diff --git a/theory/paper_pasc/pasc_paper.tex b/theory/paper_pasc/pasc_paper.tex index 3a861d4482c6fa19a5f392e7a20b3c37d0d8483b..99087f3591383abfe468cbd3905ed9b46bb422ab 100644 --- a/theory/paper_pasc/pasc_paper.tex +++ b/theory/paper_pasc/pasc_paper.tex @@ -543,6 +543,11 @@ E5-2670\footnote{\url{http://ark.intel.com/products/64595/Intel-Xeon-Processor-E clocked at $2.6~\rm{GHz}$ with each $128~\rm{GByte}$ of RAM. The nodes are connected using a Mellanox FDR10 Infiniband 2:1 blocking configuration. +This system is similar to many Tier-2 systems available in most universities or +computing facilities. Demonstrating strong scaling on such a machine is +essential to show that the code can be efficiently used even on commodity +hardware available to most researchers in the field. + The code was compiled with the Intel compiler version \textsc{2016.0.1} and linked to the Intel MPI library version \textsc{5.1.2.150} and metis library version \textsc{5.1.0}. @@ -573,8 +578,8 @@ of 16 MPI ranks. \caption{Strong scaling test on the Cosma-5 machine (see text for hardware description). \textit{Left panel:} Code Speed-up. \textit{Right panel:} Corresponding parallel efficiency. Using 16 threads per node (no use of - hyper-threading) with one MPI rank per node, a good parallel efficiency is - achieved when increasing the thread count from 1 (1 node) to 128 (8 nodes) + hyper-threading) with one MPI rank per node, a good parallel efficiency (60\%) + is achieved when increasing the thread count from 1 (1 node) to 128 (8 nodes) even on this relatively small test case. The dashed line indicates the efficiency when running on one single node but using all the physical and virtual cores (hyper-threading). As these CPUs only have one FPU per core, we @@ -596,6 +601,10 @@ at $2.7~\rm{GHz}$ with each $32~\rm{GByte}$ of RAM. The nodes are split in 18 Infiniband FDR10 non-blocking Tree. Islands are then connected using a 4:1 Pruned Tree. +This system is similar in nature to the cosma-5 system used in the previous set +of tests but is much larger, allowing us to demonstrate the scalibility of our +framework on the largest systems. + The code was compiled with the Intel compiler version \textsc{2015.5.223} and linked to the Intel MPI library version \textsc{5.1.2.150} and metis library version \textsc{5.0.2}. @@ -629,6 +638,10 @@ each $16~\rm{GByte}$ of RAM. Of notable interest is the presence of two floating units per compute core. The system is composed of 28 racks containing each 1,024 nodes. The network uses a 5D torus to link all the racks. +This system is larger than SuperMUC used above and uses a completely different +architecture. We use it here to demonstrate that our results are not dependant +on the hardware being used. + The code was compiled with the IBM XL compiler version \textsc{30.73.0.13} and linked to the corresponding MPI library and metis library version \textsc{4.0.2}.