Recherche avancée

Sur d’autres sites (4948)

• Processing h264 video/audio stream

  1er mars 2024, par Dinamo

  I have separate audio and video streams from a camera that I'm trying to merge to a single file.

  


  Video processing

  


  I have JVT NAL sequence, H.264 video, main @ L 31 data, I had the frames separated and I appended (concat) the frames to one file.

  


  here is the ffprobe output of the data :

  


  ffprobe version 4.2.7-0ubuntu0.1 Copyright (c) 2007-2022 the FFmpeg developers
  built with gcc 9 (Ubuntu 9.4.0-1ubuntu1~20.04.1)
  configuration: --prefix=/usr --extra-version=0ubuntu0.1 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --arch=amd64 --enable-gpl --disable-stripping --enable-avresample --disable-filter=resample --enable-avisynth --enable-gnutls --enable-ladspa --enable-libaom --enable-libass --enable-libbluray --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libcodec2 --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libgme --enable-libgsm --enable-libjack --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-libpulse --enable-librsvg --enable-librubberband --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libssh --enable-libtheora --enable-libtwolame --enable-libvidstab --enable-libvorbis --enable-libvpx --enable-libwavpack --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzmq --enable-libzvbi --enable-lv2 --enable-omx --enable-openal --enable-opencl --enable-opengl --enable-sdl2 --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-nvenc --enable-chromaprint --enable-frei0r --enable-libx264 --enable-shared
  libavutil      56. 31.100 / 56. 31.100
  libavcodec     58. 54.100 / 58. 54.100
  libavformat    58. 29.100 / 58. 29.100
  libavdevice    58.  8.100 / 58.  8.100
  libavfilter     7. 57.100 /  7. 57.100
  libavresample   4.  0.  0 /  4.  0.  0
  libswscale      5.  5.100 /  5.  5.100
  libswresample   3.  5.100 /  3.  5.100
  libpostproc    55.  5.100 / 55.  5.100
Input #0, h264, from 'frame_data.h264':
  Duration: N/A, bitrate: N/A
    Stream #0:0: Video: h264 (Main), yuvj420p(pc, bt709, progressive), 1280x720, 25 fps, 25 tbr, 1200k tbn, 50 tbc


  


  the file is being played on vlc, however the video is played like it is on fast forward (every 2 seconds of the video should be about 1 second)

  


  The video should run at 15fps (not sure about that because of the mentioned avi file)

  


  here is ffprobe output of working avi file that contain the video stream :

  


  Input #0, avi, from 't.avi':
  Duration: 00:03:29.00, start: 0.000000, bitrate: 1116 kb/s
    Stream #0:0: Video: h264 (Main) (H264 / 0x34363248), yuvj420p(pc, bt709, progressive), 1280x720, 849 kb/s, 30 fps, 15 tbr, 30 tbn, 60 tbc


  


  I tried this command ffmpeg -i frame_data.h264 -filter:v fps=15 test.h264 but the video is still playing like its on fast forward

  


  vlc data before changing fps to 15

  


  


  


  vlc data after changing fps to 15

  


  


  


  frames info (raw)

  


  [FRAME]
media_type=video
stream_index=0
key_frame=1
pkt_pts=N/A
pkt_pts_time=N/A
-> pkt_dts=N/A
-> pkt_dts_time=N/A
best_effort_timestamp=N/A
best_effort_timestamp_time=N/A
-> pkt_duration=48000
-> pkt_duration_time=0.040000
pkt_pos=1476573
pkt_size=57677
width=1280
height=720
pix_fmt=yuvj420p
sample_aspect_ratio=N/A
pict_type=I
coded_picture_number=189
display_picture_number=0
interlaced_frame=0
top_field_first=0
repeat_pict=0
color_range=pc
color_space=bt709
color_primaries=bt709
color_transfer=bt709
chroma_location=left
[/FRAME]
[FRAME]
media_type=video
stream_index=0
key_frame=0
pkt_pts=N/A
pkt_pts_time=N/A
-> pkt_dts=N/A
-> pkt_dts_time=N/A
best_effort_timestamp=N/A
best_effort_timestamp_time=N/A
-> pkt_duration=48000
-> pkt_duration_time=0.040000
pkt_pos=1534250
pkt_size=3928
width=1280
height=720
pix_fmt=yuvj420p
sample_aspect_ratio=N/A
pict_type=P
coded_picture_number=190
display_picture_number=0
interlaced_frame=0
top_field_first=0
repeat_pict=0
color_range=pc
color_space=bt709
color_primaries=bt709
color_transfer=bt709
chroma_location=left
[/FRAME]


  


  frame info from working (processed) avi

  


  [FRAME]
media_type=video
stream_index=0
key_frame=0
pkt_pts=N/A
pkt_pts_time=N/A
-> pkt_dts=500
-> pkt_dts_time=16.666667
best_effort_timestamp=500
best_effort_timestamp_time=16.666667
-> pkt_duration=1
-> pkt_duration_time=0.033333
pkt_pos=1772182
pkt_size=3070
width=1280
height=720
pix_fmt=yuvj420p
sample_aspect_ratio=N/A
pict_type=P
coded_picture_number=191
display_picture_number=0
interlaced_frame=0
top_field_first=0
repeat_pict=0
color_range=pc
color_space=bt709
color_primaries=bt709
color_transfer=bt709
chroma_location=left
[/FRAME]


  


  pkt_pts and pkt_dts are missing in the raw data, maybe that is the reason the video plays on fast forward ? in the working (processed) avi pkt_dts, pkt_dts_time, pkt_duration_time are not missing.
pkt_duration_time is always 0.033333
pkt_dts always jumps by 2 (there is no odd pkt_dts)

  


  Audio processing

  


  I have raw pcm audio of the video :

  


  here is an output of ffplay -f s16le -ar 16k -ac 1 frame_data2.h264 on the raw data

  


  

  


  The raw audio does not playing well using this command.

  


  I guessed the parameters (incorrectly ?) from working avi file that contains the pcm data :

  


  Stream #0:1: Audio: pcm_s16le ([1][0][0][0] / 0x0001), 16000 Hz, 1 channels, s16, 256 kb/s


  


  here is frame info from working (processed) avi file

  


  [FRAME]
media_type=audio
stream_index=1
key_frame=1
pkt_pts=4320
pkt_pts_time=0.270000
pkt_dts=4320
pkt_dts_time=0.270000
best_effort_timestamp=4320
best_effort_timestamp_time=0.270000
pkt_duration=480
pkt_duration_time=0.030000
pkt_pos=11670
pkt_size=960
sample_fmt=s16
nb_samples=480
channels=1
channel_layout=unknown
[/FRAME]


  


  I'm trying to understand how should I process the video and the audio so that they will play well (merge them myself with the right av processing to avi/mp4 file)

  


  I also find this extra data that was included for each frame :
I suspect the first column is a sequence number maybe related to dts somehow, second column is a timestamp (milliseconds ?) (maybe you can help me parse it)

  


  600 0xd96533 (audio)
601 0xd9e1dd (audio)
602 0xda4f52 (audio)
603 0xda5a63 (video)
604 0xdacc4b (audio)
605 0xdb39a3 (audio)
606 0xdb5ee9 (video)
607 0xdbb6d8 (audio)
608 0xdc23fe (audio)
609 0xdcb255 (audio)
610 0xdd0e69 (audio)
611 0xdd8b96 (audio)
612 0xdd67d0 (video)
613 0xddf8bd (audio)
614 0xde75fe (audio)
615 0xde6c28 (video)
616 0xdee328 (audio)
617 0xdf6012 (audio)
618 0xdfcd9d (audio)
619 0xe04a7d (audio)
620 0xe07523 (video)
621 0xe0b80c (audio)
622 0xe134db (audio)
623 0xe1798b (video)
624 0xe1a251 (audio)
625 0xe21f5c (audio)
626 0xe28ce1 (audio)
627 0xe27df7 (video)
628 0xe309a7 (audio)
629 0xe376fe (audio)
630 0xe3826e (video)
631 0xe3f3fd (audio)
632 0xe46154 (audio)
633 0xe486e9 (video)
634 0xe4de79 (audio)
635 0xe54bbe (audio)
636 0xe58b79 (video)
637 0xe5c8cb (audio)
638 0xe6361e (audio)
639 0xe6b35b (audio)
640 0xe68fb7 (video)
641 0xe72093 (audio)
642 0xe79db1 (audio)
643 0xe7942f (video)
644 0xe80b09 (audio)
645 0xe887ed (audio)
646 0xe8f546 (audio)
647 0xe97256 (audio)
648 0xe99d2c (video)
649 0xe9dfbd (audio)
650 0xea5ca8 (audio)


  


  Thanks.

  


• How to Measure Marketing Effectiveness : A Step-by-Step Guide

  22 février 2024, par Erin

  Are you struggling to prove that your marketing efforts are having a measurable impact on your company’s performance ? We get it. 

  You would think that digital marketing would make it easier to track the effectiveness of your marketing efforts. But in many ways, it’s harder than ever. With so many channels and strategies competing against each other, it can feel impossible to pin down the campaign that caused a conversion. 

  That leaves you in a tricky spot as a marketing manager. It can be hard to know which campaigns to persevere with and harder still to prove your worth to stakeholders. 

  Thankfully, there are several strategies you can use to measure the success of your campaigns and put a value on your efforts. So, if you want to learn how you can measure the effectiveness of your marketing, improve the ROI of your efforts and prove your value as an employee, read on. 

  What is marketing effectiveness ?

  Marketing effectiveness measures how successful a marketing strategy or campaign is and the extent to which it achieves goals and business objectives.

  

  It’s a growing concern for brands, with research showing that 61.2% say measuring marketing effectiveness has become a more prominent factor in decision-making over the last three years. In other words, it’s becoming critical for marketers to know how to measure their effectiveness. 

  But it’s getting harder to do so. A combination of factors, including channel fragmentation, increasingly convoluted customer journeys, and the deprecation of third-party cookies, makes it hard for marketing teams to measure marketing performance. 

  Why you need to measure marketing effectiveness

  Imagine ploughing thousands of dollars into a campaign and not being confident that your efforts bore fruit. It’s unthinkable, right ? If you care about optimising campaigns and improving your worth as a marketer, measuring marketing effectiveness is necessary. 

  

  Optimise marketing campaigns

  Do you know how effectively each campaign generates conversions and drives revenue ? No ? Then, you need to measure marketing effectiveness.

  Doing so could also shine a light on ways to improve your campaigns. One paid ad campaign may suffer from a poor return on ad spend caused by high CPCs. Targeting less competitive keywords could dramatically reduce your costs. 

  Improve ROI

  Today, marketing budgets make up almost 10% of a company’s total revenue, up from 6.4% in 2021. With so much revenue at stake, you’ve got to deliver a return on that investment. 

  Measuring marketing effectiveness can help you identify the campaigns or strategies delivering the highest ROI so you can invest more heavily into them. On the other side of the same coin, you can use the data to strike off any campaigns that aren’t pulling their weight — increasing your ROI even further. 

  Demonstrate value

  Let’s get selfish for a second. Whether you’re an in-house marketing manager or work for an agency, the security of your paycheck depends on your ability to deliver high-ROI campaigns. 

  Measuring your marketing effectiveness lets you showcase your value to your company and clients. It helps you build stronger relationships that can lead to bigger and better opportunities in the future. 

  We should take this opportunity to point out that a good tool for measuring marketing effectiveness is equally important. You probably think Google Analytics will do the job, right ? But when you start implementing the strategies we discuss below, there’s a good chance you’ll have data quality issues. 

  That was the case for full-service marketing agency MHP/Team SI, which found Google Analytics’ data sampling severely limited the quantity and quality of insights they could collect. It was only by switching to Matomo, a platform that doesn’t use data sampling, that the agency could deliver the insights its clients needed to grow. 

  Further reading :

  • How to check website traffic as accurately as possible
  • 8 best tools to analyse website traffic

  Try Matomo for Free

  Get the web insights you need, without compromising data accuracy.

  Start for free

  No credit card required

  How to measure marketing effectiveness

  Measuring marketing effectiveness is not always easy, especially if you have long buying cycles and a lack of good-quality data. Make things as easy as possible by following the steps below :

  Know what success looks like

  You can’t tell whether your campaigns are effective if you don’t know what you are trying to achieve. That’s why the first step in measuring marketing effectiveness is to set a clear goal. 

  So, ask yourself what success looks like for each campaign you launch. 

  Remember, a campaign doesn’t have to drive leads to be considered effective. If all you wanted to do was raise brand awareness or increase organic traffic, you could achieve both goals without recording a single conversion. 

  We’d wager that’s probably not true for most marketing managers. It’s much more likely you want to achieve something like the following :

  • Generating 100 new customers
  • Increasing revenue by 20%
  • Selling $5,000 of your new product line
  • Reducing customer churn by 50%
  • Achieving a return on ad spend of 150%

  Conventional goal-setting wisdom applies here. So, ensure your goals are measurable, timely, relevant and achievable. 

  Track conversions

  Setting up conversion tracking in your web analytics platform is vital to measuring marketing effectiveness accurately. 

  What you count as a conversion event will depend on the goals you’ve set above. It doesn’t have to be a sale, mind you. Downloading an ebook or signing up for a webinar are worthy conversion goals, especially if you know they increase the chances of a customer converting. 

  

  Whichever platform you choose, ensure it can meet your current and future needs. This is one of the reasons open-source content management system Concrete CMS opted for Matomo when choosing a new website analytics platform. The flexibility of the Matomo platform gave Concrete CMS the adaptability it needed for future growth. 

  Try Matomo for Free

  Get the web insights you need, without compromising data accuracy.

  Start for free

  No credit card required

  Decide on an attribution model

  Marketing attribution is a way of measuring the impact of different channels and touchpoints across the customer journey. If you can assign a value to each conversion, you can use a marketing attribution model to quantify the value of your channels and campaigns.

  While most web analytics platforms simply credit the last touchpoint, marketing attribution offers a more comprehensive view by considering all interactions along the customer journey. This distinction is important because relying solely on the last touchpoint can lead to skewed insights and misallocation of resources and budget. 

  By adopting a marketing attribution approach, you can make more informed decisions, optimizing your campaigns and maximizing your return on investment.

  

  There are several different attribution models you can use to give credit to your various campaigns. These include :

  • First interaction : Gives all the credit to the first channel in the customer journey.
  • Last interaction : Gives all the credit to the last channel in the customer journey.
  • Last non-direct attribution : Gives all credit to the final touchpoint in the customer journey, except for direct interactions. In those cases, credit is given to the touchpoint just before the direct one.
  • Linear attribution : Distributes credit equally across all touchpoints.
  • Position-based attribution : Attributes 40% credit to the first and last touchpoints and distributes the remaining 20% evenly across all other touchpoints. 

  Consider carefully which attribution model to use, as this can significantly impact your marketing effectiveness calculation by giving certain campaigns too much credit.

  Try Matomo for Free

  Get the web insights you need, without compromising data accuracy.

  Start for free

  No credit card required

  Analyse KPIs

  Tracking KPIs is essential if you want to quantify the impact of your marketing campaigns. But which metrics should you track ?

  To improve brand awareness or traffic, so-called vanity metrics like sessions, returning visitors, and organic traffic may suffice as KPIs. 

  However, that’s not going to be the case for most marketers, whose performance is tied to revenue and ROI. If that’s you, put vanity metrics to one side and focus on the following conversion metrics instead :

  • Conversion rate : the percentage of users who complete a desired action. 
  • Return on ad spend : the revenue earned for every dollar spent on a campaign.
  • Return on investment : a broader calculation than ROAS, typically calculated across all your marketing efforts. 
  • Customer lifetime value : the total amount a customer will spend throughout their relationship with your company.
  • Customer acquisition cost : the cost to acquire each customer on average.

  

  Your analytics platform and advertising tools should track most of these KPIs by default. Matomo, for instance, automatically calculates your conversion rate in the Goals report. 

  How to present your marketing effectiveness

  Calculating your marketing effectiveness is one thing, but it’s important to share this information with stakeholders — whether those are executives in your company or your agency’s clients. 

  Follow the steps below to create an insightful and compelling marketing report :

  • Set the scene. There’s no guarantee that the people reading your report will know your goals. So, add context at the start of the reporting by spelling out what you are trying to achieve and why. 
  • Select the right data. You don’t want to overwhelm the reader with facts and figures, but you do need to provide hard evidence of your success. Include the KPIs you used to measure your success and show how these have changed over time. You can also support your report with audience insights such as heatmaps or customer surveys.
  • Tell a story with your presentation. Give your presentation a narrative arc with a beginning, middle, and end. Start with what you want to achieve, describe how you plan to achieve it and end with the results. Support your story with graphs and other visual aids that hold your reader’s attention. 
  • Provide a concise summary. Not everyone will read your presentation cover to cover. With that in mind, provide a summary of your report at the start or end that shows what you achieved and quantifies your marketing effectiveness. 

  How to improve marketing effectiveness

  Don’t settle for simply measuring your marketing effectiveness. Use the following strategies to make future campaigns as effective as possible. 

  Understand customer behaviour

  More effective marketing campaigns start by deeply understanding your customers, who they are, and how they behave. This allows you to take an audience-first approach to your marketing efforts and design campaigns around the unique needs of your customers. 

  Gather as much first-party data as you can. Surveys, focus groups, and other market research techniques can help you learn more about who your customers are, but don’t disregard the quantitative data you can gather from your web analytics platform. 

  Using Heatmaps, Session Recordings and behavioural analytics tools, you can learn exactly how customers behave when they land on your site, where they focus their attention and which pages they look at first. 

  

  These insights can help you turn an average campaign into an exceptional one. For example, a heatmap may highlight the need to move CTA buttons above the fold to increase conversions. A session recording could pinpoint the problems users have when filling out your website’s forms. 

  Further reading :

  • What Is Behavioural Analytics & How Can It Improve Website Performance
  • 9 Form Optimisation Tips to Convert More Visitors
  • How to Increase Conversions with Form Analysis

  Optimise landing pages

  Developing a culture of testing and experimentation is a great way to improve your marketing effectiveness. Let’s dive into A/B testing.

  By tweaking various elements of your landing pages, you can squeeze every last conversion from your campaigns.

  

  We have a guide on conversion funnel optimisation, which we recommend you check out, but I’ll briefly list some of the optimisations you could test :

  • Making your CTAs actionable and compelling
  • Integrating images and videos
  • Adding testimonials and other forms of social proof
  • Reducing form fields

  Use a different attribution model

  It might be that some campaigns, strategies or traffic sources aren’t getting the love they deserve. By changing your attribution model, you can significantly change the perceived effectiveness of certain campaigns. 

  Let’s say you use a last-touch attribution model, for instance. Only the last channel customers will get credit for each conversion, meaning top-of-the-funnel campaigns like SEO may be deemed less effective than they are. 

  It’s why you must continually test, tweak and validate your chosen model — and why changing it can be so powerful. 

  Measure your marketing effectiveness with Matomo

  Measuring your marketing effectiveness is hard work. But it’s vital to optimise campaigns, improve your ROI and demonstrate your value. 

  The good news is that Matomo makes things a lot easier thanks to its comprehensive conversion tracking, attribution modelling capabilities and behavioural insight features like Heatmaps, A/B Testing and Session Recordings. 

  Take steps today to start measuring (and improving) the effectiveness of your marketing with our 21-day free trial. No credit card required.

  Try Matomo for Free

  21 day free trial. No credit card required.

  
  

  Your email address
  

  Your website address
  

  Your Analytics subdomain will be .matomo.cloud (change)

  Choose your analytics subdomain
  

  .matomo.cloud

  I accept the terms and conditions and data processing agreement (DPA)

  
  Your information will be used to create an account on our cloud service. For more information please consult our privacy policy.
  
  
  

  Start improving your websites now

  

• avcodec/x86/vvc : add avg and avg_w AVX2 optimizations

  23 janvier 2024, par Wu Jianhua

  avcodec/x86/vvc : add avg and avg_w AVX2 optimizations
  The avg/avg_w is based on dav1d.
  
  See https://code.videolan.org/videolan/dav1d/-/blob/master/src/x86/mc_avx2.asm
  vvc_avg_8_2x2_c : 71.6
  
  vvc_avg_8_2x2_avx2 : 26.8
  
  vvc_avg_8_2x4_c : 140.8
  
  vvc_avg_8_2x4_avx2 : 34.6
  
  vvc_avg_8_2x8_c : 410.3
  
  vvc_avg_8_2x8_avx2 : 41.3
  
  vvc_avg_8_2x16_c : 769.3
  
  vvc_avg_8_2x16_avx2 : 60.3
  
  vvc_avg_8_2x32_c : 1669.6
  
  vvc_avg_8_2x32_avx2 : 105.1
  
  vvc_avg_8_2x64_c : 1978.3
  
  vvc_avg_8_2x64_avx2 : 425.8
  
  vvc_avg_8_2x128_c : 6536.8
  
  vvc_avg_8_2x128_avx2 : 1315.1
  
  vvc_avg_8_4x2_c : 155.6
  
  vvc_avg_8_4x2_avx2 : 26.1
  
  vvc_avg_8_4x4_c : 250.3
  
  vvc_avg_8_4x4_avx2 : 31.3
  
  vvc_avg_8_4x8_c : 831.8
  
  vvc_avg_8_4x8_avx2 : 41.3
  
  vvc_avg_8_4x16_c : 1461.1
  
  vvc_avg_8_4x16_avx2 : 57.1
  
  vvc_avg_8_4x32_c : 2821.6
  
  vvc_avg_8_4x32_avx2 : 105.1
  
  vvc_avg_8_4x64_c : 3615.8
  
  vvc_avg_8_4x64_avx2 : 412.6
  
  vvc_avg_8_4x128_c : 11962.6
  
  vvc_avg_8_4x128_avx2 : 1274.3
  
  vvc_avg_8_8x2_c : 215.8
  
  vvc_avg_8_8x2_avx2 : 29.1
  
  vvc_avg_8_8x4_c : 430.6
  
  vvc_avg_8_8x4_avx2 : 37.6
  
  vvc_avg_8_8x8_c : 1463.3
  
  vvc_avg_8_8x8_avx2 : 51.8
  
  vvc_avg_8_8x16_c : 2630.1
  
  vvc_avg_8_8x16_avx2 : 97.6
  
  vvc_avg_8_8x32_c : 5813.8
  
  vvc_avg_8_8x32_avx2 : 196.6
  
  vvc_avg_8_8x64_c : 6687.3
  
  vvc_avg_8_8x64_avx2 : 487.8
  
  vvc_avg_8_8x128_c : 13178.6
  
  vvc_avg_8_8x128_avx2 : 1290.6
  
  vvc_avg_8_16x2_c : 443.8
  
  vvc_avg_8_16x2_avx2 : 28.3
  
  vvc_avg_8_16x4_c : 1253.3
  
  vvc_avg_8_16x4_avx2 : 32.1
  
  vvc_avg_8_16x8_c : 2236.3
  
  vvc_avg_8_16x8_avx2 : 44.3
  
  vvc_avg_8_16x16_c : 5127.8
  
  vvc_avg_8_16x16_avx2 : 63.3
  
  vvc_avg_8_16x32_c : 6573.3
  
  vvc_avg_8_16x32_avx2 : 223.6
  
  vvc_avg_8_16x64_c : 30311.8
  
  vvc_avg_8_16x64_avx2 : 437.8
  
  vvc_avg_8_16x128_c : 25693.3
  
  vvc_avg_8_16x128_avx2 : 1266.8
  
  vvc_avg_8_32x2_c : 954.6
  
  vvc_avg_8_32x2_avx2 : 32.1
  
  vvc_avg_8_32x4_c : 2359.6
  
  vvc_avg_8_32x4_avx2 : 39.6
  
  vvc_avg_8_32x8_c : 5703.6
  
  vvc_avg_8_32x8_avx2 : 57.1
  
  vvc_avg_8_32x16_c : 9967.6
  
  vvc_avg_8_32x16_avx2 : 107.1
  
  vvc_avg_8_32x32_c : 21327.6
  
  vvc_avg_8_32x32_avx2 : 272.6
  
  vvc_avg_8_32x64_c : 39240.8
  
  vvc_avg_8_32x64_avx2 : 529.6
  
  vvc_avg_8_32x128_c : 52580.8
  
  vvc_avg_8_32x128_avx2 : 1338.8
  
  vvc_avg_8_64x2_c : 1647.3
  
  vvc_avg_8_64x2_avx2 : 38.8
  
  vvc_avg_8_64x4_c : 5130.1
  
  vvc_avg_8_64x4_avx2 : 58.8
  
  vvc_avg_8_64x8_c : 6529.3
  
  vvc_avg_8_64x8_avx2 : 88.3
  
  vvc_avg_8_64x16_c : 19913.6
  
  vvc_avg_8_64x16_avx2 : 162.3
  
  vvc_avg_8_64x32_c : 39360.8
  
  vvc_avg_8_64x32_avx2 : 295.8
  
  vvc_avg_8_64x64_c : 49658.3
  
  vvc_avg_8_64x64_avx2 : 784.1
  
  vvc_avg_8_64x128_c : 108513.1
  
  vvc_avg_8_64x128_avx2 : 1977.1
  
  vvc_avg_8_128x2_c : 3226.1
  
  vvc_avg_8_128x2_avx2 : 61.1
  
  vvc_avg_8_128x4_c : 10280.3
  
  vvc_avg_8_128x4_avx2 : 94.6
  
  vvc_avg_8_128x8_c : 18079.3
  
  vvc_avg_8_128x8_avx2 : 155.3
  
  vvc_avg_8_128x16_c : 45121.8
  
  vvc_avg_8_128x16_avx2 : 285.3
  
  vvc_avg_8_128x32_c : 48651.8
  
  vvc_avg_8_128x32_avx2 : 581.6
  
  vvc_avg_8_128x64_c : 165078.6
  
  vvc_avg_8_128x64_avx2 : 1942.8
  
  vvc_avg_8_128x128_c : 339103.1
  
  vvc_avg_8_128x128_avx2 : 4332.6
  
  vvc_avg_10_2x2_c : 144.3
  
  vvc_avg_10_2x2_avx2 : 26.8
  
  vvc_avg_10_2x4_c : 142.6
  
  vvc_avg_10_2x4_avx2 : 45.3
  
  vvc_avg_10_2x8_c : 478.1
  
  vvc_avg_10_2x8_avx2 : 38.1
  
  vvc_avg_10_2x16_c : 518.3
  
  vvc_avg_10_2x16_avx2 : 58.1
  
  vvc_avg_10_2x32_c : 2059.8
  
  vvc_avg_10_2x32_avx2 : 93.1
  
  vvc_avg_10_2x64_c : 2383.8
  
  vvc_avg_10_2x64_avx2 : 714.8
  
  vvc_avg_10_2x128_c : 4498.3
  
  vvc_avg_10_2x128_avx2 : 1466.3
  
  vvc_avg_10_4x2_c : 228.6
  
  vvc_avg_10_4x2_avx2 : 26.8
  
  vvc_avg_10_4x4_c : 378.3
  
  vvc_avg_10_4x4_avx2 : 30.6
  
  vvc_avg_10_4x8_c : 866.8
  
  vvc_avg_10_4x8_avx2 : 44.6
  
  vvc_avg_10_4x16_c : 1018.1
  
  vvc_avg_10_4x16_avx2 : 58.1
  
  vvc_avg_10_4x32_c : 3590.8
  
  vvc_avg_10_4x32_avx2 : 128.8
  
  vvc_avg_10_4x64_c : 4200.8
  
  vvc_avg_10_4x64_avx2 : 663.6
  
  vvc_avg_10_4x128_c : 8450.8
  
  vvc_avg_10_4x128_avx2 : 1531.8
  
  vvc_avg_10_8x2_c : 369.3
  
  vvc_avg_10_8x2_avx2 : 28.3
  
  vvc_avg_10_8x4_c : 513.8
  
  vvc_avg_10_8x4_avx2 : 32.1
  
  vvc_avg_10_8x8_c : 1720.3
  
  vvc_avg_10_8x8_avx2 : 49.1
  
  vvc_avg_10_8x16_c : 1894.8
  
  vvc_avg_10_8x16_avx2 : 71.6
  
  vvc_avg_10_8x32_c : 3931.3
  
  vvc_avg_10_8x32_avx2 : 148.1
  
  vvc_avg_10_8x64_c : 7964.3
  
  vvc_avg_10_8x64_avx2 : 613.1
  
  vvc_avg_10_8x128_c : 15540.1
  
  vvc_avg_10_8x128_avx2 : 1585.1
  
  vvc_avg_10_16x2_c : 877.3
  
  vvc_avg_10_16x2_avx2 : 27.6
  
  vvc_avg_10_16x4_c : 955.8
  
  vvc_avg_10_16x4_avx2 : 29.8
  
  vvc_avg_10_16x8_c : 3419.6
  
  vvc_avg_10_16x8_avx2 : 62.6
  
  vvc_avg_10_16x16_c : 3826.8
  
  vvc_avg_10_16x16_avx2 : 54.3
  
  vvc_avg_10_16x32_c : 7655.3
  
  vvc_avg_10_16x32_avx2 : 86.3
  
  vvc_avg_10_16x64_c : 30011.1
  
  vvc_avg_10_16x64_avx2 : 692.6
  
  vvc_avg_10_16x128_c : 47894.8
  
  vvc_avg_10_16x128_avx2 : 1580.3
  
  vvc_avg_10_32x2_c : 944.3
  
  vvc_avg_10_32x2_avx2 : 29.8
  
  vvc_avg_10_32x4_c : 2022.6
  
  vvc_avg_10_32x4_avx2 : 35.1
  
  vvc_avg_10_32x8_c : 6148.8
  
  vvc_avg_10_32x8_avx2 : 51.3
  
  vvc_avg_10_32x16_c : 12601.6
  
  vvc_avg_10_32x16_avx2 : 70.8
  
  vvc_avg_10_32x32_c : 15958.6
  
  vvc_avg_10_32x32_avx2 : 124.3
  
  vvc_avg_10_32x64_c : 31784.6
  
  vvc_avg_10_32x64_avx2 : 757.3
  
  vvc_avg_10_32x128_c : 63892.8
  
  vvc_avg_10_32x128_avx2 : 1711.3
  
  vvc_avg_10_64x2_c : 1890.8
  
  vvc_avg_10_64x2_avx2 : 34.3
  
  vvc_avg_10_64x4_c : 6267.3
  
  vvc_avg_10_64x4_avx2 : 42.6
  
  vvc_avg_10_64x8_c : 12778.1
  
  vvc_avg_10_64x8_avx2 : 67.8
  
  vvc_avg_10_64x16_c : 22304.3
  
  vvc_avg_10_64x16_avx2 : 116.8
  
  vvc_avg_10_64x32_c : 30777.1
  
  vvc_avg_10_64x32_avx2 : 201.1
  
  vvc_avg_10_64x64_c : 60169.1
  
  vvc_avg_10_64x64_avx2 : 1454.3
  
  vvc_avg_10_64x128_c : 124392.8
  
  vvc_avg_10_64x128_avx2 : 3648.6
  
  vvc_avg_10_128x2_c : 3650.1
  
  vvc_avg_10_128x2_avx2 : 41.1
  
  vvc_avg_10_128x4_c : 22887.8
  
  vvc_avg_10_128x4_avx2 : 64.1
  
  vvc_avg_10_128x8_c : 14622.6
  
  vvc_avg_10_128x8_avx2 : 111.6
  
  vvc_avg_10_128x16_c : 62207.6
  
  vvc_avg_10_128x16_avx2 : 186.3
  
  vvc_avg_10_128x32_c : 59761.3
  
  vvc_avg_10_128x32_avx2 : 374.6
  
  vvc_avg_10_128x64_c : 117504.3
  
  vvc_avg_10_128x64_avx2 : 2684.6
  
  vvc_avg_10_128x128_c : 236767.6
  
  vvc_avg_10_128x128_avx2 : 15278.1
  
  vvc_avg_12_2x2_c : 78.6
  
  vvc_avg_12_2x2_avx2 : 26.1
  
  vvc_avg_12_2x4_c : 254.1
  
  vvc_avg_12_2x4_avx2 : 30.6
  
  vvc_avg_12_2x8_c : 261.8
  
  vvc_avg_12_2x8_avx2 : 39.1
  
  vvc_avg_12_2x16_c : 527.6
  
  vvc_avg_12_2x16_avx2 : 57.3
  
  vvc_avg_12_2x32_c : 1089.1
  
  vvc_avg_12_2x32_avx2 : 93.8
  
  vvc_avg_12_2x64_c : 2337.6
  
  vvc_avg_12_2x64_avx2 : 707.1
  
  vvc_avg_12_2x128_c : 4582.1
  
  vvc_avg_12_2x128_avx2 : 1414.6
  
  vvc_avg_12_4x2_c : 129.6
  
  vvc_avg_12_4x2_avx2 : 26.8
  
  vvc_avg_12_4x4_c : 427.3
  
  vvc_avg_12_4x4_avx2 : 30.6
  
  vvc_avg_12_4x8_c : 529.6
  
  vvc_avg_12_4x8_avx2 : 36.6
  
  vvc_avg_12_4x16_c : 1022.1
  
  vvc_avg_12_4x16_avx2 : 57.3
  
  vvc_avg_12_4x32_c : 1987.6
  
  vvc_avg_12_4x32_avx2 : 84.3
  
  vvc_avg_12_4x64_c : 4147.6
  
  vvc_avg_12_4x64_avx2 : 706.3
  
  vvc_avg_12_4x128_c : 8469.3
  
  vvc_avg_12_4x128_avx2 : 1448.3
  
  vvc_avg_12_8x2_c : 253.6
  
  vvc_avg_12_8x2_avx2 : 27.6
  
  vvc_avg_12_8x4_c : 836.3
  
  vvc_avg_12_8x4_avx2 : 32.1
  
  vvc_avg_12_8x8_c : 1074.6
  
  vvc_avg_12_8x8_avx2 : 45.1
  
  vvc_avg_12_8x16_c : 3616.8
  
  vvc_avg_12_8x16_avx2 : 71.6
  
  vvc_avg_12_8x32_c : 3823.6
  
  vvc_avg_12_8x32_avx2 : 140.1
  
  vvc_avg_12_8x64_c : 7764.8
  
  vvc_avg_12_8x64_avx2 : 656.1
  
  vvc_avg_12_8x128_c : 15896.1
  
  vvc_avg_12_8x128_avx2 : 1232.8
  
  vvc_avg_12_16x2_c : 462.1
  
  vvc_avg_12_16x2_avx2 : 26.8
  
  vvc_avg_12_16x4_c : 1732.1
  
  vvc_avg_12_16x4_avx2 : 29.1
  
  vvc_avg_12_16x8_c : 2097.6
  
  vvc_avg_12_16x8_avx2 : 62.6
  
  vvc_avg_12_16x16_c : 6753.1
  
  vvc_avg_12_16x16_avx2 : 47.8
  
  vvc_avg_12_16x32_c : 7373.1
  
  vvc_avg_12_16x32_avx2 : 80.8
  
  vvc_avg_12_16x64_c : 15046.3
  
  vvc_avg_12_16x64_avx2 : 621.1
  
  vvc_avg_12_16x128_c : 52574.6
  
  vvc_avg_12_16x128_avx2 : 1417.1
  
  vvc_avg_12_32x2_c : 1712.1
  
  vvc_avg_12_32x2_avx2 : 29.8
  
  vvc_avg_12_32x4_c : 2036.8
  
  vvc_avg_12_32x4_avx2 : 37.6
  
  vvc_avg_12_32x8_c : 4017.6
  
  vvc_avg_12_32x8_avx2 : 44.1
  
  vvc_avg_12_32x16_c : 8018.6
  
  vvc_avg_12_32x16_avx2 : 70.8
  
  vvc_avg_12_32x32_c : 15637.6
  
  vvc_avg_12_32x32_avx2 : 124.3
  
  vvc_avg_12_32x64_c : 31143.3
  
  vvc_avg_12_32x64_avx2 : 830.3
  
  vvc_avg_12_32x128_c : 75706.8
  
  vvc_avg_12_32x128_avx2 : 1604.8
  
  vvc_avg_12_64x2_c : 3230.3
  
  vvc_avg_12_64x2_avx2 : 33.6
  
  vvc_avg_12_64x4_c : 4139.6
  
  vvc_avg_12_64x4_avx2 : 45.1
  
  vvc_avg_12_64x8_c : 8201.6
  
  vvc_avg_12_64x8_avx2 : 67.1
  
  vvc_avg_12_64x16_c : 25632.3
  
  vvc_avg_12_64x16_avx2 : 110.3
  
  vvc_avg_12_64x32_c : 30744.3
  
  vvc_avg_12_64x32_avx2 : 200.3
  
  vvc_avg_12_64x64_c : 105554.8
  
  vvc_avg_12_64x64_avx2 : 1325.6
  
  vvc_avg_12_64x128_c : 235254.3
  
  vvc_avg_12_64x128_avx2 : 3132.6
  
  vvc_avg_12_128x2_c : 6194.3
  
  vvc_avg_12_128x2_avx2 : 55.1
  
  vvc_avg_12_128x4_c : 7583.8
  
  vvc_avg_12_128x4_avx2 : 79.3
  
  vvc_avg_12_128x8_c : 14635.6
  
  vvc_avg_12_128x8_avx2 : 104.3
  
  vvc_avg_12_128x16_c : 29270.8
  
  vvc_avg_12_128x16_avx2 : 194.3
  
  vvc_avg_12_128x32_c : 60113.6
  
  vvc_avg_12_128x32_avx2 : 346.3
  
  vvc_avg_12_128x64_c : 197030.3
  
  vvc_avg_12_128x64_avx2 : 2779.6
  
  vvc_avg_12_128x128_c : 432809.6
  
  vvc_avg_12_128x128_avx2 : 5513.3
  
  vvc_w_avg_8_2x2_c : 84.3
  
  vvc_w_avg_8_2x2_avx2 : 42.6
  
  vvc_w_avg_8_2x4_c : 156.3
  
  vvc_w_avg_8_2x4_avx2 : 58.8
  
  vvc_w_avg_8_2x8_c : 310.6
  
  vvc_w_avg_8_2x8_avx2 : 73.1
  
  vvc_w_avg_8_2x16_c : 942.1
  
  vvc_w_avg_8_2x16_avx2 : 113.3
  
  vvc_w_avg_8_2x32_c : 1098.8
  
  vvc_w_avg_8_2x32_avx2 : 202.6
  
  vvc_w_avg_8_2x64_c : 2414.3
  
  vvc_w_avg_8_2x64_avx2 : 467.6
  
  vvc_w_avg_8_2x128_c : 4763.8
  
  vvc_w_avg_8_2x128_avx2 : 1333.1
  
  vvc_w_avg_8_4x2_c : 140.1
  
  vvc_w_avg_8_4x2_avx2 : 49.8
  
  vvc_w_avg_8_4x4_c : 276.3
  
  vvc_w_avg_8_4x4_avx2 : 58.1
  
  vvc_w_avg_8_4x8_c : 524.3
  
  vvc_w_avg_8_4x8_avx2 : 72.3
  
  vvc_w_avg_8_4x16_c : 1108.1
  
  vvc_w_avg_8_4x16_avx2 : 111.8
  
  vvc_w_avg_8_4x32_c : 2149.8
  
  vvc_w_avg_8_4x32_avx2 : 199.6
  
  vvc_w_avg_8_4x64_c : 12288.1
  
  vvc_w_avg_8_4x64_avx2 : 509.3
  
  vvc_w_avg_8_4x128_c : 8398.6
  
  vvc_w_avg_8_4x128_avx2 : 1319.6
  
  vvc_w_avg_8_8x2_c : 271.1
  
  vvc_w_avg_8_8x2_avx2 : 44.1
  
  vvc_w_avg_8_8x4_c : 503.3
  
  vvc_w_avg_8_8x4_avx2 : 61.8
  
  vvc_w_avg_8_8x8_c : 1031.1
  
  vvc_w_avg_8_8x8_avx2 : 93.8
  
  vvc_w_avg_8_8x16_c : 2009.8
  
  vvc_w_avg_8_8x16_avx2 : 163.1
  
  vvc_w_avg_8_8x32_c : 4161.3
  
  vvc_w_avg_8_8x32_avx2 : 292.1
  
  vvc_w_avg_8_8x64_c : 7940.6
  
  vvc_w_avg_8_8x64_avx2 : 592.1
  
  vvc_w_avg_8_8x128_c : 16802.3
  
  vvc_w_avg_8_8x128_avx2 : 1287.6
  
  vvc_w_avg_8_16x2_c : 762.6
  
  vvc_w_avg_8_16x2_avx2 : 53.6
  
  vvc_w_avg_8_16x4_c : 1486.3
  
  vvc_w_avg_8_16x4_avx2 : 67.1
  
  vvc_w_avg_8_16x8_c : 1907.8
  
  vvc_w_avg_8_16x8_avx2 : 96.8
  
  vvc_w_avg_8_16x16_c : 3883.6
  
  vvc_w_avg_8_16x16_avx2 : 151.3
  
  vvc_w_avg_8_16x32_c : 7974.8
  
  vvc_w_avg_8_16x32_avx2 : 285.8
  
  vvc_w_avg_8_16x64_c : 25160.6
  
  vvc_w_avg_8_16x64_avx2 : 589.8
  
  vvc_w_avg_8_16x128_c : 58328.1
  
  vvc_w_avg_8_16x128_avx2 : 1169.8
  
  vvc_w_avg_8_32x2_c : 1009.1
  
  vvc_w_avg_8_32x2_avx2 : 65.6
  
  vvc_w_avg_8_32x4_c : 2091.1
  
  vvc_w_avg_8_32x4_avx2 : 96.8
  
  vvc_w_avg_8_32x8_c : 3997.8
  
  vvc_w_avg_8_32x8_avx2 : 156.3
  
  vvc_w_avg_8_32x16_c : 8216.8
  
  vvc_w_avg_8_32x16_avx2 : 269.6
  
  vvc_w_avg_8_32x32_c : 21746.1
  
  vvc_w_avg_8_32x32_avx2 : 635.3
  
  vvc_w_avg_8_32x64_c : 31564.8
  
  vvc_w_avg_8_32x64_avx2 : 1010.6
  
  vvc_w_avg_8_32x128_c : 114373.3
  
  vvc_w_avg_8_32x128_avx2 : 2013.6
  
  vvc_w_avg_8_64x2_c : 2067.3
  
  vvc_w_avg_8_64x2_avx2 : 97.6
  
  vvc_w_avg_8_64x4_c : 3901.1
  
  vvc_w_avg_8_64x4_avx2 : 154.8
  
  vvc_w_avg_8_64x8_c : 7911.6
  
  vvc_w_avg_8_64x8_avx2 : 268.8
  
  vvc_w_avg_8_64x16_c : 16508.8
  
  vvc_w_avg_8_64x16_avx2 : 501.8
  
  vvc_w_avg_8_64x32_c : 38770.3
  
  vvc_w_avg_8_64x32_avx2 : 1287.6
  
  vvc_w_avg_8_64x64_c : 110350.6
  
  vvc_w_avg_8_64x64_avx2 : 1890.8
  
  vvc_w_avg_8_64x128_c : 141354.6
  
  vvc_w_avg_8_64x128_avx2 : 3839.6
  
  vvc_w_avg_8_128x2_c : 7012.1
  
  vvc_w_avg_8_128x2_avx2 : 159.3
  
  vvc_w_avg_8_128x4_c : 8146.8
  
  vvc_w_avg_8_128x4_avx2 : 272.6
  
  vvc_w_avg_8_128x8_c : 24596.8
  
  vvc_w_avg_8_128x8_avx2 : 501.1
  
  vvc_w_avg_8_128x16_c : 35918.1
  
  vvc_w_avg_8_128x16_avx2 : 948.8
  
  vvc_w_avg_8_128x32_c : 68799.6
  
  vvc_w_avg_8_128x32_avx2 : 1963.1
  
  vvc_w_avg_8_128x64_c : 133862.1
  
  vvc_w_avg_8_128x64_avx2 : 3833.6
  
  vvc_w_avg_8_128x128_c : 348427.8
  
  vvc_w_avg_8_128x128_avx2 : 7682.8
  
  vvc_w_avg_10_2x2_c : 118.6
  
  vvc_w_avg_10_2x2_avx2 : 73.1
  
  vvc_w_avg_10_2x4_c : 189.1
  
  vvc_w_avg_10_2x4_avx2 : 89.3
  
  vvc_w_avg_10_2x8_c : 382.8
  
  vvc_w_avg_10_2x8_avx2 : 179.8
  
  vvc_w_avg_10_2x16_c : 658.3
  
  vvc_w_avg_10_2x16_avx2 : 185.1
  
  vvc_w_avg_10_2x32_c : 1409.3
  
  vvc_w_avg_10_2x32_avx2 : 290.8
  
  vvc_w_avg_10_2x64_c : 2906.8
  
  vvc_w_avg_10_2x64_avx2 : 793.1
  
  vvc_w_avg_10_2x128_c : 6292.6
  
  vvc_w_avg_10_2x128_avx2 : 1696.8
  
  vvc_w_avg_10_4x2_c : 178.8
  
  vvc_w_avg_10_4x2_avx2 : 80.1
  
  vvc_w_avg_10_4x4_c : 581.6
  
  vvc_w_avg_10_4x4_avx2 : 97.6
  
  vvc_w_avg_10_4x8_c : 693.3
  
  vvc_w_avg_10_4x8_avx2 : 128.1
  
  vvc_w_avg_10_4x16_c : 1436.6
  
  vvc_w_avg_10_4x16_avx2 : 179.8
  
  vvc_w_avg_10_4x32_c : 2409.1
  
  vvc_w_avg_10_4x32_avx2 : 292.3
  
  vvc_w_avg_10_4x64_c : 4925.3
  
  vvc_w_avg_10_4x64_avx2 : 746.1
  
  vvc_w_avg_10_4x128_c : 10664.6
  
  vvc_w_avg_10_4x128_avx2 : 1647.6
  
  vvc_w_avg_10_8x2_c : 359.3
  
  vvc_w_avg_10_8x2_avx2 : 80.1
  
  vvc_w_avg_10_8x4_c : 925.6
  
  vvc_w_avg_10_8x4_avx2 : 97.6
  
  vvc_w_avg_10_8x8_c : 1360.6
  
  vvc_w_avg_10_8x8_avx2 : 121.8
  
  vvc_w_avg_10_8x16_c : 3490.3
  
  vvc_w_avg_10_8x16_avx2 : 203.3
  
  vvc_w_avg_10_8x32_c : 5266.1
  
  vvc_w_avg_10_8x32_avx2 : 325.8
  
  vvc_w_avg_10_8x64_c : 11127.1
  
  vvc_w_avg_10_8x64_avx2 : 747.8
  
  vvc_w_avg_10_8x128_c : 31058.3
  
  vvc_w_avg_10_8x128_avx2 : 1424.6
  
  vvc_w_avg_10_16x2_c : 624.8
  
  vvc_w_avg_10_16x2_avx2 : 84.6
  
  vvc_w_avg_10_16x4_c : 1389.6
  
  vvc_w_avg_10_16x4_avx2 : 109.1
  
  vvc_w_avg_10_16x8_c : 2688.3
  
  vvc_w_avg_10_16x8_avx2 : 137.1
  
  vvc_w_avg_10_16x16_c : 5387.1
  
  vvc_w_avg_10_16x16_avx2 : 224.6
  
  vvc_w_avg_10_16x32_c : 10776.3
  
  vvc_w_avg_10_16x32_avx2 : 312.1
  
  vvc_w_avg_10_16x64_c : 18069.1
  
  vvc_w_avg_10_16x64_avx2 : 858.6
  
  vvc_w_avg_10_16x128_c : 43460.3
  
  vvc_w_avg_10_16x128_avx2 : 1411.6
  
  vvc_w_avg_10_32x2_c : 1232.8
  
  vvc_w_avg_10_32x2_avx2 : 99.1
  
  vvc_w_avg_10_32x4_c : 4017.6
  
  vvc_w_avg_10_32x4_avx2 : 134.1
  
  vvc_w_avg_10_32x8_c : 9306.3
  
  vvc_w_avg_10_32x8_avx2 : 208.1
  
  vvc_w_avg_10_32x16_c : 8424.6
  
  vvc_w_avg_10_32x16_avx2 : 349.3
  
  vvc_w_avg_10_32x32_c : 20787.8
  
  vvc_w_avg_10_32x32_avx2 : 655.3
  
  vvc_w_avg_10_32x64_c : 40972.1
  
  vvc_w_avg_10_32x64_avx2 : 904.8
  
  vvc_w_avg_10_32x128_c : 85670.3
  
  vvc_w_avg_10_32x128_avx2 : 1751.6
  
  vvc_w_avg_10_64x2_c : 2454.1
  
  vvc_w_avg_10_64x2_avx2 : 132.6
  
  vvc_w_avg_10_64x4_c : 5012.6
  
  vvc_w_avg_10_64x4_avx2 : 215.6
  
  vvc_w_avg_10_64x8_c : 10811.3
  
  vvc_w_avg_10_64x8_avx2 : 361.1
  
  vvc_w_avg_10_64x16_c : 33349.1
  
  vvc_w_avg_10_64x16_avx2 : 904.1
  
  vvc_w_avg_10_64x32_c : 41892.3
  
  vvc_w_avg_10_64x32_avx2 : 1220.6
  
  vvc_w_avg_10_64x64_c : 66983.3
  
  vvc_w_avg_10_64x64_avx2 : 2622.1
  
  vvc_w_avg_10_64x128_c : 246508.8
  
  vvc_w_avg_10_64x128_avx2 : 3316.8
  
  vvc_w_avg_10_128x2_c : 7791.6
  
  vvc_w_avg_10_128x2_avx2 : 198.8
  
  vvc_w_avg_10_128x4_c : 10534.3
  
  vvc_w_avg_10_128x4_avx2 : 337.3
  
  vvc_w_avg_10_128x8_c : 21142.3
  
  vvc_w_avg_10_128x8_avx2 : 614.8
  
  vvc_w_avg_10_128x16_c : 40968.6
  
  vvc_w_avg_10_128x16_avx2 : 1160.6
  
  vvc_w_avg_10_128x32_c : 113043.3
  
  vvc_w_avg_10_128x32_avx2 : 1644.6
  
  vvc_w_avg_10_128x64_c : 230658.3
  
  vvc_w_avg_10_128x64_avx2 : 5065.3
  
  vvc_w_avg_10_128x128_c : 335236.3
  
  vvc_w_avg_10_128x128_avx2 : 6450.3
  
  vvc_w_avg_12_2x2_c : 185.3
  
  vvc_w_avg_12_2x2_avx2 : 43.6
  
  vvc_w_avg_12_2x4_c : 340.3
  
  vvc_w_avg_12_2x4_avx2 : 55.8
  
  vvc_w_avg_12_2x8_c : 632.3
  
  vvc_w_avg_12_2x8_avx2 : 70.1
  
  vvc_w_avg_12_2x16_c : 728.3
  
  vvc_w_avg_12_2x16_avx2 : 108.1
  
  vvc_w_avg_12_2x32_c : 1392.6
  
  vvc_w_avg_12_2x32_avx2 : 176.8
  
  vvc_w_avg_12_2x64_c : 2618.3
  
  vvc_w_avg_12_2x64_avx2 : 757.3
  
  vvc_w_avg_12_2x128_c : 6408.8
  
  vvc_w_avg_12_2x128_avx2 : 1435.1
  
  vvc_w_avg_12_4x2_c : 349.3
  
  vvc_w_avg_12_4x2_avx2 : 44.3
  
  vvc_w_avg_12_4x4_c : 607.1
  
  vvc_w_avg_12_4x4_avx2 : 52.6
  
  vvc_w_avg_12_4x8_c : 1134.8
  
  vvc_w_avg_12_4x8_avx2 : 70.1
  
  vvc_w_avg_12_4x16_c : 1378.1
  
  vvc_w_avg_12_4x16_avx2 : 115.3
  
  vvc_w_avg_12_4x32_c : 2599.3
  
  vvc_w_avg_12_4x32_avx2 : 174.3
  
  vvc_w_avg_12_4x64_c : 4474.8
  
  vvc_w_avg_12_4x64_avx2 : 656.1
  
  vvc_w_avg_12_4x128_c : 11319.6
  
  vvc_w_avg_12_4x128_avx2 : 1373.1
  
  vvc_w_avg_12_8x2_c : 595.8
  
  vvc_w_avg_12_8x2_avx2 : 44.3
  
  vvc_w_avg_12_8x4_c : 1164.3
  
  vvc_w_avg_12_8x4_avx2 : 56.6
  
  vvc_w_avg_12_8x8_c : 2019.6
  
  vvc_w_avg_12_8x8_avx2 : 80.1
  
  vvc_w_avg_12_8x16_c : 4071.6
  
  vvc_w_avg_12_8x16_avx2 : 139.3
  
  vvc_w_avg_12_8x32_c : 4485.1
  
  vvc_w_avg_12_8x32_avx2 : 250.6
  
  vvc_w_avg_12_8x64_c : 8404.8
  
  vvc_w_avg_12_8x64_avx2 : 735.8
  
  vvc_w_avg_12_8x128_c : 35679.8
  
  vvc_w_avg_12_8x128_avx2 : 1252.6
  
  vvc_w_avg_12_16x2_c : 1114.8
  
  vvc_w_avg_12_16x2_avx2 : 46.6
  
  vvc_w_avg_12_16x4_c : 2240.1
  
  vvc_w_avg_12_16x4_avx2 : 62.6
  
  vvc_w_avg_12_16x8_c : 13174.6
  
  vvc_w_avg_12_16x8_avx2 : 88.6
  
  vvc_w_avg_12_16x16_c : 5334.6
  
  vvc_w_avg_12_16x16_avx2 : 144.3
  
  vvc_w_avg_12_16x32_c : 8378.1
  
  vvc_w_avg_12_16x32_avx2 : 234.6
  
  vvc_w_avg_12_16x64_c : 21300.8
  
  vvc_w_avg_12_16x64_avx2 : 761.8
  
  vvc_w_avg_12_16x128_c : 32786.8
  
  vvc_w_avg_12_16x128_avx2 : 1432.8
  
  vvc_w_avg_12_32x2_c : 2154.3
  
  vvc_w_avg_12_32x2_avx2 : 61.1
  
  vvc_w_avg_12_32x4_c : 4299.8
  
  vvc_w_avg_12_32x4_avx2 : 83.1
  
  vvc_w_avg_12_32x8_c : 7964.8
  
  vvc_w_avg_12_32x8_avx2 : 132.6
  
  vvc_w_avg_12_32x16_c : 13321.6
  
  vvc_w_avg_12_32x16_avx2 : 234.6
  
  vvc_w_avg_12_32x32_c : 21149.3
  
  vvc_w_avg_12_32x32_avx2 : 433.3
  
  vvc_w_avg_12_32x64_c : 43666.6
  
  vvc_w_avg_12_32x64_avx2 : 876.6
  
  vvc_w_avg_12_32x128_c : 83189.8
  
  vvc_w_avg_12_32x128_avx2 : 1756.6
  
  vvc_w_avg_12_64x2_c : 3829.8
  
  vvc_w_avg_12_64x2_avx2 : 83.1
  
  vvc_w_avg_12_64x4_c : 8588.1
  
  vvc_w_avg_12_64x4_avx2 : 127.1
  
  vvc_w_avg_12_64x8_c : 17027.6
  
  vvc_w_avg_12_64x8_avx2 : 310.6
  
  vvc_w_avg_12_64x16_c : 29797.8
  
  vvc_w_avg_12_64x16_avx2 : 415.6
  
  vvc_w_avg_12_64x32_c : 43854.3
  
  vvc_w_avg_12_64x32_avx2 : 773.3
  
  vvc_w_avg_12_64x64_c : 137767.3
  
  vvc_w_avg_12_64x64_avx2 : 1608.6
  
  vvc_w_avg_12_64x128_c : 316428.3
  
  vvc_w_avg_12_64x128_avx2 : 3249.8
  
  vvc_w_avg_12_128x2_c : 8824.6
  
  vvc_w_avg_12_128x2_avx2 : 130.3
  
  vvc_w_avg_12_128x4_c : 17173.6
  
  vvc_w_avg_12_128x4_avx2 : 219.3
  
  vvc_w_avg_12_128x8_c : 21997.8
  
  vvc_w_avg_12_128x8_avx2 : 397.3
  
  vvc_w_avg_12_128x16_c : 43553.8
  
  vvc_w_avg_12_128x16_avx2 : 790.1
  
  vvc_w_avg_12_128x32_c : 89792.1
  
  vvc_w_avg_12_128x32_avx2 : 1497.6
  
  vvc_w_avg_12_128x64_c : 226573.3
  
  vvc_w_avg_12_128x64_avx2 : 3153.1
  
  vvc_w_avg_12_128x128_c : 332090.1
  
  vvc_w_avg_12_128x128_avx2 : 6499.6
  Signed-off-by : Wu Jianhua <toqsxw@outlook.com>
  

  • [DH] libavcodec/x86/vvc/Makefile
  • [DH] libavcodec/x86/vvc/vvc_mc.asm
  • [DH] libavcodec/x86/vvc/vvcdsp_init.c