Suitability Report Layout
To Do This
Run a tool of your choice and see results in the
Select between available reports.
Upper part of the
Any annotation-related error the Suitability tool detects appears at the top of the
Suitability Reportwindow. If you see such errors, the displayed Suitability data may not be reliable. To view the source location associated with an error, click the button. To fix the error, read the displayed error message, modify your source code to fix the problem, rebuild your target executable, and run Suitability tool analysis again.
Upper-left part of the
Maximum Program Gain for All Sitesin the program. Your overall goal of adding parallelism is to increase the
Maximum Program Gain for All Sitesso the parallel program will execute as fast as possible. The measured serial execution runtime, predicted parallel runtime, and measured are displayed below
Maximum Program Gain for All Sites.
Use the upper-right row of to model performance. Choose a hardware configuration and threading model (parallel framework) values from the drop-down lists. If you select a
Intel® Xeon Phi™processors, an additional value for total
Below this row is a grid of data that shows the estimated performance of each parallel site detected during program execution. The
Site Labelshows the argument to the site annotation. Examine the predicted
Impact to Program Gain(higher values are better) to estimate how much each site contributes to the
Maximum Program Gain for All Sitesfor all sites (described above). To expand the data under
Combined Site Metricsor
Site Instance Metrics, click the icon to the right of that heading; to collapse data, click to the right of that heading.
To view the source associated with a site in the
Suitability Sourcewindow, double-click its name (or right-click and select View Source from the context menu). To edit the source in your code editor, use the
Edit Sourcecontext menu item.
Middle-left above the graph
If you choose a
CPU, to view detailed characteristics of the selected site as well as its tasks and locks, click the
Graph in the lower-left
Scalability of Maximum Site Gaingraph summarizes performance for the selected site. The number of CPU processors or total number of coprocessor threads appears on the horizontal X axis and the target's predicted performance gain appears on the Y axis. To change the default
CPU Countand the
Maximum CPU Count, set the Options value.
If you select a
Intel Xeon Phior
Offload to Intel Xeon Phicoprocessor (and select the column
Offload to Intel Xeon Phi), the graph's appearance changes to a gray-green color and the X axis displays
Coprocessor Threadsinstead of
CPU Count. This graph represents the predicted performance of the many-core
Intel® Xeon Phi™parallel coprocessor. For many applications, the number of task instances does not scale enough to fully utilize the many cores of the parallel coprocessor, as indicated by a hover tip. Applications that are not appropriate for a
Intel Xeon Phiprocessing system have values that appear in the gray part of the graph; in this case, consider modeling other types of the
Target System. Applications that are appropriate for offload to an
Intel Xeon Phiprocessing system have values that appear in the green part of the graph.
The lines between the graph's gray and green areas is a reference baseline, where the reference CPU chosen to calculate the
Intel® Xeon®processor peak baseline is a dual-socket 8-core
Intel Xeonprocessor E5-26xx product family (2.7 GHz, 16 cores total). When the
Maximum Site Gainexceeds this baseline, you might consider using an
Intel Xeon Phicoprocessor rather than an
Intel Xeonor similar processor.
Near the top of the vertical lines for each CPU number, a box and a circle indicate the minimum and maximum predicted gain values. The color shading indicates the predicted benefit. For example, if the minimum-maximum range appears in the red-shaded area, this site is hurting your program's performance (and power use), so you should significantly modify or remove the site and task annotations.
Below the graph is a list of issues that might be preventing better
predictedperformance gains as well as a summary of serial and predicted parallel time. To expand a line, click the down arrow to the right of the item's name. Most issues are related to the
Runtime Modeling. Later, you can use other Analyzer tools like to measure
actualperformance of your parallel program.
Loop Iterations (Tasks) Modelingor
Loop Iterations (Tasks) Modeling(or
Tasks Modeling) to experiment with different loop structures, iteration counts, and instance durations that might improve the predicted parallel performance.
Runtime impact for this site
Runtime Modelingto learn which parallel overhead categories might have an impact on parallel overhead. If you agree to address a category later by using the chosen parallel framework's capabilities or by tuning the parallel code after you have implemented parallelism, check that category.
If the chosen
Intel Xeon Phior
Offload to Intel Xeon Phi, additional options appear below the
Runtime Modelingarea. To expand this area, click the down arrow to the right of
Intel Xeon Phi Advanced Modeling.