1square(1) Scalasca Trace Tools square(1)
2
6 square - Scalasca analysis report explorer
7
9 square [OPTIONS] (EXPERIMENT_DIR | CUBE_FILE)
10
12 square, the Scalasca analysis report explorer, facilitates post-
13 processing, scoring, and interactive examination of analysis reports
14 from both runtime summarization and tracing experiments.
15 When provided with a Score-P experiment directory EXPERIMENT_DIR,
17 square post-processes intermediate analysis reports produced by a
18 measurement and/or an automatic trace analysis to derive additional
19 metrics and construct a hierarchy of measured and derived metrics, and
20 then presents this final report using the Cube GUI (unless the -s
21 option is used). If intermediate reports were already processed, the
22 final report is shown immediately. If there is more than one analysis
23 report in a Score-P experiment directory, the most comprehensive report
24 is shown by default.
25 When provided with the name of a specific analysis report CUBE_FILE,
27 post-processing is skipped and the corresponding report is shown
28 immediately.
29 Analysis report examination can only be done after measurement and
31 analysis are completed. Parallel resources are not required, and it is
32 often more convenient to examine analysis reports on a different
33 system, such as a desktop computer where interactivity is superior.
34 Depending on the measurement configuration and the provided options,
36 square places additional files into the experiment archive directory.
37 For single-run experiments, the following files are created if the
38 corresponding input files are available:
39 · summary.cubex: post-processed runtime summary result
41 · trace.cubex: post-processed trace analysis result
43 In scoring mode (-s option), square generates:
45 · scorep.score: detailed measurement score report, optionally suffixed
47 with the name of a provided filter file (-f option)
48 In multi-run mode, aggregated reports are created if the corresponding
50 input files are available:
51 · profile_aggr.cubex: aggregated runtime summary result
53 · scout_aggr.cubex: aggregated trace analysis result
55 · scout+profile.cubex: merged runtime summary and trace analysis result
57 · summary_aggr.cubex: post-processed aggregated runtime summary result
59 · trace_aggr.cubex: post-processed aggregated trace analysis result
61 · trace+summary.cubex: post-processed merged runtime summary and trace
63 result
64
66 Common options
67 -c LEVEL
68 Level of sanity checks for newly created reports (default: 'none').
69 'quick' performs various sanity checks on the experiment meta data,
70 while 'full' also executes a more time-consuming check for negative
71 metric values (which usually indicate a serious error).
72 -F Force post-processing of analysis reports, even if a post-processed
74 report already exists.
75 -f filter_file
77 Apply the specified filter file when generating a score report.
78 -s Output a textual score report. Skips launching the Cube GUI.
80 -v Enable verbose mode.
82 -n Suppress the calculation of 'Idle Threads' metric.
84 Options for multi-run experiments
86 -S MODE
87 Set aggregation mode for runtime summarization results of each
88 configuration. Currently supported modes are 'mean' and 'merge'
89 (default).
90 -T MODE
92 Set aggregation mode for trace analysis results of each
93 configuration. Currently supported modes are 'mean' and 'merge'
94 (default).
95 -A Force post-processing of every individual step report of a multi-
97 run experiment.
98 WARNING: Depending on the number and size of the individual
99 measurement reports, the time required to post-process all reports
100 can be significant!
101
103 For multi-run experiments, square provides additional options to
104 aggregate the set of measurement results into a single Cube file. The
105 user can choose between the two aggregation methods 'merge' and 'mean'
106 to combine results from different configurations, which underneath use
107 the corresponding CubeLib command-line tools. The default aggregation
108 mode is to 'merge' results.
109 Note:
111 The 'merge' operation always copies metric data from the last
112 measurement configuration in a given set in which data for a
113 particular metric is available. This should be taken into account
114 when setting up a multi-run experiment that is supposed to be
115 aggregated using the square command later on. In particular, it is
116 recommended to include a low-overhead measurement without hardware
117 performance counters at the end of a measurement configuration set
118 including hardware counter measurements in order to provide more
119 accurate time information.
120 The aggregation of multi-run measurement results happens in the
122 following order:
123 1. Aggregate results from multiple runs for each measurement
125 configuration. At this point, the only supported mode for this
126 aggregation is 'mean', which is therefore hard-coded.
127 2. Aggregate averaged runtime summarization results from all
129 configurations in ascending order using the selected mode (-S
130 option).
131 3. Aggregate averaged trace analysis analysis results from all
133 configurations in ascending order using the selected mode (-T
134 option).
135 4. Merge the aggregated runtime summarization and trace analysis
137 results into a combined report.
138 5. Post-process the combined report (step 4) if available, otherwise
140 post-process the aggregated report(s) generated in either step 2 or
141 step 3.
142 Depending on the measurement settings, those steps will be applied if
144 the respective intermediate results are found. The reports of the
145 individual runs will only be post-processed when explicitly requested
146 (-A option).
147
149 square exits with status 0 on success, and greater than 0 if errors
150 occur.
151
153 To examine an analysis report on a different system, for example, a
154 desktop or laptop computer, it is often best to post-process the report
155 using square's scoring functionality (-s option) on the system where
156 the measurement has been taken, and then copy over the resulting post-
157 processed Cube file. This is because square requires various command-
158 line tools and support files from the Score-P, CubeLib, and Scalasca
159 Trace Tools packages, which may not be available on the target
160 computer.
161
163 Please report bugs to scalasca@fz-juelich.de. Make sure to include at
164 least the following information in your bug report:
165 · The Scalasca Trace Tools version reported by 'scalasca -V'.
167 · The Scalasca Trace Tools configuration reported by 'scalasca -c'.
169 · The Score-P version reported by 'scorep --version'.
171 · The Score-P configuration reported by 'scorep-info config-summary'.
173 · The exact command line of the failing command.
175 · The exact failure/error message.
177
179 square scorep_foo_4_trace
180 Post-process measurement reports in scorep_foo_4_trace and display the
181 most comprehensive report using the Cube GUI.
182 square -s -f filter scorep_foo_4_sum
184 Post-process measurement reports in scorep_foo_4_sum and generate a
185 score report with the run-time measurement filter rules from the file
186 filter applied.
187 square -S mean scorep_foo_4_multi-run_c2_r4
189 Aggregate and post-process the measurement results of the multi-run
190 experiment with two configurations and four runs per configuration
191 stored in scorep_foo_4_multi-run_c2_r4. Then, show the most
192 comprehensive report using the Cube GUI.
193
195 scalasca(1), scan(1)
196 The full Scalasca Trace Tools documentation is available online at
198 https://www.scalasca.org.
199Version 2.5 Fri Mar 22 2019 square(1)