Cluster Prediction

Clustering of regions enables the usage of Inter-Phase Dynamism. In contrast to the traditional Intra-Phase Dynamism approach, where a region experiences a static behavior over time, Inter-Phase Dynamism says that the behavior of a region changes over time. Cluster prediction uses hardware performance counters to predict the behavior of the next instance of a region and enables READEX to tune it accordingly. More information can be found here



The build procedure for the Cluster Prediction library requires the following tools to be already installed:
  • READEX Runtime Library (RRL) as described [here].
  • Intel compiler version 2017.2.174/2018.1.163 or GCC (G++ and GFortran) version 6.3.0/7.1.0. Other Intel or GCC compiler versions can also be used, but have not been explicitly tested by the READEX developers.
  • CMake version 3.11 or higher.
  • PAPI version 5.5.1 or higher.
Please make sure that the RRL version is also compiled with the same compiler as the one used for the Cluster Prediction library.


Please download Cluster Prediction library from the following location and unpack it:

wget -c
tar -xzvf Cluster_Prediction.tar.gz

Preparing the Cluster Prediction library directory

Please prepare the Score-P build directory as follows:

cd Cluster_Prediction
mkdir build
cd build

Configuring and installing the Cluster Prediction library

You may use the following naming scheme for “-DCMAKE_INSTALL_PREFIX”:

<Desired path for Cluster Prediction library installation>/cluster_prediction/cluster_prediction_readex_<version number>_<mpi version>_<compiler version>
<version number>: for example, 11271
<mpi version>: for example, intelmpi2017.2.174
<compiler version>: for example, intel2017.2.174

To build the Cluster Prediction library please now do:

cmake ../ configure --prefix=<Desired path for Cluster Prediction library installation>/cluster_prediction/cluster_prediction_readex_<version number>_<mpi version>_<compiler_version>
make -j
make install


[Download tarball]

[1] M. Kumaraswamy, A. Chowdhury, M. Gerndt, Z. Bendifallah, O. Bouizi, U. Locans, L. Řı́ha, O. Vysocký, M. Beseda, J. Zapletal, “Domain Knowledge Specification for Energy Tuning”, 2nd Concurrency and Computation: Practice and Experience Journal, special issue, 6 July 2018.
doi: 10.1002/cpe.4650