CPU GPU utilization of ffio

CPU Usage for Decoding

My test involves pulling a single original video stream, doing some intermediate processing (consuming about 50% of CPU), then re-encoding and pushing it to an RTMP server(about 12% of CPU, using GPU encoding). I then watch the final processed live stream.

Here's my setup:

• CPU: Intel Xeon Gold 5118 2.30GHz x8
• GPU: Nvidia Tesla V100 32GB
• Origin Video: 1080p 24fps, 4Mbps h264-baseline The CPU usage below are not exact measurements, they are merely my intuitive perception from observing htop.

Decoding Scenario	Min	Avg	Max
Single stream with CPU	18%	22%	30%
Single stream with GPU	20%	23%	25%

When it comes to 6-stream parallel decoding:

• With GPU: CPU usage stabilizes at nearly 100% across all 8 cores, and the resulting video stream is almost smooth.
• With CPU: The total CPU usage fluctuates between 40% and 80%, but the video is more stuttered compared to using GPU. In my case, I might opt for the GPU solution as it appears more stable, although it seems not so friendly to energy efficiency

GPU usage statistics

There are two steps containing the use of GPU, decoding and encoding video streams respectively. For each step, there are 2 parts using GPU, h264 and pixel format conversion.

Here is a table describe the usage of GPU(nvidia) based on different conditions.(framerates are both 25fps)

image-size	hw_decoding	hw_yuv->rgb	hw_encoding	hw_rgb->yuv	GPU usage	CPU usage
1280*720	☑	☑	☑	☑	407M
1280*720	☑	☑			234M	13% core
1280*720	☑				131M	28% core
1280*720					0	47% core
1280*720		☑			103M	47% core
1920*1080	☑	☑	☑	☑	487M
1920*1080	☑	☑			268M	23% core
1920*1080	☑				161M	44% core
1920*1080					0	83% core
1920*1080		☑			107M	83% core

• when set hw_enabled=True and pix_fmt_hw_enabled=True, the speed of pixel format conversion is largely accelerated.
• when set hw_enabled=False and pix_fmt_hw_enabled=True the cpu consumption seems more than pure CPU. It MAY caused by the cudaMalloc method.