1,433
edits
AM5728 Multimedia Performance Testbench: Difference between revisions
AM5728 Multimedia Performance Testbench (view source)
Revision as of 16:52, 7 June 2016
, 7 June 2016→Total execution time
| Line 55: | Line 55: | ||
'''''Obtained Results:''''' | '''''Obtained Results:''''' | ||
[[Image:AM572x-testbench-AAC-exec-time.png|center| | [[Image:AM572x-testbench-AAC-exec-time.png|center|800px|AM572x-testbench-AAC-exec-time.png]]<br> | ||
In the chart above, is clearly shown that when using hardware acceleration, the total execution time of the AAC audio encode pipeline is significantly reduced. The average difference is 184.8 ms less in the pipeline execution time when the NEON&VFv4 extension is used. | In the chart above, is clearly shown that when using hardware acceleration, the total execution time of the AAC audio encode pipeline is significantly reduced. The average difference is 184.8 ms less in the pipeline execution time when the NEON&VFv4 extension is used. | ||