Compilers and libraries

The Cray Programming Environment

The Cray Programming Environment (CPE) provides consistent interface to multiple compilers and libraries. On Dardel you can load the cpe module to enable a specific version of the CPE. For example

module load cpe/21.11

The cpe module will make sure that the corresponding versions of several other Cray libraries are loaded, such as cray-libsci and cray-mpich. You can check the details by module show cpe/21.11.

In addition to the cpe module, there are also the PrgEnv- modules that provide compilers for different programming environment

  • PrgEnv-cray: loads the Cray compiling environment (CCE) that provides compilers for Cray systems.

  • PrgEnv-gnu: loads the GNU compiler suite.

  • PrgEnv-aocc: loads the AMD AOCC compilers.

By default the PrgEnv-cray is loaded upon login. You can switch to different compilers using module swap:

module swap PrgEnv-cray PrgEnv-gnu
module swap PrgEnv-gnu PrgEnv-aocc

Compiler wrappers

After loading the cpe and the PrgEnv- modules, you can now build your parallel applications using compiler wrappers for C, C++ and Fortran:

cc -o myexe.x mycode.c      # cc is the wrapper for C compiler
CC -o myexe.x mycode.cpp    # CC is the wrapper for C++ compiler
ftn -o myexe.x mycode.f90   # ftn is the wrapper for Fortran compiler

The compiler wrappers will choose the required compiler version, target architecture options, and will automatically link to the scientific libraries, as well as the MPI and OpenSHMEM libraries. No additional MPI flags are needed as these are included by compiler wrappers, and there is no need to add any -I, -l or -L flags for the Cray provided libraries. For libraries and include files covered by module files, you need not add anything to your Makefile. If a Makefile needs an input for -L to work correctly, try using “.”.

For code development, testing, and performance analysis, it is good practice to build code with two different tool chains. On Dardel a starting point is to use the PrgEnv-cray and the PrgEnv-gnu environments.

Cray scientific and math libraries

The Cray scientific and math libraries (CSML) provide the cray-libsci and cray-fftw modules that are designed to provide optimial performance from Cray systems.

  • cray-libsci: provides BLAS, LAPACK, ScaLAPACK, etc.

  • cray-fftw: provides fastest fourier transform.

The cray-libsci module supports OpenMP and the number of threads can be controlled by the OMP_NUM_THREADS environment variable.

The cray-libsci module is loaded upon login, and its version can be changed by the cpe module. The cray-fftw module needs to be loaded by user.

Cray message passing toolkit

The Cray message passing toolkit (CMPT) provides the cray-mpich module, which is based on ANL MPICH and has been optimized for Cray programming environment.

The cray-mpich module is loaded upon login, and its version can be changed by the cpe module. Once cray-mpich is loaded the compiler wrapper will automatically include MPI headers and link to MPI libraries.

If you would like to use SHMEM you can check the availability of the cray-openshmemx module by “module avail cray-openshmemx”.

Compiler and linker flags

Verbose printing of the flags and settings that are active when using the compiler wrappers


A suggested starting point for code optimization on AMD EPYC Zen 2 processors are

  • for the Cray compilers

# C/C++ flags
-Ofast              # Aggresive optimization
-flto               # link time optimization
-ffp=3              # optimization of floating-point math operations. Supported values are 0, 1, 2, 3, and 4.
-fcray-mallopt      # use Cray's mallopt parameters, can improve performance
-fno-cray-mallopt   # no use of Cray's mallopt parameters, can reduce memory usage
-fopenmp            # enable OpenMP

# Fortran flags
-02                 # default optimization
-O3                 # aggresive optimization
-O ipaN             # level of inline expansion N=0-5, default N=3
-hlist=a            # write optimization info to listing file
-hlist=a            # create source listing with loopmark information
-homp               # enable OpenMP
-hthread            # level of optimization of OpenMP directive, N=0-3, default N=2
  • for the GCC compilers

# General flags

# C/C++, Fortran flags
-O3                 # aggresive optimization
-march=znver2       # name of the target architecture
-mtune=znver2       # name of the target processor for which code performance will be tuned
-mfma               # enable fma instructions
-mavx2              # enable avx2 instructions
-m3dnow             # enable 3dnow instructions
-fomit-frame-pointer  # omit the frame pointer in functions that do not need one
-fopenmp            # enable OpenMP

# Fortran flags
-std=legacy         # specify legacy Fortran standard
-fallow-argument-mismatch  # allow for mismatches between calls and procedure definitions
  • for the AOCC compilers

# C/C++/Fortran flags
-02                 # default optimization
-O3                 # aggresive optimization
-O ipaN             # level of inline expansion N=0-5, default N=3
-flto               # link time optimization
-funroll-loops      # loop unrolling
-unroll-aggressive  # advance loop optimization
-fopenmp            # enable OpenMP

# Fortran flags
-ffree-form         # support for free form Fortran

Build examples

Example 1: Build an MPI parallelized Fortran code within the PrgEnv-cray environment

In this example we build and test run a Hello World code hello_world_mpi.f90.

program hello_world_mpi
include "mpif.h"
integer myrank,size,ierr
call MPI_Init(ierr)
call MPI_Comm_rank(MPI_COMM_WORLD,myrank,ierr)
call MPI_Comm_size(MPI_COMM_WORLD,size,ierr)
write(*,*) "Processor ",myrank," of ",size,": Hello World!"
call MPI_Finalize(ierr)
end program

The build is done within the PrgEnv-cray environment using the Cray Fortran compiler, and the testing is done on a Dardel CPU node reserved for interactive use.

# Check which compiler the compiler wrapper is pointing to
ftn --version
# returns Cray Fortran : Version 13.0.0

# Compile the code
ftn hello_world_mpi.f90 -o hello_world_mpi.x

# Test the code in interactive session.
# First queue to get one node reserved for 10 minutes
salloc -N 1 -t 0:10:00 -A <project name> -p main
# wait for the node. Then run the program using 128 MPI ranks with
srun -n 128 ./hello_world_mpi.x
# with program output to standard out
# ...
# Processor  123  of  128 : Hello World
# ...
# Processor  47  of  128 : Hello World
# ...

Having here used the ftn compiler wrapper, the linking to the cray-mpich library was done without the need to specify linking flags. As is expected for this code, in runtime each MPI rank is writing its Hello World to standard output without any synchronization with the other ranks.

Example 2: Build a C code with PrgEnv-gnu. The code requires linking to a Fourier transform library.

# Download a C program that illustrates use of the FFTW library
mkdir fftw_test
cd fftw_test

# Change from the PrgEnv-cray to the PrgEnv-gnu environment
ml PDC/21.11
ml cpeGNU/21.11
# Lmod is automatically replacing "cce/13.0.0" with "gcc/11.2.0".
# Lmod is automatically replacing "PrgEnv-cray/8.2.0" with "cpeGNU/21.11".
# Due to MODULEPATH changes, the following have been reloaded:
  1) cray-mpich/8.1.11

# Check which compiler the cc compiler wrapper is pointing to
cc --version
# gcc (GCC) 11.2.0 20210728 (Cray Inc.)

ml avail
# The listing reveals that cray-libsci/ is already loaded.

# In addition, the program needs linking also to a Fourier transform library.
ml spider fftw
# gives a listing of available Fourier transform libraries.
# Load a recent version of the Cray-FFTW library with
module add cray-fftw/

# Build the code with
cc fftw_test.c -o fftw_test.x

# Test the code in interactive session.
# First queue to get one reserved core for 10 minutes
salloc -n 1 -t 0:10:00 -A <project name> -p shared
# wait for the core. Then run the program with
srun -n 1 ./fftw_test.x

Having loaded the cray-fftw module, no additional linking flag(s) was needed for the cc compiler wrapper.

Example 3: Build a program with the EasyBuild cpeGNU/21.09 toolchain

# Load an EasyBuild-user module
ml PDC/21.11
ml EasyBuild-user/4.5.0

# Look for a recipe for the Libxc library
eb -S Libxc
# Returns a list of available EasyBuild easyconfig files.
# Choose an easyconfig file for the cpeGNU/21.11 toolchain.

# Make a dry-run
eb libxc-5.1.6-cpeGNU-21.11.eb --robot --dry-run

# Check if dry-run looks reasonable. Then proceed to build with
eb libxc-5.1.6-cpeGNU-21.11.eb --robot

# The program is now locally installed in the user's
# ~/.local/easybuild directory and can be loaded with
ml PDC/21.11
ml EasyBuild-user/4.5.0
ml libxc/5.1.6-cpeGNU-21.11


HPE Cray user manuals and reference information

The Cray programming environment (CPE)

HPE Cray Programming Environment User Guide

HPE Cray reference information

HPE Cray Clang C and C++ Quick Reference (13.0) (S-2179)

HPE Cray Fortran Reference Manual (13.0) (S-3901)

HPE Performance Analysis Tools User Guide

References on AMD processors

AMD Optimizing C/C++ and Fortran Compilers (AOCC)

Using MKL efficiently

Best practice Guide AMD EPYC

AMD EPYC product line

AMD EPYC wiki page