Vectorization Accuracy Levels in Command Line
For each perspective,
Intel® Advisor
has several levels of collection accuracy. Each accuracy level is a set of analyses and properties that control what data is collected and the level of collection details. The higher accuracy value you choose, the higher runtime overhead is added.In CLI, each accuracy level corresponds to a set of commands with specific options that you should run one by one to get a desired result.
The following accuracy levels are available:
Comparison / Accuracy Level | Low | Medium | High |
---|---|---|---|
Overhead | 1.1x
| 5 - 8x
| 10 - 40x
|
Goal | Get basic insights about how well your application is vectorized and how you can improve vectorization efficiency
| Get more insights about how well your application is vectorized and the number of iterations in loops/functions
| Get detailed insights about your application performance, including performance issues and detailed optimization recommendations
|
Analyses | Survey
| Survey + Characterization (Trip Counts)
| Survey + Characterization (Trip Counts, FLOP, Call Stacks) + Memory Access Patterns
|
Result | Basic Survey report
| Survey report extended with trip count data
| Extended Survey report with trip counts and floating-point and integer operations (FLOP and INTOP)
Memory Access Patters with memory traffic data and memory usage issues
|
You can generate commands for a desired accuracy level from the
Intel Advisor
GUI. See
Generate Command Lines from GUI for details.
There is a variety of techniques available to minimize data collection, result size, and execution overhead. Check
Minimize Analysis Overhead .
Consider the following command examples.
Note
: In the commands below, make sure to replace the
myApplication
with your application executable path and name
before
executing a command. If your application requires additional command line options, add them
after
the executable name.Low Accuracy
To run the
Vectorization and Code Insights
perspective with the low accuracy:
advisor --collect=survey --project-dir=./advi_results -- ./myApplication
Medium Accuracy
To run the
Vectorization and Code Insights
perspective with the medium accuracy:
- Run the Survey analysis:advisor --collect=survey --project-dir=./advi_results -- ./myApplication
- Run the Trip Counts analysis:advisor --collect=tripcounts --enable-data-transfer-analysis --project-dir=./advi_results -- ./myApplication
High Accuracy
To run the
Vectorization and Code Insights
perspective with the high accuracy:
- Run the Survey analysis:advisor --collect=survey --project-dir=./advi_results -- ./myApplication
- Run the Trip Counts and FLOP analysis:advisor --collect=tripcounts --flop --stacks --project-dir=./advi_results -- ./myApplication
- Run the Memory Access Pattern analysis for the loops that have thePossible Inefficient Memory Access Patternissue:advisor --collect=map --select=has_issue --project-dir=./advi_results -- ./myApplication
You can view the results in the
Intel Advisor
GUI or generate an interactive HTML report.