Recherche avancée

Sur d’autres sites (10992)

• Anatomy of an optimization : H.264 deblocking

  26 mai 2010, par Dark Shikari — H.264, assembly, development, speed, x264

  As mentioned in the previous post, H.264 has an adaptive deblocking filter. But what exactly does that mean — and more importantly, what does it mean for performance ? And how can we make it as fast as possible ? In this post I’ll try to answer these questions, particularly in relation to my recent deblocking optimizations in x264.

  H.264′s deblocking filter has two steps : strength calculation and the actual filter. The first step calculates the parameters for the second step. The filter runs on all the edges in each macroblock. That’s 4 vertical edges of length 16 pixels and 4 horizontal edges of length 16 pixels. The vertical edges are filtered first, from left to right, then the horizontal edges, from top to bottom (order matters !). The leftmost edge is the one between the current macroblock and the left macroblock, while the topmost edge is the one between the current macroblock and the top macroblock.

  Here’s the formula for the strength calculation in progressive mode. The highest strength that applies is always selected.

  If we’re on the edge between an intra macroblock and any other macroblock : Strength 4
  If we’re on an internal edge of an intra macroblock : Strength 3
  If either side of a 4-pixel-long edge has residual data : Strength 2
  If the motion vectors on opposite sides of a 4-pixel-long edge are at least a pixel apart (in either x or y direction) or the reference frames aren’t the same : Strength 1
  Otherwise : Strength 0 (no deblocking)

  These values are then thrown into a lookup table depending on the quantizer : higher quantizers have stronger deblocking. Then the actual filter is run with the appropriate parameters. Note that Strength 4 is actually a special deblocking mode that performs a much stronger filter and affects more pixels.

  One can see somewhat intuitively why these strengths are chosen. The deblocker exists to get rid of sharp edges caused by the block-based nature of H.264, and so the strength depends on what exists that might cause such sharp edges. The strength calculation is a way to use existing data from the video stream to make better decisions during the deblocking process, improving compression and quality.

  Both the strength calculation and the actual filter (not described here) are very complex if naively implemented. The latter can be SIMD’d with not too much difficulty ; no H.264 decoder can get away with reasonable performance without such a thing. But what about optimizing the strength calculation ? A quick analysis shows that this can be beneficial as well.

  Since we have to check both horizontal and vertical edges, we have to check up to 32 pairs of coefficient counts (for residual), 16 pairs of reference frame indices, and 128 motion vector values (counting x and y as separate values). This is a lot of calculation ; a naive implementation can take 500-1000 clock cycles on a modern CPU. Of course, there’s a lot of shortcuts we can take. Here’s some examples :

  • If the macroblock uses the 8×8 transform, we only need to check 2 edges in each direction instead of 4, because we don’t deblock inside of the 8×8 blocks.
  • If the macroblock is a P-skip, we only have to check the first edge in each direction, since there’s guaranteed to be no motion vector differences, reference frame differences, or residual inside of the macroblock.
  • If the macroblock has no residual at all, we can skip that check.
  • If we know the partition type of the macroblock, we can do motion vector checks only along the edges of the partitions.
  • If the effective quantizer is so low that no deblocking would be performed no matter what, don’t bother calculating the strength.

  But even all of this doesn’t save us from ourselves. We still have to iterate over a ton of edges, checking each one. Stuff like the partition-checking logic greatly complicates the code and adds overhead even as it reduces the number of checks. And in many cases decoupling the checks to add such logic will make it slower : if the checks are coupled, we can avoid doing a motion vector check if there’s residual, since Strength 2 overrides Strength 1.

  But wait. What if we could do this in SIMD, just like the actual loopfilter itself ? Sure, it seems more of a problem for C code than assembly, but there aren’t any obvious things in the way. Many years ago, Loren Merritt (pengvado) wrote the first SIMD implementation that I know of (for ffmpeg’s decoder) ; it is quite fast, so I decided to work on porting the idea to x264 to see if we could eke out a bit more speed here as well.

  Before I go over what I had to do to make this change, let me first describe how deblocking is implemented in x264. Since the filter is a loopfilter, it acts “in loop” and must be done in both the encoder and decoder — hence why x264 has it too, not just decoders. At the end of encoding one row of macroblocks, x264 goes back and deblocks the row, then performs half-pixel interpolation for use in encoding the next frame.

  We do it per-row for reasons of cache coherency : deblocking accesses a lot of pixels and a lot of code that wouldn’t otherwise be used, so it’s more efficient to do it in a single pass as opposed to deblocking each macroblock immediately after encoding. Then half-pixel interpolation can immediately re-use the resulting data.

  Now to the change. First, I modified deblocking to implement a subset of the macroblock_cache_load function : spend an extra bit of effort loading the necessary data into a data structure which is much simpler to address — as an assembly implementation would need (x264_macroblock_cache_load_deblock). Then I massively cleaned up deblocking to move all of the core strength-calculation logic into a single, small function that could be converted to assembly (deblock_strength_c). Finally, I wrote the assembly functions and worked with Loren to optimize them. Here’s the result.

  And the timings for the resulting assembly function on my Core i7, in cycles :

  deblock_strength_c : 309
  deblock_strength_mmx : 79
  deblock_strength_sse2 : 37
  deblock_strength_ssse3 : 33

  Now that is a seriously nice improvement. 33 cycles on average to perform that many comparisons–that’s absurdly low, especially considering the SIMD takes no branchy shortcuts : it always checks every single edge ! I walked over to my performance chart and happily crossed off a box.

  But I had a hunch that I could do better. Remember, as mentioned earlier, we’re reloading all that data back into our data structures in order to address it. This isn’t that slow, but takes enough time to significantly cut down on the gain of the assembly code. And worse, less than a row ago, all this data was in the correct place to be used (when we just finished encoding the macroblock) ! But if we did the deblocking right after encoding each macroblock, the cache issues would make it too slow to be worth it (yes, I tested this). So I went back to other things, a bit annoyed that I couldn’t get the full benefit of the changes.

  Then, yesterday, I was talking with Pascal, a former Xvid dev and current video hacker over at Google, about various possible x264 optimizations. He had seen my deblocking changes and we discussed that a bit as well. Then two lines hit me like a pile of bricks :

  <_skal_> tried computing the strength at least ?
  <_skal_> while it’s fresh

  Why hadn’t I thought of that ? Do the strength calculation immediately after encoding each macroblock, save the result, and then go pick it up later for the main deblocking filter. Then we can use the data right there and then for strength calculation, but we don’t have to do the whole deblock process until later.

  I went and implemented it and, after working my way through a horde of bugs, eventually got a working implementation. A big catch was that of slices : deblocking normally acts between slices even though normal encoding does not, so I had to perform extra munging to get that to work. By midday today I was able to go cross yet another box off on the performance chart. And now it’s committed.

  Sometimes chatting for 10 minutes with another developer is enough to spot the idea that your brain somehow managed to miss for nearly a straight week.

  NB : the performance chart is on a specific test clip at a specific set of settings (super fast settings) relevant to the company I work at, so it isn’t accurate nor complete for, say, default settings.

  Update : Here’s a higher resolution version of the current chart, as requested in the comments.
  

  http://git.videolan.org/?p=x264.git ;a=commit ;h=b9ec3ea27812288485329ac7771143021cd4917b

• How to sell Piwik services without any confusion ?

  10 octobre 2017, par InnoCraft — Plugins

  As you may know, Piwik is a Free software under the GPL license which guarantees you :

  • The freedom to run the program for any purpose.
  • The freedom to study how it works and change it.
  • The freedom to improve the program, and release your changes.
  • The freedom to redistribute it under the GPL license, and to sell it if you wish.

  In this article we will focus on the Free aspect of Piwik, which is how to rebrand Piwik, how to offer your clients a better experience, and possibly how to make a profit from it ?

  How to sell Piwik services as an agency ?

  As a web analytics software, Piwik is often installed by web agencies when it comes to designing a brand new website for a given customer.
  Most of the time agencies are using Piwik for the following reasons :

  • free of charge
  • data ownership
  • user privacy compliance
  • feature rich while easy to use
  • open source

  Most of the agencies are charging their customers for the installation process, tracking code implementation, analysing reports to get insights about users… but do you know that you could also sell the software as your own brand ? This is where the “White Label” plugin, developed by the InnoCraft company, comes into play.

  White labelling for Piwik

  Creating a “white label” plugin came into the mind of InnoCraft founders when they realized that on any modern Piwik installation, the following components were visible :

  • Piwik branded widgets within the dashboards
  • Piwik marketplace plugin teasers on the admin page
  • Piwik help and support pages
  • the “Piwik” word in general
  • Piwik Mobile app banners

  

  Example of Piwik branded widgets

  In order to remove all those mentions of Piwik and to start selling this web analytics under your own name, you can either hack Piwik on your own (it is going to take you some precious time and money) or have a look at the White Label plugin on the marketplace where InnoCraft has solved all the challenges already for you.

  The White Label plugin is straightforward. Once downloaded and installed, you will have access to a dedicated interface where you will be able to change the Piwik name by a new custom brand of your choice :

  

  Piwik White Label settings

  Once you click Save, all “Piwik” mentions will be substituted by your company name/service :

  

  Here the Piwik version is changed by the name of the company

  How to make your installation even more customized ?

  Few Piwik users know about this trick, but since 2014 the Piwik templates can be customized through Themes. You are free to design your own template, installing existing ones, or even monetize them through the marketplace :

  

  A simple example of how Piwik can be easily customized, here fonts and colours are changed

  If you want to know how you can tweak your existing template and make it match your brand and image, just follow our theme documentation. A simple theme with your colors can be built in a few minutes simply by defining different color codes. You can also browse the public themes on the Marketplace.

  Get White Label for Piwik

  Tell us your story

  If you are an agency or any business related in selling Piwik services, we recommend having a look at our FAQ for rebranding, selling, reusing, re-licensing, and including Piwik in my offering. Are you interested or already re-selling Piwik services ? We would love to hear your story and write a blog post about it.

  Write for Piwik

  Do not hesitate to contact the Piwik core team, we’re looking forward to hearing from you.

• How to make your plugin multilingual – Introducing the Piwik Platform

  29 octobre 2014, par Thomas Steur — Development

  This is the next post of our blog series where we introduce the capabilities of the Piwik platform (our previous post was Generating test data – Introducing the Piwik Platform). This time you’ll learn how to equip your plugin with translations. Users of your plugin will be very thankful that they can use and translate the plugin in their language !

  Getting started

  In this post, we assume that you have already set up your development environment and created a plugin. If not, visit the Piwik Developer Zone where you’ll find the tutorial Setting up Piwik and other Guides that help you to develop a plugin.

  Managing translations

  Piwik is available in over 50 languages and comes with many translations. The core itself provides some basic translations for words like “Visitor” and “Help”. They are stored in the directory /lang. In addition, each plugin can provide its own translations for wordings that are used in this plugin. They are located in /plugins/*/lang. In those directories you’ll find one JSON file for each language. Each language file consists in turn of tokens that belong to a group.

  {
  
      "MyPlugin":{
  
          "BlogPost": "Blog post",
  
          "MyToken": "My translation",
  
          "InteractionRate": "Interaction Rate"
  
      }
  
  }

  A group usually represents the name of a plugin, in this case “MyPlugin”. Within this group, all the tokens are listed on the left side and the related translations on the right side.

  Building a translation key

  As you will later see to actually translate a word or a sentence you’ll need to know the corresponding translation key. This key is built by combining a group and a token separated by an underscore. You can for instance use the key MyPlugin_BlogPost to get a translation of “Blog post”. Defining a new key is as easy as adding a new entry to the “MyPlugin” group.

  Providing default translations

  If a translation cannot be found then the English translation will be used as a default. Therefore, you should always provide a default translation in English for all keys in the file en.json (ie, /plugins/MyPlugin/lang/en.json).

  Adding translations for other languages

  This is as easy as creating new files in the lang subdirectory of your plugin. The filename consists of a 2 letter ISO 639-1 language code completed by the extension .json. This means German translations go into a file named de.json, French ones into a file named fr.json. To see a list of languages you can use have a look at the /lang directory.

  Reusing translations

  As mentioned Piwik comes with quite a lot of translations. You can and should reuse them but you are supposed to be aware that a translation key might be removed or renamed in the future. It is also possible that a translation key was added in a recent version and therefore is not available in older versions of Piwik. We do not currently announce any of such changes. Still, 99% of the translation keys do not change and it is therefore usually a good idea to reuse existing translations. Especially when you or your company would otherwise not be able to provide them. To find any existing translation keys go to Settings => Translation search in your Piwik installation. The menu item will only appear if the development mode is enabled.

  Translations in PHP

  Use the Piwik::translate() function to translate any text in PHP. Simply pass any existing translation key and you will get the translated text in the language of the current user in return. The English translation will be returned in case none for the current language exists.

  $translatedText = Piwik::translate('MyPlugin_BlogPost');

  Translations in Twig Templates

  To translate text in Twig templates, use the translate filter.

  {{ 'MyPlugin_BlogPost'|translate }}

  Contributing translations to Piwik

  Did you know you can contribute translations to Piwik ? In case you want to improve an existing translation, translate a missing one or add a new language go to Piwik Translations and sign up for an account. You won’t need any knowledge in development to do this.

  Advanced features

  Of course there are more useful things you can do with translations. For instance you can use placeholders like %s in your translations and you can use translations in JavaScript as well. In case you want to know more about those topics check out our Internationalization guide. Currently, this guide only covers translations but we will cover more topics like formatting numbers and handling currencies in the future.

  Congratulations, you have learnt how to make your plugin multilingual !

  If you have any feedback regarding our APIs or our guides in the Developer Zone feel free to send it to us.