Why is KNLMeansCL slowing me down so much

[Machmir]

Here's the attempted script with KNL included. It's not an interlaced source. I go onto the (De-)Interlace tab to set Auto Deinterlace Handling to None. The source is 1920x1080 but I crop the black sides so it is 1440x1080 for the encode.

# Imports
import os
import sys
import vapoursynth as vs
# getting Vapoursynth core
core = vs.core
# Import scripts folder
scriptPath = 'C:/Program Files/Hybrid/64bit/vsscripts'
sys.path.insert(0, os.path.abspath(scriptPath))
# Loading Plugins
core.std.LoadPlugin(path="C:/Program Files/Hybrid/64bit/vsfilters/DenoiseFilter/CTMF/CTMF.dll")
core.std.LoadPlugin(path="C:/Program Files/Hybrid/64bit/vsfilters/Support/fmtconv.dll")
core.std.LoadPlugin(path="C:/Program Files/Hybrid/64bit/vsfilters/ResizeFilter/nnedi3/vsznedi3.dll")
core.std.LoadPlugin(path="C:/Program Files/Hybrid/64bit/vsfilters/GrainFilter/RemoveGrain/RemoveGrainVS.dll")
core.std.LoadPlugin(path="C:/Program Files/Hybrid/64bit/vsfilters/DenoiseFilter/KNLMeansCL/KNLMeansCL.dll")
core.std.LoadPlugin(path="C:/Program Files/Hybrid/64bit/vsfilters/DeblockFilter/Deblock/Deblock.dll")
core.std.LoadPlugin(path="C:/Program Files/Hybrid/64bit/vsfilters/SharpenFilter/AWarpSharp2/libawarpsharp2.dll")
core.std.LoadPlugin(path="C:/Program Files/Hybrid/64bit/vsfilters/SourceFilter/LSmashSource/vslsmashsource.dll")
# Import scripts
import hnwvsfunc
import psharpen
import havsfunc
import mvsfunc
# source: 'E:\Pumbaa.mkv'
# current color space: YUV420P8, bit depth: 8, resolution: 1920x1080, fps: 23.976, color matrix: 709, yuv luminance scale: limited, scanorder: progressive
# Loading E:\Pumbaa.mkv using LWLibavSource
clip = core.lsmas.LWLibavSource(source="E:\Pumbaa.mkv", format="YUV420P8", cache=0, prefer_hw=0)
# Setting color matrix to 709.
clip = core.std.SetFrameProps(clip, _Matrix=1)
clip = clip if not core.text.FrameProps(clip,'_Transfer') else core.std.SetFrameProps(clip, _Transfer=1)
clip = clip if not core.text.FrameProps(clip,'_Primaries') else core.std.SetFrameProps(clip, _Primaries=1)
# Setting color range to TV (limited) range.
clip = core.std.SetFrameProp(clip=clip, prop="_ColorRange", intval=1)
# making sure frame rate is set to 23.976
clip = core.std.AssumeFPS(clip=clip, fpsnum=24000, fpsden=1001)
# cropping the video to 1440x1080
clip = core.std.CropRel(clip=clip, left=236, right=244, top=0, bottom=0)
# line darkening using Toon
clip = havsfunc.Toon(input=clip,str=0.50)
# applying delocking using Deblock
clip = core.deblock.Deblock(clip=clip, quant=33, boffset=14)
# denoising using KNLMeansCL
clip = havsfunc.KNLMeansCL(clip=clip, a=1)
# sharpening using AWarpSharp2
clip = core.warp.AWarpSharp2(clip=clip, blur=2, depth=2)
# sharpening using PSharpen
clip = psharpen.psharpen(clip=clip)
# Anti Aliasing using DAAMod
clip = hnwvsfunc.daamod(c=clip)
clip = havsfunc.FineDehalo(clip)
# adjusting output color from: YUV420P8 to YUV420P10 for x265Model
clip = core.resize.Bicubic(clip=clip, format=vs.YUV420P10, range_s="limited")
# set output frame rate to 23.976fps
clip = core.std.AssumeFPS(clip=clip, fpsnum=24000, fpsden=1001)
# Output
clip.set_output()