On XSEDE digital services, how are compute jobs charged?
Computational services on the Extreme Science and Engineering Discovery Environment (XSEDE) are allocated and charged in service units (SUs). SUs are defined locally on each system, with conversion factors among systems based on High-Performance LINPACK (HPL) benchmark results.
To calculate the conversion of SUs from one XSEDE digital service to the equivalent amount of SUs on another, use the XSEDE SU Converter.
XSEDE compute resources have complex multi-core and memory hierarchies. Each digital service has a specific configuration that determines how many cores can be dedicated to a job without impeding the code (and other user and system codes). Each service provider defines for its system the minimum number of SUs charged for a job running in the default batch queue (calculated by multiplying the job's wall time by the number of cores it used). The actual charge will depend on the specific requirements of your job (e.g., the mapping of the cores across the machine, or the priority you wish to obtain).