Performance: Advanced Optimization Features Low Overhead Sampling Profiling
Event-based sampling finds your bottleneck with very low overhead (typically less than 5 percent). Identify problems such as cache misses, branch mis-predictions, and bus bandwidth. Because it is system-wide, event-based sampling can be used to tune libraries and drivers as well as application programs. No special builds or instrumentation are required.
Click to enlarge
Time- and Event-based sampling capability
See the Answers on Your Source
Source and disassembly views show you exactly which lines of code are taking the most time.
Click to enlarge
Performance data displayed on the source and assembly code
Find the Critical Path Using Call Graph Profiling
Call Graph determines calling sequences and graphically displays the critical path. It also shows you the context of the bottleneck. To be effective, you often need to know not only where the application is spending its time, but how it got there. See which functions took the most time to process or were blocked the longest.
Click to enlarge
Call Graph Profiling – Critical path shown in red. Selecting in the table (light blue row) selects in the graph (light blue box) and scrolls the view to make the function visible.
Identify System Issues with Counter Monitor
Quickly identify system level performance issues using the Counter Monitor to track system activity and resource consumption during runtime. For instance, it indicates whether reduced available memory or performance issues associated with file I/O slow down the application.
Click to enlarge
Counter Monitor – Allows real-time performance viewing
Tap Into an Expert Knowledge Base with Intel® Tuning Assistant
Increase productivity using Intel® Tuning Assistant to automatically provide advice based on an extensive knowledge base.
Click to enlarge
Intel Tuning Assistant – Provides tuning advice
| 
