Tesla P4 Low Speech When Render Video 720p

I have a Tesla P4 GPU installed on a Dell R630 server with driver version 430.83. However, when I test the speed with and without the GPU, they are the same. Sometimes the performance without the GPU seems even better. Can anyone using a Tesla P4 explain this? Is this speed normal? If it’s not, please guide me on how I can improve the speed.

Render with None-GPU:
ffmpeg -y -i input.mp4 -s hd720 -c:v libx264 -crf 32 -c:a aac -strict -2 output_hd.mp4
Output #0, mp4, to ‘output_hd.mp4’:
Metadata:
major_brand : mp42
minor_version : 0
compatible_brands: isommp42
encoder : Lavf58.29.100
Stream #0:0(eng): Video: h264 (libx264) (avc1 / 0x31637661), yuv420p, 1280x720 [SAR 2049:2048 DAR 683:384], q=-1–1, 30 fps, 15360 tbn, 30 tbc (default)
Metadata:
creation_time : 2023-06-30T08:39:34.000000Z
handler_name : Mainconcept MP4 Video Media Handler
encoder : Lavc58.54.100 libx264
Side data:
cpb: bitrate max/min/avg: 0/0/0 buffer size: 0 vbv_delay: -1
Stream #0:1(eng): Audio: aac (LC) (mp4a / 0x6134706D), 44100 Hz, stereo, fltp, 128 kb/s (default)
Metadata:
creation_time : 2023-06-30T08:39:34.000000Z
handler_name : Mainconcept MP4 Sound Media Handler
encoder : Lavc58.54.100 aac
frame= 7105 fps= 92 q=38.0 size= 4864kB time=00:03:57.21 bitrate= 168.0kbits/s speed=3.07x
Render with GPU Tesla P4:
Output #0, mp4, to ‘output_hd.mp4’:
Metadata:
major_brand : mp42
minor_version : 0
compatible_brands: isommp42
encoder : Lavf58.29.100
Stream #0:0(eng): Video: h264 (libx264) (avc1 / 0x31637661), nv12, 1280x720 [SAR 2049:2048 DAR 683:384], q=-1–1, 30 fps, 15360 tbn, 30 tbc (default)
Metadata:
creation_time : 2023-06-30T08:39:34.000000Z
handler_name : Mainconcept MP4 Video Media Handler
encoder : Lavc58.54.100 libx264
Side data:
cpb: bitrate max/min/avg: 0/0/0 buffer size: 0 vbv_delay: -1
Stream #0:1(eng): Audio: aac (LC) (mp4a / 0x6134706D), 44100 Hz, stereo, fltp, 128 kb/s (default)
Metadata:
creation_time : 2023-06-30T08:39:34.000000Z
handler_name : Mainconcept MP4 Sound Media Handler
encoder : Lavc58.54.100 aac
frame= 4285 fps= 62 q=38.0 size= 2816kB time=00:02:23.29 bitrate= 161.0kbits/s speed=2.09x

Below is ffmpeg worked with GPU

±----------------------------------------------------------------------------+
| NVIDIA-SMI 430.83 Driver Version: 430.83 CUDA Version: 10.1 |
|-------------------------------±---------------------±---------------------+
| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |
|===============================+======================+======================|
| 0 Tesla P4 On | 00000000:00:10.0 Off | 0 |
| N/A 44C P0 24W / 75W | 287MiB / 7611MiB | 2% Default |
±------------------------------±---------------------±---------------------+

±----------------------------------------------------------------------------+
| Processes: GPU Memory |
| GPU PID Type Process name Usage |
|=============================================================================|
| 0 983 G /usr/lib/xorg/Xorg 59MiB |
| 0 1058 G /usr/bin/gnome-shell 8MiB |
| 0 81322 C ffmpeg 209MiB |
±----------------------------------------------------------------------------+

Thank you in advance.
Best regards and thank you.