Sign in with
Sign up | Sign in

Nvidia Reveals Next-Generation "Pascal" GPU for 2016

By - Source: Tom's Hardware US | B 45 comments
Tags :

Pascal will use 3D packaging and a new tech called NVLink.

During GTC 2014, Nvidia CEO Jen-Hsun Huang revealed the next-generation GPU, Pascal. This chip is aimed at next-generation super-computers, workstations, gaming PCs and cloud super-computers. The chip is also based on a technology called NVLink, and uses 3D memory to amplify the bandwidth between the GPU and memory sub-system. Pascal fits in a module that's a third the size of a PCIe card.

NVLink is chip-to-chip communications. The programming model is basically PCI Express with enhanced DMA capability, Huang said, and that software can adopt this interface very easily. This solution enables programmers to bind memory between the CPU and GPU, the GPU and GPU, and the second generation cache coherency between the GPU and CPU cache.

"One of the benefits of parallel computing is to be able to take all these GPUs and put them in parallel, and treat them like one big massive GPU. If we'd only have the bandwidth to communicate from GPU to GPU," Huang said during the keynote. "NVLink allows us to do just that."

He also described 3D packaging: for the first time, Nvidia is building heterogeneous chips on top of other chips on a single wafer. This solution starts off with a base wafer where interconnections are carried out among the chips. Thus, instead of going off to a PC board, Nvidia is doing the interchip routing on the wafer itself.

"Thousands of little bumps characterized by that vertical signal on these chips are flipped and bumped onto the base wafer," Huang explained. "The interface went from hundreds of bits to thousands of bits. You can just imagine a GPU with thousands and thousands of memory interfaced bits."

He said Nvidia stacked the memory bits one on top of the other, and punched holes through them. Each DRAM is then stacked on top of each other, all stacked on top of a wafer that can have incredibly small wires that connect to the GPU.

After announcing Pascal, Huang revealed a roadmap with a release schedule for some time in 2016, following Maxwell in 2014 and Kepler in 2012. Thanks to the NVLink and 3D packaging, the company can continue to scale with Moore's Law, Huang said.

Check out more Nvidia news from GTC here.

Add your comment Display 46 Comments.
Top Comments
  • 37 Hide
    CaptainTom , March 25, 2014 3:09 PM
    Quote:
    Whats AMD's solution to this?
    A card that is 5% weaker and half the price...
  • 26 Hide
    HiTechObsessed , March 25, 2014 2:17 PM
    They need to announce the release of Maxwell GPUs before announcing the next-next generation graphics cards lol
  • 14 Hide
    warezme , March 25, 2014 2:34 PM
    what the heck? There isn't even a decent Maxwell desktop GPU out yet and we have a fancy Pascal outing already?
Other Comments
  • 26 Hide
    HiTechObsessed , March 25, 2014 2:17 PM
    They need to announce the release of Maxwell GPUs before announcing the next-next generation graphics cards lol
  • -2 Hide
    StarBound , March 25, 2014 2:19 PM
    I'm getting a 780ti this week. Will I replace my card before the end of the year then?
  • 1 Hide
    Jack Revenant , March 25, 2014 2:25 PM
    I'd wager that this will be a real success for Nvidia.
  • 14 Hide
    warezme , March 25, 2014 2:34 PM
    what the heck? There isn't even a decent Maxwell desktop GPU out yet and we have a fancy Pascal outing already?
  • -4 Hide
    spartanmk2 , March 25, 2014 2:40 PM
    Whats AMD's solution to this?
  • 37 Hide
    CaptainTom , March 25, 2014 3:09 PM
    Quote:
    Whats AMD's solution to this?
    A card that is 5% weaker and half the price...
  • -2 Hide
    ferooxidan , March 25, 2014 3:21 PM
    Please Tom, out with GTX Titan Z preview and review already!
  • 12 Hide
    Gin Fushicho , March 25, 2014 3:26 PM
    Quote:
    Quote:
    Quote:
    Whats AMD's solution to this?
    A card that is 5% weaker and half the price...
    And what are the bitcoin miner's answer to that?Yep, you guessed it. Thanks Obam-uh, Bitcoin.
    Scrypt-coin.... not Bitcoin. Nobody mines Bitcoins with GPU's.
  • 0 Hide
    dark_knight33 , March 25, 2014 5:30 PM
    Quote:
    [And what are the bitcoin miner's answer to that?Yep, you guessed it. Blah, blah, blah.
    Seriously...? Stupidest comment I've read all week.
  • -5 Hide
    danwat1234 , March 25, 2014 8:10 PM
    So.. cancer will be cured by 2017 or so thanks to these GPUs? Maybe
  • 6 Hide
    renz496 , March 25, 2014 8:18 PM
    Quote:
    what the heck? There isn't even a decent Maxwell desktop GPU out yet and we have a fancy Pascal outing already?


    nothing new. we know there will be maxwell (in name only) since fermi.
  • 6 Hide
    10tacle , March 25, 2014 9:21 PM
    Quote:
    nothing new. we know there will be maxwell (in name only) since fermi.


    True, Nvidia has always shown us two or three generations ahead on a map of the future. But I don't ever remember them giving this much technical detail before in a product two generations away from the current one.
  • 0 Hide
    The_Icon , March 25, 2014 10:07 PM
    With so much processing power, GPUs should take part in more CPU tasks instead of sitting idly.
  • -1 Hide
    schnitter , March 25, 2014 10:07 PM
    Have a 680 GTX, not interested in any video card until DirectX 12 comes out. Useless to spend money on top-end now when DirectX 12 is around the corner.
  • 3 Hide
    renz496 , March 25, 2014 10:15 PM
    Quote:
    Quote:
    nothing new. we know there will be maxwell (in name only) since fermi.


    True, Nvidia has always shown us two or three generations ahead on a map of the future. But I don't ever remember them giving this much technical detail before in a product two generations away from the current one.


    i think nvidia are trying to win more contract in the future that's why they are talking stuff that will not coming 2 years later right now. they need to convince those company why choosing nvidia is the right choice. nvidia used to dominate the HPC stuff with their Tesla but now they got more competition from AMD and Intel (Xeon Phi) in that space. releasing a bit of info about upcoming architecture could be one of their strategy
  • 6 Hide
    Christopher Sellard , March 25, 2014 10:30 PM
    Quote:
    Have a 680 GTX, not interested in any video card until DirectX 12 comes out. Useless to spend money on top-end now when DirectX 12 is around the corner.
    um dx 12 is coming to older generation cards that currently have dx 11
  • 5 Hide
    tomfreak , March 25, 2014 10:49 PM
    let me guess, future motherboard instead of having SLI capable, they will have a Nvlink capable as a "feature"?
  • 3 Hide
    thor220 , March 25, 2014 11:19 PM
    It would be allot easier to convince mobo manufacturers to use your new proprietary NLink interface if say it was beneficial to them. In Nvidia's case, they expect the mobo manufacturers to hop for them on some niche product that will cost more to add onto motherboards. You can't have your cake and eat it too Nvidia. If you want mobos to use the new interface, you have to open it up to AMD and Intel. It's just not economical for them to accept it as a standard.
  • 0 Hide
    renz496 , March 25, 2014 11:35 PM
    Quote:
    It would be allot easier to convince mobo manufacturers to use your new proprietary NLink interface if say it was beneficial to them. In Nvidia's case, they expect the mobo manufacturers to hop for them on some niche product that will cost more to add onto motherboards. You can't have your cake and eat it too Nvidia. If you want mobos to use the new interface, you have to open it up to AMD and Intel. It's just not economical for them to accept it as a standard.


    from what i understand this NVLink is for HPC and server stuff only although there are possibility for nvidia to incorporate this tech into their SLI technology. maybe they can make something similar to NF200 chipset.

    Quote:
    NVLink was created chiefly for use in supercomputing clusters and other enterprise-class deployments where many GPUs may be installed into a single server. Interestingly, as part of today's announcements, IBM revealed that it will incorporate NVLink into future CPUs. We don't have any details yet about which CPUs or what proportion of the Power CPU lineup will use NVLink, though.


    http://techreport.com/news/26226/nvidia-pascal-to-use-stacked-memory-proprietary-nvlink-interconnect

    EDIT: from anandtech article it seems NVLink will ditch PCI/PCIE slot altogether and will have it's own connector. so i don't think we are going to see NVLink on regular dekstop mobo.

    Quote:
    But the rabbit hole goes deeper. To pull off the kind of transfer rates NVIDIA wants to accomplish, the traditional PCI/PCIe style edge connector is no good; if nothing else the lengths that can be supported by such a fast bus are too short. So NVLink will be ditching the slot in favor of what NVIDIA is labeling a mezzanine connector, the type of connector typically used to sandwich multiple PCBs together (think GTX 295).


    Quote:
    With all of that said, while NVIDIA has grand plans for NVLink, it’s also clear that PCIe isn’t going to be completely replaced anytime soon on a large scale. NVIDIA will still support PCIe – in fact the blocks can talk PCIe or NVLink – and even in NVLink setups there are certain command and control communiques that must be sent through PCIe rather than NVLink. The best case scenario for NVLink right now is that it takes hold in servers, while workstations and consumers would continue to use PCIe as they do today.


    http://www.anandtech.com/show/7900/nvidia-updates-gpu-roadmap-unveils-pascal-architecture-for-2016
Display more comments
React To This Article