Slashdot Mirror


Intel Discloses Its Forthcoming Discrete GPU Strategy and Design Efforts (hothardware.com) (hothardware.com)

MojoKid writes: Intel has been uncharacteristically vocal about its most recent plans to enter the discrete GPU market. Over the last year or so, the company has disclosed a few morsels of information and made some high-profile hires, in its bid to build-up and flesh-out its latest discrete GPU plans. This week, Intel decided to have a sit down with HotHardware, offering the opportunity to chat with Ari Rauch, Vice President of the Core And Visual Computing Group at Intel, to discuss what makes this most recent endeavor different from the company's previous and now discontinued attempts in the discrete GPU space. As a follow up, HotHardware also enlisted readership questions to engage with Intel about its upcoming GPU plans, compiling responses in a Q&A format.

In short, this isn't Larabee 2.0, not by a long shot. Intel is gearing up for a traditional GPU architecture design, coupled with some of the company's own strategic IP that it can bring to the table, to help differentiate its products. Further, Rauch noted Intel "will bring discrete GPUs to both client and data center segments aiming at delivering the best quality and experiences across the board including gaming, content creation, and enterprise. These products will see first availability over a period of time, beginning in 2020."

When questioned on their current silicon fabrication hiccups and delays and how it might affect Intel's ability to execute in this highly competitive space, Rauch noted, "we feel very confident about our product roadmap across software, architecture, and manufacturing." Based on some of the responses to product positioning questions, it also appears Intel is gearing up to address all performance envelopes as well, from entry-level to midrange and high-end graphics cards.

92 comments

  1. Job 1 : Suck less by Anonymous Coward · · Score: 0

    "coupled with some of the company's own strategic IP that it can bring to the table, to help differentiate its products" - From the rest of their general sucking you mean? Yeah good idea.

  2. This is really good news by Anonymous Coward · · Score: 0

    If you're shorting Intel. I can't wait to see them waste billions of dollars in another failed effort to break into a new market and begin barely selling the worst performing product. Again.

  3. Information-Free Article by mentil · · Score: 4, Informative

    Skimmed the article. The opening data is almost all stuff that's been previously revealed, or is obvious. The Q&A session is painful PR-speak noncommittal vagueness.

    I want to know if it's going to support DXR (directx raytracing) or how many generations of architectures they're committing to. If they buy up another promising game and then shut it down like they did when they cancelled Larrabee, I'll be peeved.

    --
    Corruption is convincing someone that the selfless ideal is the same as their selfish ideal.
    1. Re:Information-Free Article by _merlin · · Score: 3, Insightful

      I'll believe Intel can build a discrete GPU worth buying when I see it. Every attempt so far has been flawed (Real3D i740 starved for texture bandwidth), weak (Silicon Image GMA950 with terrible performance and even worse drivers on Windows), or vapourware (Larrabee). There's no indication that it'll be different this time.

    2. Re:Information-Free Article by Anonymous Coward · · Score: 0

      That'd be pretty dumb for them to follow Nvidia's proprietary BS marketing gimmick lead or give you any hard numbers in a puff piece. They want to hook idiots' eyeballs and get you thinking this means something.

      The proverbial you, of course.

    3. Re:Information-Free Article by supercell · · Score: 1

      Of course, There are no details, because this is a vapor-ware press release to push up the stock price. They have developed no IP to do the things needed to compete with Nvidia or AMD in the next 2-3 years. This is laughable.

    4. Re:Information-Free Article by Anonymous Coward · · Score: 0

      No shit thanks for explaining the obvious. You really did.

    5. Re:Information-Free Article by Anonymous Coward · · Score: 0

      That he'd directly call out "One way to think about this is our current Gen 9 GPUs in the market today are significantly different from Larrabee. Our incredibly accomplished team is now working on a new architecture for GPUs." Really??? They were never even similar... Larrabee was more aligned with the Xeon Phi than the 5th Gen Intel HD GMA. You know what else their Gen 9 GPUs are significantly different from? A basketball. Is it relevant? If you'd believe this PR dipshit, absolutely!

    6. Re:Information-Free Article by Anonymous Coward · · Score: 0

      But but but RAJA

    7. Re:Information-Free Article by mermeid007 · · Score: 1

      Raytracing for sure. That's still the hottest area of rendering after all these years, even though its soooo computationally complex.

    8. Re:Information-Free Article by Rockoon · · Score: 4, Interesting

      They have developed no IP to do the things needed to compete with Nvidia or AMD in the next 2-3 years.

      IP doesnt always have to be developed by a particular company. See Intels latest deal with AMD for integrated graphics.

      I have been saying for a couple years now here that Intel is in very serious trouble. Especially after those layoffs and the PR announcement for a "cloud strategy." The first key point here is that its taken several years before it became obvious to most (even here) that Intel is in any trouble at all. The second key point is that Intel did know it years ago that they were in big trouble.

      Intels biggest problem is that their vertical integration has really constrained them. Silicon (not just CPU's) doesnt leave an Intel plant without being branded Intel. They have older fabs that are idle because they wont sell time on them, and newer fabs that even at 100% capacity cant satisfy demand. The later wouldnt be a problem if Intel were the only source for a particular component by raising prices to decrease demand, but the reality is their competitors in total have far more capacity than they do.

      It is because of all this that a company like AMD would trade off some IP to Intel. It doesnt fix Intels fundamental and now unfixable problem, which is that they will never be the market leader again, never steer the markets that they partake in. From here on out they can only react to what other market players are doing.

      On the desktop process side, Intel was blindsided by the economy of AMDs chiplets, and they are still at least several years from an effective design. It isnt just about small dies on a single processor board, its about being wholly modular. The same chiplets that Threadripper uses are also used by AMD's low end Ryzen APUs.

      Intel does have some "chiplet" experience but then too it was as a reaction to a blind-sided moment when their main competitor introduced multi-core to the consumer. It was a hack that they didnt explore but should have.

      On the fabrication side, Intel is now dwarfed by the rent-a-fab market capacity on its entirety, and even individual rent-a-fabs are now overtaking them in capacity.

      I've said it before and I'll say it again. Sell your Intel stock. Even if you arent manually in the stock market, check your 401Ks and Roth IRAs. They might be able to prevent becoming a Motorola, but even if they do its still bad. Very bad. Intel is fucked.

      --
      "His name was James Damore."
    9. Re: Information-Free Article by Type44Q · · Score: 1

      IP doesnt always have to be developed by a particular company.

      Pretty sure by "IP" they meant"actual designs," not just patents.

    10. Re:Information-Free Article by mikael · · Score: 1

      It's quite simple. You take your scene, slice and dice it into triangles, even parametric surfaces like NURBS, subdivision surfaces used by Pixar, 3D models from 3Dmax, Maya, Blender. All of that gets converted into textures, material shaders and geometry mesh. The geometry mesh gets chopped up into a hierarchical bounding volume like a kd-tree. All of this can be stored in a data format loaded straight into the GPU or CPU cache. It's all vectors, matrices and parametric coordinates. Separate processors are assigned to process each pixel and do thing like supersampling, ambient occlusion, global illumination, caustics and radiosity. Nvidia have their Optix ray-tracing library. Intel have Embree.

      --
      Vintage computer adverts: http://www.vintageadbrowser.com/computers-and-software-ads
    11. Re:Information-Free Article by UnknownSoldier · · Score: 1

      Indeed. Every time I hear news about Intel and GPUs I think about this Santa comic

    12. Re:Information-Free Article by gl4ss · · Score: 1

      it's just the same thing they've been bullish or whatever crap for 15 years.

      they can't fucking come up with a good cost efficient cpu nowadays and now we should expect them to actually come up with a fast gpu?

      I mean for 15 years they've been touting the same line of "oh in a year you don't need an extra gpu, our will be just sooo fast!" and then it comes to the market and is like a budget gpu from 5 years before. literally that's what they do.

      another alternative is that it'll cost even more than a 2080 and work like a budget integrated amd gpu.

      --
      world was created 5 seconds before this post as it is.
    13. Re:Information-Free Article by thegarbz · · Score: 2

      There's no indication that it'll be different this time.

      This! Intel has nothing going for it right now. They have shown no ability to innovate in the CPU market, they have shown only to be capable of buying up another company's technology and bring it to market full of mixed messages and frankly broken promises (Optane), and their history in discrete graphics is a disaster.

      They don't deserve any benefit of the doubt. They deserve only skepticism.

    14. Re:Information-Free Article by UnknownSoldier · · Score: 1

      > If they buy up another promising game and then shut it down

      I assume you are talking about the intriguing Project Offset ?

      I never did understand Intel's logic in that. They aren't a game dev studio nor publisher. Were they hoping to showcase Intel's CPU and/or Larrabee performance "advantage" and then when that completely FAILED (compared to regular discrete GPUs) they canceled it?

      Or were they hoping to leverage buying Havok (Game Physic Engine) in 2007 when they bought Project Offset in 2008 ?

    15. Re:Information-Free Article by Z80a · · Score: 1

      The intelHD line was quite OK, specially the iris pro stuff.
      At least the intel chips now manage to boot and run the games unlike the GMA line.

    16. Re:Information-Free Article by Rockoon · · Score: 3, Interesting

      Its all fun and games when the scene data is static.

      What has prevented RTRT for all this time has been dynamic scene data - things moving around - the acceleration structures like space partitioning trees are either too expensive to generate in realtime or sacrifice too much trying to deal with it.

      Remember that GPUs have high memory bandwidth but absolutely terrible memory latency, not like CPU's where the opposite is true. Intel learned that the issue continued to remain insurmountable with their Larrabee failure. They could build those acceleration structures quickly on Larrabee, but then when it came time to render, the lack of memory bandwidth became the killer.

      As far as I know there is still no acceptable solution. nVidia is claiming they have it, but in practice they are still mainly rasterizing.

      --
      "His name was James Damore."
    17. Re:Information-Free Article by AHuxley · · Score: 1

      How to make existing CPU sell as a new GPU.

      Find a lot of working and well understood CPU product.
      Spread out a lot of CPU hardware over a long GPU looking card. A long card to fit more CPU all the way along.
      Add powerful cooling and a new look to the brand.
      Many working CPU with an easy to support open source driver get sold as a powerful new look GPU.

      Show the world a ray tracing demo.
      That existing CPU design is sold at a new GPU price.

      Start thinking of the next generation.
      Add more memory and more cpu. Take up over 4 slots. Add more power connectors along the card. More cooling.

      --
      Domestic spying is now "Benign Information Gathering"
    18. Re:Information-Free Article by KingMotley · · Score: 2

      What promises did Optane break? It seems to be exactly where everyone believed it would be. Much lower latency than SSD, at a price point somewhere between SSD and DRAM prices. Every benchmark I've seen shows that is exactly where it is.

    19. Re:Information-Free Article by mentil · · Score: 1

      They had to walk back their endurance claims by an order of magnitude, which put certain applications of the tech into question. The rollout was also much slower, at a lower density, than expected, even after delays. It was hyped/implied to be a replacement for DRAM and NAND but has drawbacks that don't let it completely replace either.

      --
      Corruption is convincing someone that the selfless ideal is the same as their selfish ideal.
    20. Re:Information-Free Article by thegarbz · · Score: 1

      What promises did Optane break? It seems to be exactly where everyone believed it would be.

      It's exactly what everyone believed it would be (a fast technology for high-end SSDs). Just not what Intel said it would be (the end of DRAM as we know it) when Optane was in the same state as this GPU announcement. Hell they even market it as "Optane Memory". The fact that everyone called out their bullshit at the time and it has proven to be exactly what we thought doesn't change this.

      I didn't say it's a bad product without a purpose. I just said it's not what Intel promised in their useless marketing releases.

    21. Re:Information-Free Article by KingMotley · · Score: 1

      Can't believe I have to explain this on slashdot, but... Optane IS memory. So is NAND, your old spinning rust drive, digital tapes, CDs, and blurays. In fact, not only is it memory, but it's also RAM (random access memory). But so is everything listed above with the exception of digital tapes. If you believe the only thing that qualifies something to be memory is DRAM, then your definition is simply wrong.

      It really could replace DRAM -- if they can get the endurance back up -- it's not bad endurance, just not really good enough to replace DRAM for most applications currently. But it'd take a lot of architecture work, and likely won't ever happen because there are very few markets in which loading an application is such a terrible pain point that people would actually pay to fix it. Some markets sure, just not enough for a tipping point.

    22. Re:Information-Free Article by thegarbz · · Score: 1

      Can't believe I have to explain this on slashdot, but... Optane IS memory.

      Maybe you should learn what marketing is and what people need to understand. Yes Optane and NAND is memory. Now why do you think that NAND isn't sold as "memory" to consumers? Why do you think Optane is?

      Your splitting hairs on definition is as dishonest as Intel's marketing division. The same marketing decision which has almost directly caused the current trend of advertising laptops with 24GB of "memory" (8GB of RAM, I'll leave it as an exercise to you to guess the rest). There's a time to split hairs (Tesla autopilot is as intelligent as real airplane autopilot) and there's a time to realise that splitting hairs for the purposes of marketing is fundamentally dishonest (using autopilot for people who don't understand what autopilot is).

      Selling an SSD while calling it "memory" is definitely in the latter. I can't believe I had to explain that difference to you. Remember if everyone was a IT technical genius then marketing departments wouldn't need to exist since everyone would read through the very bullshit that they come up with. For all intents and purposes Optane SSDs are *NOT* memory and you should never say it is to anyone outside of IT circle.

      It really could replace DRAM

      Maybe some day just not now, and not at launch, which is effectively the broken promise.

    23. Re:Information-Free Article by KingMotley · · Score: 1

      Now why do you think that NAND isn't sold as "memory" to consumers?

      Let's stop right there, because NAND *IS* sold as memory to consumers. For example, let's take one of the largest suppliers of NAND flash products that are consumer facing today... Kingston. And here is an article by them: https://www.kingston.com/us/co.... "Here's a quick primer on what you need to know about NAND Flash memory."

      Here is the wikipedia article on NAND: https://en.wikipedia.org/wiki/....

      Cameras use "Memory Sticks" -- all based on flash memory.

      I could sit here all day a google marketing press releases, articles, and spec sheets that showing how wrong you are, but you can easily do the same. Here you go: http://lmgtfy.com/?q=computer+...

      The term memory has been well defined for over 50 years now. Not going to start redefining precise, well established terms because you don't understand them, or think they mean something they don't and never did.

      -----

      As for learning what marketing is, well... Considering that I understood the marketing and you did not, I would say that of the two of us, one of us doesn't understand what marketing is at all.

      It really could replace DRAM

      Maybe some day just not now, and not at launch, which is effectively the broken promise.

      Or maybe it really could... at launch:

      Intel® Optane SSD DC P4800X with Intel Memory Drive Technology enables data centers to deliver more affordable memory pools by displacing a portion of DRAM or significantly increasing the size of memory pools. This solution transparently integrates the drive into the memory subsystem and presents the SSD as DRAM to the OS and applications.

      Available March of last year. Is it better than DRAM in every way? No. Is it better than DRAM in some ways? Yes.

    24. Re:Information-Free Article by thegarbz · · Score: 1

      Let me stop you right there again.
      https://www.newegg.com/Product...
      https://www.newegg.com/Product...

      Or why not let the SIs speak for you: https://store.hp.com/us/en/cv/...

      Considering that I understood the marketing and you did not

      To channel my inner Trump: WRONG! You have clearly failed to understand the marketing. Good work finding a detailed description of NAND and ignoring the information that is most front and center to consumers. You're still splitting hairs trying to save your horrible interpretation of the situation while you continue to ignore the ACTUAL MARKETING.

      Intel® Optane SSD DC P4800X with Intel Memory Drive Technology enables data centers to deliver more affordable memory pools by displacing a portion of DRAM or significantly increasing the size of memory pools. This solution transparently integrates the drive into the memory subsystem and presents the SSD as DRAM to the OS and applications.

      WHOLY SHIT. I mean I was sort of trolling when I said you don't understand marketing. But you actually don't understand marketing! Like at all. It all makes sense now. You tried to discredit a promise Intel made on it's marketing material (which didn't make sense and failed to deliver) with ... a promise made on Intel marketing material.

      Dude, get help.

    25. Re:Information-Free Article by KingMotley · · Score: 1

      *sigh*

      Please read your own darn links. They refer to it as memory. If you aren't going to call it memory, which it is, what exactly would YOU call it? "thing that stores stuff for a computer, but isn't memory"?

      Good work finding a detailed description of NAND and ignoring the information that is most front and center to consumers.

      I don't have to when you send them to me.

      You tried to discredit a promise Intel made on it's marketing material (which didn't make sense and failed to deliver) with ... a promise made on Intel marketing material.

      Well, it's not really just marketing material when you can buy it and do it yourself. Granted with the P4800X, it's a software hypervisor (by a 3rd party) running with your OS as a client balancing requests between DRAM and Optane, but to the OS and the applications running under it, it has nearly the same effect. It's just adding one more tier of memory caching to the memory subsystem. Not really all that hard to grasp for anyone in the field.

      ---

      I'm done with this thread. You can go on thinking that the one and only true memory is DRAM, while the rest of the world will go on realizing that you are just plain wrong. I'm sure you can do it. Just put your fingers in your ears, shouting LALALALA! or bury your head in the sand.

    26. Re:Information-Free Article by Agripa · · Score: 1

      I'll believe Intel can build a discrete GPU worth buying when I see it. Every attempt so far has been flawed (Real3D i740 starved for texture bandwidth), weak (Silicon Image GMA950 with terrible performance and even worse drivers on Windows), or vapourware (Larrabee). There's no indication that it'll be different this time.

      Larrabee was not vaporware exactly but it is worth considering why it did (or did not) fail. I suspect the development of ISPC detailed below may point to what Intel has in mind.

      https://pharr.org/matt/blog/20...
      http://tomforsyth1000.github.i...

    27. Re:Information-Free Article by Agripa · · Score: 1

      Intels biggest problem is that their vertical integration has really constrained them.

      Based on things Bob Colwell has said in his book and other places I think Intel's problem is management which was turning toxic before he left. What I have read about the failure of Larrabee and the i960 indicates the same thing.

      Intel does not need effective management while the x86 train was paying the bills but when that train slows down, I expect a panic that the older Intel under Andy Grove which moved from memory to microprocessors could have handled.

      Having to rely on Microsoft does not help.

    28. Re:Information-Free Article by thegarbz · · Score: 1

      "Kingston A1000 M.2 2280 480GB PCI-Express 3.0 x2 3D TLC Internal Solid State Drive (SSD) SA1000M8/480G"
      "Intel Optane M.2 2280 32GB PCIe NVMe 3.0 x2 Memory Module/System Accelerator MEMPEK1W032GAXT"

      One has a product name (the single most important component of marketing) called SSD the other has a product name called memory module.

      I'm done. You've displayed enough ignroance for one day.

  4. Re:All fluff and no substance by supercell · · Score: 0, Flamebait

    Muffingtonpost is left wing propaganda garbage not fit for electrons

  5. Fuck nVidia by KiloByte · · Score: 1, Insightful

    At least we know the drivers will be ok from day one. It's not humanly possible to suck more than current GPU makers.

    nVidia not only doesn't provide documentation for its cards, but even actively interferes with nouveau on its new cards (encrypting and signing crap). On every card, it's random whether either their proprietary drivers or nouveau will work without crashing. The proprietary drivers are useless if you even dabble in kernel development -- they get ported to current kernels 0-6 months after a .0 release; some of us would want -rc or next. Oh, and support gets dropped within 5 years of a cards's launch. For this reason, Debian keeps forks of a number of discontinued drivers, but perhaps you'd want to run them with current kernels or X, ha ha? And, "drivers exist" doen't mean they actually work. Even basic crap like enabling xfce's compositor causes a crash, while there's that random crash from time to time. Oh, and even physically the cards suck. Out of 3 nVidia cards I went through recently, the middle one went out in flames. Literally. With thick smoke covering the entire room.

    Compare Intel. At the family home I visit on weekends, I recently had to bring out an ancient machine (monitor problems -- none of 1864518746 SoCs I own want to talk to either my new monitor nor any (ancient) backups), with an Intel 910GL. Despite the card's age, it worked perfectly, including compositing and stuff. So does the integrated card in a spanking new machine at work. No need to think about drivers, everything is in the current kernel and X.

    I haven't tried ATI/AMD in a decade. Their drivers used to suck -- I'm told AMD very recently (as in, a year ago) rewrote their driver stack so it's actually usable. I seriously hope so as I urgently need to rebuild my rig, and I'm not waiting till 2020. So it'll be AMD for me.

    --
    The creatures outside looked from Alt-Right to Antifa; but already it was impossible to say which was which.
    1. Re:Fuck nVidia by Anonymous Coward · · Score: 0

      Any video driver requiring the installation of .net sucks.
      By this, you can also find out when nvidia drivers started sucking,
      when they introduced the requirement for .net just to have a control panel for the display driver.

    2. Re:Fuck nVidia by wierd_w · · Score: 0

      AMD did it before nVidia a good 5 years or so. I distinctly remember outright refusing to purchase Radeon graphics for this very reason.

      The usual drivel of "But our DEVELOPMENT TIMES!!!!ELEVENTYONE!" is bullshit. Use a real compiler, and not visual studio. Use real winapi, and not the .net McInterfaces. Your product will be much faster, and wont have absurd dependencies.

      No, your raging vagina being hurt by this simple fact is not sufficient reason to foist shit onto end users.

      Thanks.

    3. Re:Fuck nVidia by pezezin · · Score: 1

      I just built a new machine with a Vega 56, and it works perfectly on Linux. You just need a distro with a recent enough kernel that includes the amdgpu driver.

    4. Re:Fuck nVidia by drinkypoo · · Score: 1

      At least we know the drivers will be ok from day one.

      I'm sure they will be of the same high^W quality as Intel's MELTDOWN and SPECTRE patches.

      --
      "You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
    5. Re:Fuck nVidia by Anonymous Coward · · Score: 0

      Yeah, from what I heard Intel 9xx (PCIe) chips have fine drivers. But Intel 8xx (AGP) chips suck ass, and with my ancient 845G system the two only configurations I found to work with adequate stability are using xf86-video-i810 (deprecated 10 years ago) or disabling all acceleration except Xv.

    6. Re:Fuck nVidia by thegarbz · · Score: 1

      Despite the card's age, it worked perfectly

      No man. *Because* of the card's age it worked perfectly. You slot in an 8 year old card from any manufacturer in a Linux box and it works perfectly.

    7. Re:Fuck nVidia by KiloByte · · Score: 1

      Nor for nVidia -- they have already dropped drivers for any generation up to Geforce 500. And nouveau works adequately only for some cards. With nVidia's hostility to independent driver writers, it's a wonder nouveau is even in this state.

      --
      The creatures outside looked from Alt-Right to Antifa; but already it was impossible to say which was which.
    8. Re:Fuck nVidia by Anonymous Coward · · Score: 0

      There are problems still with both AMD and NVIDIA proprietary graphics components.

    9. Re:Fuck nVidia by thegarbz · · Score: 1

      Are you implying that you can't get Linux working on a card of that generation? That would be news to many. Just because someone drops support for a driver doesn't mean that it doesn't work. This is even more certain in the Linux world than anywhere else, and kind of my point: Linux has phenomenal hardware support, but only in the long run.

    10. Re:Fuck nVidia by Anonymous Coward · · Score: 0

      The current Adrenalin control panel is written with Qt, so no .Net bullshit.

    11. Re:Fuck nVidia by Anonymous Coward · · Score: 0

      Thanks for the gratuitous equivocation, chump, but you do realize that AMDGPU is not proprietary right?

  6. Re:All fluff and no substance by Anonymous Coward · · Score: 0, Insightful

    And yet the video speaks for itself. Unless you idiots are going to say that's not really him but some obese diaper wearing manchild body double? Pathetic. You're a coward, you ARE the muffington lol. Feckless Republicans.

    Mueller will handle you soon.

  7. New that's not really new by Anonymous Coward · · Score: 0

    Intel isn't going to magically overnight create a real GPU for the high end graphics market. It may add more horsepower to what it already has but more inline with what we used to call mainstream dedicated graphics which Nvidia and AMD have sort of abandoned because of lack of profit in that area. Most people are fine with Intel graphics for day to day work. But as Intel looks to VR support at least in basic support I think that's more their goal.

    1. Re:New that's not really new by drinkypoo · · Score: 1

      Most people are fine with Intel graphics for day to day work. But as Intel looks to VR support at least in basic support I think that's more their goal.

      Good luck to them, then. They don't have any reasonable plan for becoming competitive in that space. Between MELTDOWN and their inability to drive down failure rates in their new process, Intel has lost their competitive advantage completely. Now they think they're going to suddenly become a credible GPU vendor, in spite of ample historical evidence to the contrary? Tee hee hee.

      At this stage Intel should be focusing on developing a credible Integrated GPU, and worry about discrete ones later. And on becoming a leader in process technology again, no matter how much money they have to burn to do it. It was what kept them relevant.

      --
      "You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
  8. Article has no details at all, just wait til 2020! by IYagami · · Score: 3, Interesting

    From the interview:

    Q: Will Intel’s new GPU architecture eventually migrate down onto the CPU or will the discrete and integrated solutions remain separate architectures?
    A: Leveraging Intel’s broad portfolio of products is critical to building winning platforms: lots of performance, in compelling form factors, in compelling power envelopes. We’re excited by the opportunity to build technologies that will allow us to take experiences, features, and innovation to new and unique form factors, and to an install base of a billion screens around the world.

    Are they going to improve the integrated graphics in their CPUs? (which currently is the weakest link in their offering, AMD Ryzen APUs have Vega GPU cores). According to the interview....... I don't know!

    I think there is WAY more progress in the AMD and ARM front

  9. Uncharacteristically? by drinkypoo · · Score: 1

    Intel has been uncharacteristically vocal about its most recent plans to enter the discrete GPU market.

    What? Like any prior time was secret? Each time has been accompanied by plenty of press releases, and each time so far has been an abject failure. But this time for sure!

    --
    "You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
  10. Re:All fluff and no substance by Anonymous Coward · · Score: 1

    These days I consider Wall Street Journal center left, New Yorker Times left, and New Yorker far left.

      Muffingtonpost? Tis a bad joke.

  11. Re: All fluff and no substance by Anonymous Coward · · Score: 0

    That's stupid. You are the only person who thinks that. You are so far wrong, you are off the chart.

  12. Sure, Intel can do worse! by Anonymous Coward · · Score: 0

    The catastrophe they offered as Windows drivers for their Silicon Image GMA950 based graphics "solutions" back then, makes nVidia drivers look almost elegant.

    1. Re:Sure, Intel can do worse! by _merlin · · Score: 1

      Yeah, the Direct3D drivers for GMA950 were absolutely terrible. Somehow the Windows OpenGL drivers actually support more features (e.g. Windows OpenGL driver supports non-power-of-two textures while Direct3D driver doesn't). They were pretty bad on Mac OS X as well. I had a white MacBook with one, and using an external monitor to extend the desktop would cause regular kernel panics. The way it stole RAM bandwidth from the CPU made performance suck, and that got worse with an external monitor connected, too.

  13. You misspelled LLVM there. by Anonymous Coward · · Score: 0

    And POSIX too. :)

    Also, Vulcan FTW!

  14. Re:All fluff and no substance by Anonymous Coward · · Score: 0

    obese diaper wearing manchild

    How dare you refer to President Bonespur in such demeaning manor. Even if it is true, you have to at least treat the position he holds with a certain amount of respect.

  15. Overpriced, with dedicated HW spyware by Anonymous Coward · · Score: 0

    and with a host of critical HW bugs, just like their CPU lineup! No thanks.

    1. Re:Overpriced, with dedicated HW spyware by HiThere · · Score: 1

      I've got to admit my first though was "How is a GPU going to allow spyware the massively infect systems?". (My real thought was "malware", but only the spyware provides them with any benefit.

      --

      I think we've pushed this "anyone can grow up to be president" thing too far.
  16. Larabee 2.0 by Anonymous Coward · · Score: 0

    The original Larabee cost more to develop than the combined R+D spend of both ATI and Nvidia (at the time) across the entire history of both GPU companies- and Larabee didn't even come close to challenging the WORST GPU's from either industry winner available when Larabee went live.

    Pro-tip: Larabee was designed, at the high level, by Abrash- the REAL talent behind iD's original Quake game. Not beinf one of iD's three owners, Abrash wasn't rewarded well and left iD shortly afterwards. Years later he took he (by then completely obsolete) understanding of a game rendering loop to Intel= which became the Larabee design. Yes, Larabee was rendering like the software rendering of Quake, before Quake was ported to 3DFX's Voodoo.

    Intel's history of engineering is the WORST in the sem-conductor biz, only disguised by the insane amounts of funds Intel is able to throw at new projects. Even then most of them crash and burn. Intel's processor 'success' (only with the x86 branch- other Intel attempts were bombs) has mostly been down to Intel 'borrowing' other company's leading tech (sometime legally, sometimes- as with the Pentium Pro- by stealing every RISC tech possible, then paying tiny fines down the road).

    AMD is great at GPU work (as the consoles from Microsoft and Sony prove) but struggles today in the PC space. Nvidia is the clear leader, but now has to charge the Earth for good discrete GPUs to simply stay in biz. And Nvidia's latest- Turing- has proven to be a tech bomb with each of the Turing chips (3) failing after a short period of time.

    Intel has employed an ex-AMD 'lead' engineer who single handedly SUNK AMD's discrete GPU ambitions, and set AMD behind Nvidia for more than five years. He is guarnteed to make poor Intel engineering even worse.

    Why didn't Intel buy Nvida- well they tried but wouldn't allow the Nvidia boss to take over the merged company. AMD has 'protections' from take-overs few know about (hint- AMD has 'strategic' value. Intel could have bought UK PowerVR, the company behind all of Apple's mobile GPU success until very recently. But Intel's prior partnership with PowerVR proved hopeless when Intel could not write drivers for PowerVR GPUs to save its life.

    Intel is like a recently dead dinosaur- where the message of its death has yet to reach the tail. Intel is out of the CPU biz now in all sectors and was never a runner in the GPU biz. Intel is left trying to TALK a good game to keep its rapidly panicing investors onboard.

    PS Intel has tried to build its own GPU on at least SEVEN different times, and has bought more graphics companies than you can count. Intel's last 'grand idea' was buying the horrific McFee trojan company- and look how that worked out.

    1. Re:Larabee 2.0 by petermgreen · · Score: 1

      Intel is out of the CPU biz now in all sectors

      Lol, intel and AMD are the only CPU vendors with any significant presence in the mid range.

      --
      note: i'm known as plugwash most places but i screwd up registering that here somehow in the past and now can't register
  17. "Will not lag behind..." by Sqreater · · Score: 1

    Oh, man. Should be "Will push ahead of.." They have lost already. The feminized Intel is on a downward spiral. You have to lead your target, not aim directly at it. The new product sounds like it will be merely current GPU technology made proprietary with some Intel IP added to lock clients into Intel's also- ran GPU technology. And if they started doing that three years ago they are already behind in technology. Not a great job Intel.

    --
    E Proelio Veritas.
  18. 'Ray Tracing' dribble. by Anonymous Coward · · Score: 0

    Nvidia's 1200 dollar Turing 2080TI has, like all Truring chips, little ASIC hacks that allow more efficient paths between the triangle rasterising system and the shader system. NONE of these chips has 'ray tracing' units.

    Anyway this ASIC allows the software machine that drives Turing to be reconfigured to do NON-real time ray-tracing back end work for programs like Maya at maybe 10 times the efficieny of Pascal.

    In games though, the ASIC allows around ONE ray per pixel with ONE ray collison at 1080P. Real ray tracing is tens of thousands to millions of rays per pixel, with multiple world space collisions per ray.

    AND to use the ASIC, there is a massive state conversion period to reconfigure the Turing chip when running OpenGL, Vulkan, DX12 or DX11.

    Nvidia's turing had two new techs vs Pascal- this NON-realtime back-end ray tracing accelerator for pro-work that I mentioned. And the so-called tensor cores that Nvidia actually placed into the chip for CRYPTO-CURRENCY mining. You see Nvidia had been working with dodgy new crypto-currency outlets to base new mining algorithms on the low precision 3d matrix multiplier that is a tensor core. Turing was designed up and down to be a MINING card. The mining went bust before Turing released, and Nvidia's boss sold the two unique features FALSELY as 'gaming' features to get PC gamering's most stupid to buy them.

    Ray tracing has existed forever- and has always been understood to be the WORST way to do any form of real-time work. The best CGI cartoons ONLY use ray rendering for special sequences - never for the ordinary pipelines. But it sounds cool to know-nothing dribblers like the OP.

    1. Re:'Ray Tracing' dribble. by mikael · · Score: 1

      There is a raytracing extension to Vulkan and OpenGL which allows an optimized kd-tree to be stored in a buffer and interrogated using custom instructions.

      --
      Vintage computer adverts: http://www.vintageadbrowser.com/computers-and-software-ads
    2. Re:'Ray Tracing' dribble. by Anonymous Coward · · Score: 1

      The tensor ALUs are for "AI/machine-learning" inferencing. Not so great as designed-for-crypto stuff without instructions for all the bitwise manipulation found in those algorithms.

  19. Will its GPUs also have horrible security holes? by Anonymous Coward · · Score: 0

    Just wait until some javascript graphics library running on your GPU can read anything. Why can't intel just tell the NSA to fuck off, and try actually making products that arent shit?

  20. But why? by Anonymous Coward · · Score: 0

    Intel was trying to move from GPUs towards ray-tracing on multi-core CPUs, now that Nvidia is moving to ray-tracing Intel wants to move towards GPUs? Why the role reversal?

    1. Re:But why? by UnknownSoldier · · Score: 1

      Because Intel isn't a perceived "market leader" in the graphics space the way nVidia is.

      But yes, it is rather ironic.

  21. Re: All fluff and no substance by Anonymous Coward · · Score: 0

    The American people didn't treat the office of the President of the United States of America with respect when they elected a reality TV clown.

  22. Was this an interview? by Artem+S.+Tashkinov · · Score: 2

    What a lousy "interview" - I failed to see a single reply for the first six questions and stopped reading at that point.

  23. Might be too little, too late? But .... by King_TJ · · Score: 1

    I hope they're really successful with high performance video chipsets. Right now, I'd welcome additional competition in that space, no matter who is doing it.
    The current situation is pretty ridiculous -- where every single person on the planet interested in 3D gaming or design/CAD/CAM or animation/rendering work is stuck with what one of only two vendors have to offer them.

    Every time people come up with a new reason to buy fast video cards (like crypto-mining the latest e-coin), there's a massive shortage of available cards across the entire industry.

    And it's not terribly difficult to pinpoint the downsides of going the nVidia route, or conversely, going with AMD. A third vendor could figure out how to address those negatives so their offering covers all of the bases.

  24. history by Anonymous Coward · · Score: 0

    As many have pointed out Intel has a history of almost impossibly bad performing gpus. Their discrete GPUs are so bad, that writing your own code in cpu userspace is usually an order of magnitude faster than using their "accelerated" discrete gpus, and that's just for 2d graphics, let alone 3d. I have never seen such pathetic performance in a chip as intel GPUs.

  25. Just in time for the bitcoin mining boom! by Fly+Swatter · · Score: 1

    Oh, wait.

  26. Re:All fluff and no substance by HiThere · · Score: 1

    I must admit that I've never read the Huffington Post, but the rest of your comment tells me more about you than about them. WHY do you consider them whatever you think of as "left".

    --

    I think we've pushed this "anyone can grow up to be president" thing too far.
  27. "amdgpu" driver is all good intentions... by ffkom · · Score: 1

    AMD really seems committed to provide an open source driver, but while the amdgpu driver provides good performance and includes even the most exotic features and newest hardware, it is still full of bugs, and system crashes are all but infrequent.

    When you read the commit messages of Intel drivers, you get the feeling that those who write those drivers know what they are doing, and just need to follow a proper, written down hardware specification.

    In contrast, if you read the commit messages of the "amdgpu" driver, they read almost like random attempts into improving something based on trial and error. Not seldom, the descriptions of consecutive patches to the same file read like: "Implemented X" - "Replaced X with Y" - "Y turned out not to work for some users, replaced with Z" - "Reverted Z because Z broke A for some" ... and so on. The list of open bug reports is ever increasing, with tragically, no end in sight.

  28. Intel should have bought Imagination tech by Anonymous Coward · · Score: 0

    Intel just needs "Good enough" 3d graphics on chip. Imagination tech has good engineers, and drivers, for lower power 3D graphics. In fact, intel has used Imagination IP before.

  29. I have to thank Intel for failing with Larrabee by ffkom · · Score: 1

    Some competent colleagues of mine left Intel right at the time when they were asked to work on software for Larrabee, because they knew right from the start that this project was bound to fail. The very concept of the Larrabee hardware was ridiculously flawed, as anyone with eyes could see. They of course told their supervisors so, but as usual, were not heard.

    Bad for Intel, good for us, as we were back then just hiring.

  30. "plan to use telemetry .. per-user"... WTF? by ffkom · · Score: 1

    In TFA Intel states they "plan to use telemetry and machine learning, on a per-system and per-user basis" - wow, that sounds like a solid threat to turn users into their product, like Facebook does.

  31. Nice Advert Intel. Shame it'll still be shit tho.. by Anonymous Coward · · Score: 0

    ...because everyone patented the already better ways of doing traditional GPUs, and your stuff, will be cumbersome and generally shit (like *every* *time* *before*).

    Best thing would be to start stripping some of that dead weight in your company and start bringing in new talent. You need to churn a little in employees to start getting the good ideas out.

    You don't currently have any. Entering the GPU space with a commitment to 'traditional' GPU'ing when everyone is about to jump to raytracing as the next big thing? Plain stupid. (and I'm really glad I don't have shares in you)

  32. Re:All fluff and no substance by supercell · · Score: 1
    From Wikipedia:

    "HuffPost (formerly The Huffington Post and sometimes abbreviated HuffPo)[2] is a politically left-leaning, American news and opinion website and blog"

    https://en.wikipedia.org/wiki/...

  33. Re:All fluff and no substance by Anonymous Coward · · Score: 0

    The problem with that is simple; American's views of politics are hyper-skewed. Anything that is "left of Ronald Reagan" is somehow left-learning, extreme left or any of those qualifiers.

    People have gotten so used to saying that in this country over decades that it is accepted as the norm and as fact. All you have to do is look at overall voting records and how people approach things.

    For example our past president; as much as you hear all over that he is so "left-learning" or a "leftist extremist" ... all you have to do is see policy and action in nature (drone strikes, etc). He's right-wing (and correctly identified as such by anyone who knows basic Civics 101.

    Left-wing in the USA? You can call something left-wing, someone can claim they are left-wing, etc. but all that matters is performance, we have very little left-wing in this country (especially anyone prominent).

  34. Why ray tracing? by iMadeGhostzilla · · Score: 1

    If its sole purpose is added realism in gaming then I think ray tracing will be almost like VR -- cool and few people will really care about it. Current games have much larger gaps in realism elsewhere than in graphics, for example changing state of objects, sound generation, not to mention AI. That's assuming realism is the most important thing for a game to sell well.

    If the purpose is something else, I'd be curious what that is.

  35. Intel's folly by Anonymous Coward · · Score: 0

    If and when they appear, I'll let the benchmarks do the talking. Not that I'll probably buy and Intel product anyway given their track record of trying to fool the consumer.

  36. Intel's GPU... by Anonymous Coward · · Score: 0

    Trust Intel to screw things up and make GPUs an even more dangerous attack vector (if at all) in to the systems and data channels of the servers/PCs using their offering. This is a fact, based on what they are saying about their offering and history.

  37. Re:All fluff and no substance by Nite_Hawk · · Score: 1

    FWIW, here is how your expectations line up with mediabiasfactcheck.com:

    Wall Street Journal: Highly Factual, Center-Right
    https://mediabiasfactcheck.com...

    New York Times: Highly Factual, Center-Left
    https://mediabiasfactcheck.com...

    New Yorker: High Factual, Left
    https://mediabiasfactcheck.com...

    Whether or not it's their bias or your bias, you seem to view all of those sites one rank to the left relative to how they rate them.

  38. Car turbocompressor fan by Anonymous Coward · · Score: 0

    It's me or in the video that appears in the link looks as if instead of a computer fan they are milling a car turbocharger admission fan? Sure they will make history as long as no spectre gets sucked in.

  39. Why Should We Believe Intel? by Anonymous Coward · · Score: 0

    Intel has a track record, literally going back 20-25 years now. It goes like this: Announce a new GPU, hype the hell out of it. Integrated or discrete, it makes no difference. "Trust us! We are gonna blow your socks off! You won't believe our innovative new graphics technology!"

    Then, a year or two later, said product arrives and proceeds to impress... No One. It sucks, other vendors got there first and did a much better job. All the marketing flacks who pushed their garbage are either gone or 'unavailable to comment'.

    Now my attitude is, 'you are right. I'm not gonna believe it. You folks keep pushing turds out on to the market and you expect me to keep falling for it?' Either ante up with some good stuff or GTFO. And you get no, zero, nada credibility for marketing vapourware. Prior to establishing your bona fides, I consider you to be a hired huckster, willing to say anything for money.

    Intel burned up it's GPU goodwill a long time ago. The sad part is that there are an endless stream of suckers out there, still buying tickets to this particular show.

  40. horomone and Larabee by epine · · Score: 1

    There's probably a secret messages encoded in Slashdot's delightful crop of fresh misspellings.