (SCIF). This feature requires using symbolic names in the hostfile.
 

Back to Top

 

Technical Support

Your feedback is very important to us. To receive technical support for the tools provided in this product and technical information including FAQ's and product updates, you need to register for an Intel® Premier Support account at the Intel® Registration Center.

 

Note:    Registering for support varies for release product or pre-release products (alpha, beta, etc) - only released software products have support web pages at http://software.intel.com/sites/support/.

 

To register for an account, please visit the Intel® Registration Center website at http://www.intel.com/software/products/registrationcenter/index.htm. If you have forgotten your password, please email a request to: quadsupport@mailbox.intel.com. Please do not email your technical issue to this email address.

 

The product support web site, located under the SUPPORT tab of the http://www.intel.com/go/clustertools product page, provides top technical issues, FAQs & Known Issues, Documentation and Training, and product errata.  For more information, and to connect with the Intel® HPC community, visit the Intel® Cluster Studio XE forums: http://software.intel.com/en-us/forums/intel-clusters-and-hpc-technology.

 

Submitting Issues

 

To submit an issue via the Intel Premier Support website, please perform the following steps:

1.      Ensure that Java* and JavaScript* are enabled in your browser.

2.      Go to https://premier.intel.com/.

3.      Type in your Login and Password. Both are case-sensitive.

4.      Click the "Submit Issues" button in the left margin.

5.      Read the Confidentiality Statement and click the "I Accept" button.

6.      Click on the "Go" button next to the "Product" drop-down list.

7.      Click on the "Submit Issue" link in the left navigation bar.

8.      Choose "Development Environment (tools, SDV, EAP)" from the "Product Type" drop-down list.

9.      If this is a software or license-related issue choose "Intel(R) Cluster Studio XE" from the "Product Name" drop-down list.

10.   Enter your question and complete the fields in the web-page windows that follow to successfully submit the issue.

 

Follow these guidelines when forming your problem report or product suggestion:

 

1.      Describe your difficulty or suggestion. For problem reports, please be as specific as possible (for example, including compiler and link command-line options), so that we may reproduce the problem. Please include a small test case if possible.

2.      Describe your system configuration information. Be sure to include specific information that may be applicable to your setup: operating system, name and version number of the installed applications, and anything else that may be relevant to helping us address your concern.

 

Back to Top

 

Disclaimer and Legal Information

INFORMATION IN THIS DOCUMENT IS PROVIDED IN CONNECTION WITH INTEL PRODUCTS. NO LICENSE, EXPRESS OR IMPLIED, BY ESTOPPEL OR OTHERWISE, TO ANY INTELLECTUAL PROPERTY RIGHTS IS GRANTED BY THIS DOCUMENT. EXCEPT AS PROVIDED IN INTEL'S TERMS AND CONDITIONS OF SALE FOR SUCH PRODUCTS, INTEL ASSUMES NO LIABILITY WHATSOEVER AND INTEL DISCLAIMS ANY EXPRESS OR IMPLIED WARRANTY, RELATING TO SALE AND/OR USE OF INTEL PRODUCTS INCLUDING LIABILITY OR WARRANTIES RELATING TO FITNESS FOR A PARTICULAR PURPOSE, MERCHANTABILITY, OR INFRINGEMENT OF ANY PATENT, COPYRIGHT OR OTHER INTELLECTUAL PROPERTY RIGHT.

 

A "Mission Critical Application" is any application in which failure of the Intel Product could result, directly or indirectly, in personal injury or death. SHOULD YOU PURCHASE OR USE INTEL'S PRODUCTS FOR ANY SUCH MISSION CRITICAL APPLICATION, YOU SHALL INDEMNIFY AND HOLD INTEL AND ITS SUBSIDIARIES, SUBCONTRACTORS AND AFFILIATES, AND THE DIRECTORS, OFFICERS, AND EMPLOYEES OF EACH, HARMLESS AGAINST ALL CLAIMS COSTS, DAMAGES, AND EXPENSES AND REASONABLE ATTORNEYS' FEES ARISING OUT OF, DIRECTLY OR INDIRECTLY, ANY CLAIM OF PRODUCT LIABILITY, PERSONAL INJURY, OR DEATH ARISING IN ANY WAY OUT OF SUCH MISSION CRITICAL APPLICATION, WHETHER OR NOT INTEL OR ITS SUBCONTRACTOR WAS NEGLIGENT IN THE DESIGN, MANUFACTURE, OR WARNING OF THE INTEL PRODUCT OR ANY OF ITS PARTS.

 

Intel may make changes to specifications and product descriptions at any time, without notice. Designers must not rely on the absence or characteristics of any features or instructions marked "reserved" or "undefined". Intel reserves these for future definition and shall have no responsibility whatsoever for conflicts or incompatibilities arising from future changes to them. The information here is subject to change without notice.  Do not finalize a design with this information.

 

The products described in this document may contain design defects or errors known as errata which may cause the product to deviate from published specifications. Current characterized errata are available on request.

 

Contact your local Intel sales office or your distributor to obtain the latest specifications and before placing your product order.

 

Copies of documents which have an order number and are referenced in this document, or other Intel literature, may be obtained by calling 1-800-548-4725, or go to: http://www.intel.com/design/literature.htm

 

MPEG-1, MPEG-2, MPEG-4, H.261, H.263, H.264, MP3, DV, VC-1, MJPEG, AC3, AAC, G.711, G.722, G.722.1, G.722.2, AMRWB, Extended AMRWB (AMRWB+), G.167, G.168, G.169, G.723.1, G.726, G.728, G.729, G.729.1, GSM AMR, GSM FR are international standards promoted by ISO, IEC, ITU, ETSI, 3GPP and other organizations. Implementations of these standards, or the standard enabled platforms may require licenses from various entities, including Intel Corporation.

 

BlueMoon, BunnyPeople, Celeron, Celeron Inside, Centrino, Centrino Inside, Cilk, Core Inside, E-GOLD, Flexpipe, i960, Intel, the Intel logo, Intel AppUp, Intel Atom, Intel Atom Inside, Intel CoFluent, Intel Core, Intel Inside, Intel Insider, the Intel Inside logo, Intel NetBurst, Intel NetMerge, Intel NetStructure, Intel SingleDriver, Intel SpeedStep, Intel Sponsors of Tomorrow., the Intel Sponsors of Tomorrow. logo, Intel StrataFlash, Intel vPro, Intel Xeon Phi, Intel XScale, InTru, the InTru logo, the InTru Inside logo, InTru soundmark, Itanium, Itanium Inside, MCS, MMX, Pentium, Pentium Inside, Puma, skoool, the skoool logo, SMARTi, Sound Mark, Stay With It, The Creators Project, The Journey Inside, Thunderbolt, Ultrabook, vPro Inside, VTune, Xeon, Xeon Inside, X-GOLD, XMM, X-PMU and XPOSYS are trademarks of Intel Corporation in the U.S. and/or other countries.

 

 

* Other names and brands may be claimed as the property of others.

 

Microsoft, Windows, and the Windows logo are trademarks, or registered trademarks of Microsoft Corporation in the United States and/or other countries.

 

Java is a registered trademark of Oracle and/or its affiliates.

 

Copyright (C) 2011–2012, Intel Corporation. All rights reserved.


 

 

 

Optimization Notice

Intel’s compilers may or may not optimize to the same degree for non-Intel microprocessors for optimizations that are not unique to Intel microprocessors. These optimizations include SSE2, SSE3, and SSSE3 instruction sets and other optimizations. Intel does not guarantee the availability, functionality, or effectiveness of any optimization on microprocessors not manufactured by Intel. Microprocessor-dependent optimizations in this product are intended for use with Intel microprocessors. Certain optimizations not specific to Intel microarchitecture are reserved for Intel microprocessors. Please refer to the applicable product User and Reference Guides for more information regarding the specific instruction sets covered by this notice.

 

Notice revision #20110804

 

Back to Top