Texas Instruments SPRAA56 appendix Expected Values Delivered to the Message Log, Debug Mode

Page 25

SPRAA56

5.3.2 Expected Values Delivered to the Message Log

CPU load, latency, time to process 30 frames, and bitrate are all sent to the Message Log rather than the Statistics View window. Table 2 shows the expected and measured values.

Table 2.

Expected and Measured Logged Benchmarks

Benchmark

 

Expected Value

Measured Value

Your Measurement

 

 

 

 

 

latency

 

<33 ms

26 ms

 

 

 

 

 

 

CPU load

 

80-90%

84-86%

 

 

 

 

 

 

bitrate

 

4084 kbps

4009-4117 kbps

 

 

 

 

 

 

Time to process 30 frames

 

1 second

1001-1004 ms

 

 

 

 

 

 

5.4Controlling the Run-Time Parameters Dynamically

After running the application on the EVM and gathering benchmarks, you may want to measure benchmarks and test operation with different frame rates, bitrates, or configurations. You can control such parameters at run-time through the GELh263rateControl menu commands. Some of the commands are:

setFrameRate. Use this slider to set the frame rate to a value from 0 to 30.

setBitRate. Type a target bitrate for the encoder algorithm between 32 and 15000.

passthroughReference. Set to 1 to bypasses the decoder and output the frame captured by the encoder without any modification. Set to 0 to use the decoder.

color. Set to 1 to enable color processing. Set to 0 to disable color processing. This slider can be used to benchmark the application with and without color processing enabled.

5.4.1 Debug Mode

The amount of data displayed in the Message Log in the default configuration may be more than what is required. By default, all benchmarks are reported every 30 frames. To control the displayed data, choose GELrtaMode and set the slider to one of the following 4 mode values:

1.ERRORS ONLY. This mode reports only dropped frames or other errors.

2.CPU LOAD ONLY. This mode displays only the CPU load and frame type every N frames.

3.EVERY N FRAMES. This mode displays more complete benchmarking every N frames, including bitrate and frame skip reports.

4.EVERY I FRAME. This mode displays more complete benchmarking when an I (intracoded) frame is encoded. The distance between I frames is an algorithm parameter that is set to 132 by default, but can be changed at runtime to another value if necessary.

DSP/BIOS Real-Time Analysis (RTA) and Debugging Applied to a Video Application

25

Image 25
Contents RTA Techniques for Performance Measurement Modifications to the Base ExampleViewing Benchmarks in the Instrumented Application References Appendix A. Performance ImpactFigures Important Benchmarks for Video ApplicationsSPRAA56 Base Application OverviewTskInput 1 LOG DSP/BIOS and RF5 Components Used3 TRC 2 STS4 UTL Requirements for Viewing RTA Benchmarks Modifications to the Base ExampleAdding the Control TSK and MBX Communication Splitting the Encode and Decode CELLsTskInput Querying the H.263 Encoder for StatusTskO utput Controlling the Frame Rate Measuring Function Execution Time with the UTL Module RTA Techniques for Performance MeasurementMeasuring End-to-End Latencies Measuring Task Scheduling LatenciesMeasuring the Frame Rate Programmatic Measurement of Total CPU Load Memory Bus Utilization 86,400 B 720*480 = 345,600 B14,400 B External memoryBitrate and Frame Type Methods for Transmitting Measured Performance Data Application-Specific Control via GEL Scripts in CCStudio Viewing Benchmarks in the Instrumented ApplicationRequirements Load the h263loopbackrta.out program Running the ApplicationSPRAA56 Interpreting the Benchmarks Expected Values for the STS Objects Expected and Measured STS Benchmarks Expected Values Delivered to the Message Log Debug ModeControlling the Run-Time Parameters Dynamically Expected and Measured Logged BenchmarksCapture and Display Task Benchmarking ReferencesOverhead of Performance Measurement Techniques Appendix A. Performance ImpactRTA Effects on CPU Load Measured Performance of Benchmarking TechniquesMemory Footprint Details Memory FootprintImportant Notice