Slashdot Mirror

← Back to Stories (view on slashdot.org)

Wolfenstein Ray Traced and Anti-Aliased, At 1080p

Posted by timothy on from the sounds-like-an-in-n'-out-burger-order dept.

An anonymous reader writes "After Intel displayed their research demo Wolfenstein: Ray Traced on Tablets, the latest progress at IDF focuses on high(est)-end gaming now running at 1080p. Besides image-based post-processing (HDR, Depth of Field) there is now also an implementation of a smart way of calculating anti-aliasing through using mesh IDs and normals and applying adaptive 16x supersampling. All that is powered by the 'cloud,' consisting of a server that holds eight Knights Ferry cards (total of 256 cores / 1024 threads). A lot of hardware, but the next iteration of the 'Many Integrated Core' (MIC) architecture, named Knights Corner (and featuring 50+ cores), might be just around the corner."

158 comments

  1. first ray trace by russ1337 · · Score: 2

    first ray trace...

    now where is a decent link.

    1. Re:first ray trace by Anonymous Coward · · Score: 0

      I was about to say the same thing. I bounced through 3 slashdot articles before I reached a "Problem Loading Page" error.

    2. Re:first ray trace by SteelAngel · · Score: 1

      What is up with this? Has Slashdot become so incestuous that we have to backlink through 5 articles to actually get to a real article which either won't load or doesn't show the pretty pictures?

    3. Re:first ray trace by Anonymous Coward · · Score: 1

      cache:http://blogs.intel.com/research/2011/09/wolfenstein_gets_ray_traced_-_2.php

      Oh, look, there's something Bing can't do.

    4. Re:first ray trace by suso · · Score: 3, Funny

      That was like the ultimate combination of keywords on slashdot. That server had no chance.

    5. Re:first ray trace by Dahamma · · Score: 1

      Mostly useless, though. None of the image links work...

    6. Re:first ray trace by TheRaven64 · · Score: 2

      On the other hand, the wayback machine's version does have working images. And it doesn't use your page view to harvest information about you.

      --
      I am TheRaven on Soylent News
    7. Re:first ray trace by im_thatoneguy · · Score: 2

      Thanks to an AC down page:

      http://software.intel.com/en-us/videos/cloud-based-ray-tracing-on-handheld-devices-at-researchintel-days-2011/

    8. Re:first ray trace by Anonymous Coward · · Score: 0

      But has been slashdotted....

    9. Re:first ray trace by VGPowerlord · · Score: 1

      On the other hand, the wayback machine's version does have working images. And it doesn't use your page view to harvest information about you.

      Except that's the first article from June rather than the second article from September.

      --
      GLaDOS for President 2016! "Well here we are again. It's always such a pleasure." -- GLaDOS, 2011
    10. Re:first ray trace by Jmc23 · · Score: 1

      Do you even know what you're linking to? Try again this time put some effort into it.

      --
      Don't complain about syntax, grammar, or spelling. There is no.hell like input on android.
    11. Re:first ray trace by Anonymous Coward · · Score: 0

      http://www.youtube.com/watch?feature=player_embedded&v=XVZDH15TRro

      A video about Wolfenstein, narrated by a German engineer, and posted by on 9/11.

    12. Re:first ray trace by Anonymous Coward · · Score: 1

      Another IDF has started and we are excited to show our latest progress. Since previous demos we enhanced our cloud-based setup that was using four Knights Ferry cards as the (Intel MIC) as the "cloud" to now run Wolfenstein: Ray Traced at even eight cards in a single machine. In order to utilize the huge amount of horse power we are now running our demo for the first time in 1080p.

      8KNF_01.jpg 8KNF_02.jpg

      As additional eye-candy we included several post processing special effects (thanks to Ben Segovia). Just to clarify: those are not specific to ray tracing and have been seen in some games already. They are operating on the pixels of the rendered image (not on the 3D scene) - in our case directly on the Knights Ferry card. They can improve the perception of the rendered scene dramatically.

      Depth of Field: The effect is well known to photographers. If we want the spectator to focus on a certain area in the picture then the less relevant parts can be blurred. Therefore the object of interest is still sharp and will attract the main attention.

      02_regular.jpg 02_regular_depth_of_field.jpg
      Depth of field on/off (3% performance difference)

      HDR Bloom: If in reality we leave from a dark room into the bright outside our eyes are adjusting over a few seconds to the new brightness. The same can also be observed with digital (video) cameras that mimic this behavior and adjust the brightness spectrum to a pleasantly looking image. While doing this cameras might produce a bloom that can also "bleed" into other objects.

      01_bright.jpg 01_bright_hdr.jpg
      Overbright scene with HDR on/off (2% performance difference)

      01_bloom.jpg
      Bloom effect

      Inter-lens reflections: While camera manufacturers are trying to avoid lens flares computer games and movies are often adding them as an artistic element. In this implementation several smaller sized version of the image, shifted to a specific color (e.g. green, blue and orange) will be blended into the original image.

      01_bright_hdr_lens_reflection.jpg
      Subtle (image-based) inter-lens reflections (0.1% performance difference)

      Another step we are doing for the first time is a smart way of anti-aliasing (thanks to Ingo Wald and Ben Segovia). There are different possibilities on how to do anti-aliasing. Most of them work pretty much brute-force and therefore invest additional calculations in areas where the improvement might not be noticeable. Our implementation will be applied after the image has been rendered. As ray tracing easily allows to just shoot a few rays for refinement we are analyzing each pixel depending on two factors if it requires more anti-aliasing:

      The angle of the polygon that got hit at that pixel
      The polygon mesh ID of that object

      If there is a high enough variation in the angle or a different mesh ID is found we will shoot 16 more rays (supersampling) for that specific pixel and average the resulting color into that pixel. (Please note that the difference can be seen best in the full-sized images that appear after clicking the thumbnails.)

      03_jaggies.jpg
      Courtyard view: Smart Anti-Aliasing off

      03_jaggies_antialiasing.jpg
      Courtyard view: Smart Anti-Aliasing on (59% performance difference)

      04_jaggies.jpg
      Close-up on cable: Smart Anti-Aliasing off

      04_jaggies_antialiasing.jpg
      Close-up on cable: Smart Anti-Aliasing on (32% performance difference)

      For future implementations more criteria like the color of the pixel (e.g. imagine an almost black spot in the picture - aliasing will not be noticeable here) or the color between neighboring pixels could be added. Further before comparing those

    13. Re:first ray trace by ikkonoishi · · Score: 2

      Here is an earlier video showing the game.
      http://www.youtube.com/watch?v=XVZDH15TRro

    14. Re:first ray trace by Anonymous Coward · · Score: 0

      Please go back on your meds.

    15. Re:first ray trace by V!NCENT · · Score: 1

      www.youtube.com
      searching for wolfenstein ray tracing
      sort by upload date
      first video being a knights demonstration
      link: http://www.youtube.com/watch?v=p0PJjC-JLt0

      --
      Here be signatures
    16. Re:first ray trace by Anonymous Coward · · Score: 0

      Here is an earlier video showing the game.
      http://www.youtube.com/watch?v=XVZDH15TRro

      Real time ray tracing is neat from a pure tech point of view (although it appears they have achieved it by throwing monster CPU power at it rather than any smart new algorithms [or maybe they did both]), but I must poo-poo Intel's marketing machine for trying to pimp this as game tech of the future.

      Unless EA releases SimChandelier, or Rockstar makes Grand Wash Auto, I'm not likely to be mashing my virtual eyeballs right up into an ornate light fixture or admiring the implausibly reflective finish of a Duesenberg. Apart from the reflective car, the rest of the graphics awfully mundane.

  2. Hmm... by Lyrata · · Score: 1

    Slashdotted already? I think not!

    --
    50,000 characters used to live here.
    1. Re:Hmm... by somersault · · Score: 1

      Those feebs! They are pathetic.

      --
      which is totally what she said
    2. Re:Hmm... by Anonymous Coward · · Score: 0

      Cower some more behind your chosen MichaelKristopeit based pseudonyms. You're completely pathetic.

    3. Re:Hmm... by DrXym · · Score: 3, Funny

      The site is too busy ray tracing to service requests.

    4. Re:Hmm... by Anonymous Coward · · Score: 0

      It's way more likely that you're just someone pretending to be Michael Kristopeit, trying to get someone to go around his house and shoot him by being consistently moronic on the internet.

      The only people interested in posting under their real name online are people who actually want reasonable discourse, not people asking for a beating.

    5. Re:Hmm... by Anonymous Coward · · Score: 0

      Nope, he's real.

      The only reason I called him a "chosen MichaelKristopeit based pseudonym" is because I highly doubt his name really ends with a number. Much less a different one every time he posts.

      He's an idiot. But he's really Michael Kristopeit.

  3. Slashdotted? by Anonymous Coward · · Score: 0

    They should use one of the MIC architecture systems to host their website...

  4. Amazing by MrEricSir · · Score: 1

    Those giant pixels never looked better!

    --
    There's no -1 for "I don't get it."
    1. Re:Amazing by Anonymous Coward · · Score: 0

      It's the 2009 Wolfenstein http://en.wikipedia.org/wiki/Wolfenstein:_Ray_Traced ...dumbass

    2. Re:Amazing by MrEricSir · · Score: 1

      thats_the_joke.jpg

      --
      There's no -1 for "I don't get it."
    3. Re:Amazing by tehcyder · · Score: 1

      It's the 2009 Wolfenstein http://en.wikipedia.org/wiki/Wolfenstein:_Ray_Traced ...dumbass

      Who is going to care about a fucking reflection in a chandelier during a scene where you're shooting hot Nazi lesbian killers in leather bikinis (IIRCl)?

      --
      To have a right to do a thing is not at all the same as to be right in doing it
  5. Get some artists already by Goaway · · Score: 1

    I think Intel would find it easier to get people excited about this technology if they actually used it to render something that looked interesting, or at the very least looked good at all.

    1. Re:Get some artists already by Anonymous Coward · · Score: 0

      Intel is wooing game studios, not the public.

    2. Re:Get some artists already by Anonymous Coward · · Score: 0

      Yes, I don't understand why they don't do something like full radiosity or something that actually looks like realworld stuff like the renderers of several commercial offerings for 3d apps do, something like maxwell render? Than it would be cool. This wolfenstein raytracing stuff looks like shit.

    3. Re:Get some artists already by Goaway · · Score: 1

      Wooing them by showing them graphics that look worse than pretty much everything else on offer? How is that supposed to work out for them?

    4. Re:Get some artists already by im_thatoneguy · · Score: 2

      I think Intel is wooing the Wall Street Journal more than anyone else.

      Intel: "Look at these amazing graphics!"
      WSJ: "Wow! Raytraced you say?
      Intel: "Yeah the future!"
      WSJ: "Ooooo! Buy stock!"

    5. Re:Get some artists already by Lorkki · · Score: 1

      Agreed. These announcements would be a lot more interesting if the demo material didn't resemble special effects nightmares from the 90's.

    6. Re:Get some artists already by Twinbee · · Score: 1

      If they used proper global illumination, then there'd be a real change. It looks like no more than one or two bounces of light to me.

      --
      Why OpalCalc is the best Windows calc
  6. Slashdotted Intel by SMoynihan · · Score: 1

    Did we?? Neither this nor the previous version seem accessible...

    1. Re:Slashdotted Intel by blair1q · · Score: 1

      I think so. The irony is delightful.

  7. Ray Traced on Tables by skovnymfe · · Score: 1

    But it's not ray traced on tables, is it? It's ray traced on a 256 core system and then somehow displayed on a tablet. Or am I reading this summary completely backwards?

    1. Re:Ray Traced on Tables by Aladrin · · Score: 1

      The summary clearly says it's rendered in the cloud on 256 cores. That link should read: "Wolfenstein: Ray Traced" on Tablets.

      --
      "If you make people think they're thinking, they'll love you; But if you really make them think, they'll hate you." - DM
    2. Re:Ray Traced on Tables by Guspaz · · Score: 1

      So, in other words "OnLive but with a software raytracer on the server-side instead of a GPU."

  8. Raytraced or not by Osgeld · · Score: 0

    Its still subpar to a budget 360 title's visuals

    1. Re:Raytraced or not by blair1q · · Score: 1

      It's code and art that's 13 years older than any 360 title.

    2. Re:Raytraced or not by Osgeld · · Score: 0

      its based on return to castle wolfenstein not the original.

    3. Re:Raytraced or not by Anonymous Coward · · Score: 1

      The original Wolfenstein was a top-down stealth shooter.

    4. Re:Raytraced or not by blair1q · · Score: 1

      Okay. 5 years. But W3D is still based on engine tech and visual standards that are much older. And I'll call "shenanigans" on your "any." There are likely many Xbox 360 games that look like crap compared with this.

      And if Intel had a good-looking Xbox 360 title's source code, this box would out box that box by 359-1 at least.

  9. MIC, now with ALOT by Quartus486 · · Score: 2

    'Many Integrated Core'? Sounds like something from a parody. 'Many Integrated Core', with 'A Lot Of Thread'. They also come in a high-end version, 'Several Interesting Rate'. Abbreviated SIR MICALOT on Knights Corner...

    1. Re:MIC, now with ALOT by xMrFishx · · Score: 1

      Well I alot of funny.

    2. Re:MIC, now with ALOT by Anonymous Coward · · Score: 0

      SIR MICALOT?

      If they like big butts, then that would make perfect sense.

    3. Re:MIC, now with ALOT by elrous0 · · Score: 1

      Yeah, but it opens up the opportunity for them to make a lot of lame jokes about "Rocking the MIC."

      --
      SJW: Someone who has run out of real oppression, and has to fake it.
  10. Unable to connect by cyberspittle · · Score: 1

    Firefox can't establish a connection to the server at blogs.intel.com.

  11. Not even very good performance by gr8_phk · · Score: 1

    I can ray trace that at about 1FPS per core. Why do they need 256 cores? And who can play anything rendered in the cloud?

    1. Re:Not even very good performance by MozeeToby · · Score: 1

      Depends if the rendering server is halfway across the country or halfway across the house. I remember people talking a while back (7 years or so) about using a home server to do the number crunching and moving back towards thin clients to access it. Wireless N bandwidth and latencies are pretty good, with modern technology you could probably make the idea work. Offer a suite of products that play well together: a powerful and easily upgraded server, lightweight laptops, and tablets. If you could make the price right for the clients you could have a quite expensive server with a ton of horse power while still making it a cheaper option for families that often have 4+ computers running.

    2. Re:Not even very good performance by iYk6 · · Score: 1

      And who can play anything rendered in the cloud?

      One person at a time.

    3. Re:Not even very good performance by sonicmerlin · · Score: 1

      Subscribers of Onlive?

    4. Re:Not even very good performance by TheTyrannyOfForcedRe · · Score: 1

      You're statement is meaningless. What core are you talking about? A PIII core? An Atom core? A core on your shiny new i5 2600? The cores in Knights Whatever aka Larabee are nowhere near as powerful as the cores in your current desktop cpu.

      --
      "Liechtenstein is the world's largest producer of sausage casings, potassium storage units, and false teeth."
  12. Next - Ray-Traced Nethack by billstewart · · Score: 1

    UUUUUUUUU
    The umber hulk hits! - more
    The umber hulk hits! - more
    The umber hulk hits! - more
    You die - more

    --

    Bill Stewart
    New Fast-Compression-only CPR http://preview.tinyurl.com/dy575ks
    1. Re:Next - Ray-Traced Nethack by PylonHead · · Score: 4, Funny

      The ray bounces!
      The ray hits you!
      You die...

      --
      # (/.);;
      - : float -> float -> float =
    2. Re:Next - Ray-Traced Nethack by Anonymous Coward · · Score: 0

      I'd rather see ray-traced, 1080p Dwarf Fortress.
      It would be a great demo of the technology, what with all the hairy dorfs, zombie fish somehow capable of walking and computers the size of sky-scrapers to calculate 8+8.
      Oh and let's not forget the cats. Millions and millions of cats. It will be like that PS3 demo with the leave tornados, except cats... a cat tornado.
      All that... IN 3D! AWE!

    3. Re:Next - Ray-Traced Nethack by blair1q · · Score: 2

      It hits you! You're rooted in graphics system dogma.

    4. Re:Next - Ray-Traced Nethack by Bucky24 · · Score: 1

      That would be AWESOME.

      --
      All the world's a CPU, and all the men and women merely AI agents
    5. Re:Next - Ray-Traced Nethack by Thud457 · · Score: 1

      ok, I'll give you that the cat tornado would be awsome.
      Almost as much as pirates on flying sharks that are on fire that shoot fireballs.

      The the real market for this is for server farms for Progress Quest.

      --

      the preceding comment is my own and in no way reflects the opinion of the Joint Chiefs of Staff

    6. Re:Next - Ray-Traced Nethack by Anonymous Coward · · Score: 0

      Eat Ray

  13. Link to Video (not slashdotted yet) by Anonymous Coward · · Score: 2, Informative

    http://software.intel.com/en-us/videos/cloud-based-ray-tracing-on-handheld-devices-at-researchintel-days-2011/

  14. Side affects of ray tracing by sl4shd0rk · · Score: 4, Funny

    Intel is apparently running the ray tracing process on the same server their blog is on.

    --
    Join the Slashcott! Feb 10 thru Feb 17!
    1. Re:Side affects of ray tracing by blair1q · · Score: 4, Funny

      Their blog is ray-traced.

    2. Re:Side affects of ray tracing by Anonymous Coward · · Score: 0

      I ray-traced your mom.

      Then Snotty beamed her. Twice. She claims it was wonderful.

    3. Re:Side affects of ray tracing by tehcyder · · Score: 1

      Their blog is ray-traced.

      mod parent +1 awesome

      --
      To have a right to do a thing is not at all the same as to be right in doing it
  15. Google Cache Link by Nyder · · Score: 1, Flamebait

    https://webcache.googleusercontent.com/search?q=cache:hmhYOuzN3B4J:blogs.intel.com/research/2011/09/wolfenstein_gets_ray_traced_-_2.php+&cd=1&hl=en&ct=clnk&gl=us

    Here ya go.

    --
    Be seeing you...
    1. Re:Google Cache Link by Anonymous Coward · · Score: 0

      it has some nice pictures about the last generation of games. for example this one http://blogs.intel.com/research/assets_c/2011/09/01_bloom1.php

    2. Re:Google Cache Link by Anonymous Coward · · Score: 0

      Why is this marked as flamebait? I found his link to a cached version of the website quite helpful as the original link has been slashdotted...

    3. Re:Google Cache Link by FrootLoops · · Score: 1

      I was hoping it was just a misclick.

  16. Youtube link here. by Anonymous Coward · · Score: 1

    http://www.youtube.com/watch?v=XVZDH15TRro&feature=player_embedded

    1. Re:Youtube link here. by dingen · · Score: 1

      That's the old video from last year. Although the German Intel engineer is pretty funny to listen to, especially when he talks about "ze monsters".

      --
      Pretty good is actually pretty bad.
  17. Cluster = Cloud by HalAtWork · · Score: 1

    Ok, so cluster = cloud now? Even though they both serve very different purposes?

    --
    Twinstiq, game news
    1. Re:Cluster = Cloud by loufoque · · Score: 2

      *remote* cluster = cloud

    2. Re:Cluster = Cloud by MozeeToby · · Score: 1

      *remote* cluster = cloud = unacceptable latencies for gaming.

      The only way this concept works is if the rendering farm is running in a closet somewhere in your house.

    3. Re:Cluster = Cloud by Guspaz · · Score: 1

      OnLive made it work with acceptable latencies, but then they did it with a cheap GPU and not a 256-processor cluster.

    4. Re:Cluster = Cloud by MozeeToby · · Score: 1

      Acceptable or not depends on where you live and how good your ISP is. Personally, my mediocre cable internet regularly has latency in the 200s which is annoying enough trying to play online games, I can't imagine having that kind of latency for the basic I/O layer of the game. And that's not even at 12 midnight, when they decide to push out the schedule updates to every single cable box on their network simultaneously.

    5. Re:Cluster = Cloud by doogledog · · Score: 1

      Apparently so.

      From the video that someone linked to and may be somewhere in TFA:

      'But the calculations are not done on this device themselves, they're done in the cloud *air quotes*... which is over here' *points*
      I chuckled. And wanted to punch someone in marketing.

    6. Re:Cluster = Cloud by afidel · · Score: 1

      Uh, most modern GPU's have a lot more than 256 "cores", my fairly low end HD5750 has 720, a GTX 560 has 336 (yes a CUDA core and a SP are different, I know). These chips are the continuation of Larrabee which was meant as a GPU chip.

      --
      There are 4 boxes to use in the defense of liberty: soap, ballot, jury, ammo. Use in that order. Starting now.
    7. Re:Cluster = Cloud by __aavevi421 · · Score: 1

      The only way this concept works is if the rendering farm is running in a closet somewhere in your house.

      With liquid cooling, you could pipe it to the central heating system.

    8. Re:Cluster = Cloud by Guspaz · · Score: 2

      Sure, but a "core" in a GPU is far simpler than a "core" in a CPU, and Larrabee wasn't stripped down anywhere near that far. Larrabee was supposed to feature 32 cores in one package initially on a 45nm process, bumping it up to 48 on a later 32nm process. Intel is still on a 32nm process, so when they talk about a "256-core cluster", they're almost certainly talking about multiple systems; an 8-chip 32-core-per-chip system (or 4-chip 64-core) would not be a "cluster" in and of itself. And such a system does not sound cheap by any stretch of the imagination. Remember, Intel cancelled Larrabee because the performance, even with software rasterization, wasn't remotely competitive with modern GPUs, and software rasterization would be a heck of a lot faster than software ray tracing!

    9. Re:Cluster = Cloud by Amouth · · Score: 1

      personally i love that in the pictures of the box with the cards - they used a WD drive instead of an Intel drive in an Intel box..

      --
      '...if only "Jumping to a Conclusion" was an event in the Olympics.'
    10. Re:Cluster = Cloud by Guspaz · · Score: 1

      While this may be true in your particular case, many people are within the 1000 mile radius of an OnLive data center on a decent connection.

      People talk a lot about how the network latency would make the input lag to OnLive unbearable, but consider this: 50ms of latency gets you from Montreal to Dallas (~2800km), and GTA IV on the XBox 360 has 133-200ms of input lag despite being local. In fact, every console game that Eurogamer measured had at least 67ms of latency, and they claim that the average seemed to be about 133ms. Gamers are clearly willing to accept this latency (GTA IV, with latency higher than OnLive in many cases, is clearly a very popular game), making OnLive seem much more practical.

      I'm by no means close to an OnLive datacenter, or even in the same country (I live in Montreal, and the nearest OnLive datacenter is in D.C., if memory serves), and to me the latency would seem to be on par with a laggy console game. That is to say, not great, but no worse than I've seen with some console games. To me, the real issue with OnLive was the low bitrate; it looks OK (just OK) when there's no movement, but playing a match of UT3 on vehicles was unpleasant due to all detail being lost while in motion (and this on either a 50 meg down 14 meg up VDSL2 connection, or a 60 meg down 3 meg up cable line).

      The good news is that it's a lot easier to increase the bitrate of a video stream than it is to break the speed of light ;)

    11. Re:Cluster = Cloud by afidel · · Score: 1

      Fab42 is going to be 14nm and is being built right now, I assume they have lab equipment capable of the same so for a demo chip I can easily see them using that process node. Going from 48 cores on 32nm to 256 on 14nm doesn't seem all that incredible.

      --
      There are 4 boxes to use in the defense of liberty: soap, ballot, jury, ammo. Use in that order. Starting now.
    12. Re:Cluster = Cloud by wagnerrp · · Score: 1

      Why would schedule updates be sent individually over the internet, rather than simply broadcast to everyone on a spare channel? That just sounds like a hideously inefficient use of spectrum.

    13. Re:Cluster = Cloud by Guspaz · · Score: 1

      It would help if I had read the summary. They've got a single server with eight Knight Ferry cards, each having 32 cores. That's where they get their 256 cores from. And they're calling the single server a "cloud".

      What makes this most unimpressive is that nVidia has been making a GPU-accelerated real-time raytracing engine for years now (you can even download working demos), and before that they were selling a GPU-accelerated final-frame renderer (non-real-time raytracing). Intel is showing off in-house demos of stuff running on expensive hardware, while nVidia has been giving away the same thing to customers for years, and it's something that's actually out there that you can use. Heck, so far as I can tell, it's free.

    14. Re:Cluster = Cloud by wagnerrp · · Score: 1

      Actually, they are talking about one system. It's a custom server designed for GPU computing, and has 8 PCIe 2.0 x16 slots filling nearly the whole back side of the chassis. They're using 8 32-core cards to render the images and video.

      http://www.colfax-intl.com/ms_tesla.asp?M=102

    15. Re:Cluster = Cloud by Guspaz · · Score: 1

      So what's the advantage here? The committed an eight-card 256 core server just to render a Quake 3 era game with raytracing. nVidia has been giving away (for free, as far as I can tell) a CUDA-based real-time raytracing engine for their CUDA cards (including Tesla) for a few years now, and before then, they had a final-frame renderer (non-real-time raytracer) available that predates CUDA.

      If I can do with a $300-400 GPU in a $1000 computer what it takes Intel a massive custom-built server, what's the advantage of the Intel approach?

    16. Re:Cluster = Cloud by SuiteSisterMary · · Score: 1

      Ten years ago, I bought a P4, 1.7 ghz, 512 megs RAMBUS, several thousand dollars. Last weekend, I bought a laptop with a 4 core i5 processor for four hundred dollars. My work laptop has eight cores, i7. So yeah, today it takes a massive server. In five years, it takes a high end desktop. In ten years, it's standard beans.

      --
      Vintage computer games and RPG books available. Email me if you're interested.
    17. Re:Cluster = Cloud by jedwidz · · Score: 1

      You're generously assuming that the network latency will substitute for the local latency.

      More realistically, you'll get the baseline local latency of around 50-150ms, *plus* the network latency of let's say 50-150ms (don't forget more bandwidth means higher latency), and maybe some extra latency for processing the incoming video.

      (Not so sure about the last bit, but I guess you'll be transferring more data from system RAM to the GPU than usual. Normal video rendering performance isn't comparable since that benefits from more buffering and pipelining.)

      Anyway, all up you're looking at 100-300ms, which would garner it an *unplayable crap* rating from me 8-) (And yes, I'd apply that standard to console games as well.)

    18. Re:Cluster = Cloud by Anonymous Coward · · Score: 0

      And OnLive does it with way less operating cost.

      Knights Ferry is a 300W card. Eight of them plus the server adds up to about two hair-dryers worth of power. I don't think any cloud providers are going to get too excited at the idea of burning that much electricity for each connected user.

    19. Re:Cluster = Cloud by Guspaz · · Score: 1

      Right, but my point is that you don't need to wait five or ten years, you can buy a $400 graphics card that will do the same thing today.

    20. Re:Cluster = Cloud by smellotron · · Score: 1

      In fact, every console game that Eurogamer measured had at least 67ms of latency, and they claim that the average seemed to be about 133ms. Gamers are clearly willing to accept this latency...

      GTA players may be willing to put up with high latency, but that doesn't fly so well with button-combo-fighting games (Soul Calibur, Street Fighter both 67ms) or competitive FPS games (CoD:MW 67-84ms). Those games just will not work with the additional latency of remote rendering over the Internet. 50ms light speed one way becomes 100ms round trip minimum, and it dramatically increases the probability of packet loss (mo' bandwidth, mo' problems).

    21. Re:Cluster = Cloud by spongman · · Score: 1

      Ok, so cluster = cloud now? Even though they both serve very different purposes?

      no, a cluster is a bunch of machines working together. the 'cloud' is purely a means to acquire funding from ADHD investors.

      'fluffy' is the new 'shiny'

    22. Re:Cluster = Cloud by Anonymous Coward · · Score: 0

      For FPS games, latency above 100ms is really really bad. And if you can get it below 30ms, things just work a whole hell of a lot better in terms of feel / gameplay.

      Especially if you don't have auto-aim.

    23. Re:Cluster = Cloud by TheTyrannyOfForcedRe · · Score: 1

      The raytracing application is merely a demo. Real applications in the near term will take advantage of the fact that all of the cores on Intel's accelerator card are x86 compatible. The cores on a Nvidia graphics card are not x86 cores and probably never will be.

      With lots of x86 cores you can do interesting things like implement drivers that make your multi-core accelerator card visible to your OS as if they were real CPU cores. Imagine that you have Chrome open with 100 tabs. Chrome runs each tab in a separate process. Your Intel accelerator card with 50-256 x86 cores could be used to run Chrome processes, one process per core. All of a sudden your main CPU is no longer bogged down running flash and background javascript crap for each of your 100 open tabs.

      Over the long term, moores law suggests that these Intel x86 accelerator cards will have enough cores and fast enough cores to do graphics acceleration for games that is good enough and fast enough. Eventually, all of these multitudes of cores will come standard inside every Intel cpu, no "accelerator card" needed. Intel has done exactly this with current gpu technology on their current line of processors. Their graphics performance is sufficient for everyone except serious gamers.

      --
      "Liechtenstein is the world's largest producer of sausage casings, potassium storage units, and false teeth."
    24. Re:Cluster = Cloud by Guspaz · · Score: 1

      The raytracing application is merely a demo. Real applications in the near term will take advantage of the fact that all of the cores on Intel's accelerator card are x86 compatible. The cores on a Nvidia graphics card are not x86 cores and probably never will be.

      With lots of x86 cores you can do interesting things like implement drivers that make your multi-core accelerator card visible to your OS as if they were real CPU cores. Imagine that you have Chrome open with 100 tabs. Chrome runs each tab in a separate process. Your Intel accelerator card with 50-256 x86 cores could be used to run Chrome processes, one process per core. All of a sudden your main CPU is no longer bogged down running flash and background javascript crap for each of your 100 open tabs.

      If there was any real benefit to this, we'd see dual-processor consumer motherboards; those died off in the Pentium II era. These days, with a modern quad-core processor, your "main CPU" is no longer bogged down with background javascript or running flash; that's already handled by different cores.

      Over the long term, moores law suggests that these Intel x86 accelerator cards will have enough cores and fast enough cores to do graphics acceleration for games that is good enough and fast enough. Eventually, all of these multitudes of cores will come standard inside every Intel cpu, no "accelerator card" needed. Intel has done exactly this with current gpu technology on their current line of processors. Their graphics performance is sufficient for everyone except serious gamers.

      Or, we'll continue to see the current progression of a steadily increasing number of fulls-sized cores, and Intel's lots-of-tiny-cores approach will be of little interest to anybody but HPC seekers.

    25. Re:Cluster = Cloud by smallfries · · Score: 1

      Have you used it? The IDF is for interactive frame-rates (haven't checked but last Intel demo I saw was about 20fps). That ray-tracer on the card takes several seconds per frame. They are not really comparable in performance.

      --
      Slashdot: where don knuth is an idiot because he cant grasp the awesome power of php
    26. Re:Cluster = Cloud by Guspaz · · Score: 1

      I've used it... It's real time on my old GTX 285. The most fancy one, "Design Garage", gets 2-3 FPS. A modern nVidia card should be significantly faster, especially in SLI. But even in SLI, it'd still be enormously cheaper than Intel's 8-card solution.

    27. Re:Cluster = Cloud by smallfries · · Score: 1

      I meant the SDK for ray-tracing, rather than the ray-tracing demo in the SDK. I've tried that on a GTX-580 and it seemed to have two different rendering modes, low quality when you move the model for 2-3fps and then a refinement step that took a couple of seconds to get the highest quality.

      --
      Slashdot: where don knuth is an idiot because he cant grasp the awesome power of php
    28. Re:Cluster = Cloud by Guspaz · · Score: 1

      Well, how much of that refinement is actually useful for Intel's target use case here? They're going to stream this as compressed video to a tablet, antialiasing (which seems to be a large part of the refinement done in many of the nVidia demos) isn't that useful since it's all going to get crammed into a video stream anyhow. Looking at Intel's claims in terms of performance hits for various operations versus what I saw in the nVidia demos, it's clear that Intel has a better raytracing rendering engine, but it's not clear to me that that's not better software rather than better hardware. Say the Intel renderer used OpenCL (since Intel is pushing it too), allowing us to run the code on either Knights Ferry or Tesla cards. Then say I put eight high-end Tesla cards in a machine and set it loose on the renderer. Which solution will be better?

      The nVidia solution can be purchased today, while the Intel solution is still in the R&D phase. That's my point, that it's not obvious how the Intel approach is better, and without comparative benchmarks or pricing, we can't say if the Intel solution is competitive.

  18. I don't get it by msobkow · · Score: 2

    What's the big deal?

    Ray tracing isn't new.

    Parallel processing isn't new.

    It's an old game.

    What makes this news?

    --
    I do not fail; I succeed at finding out what does not work.
    1. Re:I don't get it by MozeeToby · · Score: 1

      They're getting close to commodity hardware. A large 256 core server today is a run of the mill desktop in 5 years. Intel wants you to believe that GPUs have a limited lifespan, that they'll last only until real time ray tracing on the CPU can produce equivalent or better results. They could be right... but the only way to find out is going to be to wait until the hardware catches up to the point that it's economically competitive and see what the GPU makers have done in the meantime. All in all, these kind of demos cost them hardly anything at all and if they can get a couple of game developers to start seeing things their way it could pay off hugely in the future.

    2. Re:I don't get it by Anonymous Coward · · Score: 0

      > A large 256 core server today is a run of the mill desktop in 5 years

      No, it isn't. Even with the full benefit of Moore's law assumed, and rounded up, we'll only have 8 times as many cores five years from now. A run of the mill desktop has 2-4 cores, so that makes 16-32. A very long way from 256.

  19. Which one? by ZeroSerenity · · Score: 1

    Ye old Wolfenstein for DOS and SuperNES or Wolfenstein for Windows, PS3 and Xbox?

    --
    For those who seek perfection there can be no rest on this side of the grave.
    1. Re:Which one? by Trilkin · · Score: 2

      The newer Wolfenstein running on the Doom 3 engine.

      --
      Nobody cares what the CAPTCHA for your post was.
    2. Re:Which one? by Anonymous Coward · · Score: 0

      Ye old Wolfenstein for DOS and SuperNES or Wolfenstein for Windows, PS3 and Xbox?

      You forgot about the return to castle wolfenstein that was between the two. It had the good team multiplayer.

    3. Re:Which one? by Renegrade · · Score: 1

      And also:

      http://en.wikipedia.org/wiki/Castle_Wolfenstein ..which was an interesting game back in the day.

  20. Intel keeps slogging raytracing by Sycraft-fu · · Score: 1

    About once or twice a year they go on a big press buzz about raytracing. Reason is they would like that you don't spend money on graphics cards, and instead take that money and spend it on a bigger processor. So they are looking in to something that GPUs don't do so well, which is raytracing. They keep trying to get people excited about the idea of raytraced games, which would be done by systems with heavy hitting Intel CPUs, rather than rasterized games done mainly with a GPU.

    As long as they keep doing press blitzes on this, expect to keep hearing the same kind of story.

    1. Re:Intel keeps slogging raytracing by Bengie · · Score: 1

      Based on what I've read about Raytracing vs Rasterization, Raytracing *will* win out in the long run. I guess RT scales better than rast, but the overhead is expensive. Once we get to the point where RT is about the same speed as rast, it will only take 1-2 generations before RT is several factors faster.

      Whichever company is ready to push out RayTracing, will stomp the market. If you release too early, your product will just be a gimmick, if you release too late, the competition will be several times faster than you.

    2. Re:Intel keeps slogging raytracing by Anonymous Coward · · Score: 0

      But GPU's can do raytracing very well. They've been doing this for a couple of years now.

    3. Re:Intel keeps slogging raytracing by Bram+Stolk · · Score: 1

      Yes... ray tracing will indeed win in the long run.
      This is because the performance is almost independent of primitive (triangle) count.

      As a matter of fact... currently, ray tracing really complex models is already faster than rasterizing them.
      Few hundred million or more triangles or so can be done faster with RT.

      This is why their choice for content baffles me:
      They should NOT be using doom datasets for this, they should be using hundreds of millions of polygons in their dataset.
      That is where RT is shining.

      Rasterizing is O(N) in nr of triangles.
      Ray tracing is better than O(logN), approaching O(1) even.

          Bram

      --
      Bram Stolk http://stolk.org/tlctc/
    4. Re:Intel keeps slogging raytracing by Amouth · · Score: 1

      yeap - and this is Intel - a company that knows how to play for the future (to an extent).. an example is Hyper Threading.. most people pass it off but honestly if you expect for it and optimize some things for it you can see ~80% increase in performance. Now the group that came up with it and started designing it - started their research in i believe 1992.

      some companies know how to do R&D and some don't, Intel is one that does.

      --
      '...if only "Jumping to a Conclusion" was an event in the Olympics.'
    5. Re:Intel keeps slogging raytracing by Anonymous Coward · · Score: 1

      The example they showed in one of the videos posted was an engine that looked similar to Return to castle Wolfenstein, not Doom era Wolfenstein.

      They had a 1 million polygon glass chandelier, with accurate refraction as the central point of the demo they were giving. It isn't your hundred million polygon demo, but it was certainly not your doom-era graphics.

      (Personally, I suspect they could do Wolf3d or even Doom real-time raytracing on current CPU hardware... Especially at native frame sizes of 640x480)

    6. Re:Intel keeps slogging raytracing by Anonymous Coward · · Score: 0

      Rasterizing is O(N) in nr of triangles.
      Ray tracing is better than O(logN), approaching O(1) even.

      Your are conflating rays and shading.

      There's a better explanation here

    7. Re:Intel keeps slogging raytracing by Anonymous Coward · · Score: 0

      Hyperthreading existed and was done by other companies before Intel. I think SPARC or whatever had 4-threads per core HT.

      Now I know you are just trying to hero worship Intel here so I'm sorry to burst your bubble but Intel's HT implementation was crap. It wasn't written off because HT was a terrible idea but because the P4 HT was a turd sandwich. The Nehalem HT is much better than last iteration of it but is not massively innovative or anything new and wonderful like you claim.

      BTW, ray tracing (casting) is pretty much the opposite of a good use case for HT, HT works by sharing core resources that aren't being used by the other thread in the pair, if all your threads are slamming the FPUs then those extra hyperthreads aren't going to do crap; you have accomplished nothing more than to have threads x 2, performance / 2. HT only works on disjoint workloads like a typical desktop workload where all the threads are working on a random mish-mash of tasks that don't have similar patterns of operation.

    8. Re:Intel keeps slogging raytracing by jedwidz · · Score: 1

      I don't buy that argument that ray tracing wins because of computational complexity - you won't break even on performance until you're ray tracing far more triangles than you have pixels to display them on.

      And that means your average triangle isn't going to contribute to most frames at all, and when it does, you have aliasing!

    9. Re:Intel keeps slogging raytracing by Anonymous Coward · · Score: 0

      Yes, but they also want to do it in real time at an acceptable frame rate.

    10. Re:Intel keeps slogging raytracing by Bengie · · Score: 1

      When I run a synthetic benchmark on my i7-920(2.66ghz), this is what I get for my Int/DP(64bit float) performance.

      5.32bil ints/sec/thread - 8 threads
      2.65bil FP/sec/thread - 8 threads - about 21gflops w/o SSE

      You should check out the execution units on the i7, there is a lot of duplicated FP/int units, which allows HT to get some pretty hefty performance benefits. SSE units are shared, so any SSE benchmarks would take a hit with HT.

      If you can get more than 1 DP/cycle on your AMD chip with 6 "real" cores, let me know; because Intel is getting 1 DP/cycle on its "fake" cores.

      Your highest performance with HT would be one thread doing DP and another doing SSE.

    11. Re:Intel keeps slogging raytracing by Anonymous Coward · · Score: 0

      Millions of triangles? There are only 2 million pixels in a full-HD display; methinks you'd be better off with some sort of way to reduce the polygon count in a way that wouldn't be visually noticeable. Far-away objects don't need to be rendered in great detail.

    12. Re:Intel keeps slogging raytracing by grumbel · · Score: 1

      Rasterizing is O(N) in nr of triangles.
      Ray tracing is better than O(logN), approaching O(1) even.

      That's only really true for theoretical best-case scenario for raytracing and worst case for rasterization. In practice things look very different, as any real world realtime rasterisation engine will do LODs, tessellation, octrees, occlusion queries and whatever to drastically cut down the triangle count they have to render in rasterization, make it no longer O(N), but something much smaller. Equally O(logN) is only true for static scenes, when you have dynamic ones things look quite different as you and you have to include the cost of building your space partitioning into the whole thing.

      And in the end, raytracing or rasterization is really not issue, the interesting thing is how you space partition your scene, as that will have a far bigger impact.

    13. Re:Intel keeps slogging raytracing by Anonymous Coward · · Score: 0

      Another example is called Itanium, which according to 1999's projections, is used in the majority of servers and desktops having completely replaced both Sparc, power, and x86 architectures. Truly they are gods amongst men, who's foresight and wisdom exceeds all others.

  21. Nintendo beat them to it by tepples · · Score: 1

    Depends if the rendering server is halfway across the country or halfway across the house

    A rendering server halfway across the house is called a "Wii U console".

  22. Not practical by J-1000 · · Score: 1

    Their idea is to render the graphics on the server farm and stream them over to a thin client? If the server farm is local, then it's an expensive solution that only a small subset of users can afford. If it's cloud-based then there will be massive control lag. Neither idea is practical.

    1. Re:Not practical by Anonymous Coward · · Score: 0

      OnLive is already offering cloud based gaming, which is apparently quite good with a solid 'net connection.

      'course, they're also not running games that take a cluster of servers to run.

    2. Re:Not practical by Anonymous Coward · · Score: 0

      Not sure Onlive would agree with you

    3. Re:Not practical by J-1000 · · Score: 1

      Wow, I never thought people would consider 150ms of lag (for *every movement*) acceptable, but apparently they do! I wouldn't mind so much for RPGs I guess, but something like Super Mario Brothers would drive me nuts.

      Modern online games not running through the cloud are designed to mask online latency by providing you with instant feedback for certain actions (movement, firing animations). OnLive games, unless custom-coded, would not have this luxury. It would be akin to playing the original Quake (aka NetQuake) online... press button, wait, press button, wait.

    4. Re:Not practical by Anonymous Coward · · Score: 0

      where do you get the idea of massive control lag?
      maybe that is true for some people but in the long run latency to "carefully" placed server farms will be 5ms. (right now it is 5ms for me to ping google) I really doubt anybody would even notice.
      This would be just perfect, it would give developers pretty much a single target to optimize for, it would consolidate gaming for consoles and pcs and ensure that those games always run as intended and are much easier to fix if any issues arise.

      Depending on how well the engine is implimented i have the strong feeling that input lag is way above 5 or even 20ms for a lot of games.
      All in all I mean to say that nobody will care about 5ms input lag if they get smooth as silk games without having to worry about what graphics card to get or if the game is working fine with their particular model or if their CPU is powerful enough etc.
      Also it would make pirating games virtually impossible for a long time (at least for the general public, there will probably be invite-only private server farms that have pirated versions of those games running at some point)
      Probably it would also result in gaming flatrates where you pay $X per month to your ISP or whoever and can play any title they have.

      So personally I think this is a great development and the potential is huge and it just comes down to the power demand and developers picking up on it.

    5. Re:Not practical by J-1000 · · Score: 1

      If OnLive could do 5-20ms they would. But according to this article it runs about 150-200ms. And of course this will vary depending on your location. Google has the cash to distribute a lot more servers than some little gaming service.

    6. Re:Not practical by Johann+Lau · · Score: 1

      100 ms lag isn't even acceptable for a fucking web GUI. and that's that.

  23. meh by stackOVFL · · Score: 1

    They should have done the demo using Duke Nukem.

    1. Re:meh by robthebloke · · Score: 1

      You want to wait 15 years for a frame?

  24. Wrong Wolfenstein by Anonymous Coward · · Score: 0

    Bother. Wrong Wolfenstein.

  25. Google Caches! by antdude · · Score: 1

    http://webcache.googleusercontent.com/search?q=cache:hmhYOuzN3B4J:blogs.intel.com/research/2011/09/wolfenstein_gets_ray_traced_-_2.php+http://blogs.intel.com/research/2011/09/wolfenstein_gets_ray_traced_-_2.php&cd=1&hl=en&ct=clnk&gl=us&client=mozilla

    http://webcache.googleusercontent.com/search?q=cache:hmhYOuzN3B4J:blogs.intel.com/research/2011/09/wolfenstein_gets_ray_traced_-_2.php+http://blogs.intel.com/research/2011/09/wolfenstein_gets_ray_traced_-_2.php&hl=en&client=mozilla&gl=us&strip=1 (texts only)

    However, no images. :(

    --
    Ant(Dude) @ Quality Foraged Links (AQFL.net) & The Ant Farm (antfarm.ma.cx / antfarm.home.dhs.org).
  26. Re:thi5 FP for gNAA by Goaway · · Score: 0

    FP=Fnineteenth Post.

  27. Lag? by FrootLoops · · Score: 1

    Is the lag for this type of solution tolerable? I can see it going both ways and (shockingly) don't have the necessary hardware to test this combo out myself. I have no experience with OnLive either.

    1. Re:Lag? by smellotron · · Score: 1

      Is the lag for this type of solution tolerable?

      Maybe for single-player games, but not for competitive twitch-games online. Most modern LCDs come with gobs of post-processing that puts display latency up to the 100-200ms range (of course, you turn this off if you care). I find it extreme enough to absolutely destroy my shotgun accuracy in a local split-screen game. I expect remote rendering would have a similar effect, only worse because the Internet is less deterministic than a TV's post-processing pipeline.

    2. Re:Lag? by Bengie · · Score: 1

      I get a 19ms ping to Chicago, which is somewhere upwards of 500mi via the trace route in another state. Put in some more localized rendering farms, like per State, and you could easily keep latency low enough for the average user.

      Jitter could be an issue if the network isn't well designed. It would probably show up as micro-stuttering.

  28. A screen shot with images! by antdude · · Score: 2

    It finally gave me images and I took a screen shot/capture to upload to share: http://i.imgur.com/opSLl.jpg ... :)

    --
    Ant(Dude) @ Quality Foraged Links (AQFL.net) & The Ant Farm (antfarm.ma.cx / antfarm.home.dhs.org).
  29. Raytracing vs Rasterization by igomaniac · · Score: 1

    The future of rendering in video games has always been evident if you look at high-end rendering for films. If you look at a product like Renderman, ray-tracing is used for specific materials in the scene, but not commonly used for rendering the whole frame. Getting realistic materials out of the renderer is the real problem, not rendering mirror balls.

    --

    The interactive way to Go -- http://www.playgo.to/iwtg/en/
  30. Calling a Larrabee a Larrabee by Nom+du+Keyboard · · Score: 1

    Call it what it is: either Larrabee 2 or Son of Larrabee. Trying to hide it behind a new name doesn't change the underlying idea behind it, or it's failures so far. And telling us that Larrabee 3.0 (Grandson of Larrabee) will be the one that really works smacks of Microsoft software.

    --
    "It's the height of ridiculousness to say for those 9 lines you get hundreds of millions."
    1. Re:Calling a Larrabee a Larrabee by Anomalyst · · Score: 1

      Smack ... Microsoft software, I see what you did there.

      --
      There is no right to feel safe thru security vaudeville at the expense of everyone's freedom, privacy and tax money.
  31. Hype Never Gets Old by Tatarize · · Score: 1

    In fact I hear they have hype out on Blue Ray in 3D super HD.

    --

    It is no longer uncommon to be uncommon.
  32. low res by Anonymous Coward · · Score: 0

    Only 1080p? My single ATI graphics card does better than that on a monitor. It's the TV's that still need to catch up with the pixels.

    1. Re:low res by robthebloke · · Score: 1

      What? Your ATI does raytracing in realtime at 1080p?

  33. DOF by Syberz · · Score: 1

    Am I the only one who hates depth of field effects in games? When the computer/game can determine what my eyes are focusing on, then DOF will be practical. Just because the crosshair is on something, it doesn't mean that that's what I'm looking at, my eyes are very good at creating their own depth of field effects, thank you.

    --
    ~Syberz
    1. Re:DOF by Wizarth · · Score: 1

      Not only games but also movies. There's some argument for making sure the person is looking at the thing you want them to, but if you need to make everything else blurry to do so, makes you wonder.

      It's one of the reasons 3D films don't work in general - they include depth of field. The only 3D film I've seen that really worked was Avatar - which has no depth of field. At all. I enjoy the movie more for this technical reason alone - I can look where I want!

  34. cool but by Iniamyen · · Score: 1

    Does this encourage more porn content delivery in some way? If not, it will probably take awhile to get to market.

  35. Hmm by filedosya · · Score: 1

    Very Nice http://www.filedosya.com/