Having trawled the internet I have finally successfully compiled FFMPEG with OpenCL enabled and this has allowed me to attempt HDR -> SDR Conversion using my NVIDIA P400 ( Stream Limit Patch Applied).
This has been in no small part due to the various detailed guides / explanations from 林正浩. Unfortunately I don't have a HUGE understanding of the commands, and I am more or less copying various different commands to try and achieve what I want!
My issue is Hardware tone mapping seems no quicker than software tone mapping.
The following achieves approx 0.4x speed:
ffmpeg -hwaccel nvdec -init_hw_device opencl=ocl -filter_hw_device ocl -threads 4 -extra_hw_frames 3 -I INPUT.mkv -vf "format=p010,hwupload,tonemap_opencl=t=bt709:r=tv:p=bt709:m=bt709:tonemap=hable:format=p010,hwdownload,format=p010" OUTPUT
A command I had tried previously using software achieved similar 0.6x - 0.4x:
ffmpeg -I INPUT.mkv -vf zscale=t=linear:npl=100,format=gbrpf32le,zscale=p=bt709,tonemap=tonemap=hable:desat=0,zscale=t=bt709:m=bt709:r=tv,format=yuv420p -c:a copy -max_muxing_queue_size 9999 /dev/shm/output.mkv
I know they are fairly difference commands but like I said; cutting and pasting from various examples.
My question is What is the most efficient command for HW Accelerated Tonemapping HDR -> SDR, and ideally downscaling to 1080p from 4k? ( I haven't pressed that far into my learning)
I hope people can see I have looked into it and not just asked for help; I have tried and failed to find an answer!
Thank you in advance