We further analyse the workload of the compute cores by highlighting a set of cases, summarised in Table \ref{table:cases}. We will focus case (\circlenumber{A}), which creates the highest number of beams, as well as on CPU-bound cases useful for performing surveys, with either 24 stations (\circlenumber{B}) or 64 stations (\circlenumber{C}) as input. Cases \circlenumber{D} and \circlenumber{E}focus on high-resolution observations of known sources, and are I/O bound configurations with 24 and 64 stations, respectively. Case \circlenumber{F} focusses on the observations of known sources as well, using Stokes I output, which allows more beams to be created. Channel-level dedispersion is applied for all cases that observe known sources.
We further analyse the workload of the compute cores by highlighting a set of cases, summarised in Table \ref{table:cases}. We will focus on case \circlenumber{A}, which creates the highest number of beams, and on CPU-bound cases useful for performing surveys, with either 24 stations (\circlenumber{B}) or 64 stations (\circlenumber{C}) as input. Cases \circlenumber{D} and \circlenumber{E}represent high-resolution observations of known sources, and are I/O bound configurations with 24 and 64 stations, respectively. Case \circlenumber{F} focusses on the observations of known sources as well, using Stokes I output, which allows more beams to be created. Channel-level dedispersion is applied for all cases that observe known sources.
The average workload of the compute cores for each case is shown in Figure \ref{fig:execution-times}. For the CPU-bound cases \circlenumber{B} and \circlenumber{C}, the average load has to be lower than 100\% to recover from small delays in the processing, that can occur since the BG/P is not a real-time system. These fluctuations typically occur due to clashes within the BG/P torus network which is used for both all-to-all-exchanges, and cannot be avoided in all cases.
The average workload of the compute cores for each case is shown in Figure \ref{fig:execution-times}. For the CPU-bound cases \circlenumber{B} and \circlenumber{C}, the average load has to be lower than 100\% to recover from small delays in the processing, that can occur since the BG/P is not a real-time system. These fluctuations typically occur due to clashes within the BG/P torus network which is used for both all-to-all-exchanges, and cannot be avoided in all cases.
