Run the specified type of analysis and collect data.
Arguments
<analysis_type> Type of analysis to run.
survey | Survey the target (your executable application) and collect data about sites in the code that may benefit from parallelism. After examining parallelism candidate sites, annotate sites that deserve further investigation. Synonyms for the survey argument keyword are hotspots and top-down. |
suitability | Collect suitability data by executing annotated code to analyze the proposed parallelism opportunities and estimate where performance gains are most likely. |
correctness | Collect correctness data from annotated code. Helps to predict and eliminate data sharing problems before adding parallelism. It is generally best to use an application with debug information to collect correctness data. |
Modifiers
Action-options: data-limit,exclude-files,executable-of-interest,interval,mrte-mode,no-auto-finalize,no-follow-child,project-dir,search-dir,start-paused,target-duration-type,user-data-dir
The search-dir action-option is strongly recommended when using the collect action to collect annotation data. It is required if you want to generate annotation reports with the result.
Options for suitability reports only: reduce-lock-contention,reduce-lock-overhead,reduce-site-overhead,reduce-task-overhead
Description
Use the collect action to run the specified type of analysis. Before performing an analysis, see About Choosing and Building a Target.
It is best to perform analyses in the order described in the Workflows section.
Example
This example collects survey data to identify hotspots. The instructions -search-dir src:=./src specify a recursive search for source files in the ./src search directory. The instructions -project-dir ./advi specify that the result should be written to the ./advi project directory instead of the default working directory.
$ advixe-cl -collect survey -project-dir ./advi -search-dir src:=./src -- ./bin/myApplication