Development/Intel Compiler

From bwHPC Wiki
< Development
Revision as of 12:44, 28 January 2014 by M Neuer (talk | contribs) (General compiler usage)
Jump to: navigation, search
Navigation: bwHPC BPR


1 General compiler usage

The basic operations can be performed with the same commands for all available compilers. For advanced usage such as optimization and profiling you should consult the best practice guide of the compiler you intend to use (GCC, Intel Suite). To get a list of the compilers installed on the system execute

$ module avail compiler

Both Intel and GCC have compilers for different languages which will be available after the module is loaded.

Compiler Suite Language Command
Intel Composer C icc
C++ icpc
Fortran ifort
GCC C gcc
C++ g++
Fortran gfortran

The following compiler commands work for all the compilers in the list above even though the examples will be for icc only. When ex.c is a C source code file such as

#include <stdio.h>
int main() {
    printf("Hello world\n");
    return 0;
}

it can be compiled and linked with the single command

$ icc ex.c -o ex

to produce an executable named ex. This process can be divided into two steps:

$ icc -c ex.c
$ icc ex.o -o ex

When using libraries you must sometimes specify where the include files are (option -I) and where the library files are (option -L). In addition you have to tell the compiler which library you want to use (option -l). For example after loading the module numlib/fftw you can compile code for fftw using

$ icc -c ex.c -I$FFTW_INC_DIR
$ icc ex.o -o ex -L$FFTW_LIB_DIR -lfftw3

When the program crashes or doesn't produce the expected output the compiler can help you by printing warning messages:

$ icc -Wall ex.c -o ex

If the problem can't be solved this way you can inspect what exactly your program does using a debugger. To use the debugger properly with your program you have to compile it with debug information (option -g):

$ icc -g ex.c -o ex

Although -Wall should always be set, the -g option should only be stated when you want to find bugs because it slows down the program and makes it lager.

2 Intel Suite

The Intel Composer XE Suite consists of tools to compile and debug C, C++ and Fortran programs:

icc Intel C compiler
icpc Intel C++ compiler
ifort Intel Fortran compiler
idb Intel debugger in GUI mode
idbc Intel debugger in console mode

Aside from that the suite also includes the TBB (Threading Building Blocks) and IPP (Integrated Performance Primitives) libraries.

Loading: There are different versions of the Intel compilers installed. To get a list of these installations execute the following command:

$ module avail compiler/intel

There is a default version which will be loaded when no version is explicitly specified, so the command

$ module load compiler/intel

will load the default version.

Online documentation: http://software.intel.com/en-us/articles/intel-c-composer-xe-documentation

Local documentation: For version specific documentation see the help page of the module. For example

$ module help compiler/intel

will show the information for the default version. For detailed lists of the different program options consult the particular man page:

$ man icc
$ man icpc
$ man ifort
$ man idb

Optimizations: You can turn on various optimization options to enhance the performance of your program. Which options are the best depends on the specific program and can be determined by benchmarking your code. A command which gives good performance and a decent file size is

$ icc -xHost -O2 ex.c

There are more aggressive optimization flags but the compiled programs can get quite large and the compilation process will probably take much longer. Moreover it can happen that the so compiled program is even slower. Such a command would be for example

$ icc -fast ex.c

A tutorial on optimization can be found at http://download-software.intel.com/sites/default/files/article/301481/compiler-essentials.1.pdf and to get the different optimization options execute

$ icc -help opt
$ icc -help advanced

Profiling: If you want to profile your program using gprof you have to compile your code with the profile flag:

$ icc -p ex.c -o ex

3 GCC

The GNU Compiler Collection (GCC) consists of tools to compile and debug C, C++ and Fortran programs:

gcc GNU C compiler
g++ GNU C++ compiler
gfortran GNU Fortran compiler
gdb GNU debugger

Loading: There is a version of GCC available on the system without loading a module but it may be outdated and it is recommended to load the GNU compiler module. To get a list of all the different versions installed on the system execute the following command:

$ module avail compiler/gnu

There is a default version which will be loaded when no version is explicitly specified, so the command

$ module load compiler/gnu

will load the default version.

Online documentation: http://gcc.gnu.org/onlinedocs/

Local documentation: For version specific documentation see the help page of the module. For example

$ module help compiler/gnu

will show the information for the default version. For detailed lists of the different program options consult the particular man page:

$ man gcc
$ man g++
$ man gfortran
$ man gdb

Optimizations: You can turn on various optimization options to enhance the performance of your program. Which options are the best depends on the specific program and can be determined by benchmarking your code. A command which gives good performance and a decent file size is

$ gcc -march=native -O2 ex.c -o ex

There are more aggressive optimization flags but the compiled programs can get quite large and the compilation process will probably take much longer. Moreover it can happen that the so compiled program is even slower. Such a command would be for example

$ gcc -march=native -O3 ex.c -o ex

For a complete list of all the optimization options execute

$ gcc --help=optimizers

Profiling: If you want to profile your program using gprof you have to compile your code with the profile flag:

$ gcc -pg ex.c -o ex