You can customize any of the charts in the Timeline view. Open the Configure Counters dialog box to define which counters Streamline tracks and under which charts those counters appear. Available counters depend on your hardware type. For more information on how to customize these charts, see Using the Counters Configuration dialog box.
Here are some of the default charts in the Timeline view:
The number of cycles used by each core.
The total number of instructions executed by each core.
The number of cache coherency hits and misses. A cache coherency miss occurs every time a processor tries to read from or write to the cache when it is in incoherent state. This is more common in SMP systems where multiple processors share resources. A coherency hit occurs when a processor reads from or writes to a cache that is in a valid state.
- CPU Activity
The percentage of the CPU time spent in system or user code, the remainder being idle time.
- CPU Wait
Measures the amount of times the core was forced to wait as a percentage. Streamline shows CPU wait charts for I/O, contention, and mutexes, if applicable.
Maps the amount of both soft IRQs and standard, hardware IRQs. Soft IRQs are similar to IRQs, but are handled in software. Soft IRQs are usually delivered at a time that is relatively convenient for the kernel code.
- Disk IO
Measures the number of times the core triggered reads and writes to disk.
Charts the available system memory over the time of the execution.
If you are using a target with more than one core, some graphs in the Timeline view have a disclosure control. Use this to break each graph into multiple sections, one for each core in your system.
If you have built
gator.ko to support
Mali and have run a capture session on a Mali-400 target, the following
charts are added to the default set of Timeline view charts:
GPU Vertex chart - Streamline reports whether the status of the Mali-400 vertex processor is idle or active. The load on the vertex processor is proportional to the number of vertices and the complexity of the shader used to transform their coordinates.
GPU Fragment chart - Streamline reports whether the status of the Mali-400 fragment processor is idle or active. The load on the fragment processor is proportional to the number of pixels to be rendered and the complexity of the shader used to determine the final pixel color. Pixels rendered include on and off screen pixels and the additional pixels required for super sampling.