Recherche avancée

Sur d’autres sites (11347)

• Neutral net or neutered

  4 juin 2013, par Mans — Law and liberty

  In recent weeks, a number of high-profile events, in the UK and elsewhere, have been quickly seized upon to promote a variety of schemes for monitoring or filtering Internet access. These proposals, despite their good intentions of protecting children or fighting terrorism, pose a serious threat to fundamental liberties. Although at a glance the ideas may seem like a reasonable price to pay for the prevention of some truly hideous crimes, there is more than first meets the eye. Internet regulation in any form whatsoever is the thin end of a wedge at whose other end we find severely restricted freedom of expression of the kind usually associated with oppressive dictatorships. Where the Internet was once a novelty, it now forms an integrated part of modern society ; regulating the Internet means regulating our lives.

  Terrorism

  Following the brutal murder of British soldier Lee Rigby in Woolwich, attempts were made in the UK to revive the controversial Communications Data Bill, also dubbed the snooper’s charter. The bill would give police and security services unfettered access to details (excluding content) of all digital communication in the UK without needing so much as a warrant.

  The powers afforded by the snooper’s charter would, the argument goes, enable police to prevent crimes such as the one witnessed in Woolwich. True or not, the proposal would, if implemented, also bring about infrastructure for snooping on anyone at any time for any purpose. Once available, the temptation may become strong to extend, little by little, the legal use of these abilities to cover ever more everyday activities, all in the name of crime prevention, of course.

  In the emotional aftermath of a gruesome act, anything with the promise of preventing it happening again may seem like a good idea. At times like these it is important, more than ever, to remain rational and carefully consider all the potential consequences of legislation, not only the intended ones.

  Hate speech

  Hand in hand with terrorism goes hate speech, preachings designed to inspire violence against people of some singled-out nation, race, or other group. Naturally, hate speech is often to be found on the Internet, where it can reach large audiences while the author remains relatively protected. Naturally, we would prefer for it not to exist.

  To fulfil the utopian desire of a clean Internet, some advocate mandatory filtering by Internet service providers and search engines to remove this unwanted content. Exactly how such censoring might be implemented is however rarely dwelt upon, much less the consequences inadvertent blocking of innocent material might have.

  Pornography

  Another common target of calls for filtering is pornography. While few object to the blocking of child pornography, at least in principle, the debate runs hotter when it comes to the legal variety. Pornography, it is claimed, promotes violence towards women and is immoral or generally offensive. As such it ought to be blocked in the name of the greater good.

  The conviction last week of paedophile Mark Bridger for the abduction and murder of five-year-old April Jones renewed the debate about filtering of pornography in the UK ; his laptop was found to contain child pornography. John Carr of the UK government’s Council on Child Internet Safety went so far as suggesting a default blocking of all pornography, access being granted to an Internet user only once he or she had registered with some unspecified entity. Registering people wishing only to access perfectly legal material is not something we do in a democracy.

  The reality is that Google and other major search engines already remove illegal images from search results and report them to the appropriate authorities. In the UK, the Internet Watch Foundation, a non-government organisation, maintains a blacklist of what it deems ‘potentially criminal’ content, and many Internet service providers block access based on this list.

  While well-intentioned, the IWF and its blacklist should raise some concerns. Firstly, a vigilante organisation operating in secret and with no government oversight acting as the nation’s morality police has serious implications for freedom of speech. Secondly, the blocks imposed are sometimes more far-reaching than intended. In one incident, an attempt to block the cover image of the Scorpions album Virgin Killer hosted by Wikipedia (in itself a dubious decision) rendered the entire related article inaccessible as well as interfered with editing.

  Net neutrality

  Content filtering, or more precisely the lack thereof, is central to the concept of net neutrality. Usually discussed in the context of Internet service providers, this is the principle that the user should have equal, unfiltered access to all content. As a consequence, ISPs should not be held responsible for the content they deliver. Compare this to how the postal system works.

  The current debate shows that the principle of net neutrality is important not only at the ISP level, but should also include providers of essential services on the Internet. This means search engines should not be responsible for or be required to filter results, email hosts should not be required to scan users’ messages, and so on. No mandatory censoring can be effective without infringing the essential liberties of freedom of speech and press.

  Social networks operate in a less well-defined space. They are clearly not part of the essential Internet infrastructure, and they require that users sign up and agree to their terms and conditions. Because of this, they can include restrictions that would be unacceptable for the Internet as a whole. At the same time, social networks are growing in importance as means of communication between people, and as such they have a moral obligation to act fairly and apply their rules in a transparent manner.

  Facebook was recently under fire, accused of not taking sufficient measures to curb ‘hate speech,’ particularly against women. Eventually they pledged to review their policies and methods, and reducing the proliferation of such content will surely make the web a better place. Nevertheless, one must ask how Facebook (or another social network) might react to similar pressure from, say, a religious group demanding removal of ‘blasphemous’ content. What about demands from a foreign government ? Only yesterday, the Turkish prime minister Erdogan branded Twitter ‘a plague’ in a TV interview.

  Rather than impose upon Internet companies the burden of law enforcement, we should provide them the latitude to set their own policies as well as the legal confidence to stand firm in the face of unreasonable demands. The usual market forces will promote those acting responsibly.

  Further reading

  • Tory-Labour pact could save data bill, says Lord Howard
  • Internet companies warn May over ‘snooper’s charter’
  • Snooper’s charter ‘should be replaced by strengthening of existing powers’
  • Exclusive : ‘Snooper’s charter’ would not have prevented Woolwich attack, says MI5
  • Search engines urged to block more online porn sites
  • Why technology must be the solution to child abuse material online
  • Google must take more action to police explicit content, says Vince Cable
  • Facebook bows to campaign groups over ‘hate speech’
  • Facebook sexism campaign attracts thousands online
  • Türkischer Ministerpräsident : Twitter ist eine Plage
  • Valls : « La traque sur Internet doit être une priorité pour nous »
  • La Cnil, futur juge d’Internet
  • “National security matter” : Third agency caught unilaterally blocking web sites

• Developing A Shader-Based Video Codec

  22 juin 2013, par Multimedia Mike — Outlandish Brainstorms

  Early last month, this thing called ORBX.js was in the news. It ostensibly has something to do with streaming video and codec technology, which naturally catches my interest. The hype was kicked off by Mozilla honcho Brendan Eich when he posted an article asserting that HD video decoding could be entirely performed in JavaScript. We’ve seen this kind of thing before using Broadway– an H.264 decoder implemented entirely in JS. But that exposes some very obvious limitations (notably CPU usage).

  But this new video codec promises 1080p HD playback directly in JavaScript which is a lofty claim. How could it possibly do this ? I got the impression that performance was achieved using WebGL, an extension which allows JavaScript access to accelerated 3D graphics hardware. Browsing through the conversations surrounding the ORBX.js announcement, I found this confirmation from Eich himself :

  You’re right that WebGL does heavy lifting.

  As of this writing, ORBX.js remains some kind of private tech demo. If there were a public demo available, it would necessarily be easy to reverse engineer the downloadable JavaScript decoder.

  But the announcement was enough to make me wonder how it could be possible to create a video codec which effectively leverages 3D hardware.

  Prior Art
  In theorizing about this, it continually occurs to me that I can’t possibly be the first person to attempt to do this (or the ORBX.js people, for that matter). In googling on the matter, I found various forums and Q&A posts where people asked if it were possible to, e.g., accelerate JPEG decoding and presentation using 3D hardware, with no answers. I also found a blog post which describes a plan to use 3D hardware to accelerate VP8 video decoding. It was a project done under the banner of Google’s Summer of Code in 2011, though I’m not sure which open source group mentored the effort. The project did not end up producing the shader-based VP8 codec originally chartered but mentions that “The ‘client side’ of the VP8 VDPAU implementation is working and is currently being reviewed by the libvdpau maintainers.” I’m not sure what that means. Perhaps it includes modifications to the public API that supports VP8, but is waiting for the underlying hardware to actually implement VP8 decoding blocks in hardware.

  What’s So Hard About This ?
  Video decoding is a computationally intensive task. GPUs are known to be really awesome at chewing through computationally intensive tasks. So why aren’t GPUs a natural fit for decoding video codecs ?

  Generally, it boils down to parallelism, or lack of opportunities thereof. GPUs are really good at doing the exact same operations over lots of data at once. The problem is that decoding compressed video usually requires multiple phases that cannot be parallelized, and the individual phases often cannot be parallelized. In strictly mathematical terms, a compressed data stream will need to be decoded by applying a function f(x) over each data element, x₀ .. x_n. However, the function relies on having applied the function to the previous data element, i.e. :

  f(xn) = f(f(xn-1))
  

  What happens when you try to parallelize such an algorithm ? Temporal rifts in the space/time continuum, if you’re in a Star Trek episode. If you’re in the real world, you’ll get incorrect, unusuable data as the parallel computation is seeded with a bunch of invalid data at multiple points (which is illustrated in some of the pictures in the aforementioned blog post about accelerated VP8).

  Example : JPEG
  Let’s take a very general look at the various stages involved in decoding the ubiquitous JPEG format :

  
  
  

  What are the opportunities to parallelize these various phases ?
  

  • Huffman decoding (run length decoding and zig-zag reordering is assumed to be rolled into this phase) : not many opportunities for parallelizing the various Huffman formats out there, including this one. Decoding most Huffman streams is necessarily a sequential operation. I once hypothesized that it would be possible to engineer a codec to achieve some parallelism during the entropy decoding phase, and later found that On2′s VP8 codec employs the scheme. However, such a scheme is unlikely to break down to such a fine level that WebGL would require.
  • Reverse DC prediction : JPEG — and many other codecs — doesn’t store full DC coefficients. It stores differences in successive DC coefficients. Reversing this process can’t be parallelized. See the discussion in the previous section.
  • Dequantize coefficients : This could be very parallelized. It should be noted that software decoders often don’t dequantize all coefficients. Many coefficients are 0 and it’s a waste of a multiplication operation to dequantize. Thus, this phase is sometimes rolled into the Huffman decoding phase.
  • Invert discrete cosine transform : This seems like it could be highly parallelizable. I will be exploring this further in this post.
  • Convert YUV -> RGB for final display : This is a well-established use case for 3D acceleration.

  Crash Course in 3D Shaders and Humility
  So I wanted to see if I could accelerate some parts of JPEG decoding using something called shaders. I made an effort to understand 3D programming and its associated math throughout the 1990s but 3D technology left me behind a very long time ago while I got mixed up in this multimedia stuff. So I plowed through a few books concerning WebGL (thanks to my new Safari Books Online subscription). After I learned enough about WebGL/JS to be dangerous and just enough about shader programming to be absolutely lethal, I set out to try my hand at optimizing IDCT using shaders.

  Here’s my extremely high level (and probably hopelessly naive) view of the modern GPU shader programming model :

  
  
  

  The WebGL program written in JavaScript drives the show. It sends a set of vertices into the WebGL system and each vertex is processed through a vertex shader. Then, each pixel that falls within a set of vertices is sent through a fragment shader to compute the final pixel attributes (R, G, B, and alpha value). Another consideration is textures : This is data that the program uploads to GPU memory which can be accessed programmatically by the shaders).

  These shaders (vertex and fragment) are key to the GPU’s programmability. How are they programmed ? Using a special C-like shading language. Thought I : “C-like language ? I know C ! I should be able to master this in short order !” So I charged forward with my assumptions and proceeded to get smacked down repeatedly by the overall programming paradigm. I came to recognize this as a variation of the scientific method : Develop a hypothesis– in my case, a mental model of how the system works ; develop an experiment (short program) to prove or disprove the model ; realize something fundamental that I was overlooking ; formulate new hypothesis and repeat.

  First Approach : Vertex Workhorse
  My first pitch goes like this :

  • Upload DCT coefficients to GPU memory in the form of textures
  • Program a vertex mesh that encapsulates 16×16 macroblocks
  • Distribute the IDCT effort among multiple vertex shaders
  • Pass transformed Y, U, and V blocks to fragment shader which will convert the samples to RGB

  So the idea is that decoding of 16×16 macroblocks is parallelized. A macroblock embodies 6 blocks :

  
  
  

  It would be nice to process one of these 6 blocks in each vertex. But that means drawing a square with 6 vertices. How do you do that ? I eventually realized that drawing a square with 6 vertices is the recommended method for drawing a square on 3D hardware. Using 2 triangles, each with 3 vertices (0, 1, 2 ; 3, 4, 5) :

  
  
  

  A vertex shader knows which (x, y) coordinates it has been assigned, so it could figure out which sections of coefficients it needs to access within the textures. But how would a vertex shader know which of the 6 blocks it should process ? Solution : Misappropriate the vertex’s z coordinate. It’s not used for anything else in this case.

  So I set all of that up. Then I hit a new roadblock : How to get the reconstructed Y, U, and V samples transported to the fragment shader ? I have found that communicating between shaders is quite difficult. Texture memory ? WebGL doesn’t allow shaders to write back to texture memory ; shaders can only read it. The standard way to communicate data from a vertex shader to a fragment shader is to declare variables as “varying”. Up until this point, I knew about varying variables but there was something I didn’t quite understand about them and it nagged at me : If 3 different executions of a vertex shader set 3 different values to a varying variable, what value is passed to the fragment shader ?

  It turns out that the varying variable varies, which means that the GPU passes interpolated values to each fragment shader invocation. This completely destroys this idea.

  Second Idea : Vertex Workhorse, Take 2
  The revised pitch is to work around the interpolation issue by just having each vertex shader invocation performs all 6 block transforms. That seems like a lot of redundant. However, I figured out that I can draw a square with only 4 vertices by arranging them in an ‘N’ pattern and asking WebGL to draw a TRIANGLE_STRIP instead of TRIANGLES. Now it’s only doing the 4x the extra work, and not 6x. GPUs are supposed to be great at this type of work, so it shouldn’t matter, right ?

  I wired up an experiment and then ran into a new problem : While I was able to transform a block (or at least pretend to), and load up a varying array (that wouldn’t vary since all vertex shaders wrote the same values) to transmit to the fragment shader, the fragment shader can’t access specific values within the varying block. To clarify, a WebGL shader can use a constant value — or a value that can be evaluated as a constant at compile time — to index into arrays ; a WebGL shader can not compute an index into an array. Per my reading, this is a WebGL security consideration and the limitation may not be present in other OpenGL(-ES) implementations.

  Not Giving Up Yet : Choking The Fragment Shader
  You might want to be sitting down for this pitch :

  • Vertex shader only interpolates texture coordinates to transmit to fragment shader
  • Fragment shader performs IDCT for a single Y sample, U sample, and V sample
  • Fragment shader converts YUV -> RGB

  Seems straightforward enough. However, that step concerning IDCT for Y, U, and V entails a gargantuan number of operations. When computing the IDCT for an entire block of samples, it’s possible to leverage a lot of redundancy in the math which equates to far fewer overall operations. If you absolutely have to compute each sample individually, for an 8×8 block, that requires 64 multiplication/accumulation (MAC) operations per sample. For 3 color planes, and including a few extra multiplications involved in the RGB conversion, that tallies up to about 200 MACs per pixel. Then there’s the fact that this approach means a 4x redundant operations on the color planes.

  It’s crazy, but I just want to see if it can be done. My approach is to pre-compute a pile of IDCT constants in the JavaScript and transmit them to the fragment shader via uniform variables. For a first order optimization, the IDCT constants are formatted as 4-element vectors. This allows computing 16 dot products rather than 64 individual multiplication/addition operations. Ideally, GPU hardware executes the dot products faster (and there is also the possibility of lining these calculations up as matrices).

  I can report that I actually got a sample correctly transformed using this approach. Just one sample, through. Then I ran into some new problems :

  Problem #1 : Computing sample #1 vs. sample #0 requires a different table of 64 IDCT constants. Okay, so create a long table of 64 * 64 IDCT constants. However, this suffers from the same problem as seen in the previous approach : I can’t dynamically compute the index into this array. What’s the alternative ? Maintain 64 separate named arrays and implement 64 branches, when branching of any kind is ill-advised in shader programming to begin with ? I started to go down this path until I ran into…

  Problem #2 : Shaders can only be so large. 64 * 64 floats (4 bytes each) requires 16 kbytes of data and this well exceeds the amount of shader storage that I can assume is allowed. That brings this path of exploration to a screeching halt.

  Further Brainstorming
  I suppose I could forgo pre-computing the constants and directly compute the IDCT for each sample which would entail lots more multiplications as well as 128 cosine calculations per sample (384 considering all 3 color planes). I’m a little stuck with the transform idea right now. Maybe there are some other transforms I could try.

  Another idea would be vector quantization. What little ORBX.js literature is available indicates that there is a method to allow real-time streaming but that it requires GPU assistance to yield enough horsepower to make it feasible. When I think of such severe asymmetry between compression and decompression, my mind drifts towards VQ algorithms. As I come to understand the benefits and limitations of GPU acceleration, I think I can envision a way that something similar to SVQ1, with its copious, hierarchical vector tables stored as textures, could be implemented using shaders.

  So far, this all pertains to intra-coded video frames. What about opportunities for inter-coded frames ? The only approach that I can envision here is to use WebGL’s readPixels() function to fetch the rasterized frame out of the GPU, and then upload it again as a new texture which a new frame processing pipeline could reference. Whether this idea is plausible would require some profiling.

  Using interframes in such a manner seems to imply that the entire codec would need to operate in RGB space and not YUV.

  Conclusions
  The people behind ORBX.js have apparently figured out a way to create a shader-based video codec. I have yet to even begin to reason out a plausible approach. However, I’m glad I did this exercise since I have finally broken through my ignorance regarding modern GPU shader programming. It’s nice to have a topic like multimedia that allows me a jumping-off point to explore other areas.

• Revision 450c7b57a8 : Only do metrics on cropped (visible) area of picture. The part where we align i

  10 juin 2013, par Ronald S. Bultje

  Changed Paths :
   Modify /vp9/encoder/vp9_onyx_if.c

  
   Modify /vp9/encoder/vp9_ssim.c

  
   Modify /vpx_scale/generic/yv12config.c

  
   Modify /vpx_scale/yv12config.h

  
  
  Only do metrics on cropped (visible) area of picture.

  The part where we align it by 8 or 16 is an implementation detail that
  shouldn't matter to the outside world.

  Change-Id : I9edd6f08b51b31c839c0ea91f767640bccb08d53