| 1 | \section{CPU Requirements}
|
|---|
| 2 |
|
|---|
| 3 | We tested the speed of the extractors by running them on an Intel\ Pentium\ IV,
|
|---|
| 4 | 2.4\,GHz~CPU machine at IFAE and measured
|
|---|
| 5 | the number of executed events per seconds. This was done using the CPU-time measure features which incorporates each task in MARS.
|
|---|
| 6 | \par
|
|---|
| 7 | The results could easily differ by about 20\% from one try to another (using the
|
|---|
| 8 | same extractor), but in general,
|
|---|
| 9 | the differences between the extractors are much bigger than the intrinsic fluctuation.
|
|---|
| 10 | Table~\ref{tab:cpu} shows the obtained results. The numbers in this list have to be compared to the
|
|---|
| 11 | I/O speed of about 400~evts/sec. of the {\textit{\bf MRead}}-task which performs the reading
|
|---|
| 12 | (and de-compression) of the merpped root-files in MARS. Thus, for time being, every extractor being faster
|
|---|
| 13 | than this reference number does not limit the total event reconstruction speed. Only the integrating spline
|
|---|
| 14 | extractors lie below this limit and would need to be optimized further.
|
|---|
| 15 |
|
|---|
| 16 | \begin{table}[htp]
|
|---|
| 17 | \centering
|
|---|
| 18 | \begin{tabular}{|c|c|c|c|}
|
|---|
| 19 | \hline
|
|---|
| 20 | \hline
|
|---|
| 21 | \multicolumn{4}{|c|}{\large Measured Extraction Speed} \rule{0mm}{6mm} \rule[-2mm]{0mm}{6mm} \hspace{-3mm}\\
|
|---|
| 22 | \hline
|
|---|
| 23 | \hline
|
|---|
| 24 | Nr. & Name & Events/sec. & comments\\
|
|---|
| 25 | & & (CPU) & \\
|
|---|
| 26 | \hline
|
|---|
| 27 | \hline
|
|---|
| 28 | 1 & Fixed Win. (4,4) & 3500--4500 & no time \\
|
|---|
| 29 | 2 & Fixed Win. (4,6) & 3500--4500 & no time \\
|
|---|
| 30 | 3 & Fixed Win. (6.6) & 3200--4000 & no time \\
|
|---|
| 31 | 4 & Fixed Win. (8,8) & 3200--4000 & no time \\
|
|---|
| 32 | 5 & Fixed W. (14,10) & 2700--3300 & no time \\
|
|---|
| 33 | \hline
|
|---|
| 34 | 6 & Fix. Win. Spline (4,4) & 1700--2200 & no time \\
|
|---|
| 35 | 7 & Fix. Win. Spline (4,6) & 1700--2200 & no time \\
|
|---|
| 36 | 8 & Fix. Win. Spline (6.6) & 1700--2100 & no time \\
|
|---|
| 37 | 9 & Fix. Win. Spline (8,8) & 1300--1800 & no time \\
|
|---|
| 38 | 10 & Fix. Win. Spl. (14,10) & 600--1200 & no time \\
|
|---|
| 39 | \hline
|
|---|
| 40 | 11 & Fix. Win. Peak S. (2,2) & 2300--2900 & no time \\
|
|---|
| 41 | 12 & Fix. Win. Peak S. (4,4) & 2300--2900 & no time \\
|
|---|
| 42 | 13 & Fix. Win. Peak S. (4.6) & 2300--2900 & no time \\
|
|---|
| 43 | 14 & Fix. Win. Peak S. (6,6) & 2300--2900 & no time \\
|
|---|
| 44 | 15 & Fix. Win. Peak S. (8,8) & 2200--2800 & no time \\
|
|---|
| 45 | 16 & Fix. Win. Pk S. (14,10) & 2000--2500 & no time \\
|
|---|
| 46 | \hline
|
|---|
| 47 | 17 & Slid. Win. (2,2) & 400--700 & \\
|
|---|
| 48 | 18 & Slid. Win. (4,4) & 500--800 & \\
|
|---|
| 49 | 19 & Slid. Win. (4.6) & 500--800 & \\
|
|---|
| 50 | 20 & Slid. Win. (6,6) & 1000--1300 & \\
|
|---|
| 51 | 21 & Slid. Win. (8,8) & 1100--1400 & \\
|
|---|
| 52 | 22 & Slid. W. (14,10) & 1000--1800 & \\
|
|---|
| 53 | \hline
|
|---|
| 54 | 23 & Spline Amplitude & 700--1000 & \\
|
|---|
| 55 | 24 & Spline Int. (1,1.5)& 300--500 & \\
|
|---|
| 56 | 25 & Spline Int. (2,3) & 200--400 & \\
|
|---|
| 57 | 26 & Spline Int. (4,6) & 150--200 & to be optimized \\
|
|---|
| 58 | 27 & Spline Int. (6,9) & 80--120 & to be optimized \\
|
|---|
| 59 | \hline
|
|---|
| 60 | 28 & Dig. Filt. (6,6) & 700--900 & \\
|
|---|
| 61 | 29 & Dig. Filt. (4,4) & 700--900 & \\
|
|---|
| 62 | 34 & Dig. Filt. Pk S. & 500--600 & \\
|
|---|
| 63 | \hline
|
|---|
| 64 | \hline
|
|---|
| 65 | \end{tabular}
|
|---|
| 66 | \caption{The extraction speed measured for every extractor.}
|
|---|
| 67 | \label{tab:cpu}
|
|---|
| 68 | \end{table}
|
|---|
| 69 |
|
|---|
