Intel® Parallel Studio XE 2015 Composer Edition for C++ Linux* Installation Guide and Release Notes 24 July 2014 Table of Contents 1 Introduction ......................................................................................................................... 4 1.1 Change History ............................................................................................................ 4 1.1.1 Changes since Intel® Composer XE 2013 SP1 (New in Intel® Parallel Studio XE 2015 Composer Edition) ...
3 2.9 Known Installation Issues............................................................................................12 2.10 Installation Folders ......................................................................................................12 2.11 Removal/Uninstall .......................................................................................................14 Intel® C++ Compiler ...................................................................................................
.4 Other Changes ...........................................................................................................20 3.4.1 Establishing the Compiler Environment................................................................20 3.4.2 Instruction Set Default Changed to Require Intel® Streaming SIMD Extensions 2 (Intel® SSE2) .....................................................................................................................20 3.4.3 Linux* 3.
7 Intel® Math Kernel Library .................................................................................................30 7.1 Changes in This Version .............................................................................................31 7.1.1 7.2 What’s New in Intel MKL 11.2 ..............................................................................31 Attributions ..................................................................................................................
Control diagnostic strictness of Pointer Checker for problems with pointers to structure fields aligned_new header GNU-compatible function multiversioning for CPU dispatching Improved debugging of lambda functions Debug information now in DWARF Version 3 format by default Extended offload syntax to allow copying of non-contiguous memory New pragma directives to control inlining behavior per function New INTEL_PROF_DYN_PREFIX environment variable to add custom
1.3 Intel® Debugger (IDB) is removed from this release The Intel Debugger (IDB) has been removed from this release. A debugger based on the GNU* Project Debugger (GDB*) is now provided for debugging. 1.4 System Requirements For an explanation of architecture names, see http://intel.
For the best experience, a multi-core or multi-processor system is recommended 2GB of RAM (4GB recommended) 7.5GB free disk space for all features One of the following Linux distributions (this is the list of distributions tested by Intel; other distributions may or may not work and are not recommended - please refer to Technical Support if you have questions): o Fedora* 20 o Red Hat Enterprise Linux* 5, 6, 7 o SUSE LINUX Enterprise Server* 11 o Ubuntu* 12.04 LTS (64-bit only), 13.10, 14.
architecture processor. However, if your application uses Intel® Integrated Performance Primitives or Intel® Threading Building Blocks, executing the application will require a processor supporting the Intel® SSE2 instructions. Compiling very large source files (several thousands of lines) using advanced optimizations such as -O3, -ipo and -openmp, may require substantially larger amounts of RAM.
1.7 Japanese Language Support Intel compilers provide support for Japanese language users (when the combined JapeneseEnglish installation is used). Error messages, visual development environment dialogs and some documentation are provided in Japanese in addition to English. By default, the language of error messages and dialogs matches that of your operating system language selection. Japanese-language documentation can be found in the ja_JP subdirectory for documentation and samples.
Note that there are several different downloadable files available, each providing different combinations of components. Please read the download web page carefully to determine which file is appropriate for you. You do not need to uninstall previous versions or updates before installing a newer version – the new version will coexist with the older versions. Please do not run the install script as a background process (i.e. running “./install.sh &”). This is not supported. 2.
enabled by default – you can opt-in during installation or at a later time, and may opt-out at any time. For more information please see http://intel.ly/SoftwareImprovementProgram. 2.4 Installation of Intel® Manycore Platform Software Stack (Intel® MPSS) The Intel® Manycore Platform Software Stack (Intel® MPSS) may be installed before or after installing the Intel® Parallel Studio XE for Linux* product. Using the latest version of Intel® MPSS available is recommended.
For example: l_ccompxe_online_2015.0.0XX.sh –duplicate icc15_install_config.ini --download-dir "/temp/custom_pkg_ic15" The configuration file and installable package will be created under “"/temp/custom_pkg_ic15”. 2.7 Using a License Server If you have purchased a "floating" license, see http://intel.ly/pjGfwC for information on how to install using a license file or license server. This article also provides a source for the Intel® License Server that can be installed on any of a wide variety of systems.
mkl – symbolic link to the directory for the latest installed version of Intel® Math Kernel Library tbb – symbolic link to the directory for the latest installed version of Intel® Threading Building Blocks ism – contains files for Intel® Software Manager composerxe – symbolic link to the composer_xe_2015 directory composer_xe_2015 – directory containing symbolic links to subdirectories for the latest installed Intel® Parallel Studio XE 2015 compiler release composer_xe_2015..
uninstall – Files for uninstallation If you have both the Intel C++ and Intel Fortran compilers installed, they will share folders for a given version and update. This directory layout allows you to choose whether you want the latest compiler, no matter which version, the latest update of the Intel® Parallel Studio XE 2015 compiler, or a specific update. Most users will reference /bin for the compilervars.sh [.csh] script, which will always get the latest compiler installed. 2.
3.2 New and Changed Features This product now contains Intel® C++ Compiler 15.0. The following features are new or significantly enhanced in this version. For more information on these features, please refer to the documentation.
of native ISA at link time by using the new option /Qgpu-arch: for Windows and –mgpuarch= for Linux. The option is described in detail in the User’s Guide. 3.2.2 Static Analysis is deprecated Support for Static Analysis is deprecated and will be removed in a future release. If you have concerns or feedback, please comment. 3.2.
It is strongly recommended that you read the documentation for full details. See the Intel Compiler User’s Guide under Compiler Reference->Compiler Option Categories and Descriptions->Optimization Report Options. 3.2.7 Updated Support for Upcoming OpenMP* features added in the Intel® C++ Compiler 15.0 Intel Compiler 15.0 adds the following OpenMP* 4.0 features: cancel and cancellation point directives depend clause for task directives OpenMP* 4.0 user defined reductions are not supported. 3.2.
3.2.13 Static Analysis Feature (formerly “Static Security Analysis” or “Source Checker”) Requires Intel® Inspector XE The “Source Checker” feature, from compiler version 11.1, has been enhanced and renamed “Static Analysis”. The compiler options to enable Static Analysis remain the same as in compiler version 11.1 (for example, -diag-enable sc), but the results are now written to a file that is interpreted by Intel® Inspector XE rather than being included in compiler diagnostics output. 3.
-qoffload-attribute-target= -qoffload-option,,,”option list” o “jit” added as tool for offload to Intel® Graphics Technology -f[no-]fat-lto-objects -prof-gen=threadsafe -qopt-report[=n] -qopt-report-file=[stdout | stderr | ] -qopt-report-per-object -qopt-report-phase=[,,…] -qopt-report-routine=[,,…] -qopt-report-filter= -qopt-report-format=[text|vs] -qopt-report-names=[mangled|unmangled] -qopt-report-hel
current file directory as the first search directory for includes with quotes as in "#include "file"". Enforce same code to be executed regardless of data alignment with –no-optdynamic-align By default, the compiler may generate multiple code paths to execute depending on the alignment of data in order to improve performance which may affect the consistency of floatingpoint calculations. To disable this behavior, use –no-opt-dynamic-align 3.3.5 3.3.
To specify the older default of generic IA-32, specify –mia32 “asm” keyword no longer accepted with –std=c99 in Intel® C++ Compiler 15.0 for Linux* When using –std=c99, the asm keyword will not be recognized starting with the Intel C++ Compiler 15.0. This matches current gcc behavior. Use –std=gnu99 to recognize the asm keyword while maintaining C99 compilation. 3.4.3 3.5 Known Issues 3.5.1.
generate different diagnostics during these two compilations. The new tag permits easier association with either the CPU or Target compilation. $ icc -c sample.c sample.c(1): warning #1079: *MIC* return type of function "main" must be "int" void main() ^ sample.c(5): warning #120: *MIC* return value type does not match the function type return 0; ^ sample.c(1): warning #1079: return type of function "main" must be "int" void main() ^ sample.
3.5.2.6 Calling exit() from an offload region When calling exit() from within an offload region, the application terminates with an error diagnostic “offload error: process on the device 0 unexpectedly exited with code 0” 3.5.3 Known issues for offload to Intel® Graphics Technology 3.5.3.1 Host-side execution of offload code is not parallelized The compiler will generate both a target and host version of the parallel loop under #pragma offload.
o o o o 3.5.4 OpenMP* cilk_spawn or cilk_sync Intel® Cilk™ Plus reducers ANSI C runtime library calls (with the exception of SVML, math.h, and mathimf.h calls and a few others) 64-bit float and integer operations are inefficient Intel® Cilk™ Plus Known Issues Static linkage of the runtime is not supported Static versions of the Intel® Cilk™ Plus library are not provided by design.
If you have already created a static analysis result that was affected by this issue and you are able to open that result in the Intel® Inspector XE GUI, then you can hide the undesired messages as follows: The messages you will want to suppress are “Arg count mismatch” and “Arg type mismatch”. For each problem type, do the following: Click on the undesired problem type in the Problem filter. This hides all other problem types.
4.2 Using GNU* GDB GNU* GDB provided with Intel® Parallel Studio XE 2015 comes in different versions: IA-32/Intel® 64 debugger: Debug applications natively on IA-32 or Intel® 64 systems with gdb-ia on the command line. A standard Eclipse* IDE can be used for this as well if a graphical user interface is desired. Intel® Xeon Phi™ coprocessor debugger: Debug applications remotely on Intel® Xeon Phi™ coprocessor systems.
The link between the two debuggers will be kept alive. The Intel® MIC Architecture-side debugger will stay connected to the debug agent and the application will remain loaded in the CPU-side debugger, including all breakpoints that have been set. At this point, both debugger windows can safely be closed. 4.4.3 Intel® MIC Architecture-side debugger asserts on setting source directories Setting source directories in the GNU* GDB might lead to an assertion.
5.1.1 Integration notes If you already have the proper versions of Eclipse, CDT and a functional JRE installed and configured in your environment, then you can add the Intel C++ Eclipse Product Extension to your Eclipse Platform, as described in the section, below, entitled How to Install the Intel C++ Eclipse Product Extension in Your Eclipse Platform.
5.3 How to Obtain and Install Eclipse, CDT and a JRE Eclipse is a Java application and therefore requires a Java Runtime Environment (JRE) to execute. The choice of a JRE is dependent on your operating environment (machine architecture, operating system, etc.) and there are many JRE's available to choose from. A package containing both Eclipse 4.3 and CDT 8.2 is available from: http://www.eclipse.org/downloads/ Scroll down to find “Eclipse IDE for C/C++ Developers”.
also occur if the software is installed from the root account at the system level, but executed by less privileged user accounts. The cause for this failure is that a more granular level of security has been implemented on Fedora, but this new security capability can adversely affect access to system resources, such as dynamic libraries. This new SELinux security capability may require adjustment by your system administrator in order for the compiler installation to work for regular users. 5.
7.1 Changes in This Version 7.1.1 What’s New in Intel MKL 11.2 Intel MKL now provides optimizations for all Intel® Atom™ processors that support Intel® Streaming SIMD Extensions 4.1 (Intel® SSE4.1) and Intel® Streaming SIMD Extensions 4.2 (Intel® SSE4.
o Improved performance of Level 3 BLAS functions for 64-bit processors supporting Intel AVX2 o Improved ?GEMM performance on small matrices for all processors when MKL_DIRECT_CALL or MKL_DIRECT_CALL_SEQ is defined during compilation (see the Intel® Math Kernel Library User’s Guide for more details ) o Improved performance of DGER and DGEMM for the beta=1, k=1 case for 64-bit processors supporting Intel SSE4.
o Enabled Automatic Offload in P?GEMM routines for large distribution blocking factors Sparse BLAS: o Optimized SpMV kernels for Intel AVX-512 instruction set o Added release example for diagonal format use in Sparse BLAS o Improved Sparse BLAS level 2 and 3 performance for systems supporting Intel SSE4.
Introduced an Intel MKL mode that ignores all settings specified by Intel MKL environment variables o User can set up the mode by calling mkl_set_env_mode() routine which directs Intel MKL to ignore all environment settings specific to Intel MKL so that all Intel MKL related environment variables such as MKL_NUM_THREADS, MKL_DYNAMIC, MKL_MIC_ENABLE and others are ignored; users can instead set needed parameters via Intel MKL service routines such as mkl_set_num_threads() and mkl_mic_enable() Note: API s
8 Intel® Threading Building Blocks For information on changes to Intel® Threading Building Blocks, please read the file CHANGES in the TBB documentation directory found in /composer_xe_2015.x.xxx/Documentation//tbb. 9 Disclaimer and Legal Information INFORMATION IN THIS DOCUMENT IS PROVIDED IN CONNECTION WITH INTEL(R) PRODUCTS. NO LICENSE, EXPRESS OR IMPLIED, BY ESTOPPEL OR OTHERWISE, TO ANY INTELLECTUAL PROPERTY RIGHTS IS GRANTED BY THIS DOCUMENT.
The GNU* Project Debugger, GDB is provided under the General GNU Public License GPL V3. Please consult the licenses included in the distribution for details. Celeron, Centrino, Intel, Intel logo, Intel386, Intel486, Atom, Core, Itanium, MMX, Pentium, VTune, Cilk, Xeon Phi, and Xeon are trademarks of Intel Corporation in the U.S. and other countries. * Other names and brands may be claimed as the property of others. Copyright © 2014 Intel Corporation. All Rights Reserved.