Intel® Advisor Help

report

Generate a report from data collected during a previous analysis.

GUI Equivalent

Microsoft Visual Studio* IDE:Tools > Intel Advisor 201n > select <report_type>

Intel Advisor standalone GUI: View > select <report_type>

Syntax

-report=<string> [-action-option] [-global-option] [--] <target> [<target options>]

Arguments

<string> is the list of available reports:

survey

shows results of the survey analysis

annotations

lists the annotations in the sources

custom

enables using custom report

dependencies

shows possible dependencies

hotspots

shows hotspots

joined

combined report for several analyses

map

reports memory access patterns

roofs

shows memory and compute roof values

suitability

shows possible performance gains from threading parallelism

summary

shows the collection summary

threads

shows the list of threads

top-down

shows the report in a top-down view

tripcounts

shows survey report with tripcounts data added

Default

None. You must specify an argument.

Modifiers

Action Options Description
-bottom-up (default) | -no-bottom-up

Use bottom-up mode for survey report.

-csv-delimiter=<string>

Identify a delimiter string for the CSV report output format ("comma", "semicolon" and "tab" specify the respective characters). Defaults to "comma". Used with --report.

-display-callstack

Display the call stacks for each function call.

-dynamic (default) | -no-dynamic

Select dynamic or static instruction mix to show.

-enable-task-chunking=<string>

Remove specified loops from the lis of selection. Specify the sites where task chunking will be enabled when evaluating suitability data. Sites must be specified in a comma-separated list (no spaces). This option can only be used with -report suitability.

-filter=<string>

Select specified loops only. Filter data by specified column name and value. Only survey report is supported so far.

-format=text | csv | xml

Specify output format for report.

-limit=<unsigned integer>

Specify the number of items to print. Can be used with -report.

-mix | -no-mix (default) Show instruction mix columns in survey report.
-mpi-rank=<integer>

Specify the MPI rank of the result to be imported. This option is generally used when the data collections are on a shared partition.

-option-file=<string>

Specify the PATH/name of an option file. Can be used to avoid typing many options.

-project-dir=<string>

Designate the project directory. This is the top-level directory where the data collections will be saved.

-recalculate-time (default) | -no-recalculate-time

Enable self and total times recalculation after filtering.

-reduce-lock-contention=<string>

Specify the sites where lock contention will be reduced when evaluating suitability data. Sites must be specified in a comma-separated list (no spaces). This option can only be used with -report suitability.

-reduce-lock-overhead=<string>

Specify the sites where lock overhead will be reduced when evaluating suitability data. Sites must be specified in a comma-separated list (no spaces). This option can only be used with -report suitability.

-reduce-site-overhead=<string>

Specify the sites where site overhead will be reduced when evaluating suitability data. Sites must be specified in a comma-separated list (no spaces). This option can only be used with -report suitability.

-reduce-task-overhead=<string>

Specify the sites where task overhead will be reduced when evaluating suitability data. Sites must be specified in a comma-separated list (no spaces). This option can only be used with -report suitability.

-refinalize-survey | -no-refinalize-survey (default)

Refinalize survey result collected with a previous Advisor version.

-report-output=<string>

Specify the PATH/name of an output file. Can be used with -report.

-report-template=<string>

Specify the PATH/name of a custom report template file. Can be used with -report custom.

-search-dir=<string> <all | bin | src | sym[:<p | r>]>=<directory>.

<directory> is the name of the search directory for binaries (bin), sources (src), symbols (sym), or all these file types (all). Use ':r' to perform a recursive search of all subdirectories. Use ':p' to indicate highest priority search directories (directories that should be searched prior to others, including environment paths and absolute paths). You can use these options together as ':rp'.

-show-all-columns | -no-show-all-columns (default)

Prints all available columns in survey report.

-show-all-rows (default) | -no-show-all-rows

Prints all available rows in survey report. Use it to print child rows.

-show-functions | -no-show-functions (default)

Show functions in bottom-up mode.

-show-loops (default) | -no-show-loops

Show loops in bottom-up mode.

-show-not-executed | -no-show-not-executed (default)

Show not executed and fully unrolled loops in survey report.

-s, -sort-asc=<string>

Sort data in ascending order by the specified column name. Only survey report is supported so far.

-S, -sort-desc=<string>

Sort data in descending order by the specified column name. Only survey report is supported so far.

-target-system=cpu | xeon-phi | offload-to-xeon-phi

Specify the target system to use when evaluating suitability data. This option can only be used with -report suitability.

-threading-model=tbb | cilk | openmp | tpl | other

Specify the threading model to use when evaluating suitability data. This option can only be used with -report suitability.

-top-down

Display report in top-down mode

Global Options Description
-q, -quiet

Suppress non-essential messages

-v, -verbose

Print additional information

Description

Use this action to generate the specified type of report from the result data of a previous analysis. The analysis type used during the collect action determines which report types you can specify. Suitability reports are the most configurable, allowing you to set the threading model, number of processors, and other options.

By default, a report is written to standard output in text format, but the advixe-cl tool provides a number of options you can use when generating a report.

Example

1) Generate the 'survey' report:

advixe-cl --report suitability --project-dir ./advi --search-dir src:r=./src --format=text --report-output ./out/suitability.txt

2) Generate the 'dependencies' report for data collected on rank 3 of MPI cluster:

advixe-cl --report dependencies --project-dir ./advi --mpi-rank=3 --search-dir src:r=./src

See Also