CPU / Memory Roofline Insights Perspective
- What is the maximum achievable performance with your current hardware resources?
- Does your application work optimally on current hardware resources?
- If not, what are the best candidates for optimization?
- Is memory bandwidth or compute capacity limiting performance for each optimization candidate?
- To run theCPU / Memory Roofline Insightsperspective, from theAnalysis Workflowpane:
- Choose collection accuracy level to select perspective steps and set analysis properties, depending on the desired results:
The higher accuracy value you choose, the higher runtime overhead is added to your application. TheOverheadindicator shows the overhead for the selected configuration.By default, accuracy is set toLow. For more information, see CPU Roofline Accuracy Presets.
- Low: Get the basic CPU Cache-Aware Roofline chart with self data metrics.
- Medium: Get the detailed Memory-Level Roofline chart with total data metrics and an additional memory usage report.
- Custom: Customize the perspective flow and properties.
- If you want check for loop-carried dependency, select theDependenciesanalysis. For more information about the Dependencies analysis and report, see Find Data Dependencies.
- Run the perspective: click button.While the perspective is running, you can do the following in theAnalysis Workflowtab:
- Control the perspective execution:
- Stop data collection and see the already collected data: Click the button.
- Pause data collection: Click the button.
- Cancel data collection and discard the collected data: Click the button.
- Expand an analysis with to control the analysis execution:
- Pause analysis and see the already collected data: Click the button.
- Stop analysis and start the next analysis selected: Click the button.
- Interrupt execution of all selected analyses and see the already collected data: Click the button.