Timing in seconds for MbCO + 3830 water molecules (14026 atoms), 1000 steps 12-14 A shift on Intel Gamma (Hypercube architecture).


\begin{table}[ht]
\begin{tabular}{|r|r|r|r|r|r|r|r|r|c|} \hline
Nodes & E$_{\rm ext}^1$ & E$_{\rm int}^2$ & Wait$^3$ & Comm$^4$ & List$^5$ & Integ$^6$ &
 \multicolumn{1}{c|}{Total}   & Eff.$^7$ & Speedup   \\ \hline
1$^*$& 70239.8 & 445.7 &   0.0 &    0.0 & 3821.7 & 90.5 &74595.5 = 20.72 h &  100.0\%  & 1   \\ \hline
    2 &35119.9 & 238.9 & 230.7 &  133.3 & 1978.2 & 53.8 &37754.8 = 10.49 h &   98.8\%  & 1.98\\ \hline
    4 &17559.9 & 137.2 & 141.0 &  203.9 & 1038.3 & 29.9 & 19110.2 = 5.31 h &   97.6\%  & 3.9 \\ \hline
    8 & 8582.0 &  78.2 & 107.8 &  239.9 &  550.7 & 17.4 & 9576.0 =  2.66 h &   97.4\%  & 7.8 \\ \hline
   16 & 4277.6 &  64.1 &  54.6 &  260.1 &  280.7 & 10.5 & 4947.6 =  1.37 h &   94.2\%  & 15  \\ \hline
   32 & 2144.9 &  29.4 &  46.0 &  272.6 &  146.7 &  7.1 & 2646.7 =  0.74 h &   88.1\%  & 28  \\ \hline
   64 & 1098.7 &  20.9 &  28.9 &  291.6 &   82.5 &  7.5 & 1530.1 =  0.43 h &   76.2\%  & 49  \\ \hline
  128 &  555.6 &  16.6 &  24.9 &  287.7 &   48.1 &  5.5 &  938.4 =  0.26 h &   62.1\%  & 80  \\ \hline
\end{tabular}
\end{table}


E ext : External energy terms (electrostatics + Lenard-Jones) E int : Internal energy terms (bond, angle, dihedral) Wait : Load unbalance Comm : Communication time (Vector Distr. Global {Sum,Brdcst}) List : Nonbond list generation time Integ : Time needed to integrate equations of motion Total : Total elapsed time Eff : Efficiency = speedup divided by number of nodes Speedup: Time for N nodes divided by time for one node.

Comments