Sign in

back to article Ampere, Nvidia's latest GPU architecture is finally here – spanking-new acceleration for AI across the board

Nvidia has lifted the lid on a fresh line of products based on its latest Ampere architecture, revealing its latest A100 GPU - which promises to be 20X more powerful than its predecessor and capable of powering AI supercomputers – as well as a smaller chip for running machine learning workloads on IoT devices. CEO Jensen Huang …

COMMENTS

Post your comment
House rules Send corrections
Add to 'My topics' unstar *
  1. Rameses Niblick the Third Kerplunk Kerplunk Whoops Where's My Thribble?
    Trollface

    That's all very impressive...

    ...but can it run Crysis?

    4 1 Reply
    1. Anonymous Coward
      Reply Icon
      Anonymous Coward

      Re: That's all very impressive...

      Yes but it can't run Doom... Original Doom... Dammit, that joke used to be funny.

      5 0 Reply
      1. Mr Sceptical
        Reply Icon
        Terminator

        Re: That's all very impressive...

        I was going to come in with the Crysis question, with a tangent:

        Can it give you a realistic, learning, Turing test (of behaviour) passing, AI foe in Crysis?

        And once it's beaten the best humanity can offer, time to power up the cyborgs and ROTM! --->

        0 0 Reply
    2. Anonymous Coward
      Reply Icon
      Anonymous Coward

      Re: That's all very impressive...

      Crysis....?

      I'm not holding out much hope of it being able to run a modern desktop.

      Still waiting on being able to run Wayland with Nvidia hardware....

      Not very impressive at all if they can't cover the basics.

      0 0 Reply
  2. Gonzo wizard
    Meh

    OK ok so it's fast

    But I wouldn't want the electricity bill. 400W per GPU at full utilisation. And the SuperPod - 1120 GPUs or 450Kw per hour at full utilisation... granted it is a more efficient platform than your regular CPU for ML but the heat... the running cost... :-

    2 0 Reply
    1. Stephen 1
      Reply Icon
      Headmaster

      Re: OK ok so it's fast

      Yeah that's a lot of energy, 1.62e+9 Joules in fact. Then of course you need to run it for more than one hour.

      0 0 Reply
    2. Boothy Silver badge
      Reply Icon

      Re: OK ok so it's fast

      Just as a comparison, some current GeForce RTX 2080 Ti cards pull over 300W at full load (reference cards are around 280W).

      That's with a Turing card, so on the TSMC 12nm process. Ampere uses 7nm instead, and is still pulling ~33% more power!

      0 0 Reply
    3. MiguelC Silver badge
      Reply Icon
      Mushroom

      Re: OK ok so it's fast

      I bet NVidia will soon start marketing their brand new "Personal nuclear power plants (TM)"

      2 0 Reply
  3. Ian Johnston Silver badge

    Does anyone use these for graphics?

    1 0 Reply
    1. Boothy Silver badge
      Reply Icon

      Do you mean directly? As in a workstation/PC?

      If so, then no, at least not as far as I know. The A100s' are specifically designed for data-centre usage. They don't even have video output on them.

      But Ampere, the microarcitecture the new A100 is built on, is coming to workstation and mainstream cards at some point, we just don't know when yet.

      For ref, nVidia have stated the Ampere based chips will replace all current mainstream consumer (i.e. regular GTX/RTX), prosumer (Titan) and professional (Quadro) cards. With the expectation being that the Titan and Quadro cards will be similar, if not the same as the chips being used in the A100, and the other cards being a cut down version (i.e. less CUDA cores etc).

      3 0 Reply
  4. Mike 137 Silver badge

    Impressive, but ...

    This is hardly just a "GPU" any more, is it? It may use the architectures developed for graphics processing, but it's more likely destined for deep data and AI rather than merely putting up animated screenfulls.

    0 1 Reply
    1. steelpillow Silver badge
      Reply Icon
      Facepalm

      Re: Impressive, but ...

      I believe that the G nowadays stand for General rather than niche Graphics (which it presumably also does rather well).

      1 0 Reply
  5. Anonymous Coward
    Anonymous Coward

    No love for AMD's new Radeon VII Pro then?

    0 2 Reply
  6. Nursing A Semi

    But

    As far as shareholders are aware, all these A100s are going to be sold to gamers to power their rigs for the next generation of mincraft surely?

    0 0 Reply
    1. Marcelo Rodrigues
      Reply Icon
      Joke

      Re: But

      "As far as shareholders are aware, all these A100s are going to be sold to gamers to power their rigs for the next generation of mincraft surely?"

      That's where the profits come from, you know. They will only sue if someone starts mining cryptocoins with it...

      0 0 Reply

POST COMMENT House rules

Not a member of The Register? Create a new account here.

Forgotten password ?

  • Enter your comment

  • Add an icon

Anonymous cowards cannot choose their icon

Other stories you might like

  • Nvidia wants to lure you to the Arm side with fresh server bait
    GPU giant promises big advancements with Arm-based Grace CPU, says the software is ready
    Dylan Martin Fri 17 Jun 2022 // 19:17 UTC

    Interview 2023 is shaping up to become a big year for Arm-based server chips, and a significant part of this drive will come from Nvidia, which appears steadfast in its belief in the future of Arm, even if it can't own the company.

    Several system vendors are expected to push out servers next year that will use Nvidia's new Arm-based chips. These consist of the Grace Superchip, which combines two of Nvidia's Grace CPUs, and the Grace-Hopper Superchip, which brings together one Grace CPU with one Hopper GPU.

    The vendors lining up servers include American companies like Dell Technologies, HPE and Supermicro, as well Lenovo in Hong Kong, Inspur in China, plus ASUS, Foxconn, Gigabyte, and Wiwynn in Taiwan are also on board. The servers will target application areas where high performance is key: AI training and inference, high-performance computing, digital twins, and cloud gaming and graphics.

    Continue reading
  • Lenovo reveals small but mighty desktop workstation
    ThinkStation P360 Ultra packs latest Intel Core processor, Nvidia RTX A5000 GPU, support for eight monitors
    Dan Robinson Thu 23 Jun 2022 // 17:14 UTC

    Lenovo has unveiled a small desktop workstation in a new physical format that's smaller than previous compact designs, but which it claims still has the type of performance professional users require.

    Available from the end of this month, the ThinkStation P360 Ultra comes in a chassis that is less than 4 liters in total volume, but packs in 12th Gen Intel Core processors – that's the latest Alder Lake generation with up to 16 cores, but not the Xeon chips that we would expect to see in a workstation – and an Nvidia RTX A5000 GPU.

    Other specifications include up to 128GB of DDR5 memory, two PCIe 4.0 slots, up to 8TB of storage using plug-in M.2 cards, plus dual Ethernet and Thunderbolt 4 ports, and support for up to eight displays, the latter of which will please many professional users. Pricing is expected to start at $1,299 in the US.

    Continue reading
  • Nvidia taps Intel’s Sapphire Rapids CPU for Hopper-powered DGX H100
    A win against AMD as a much bigger war over AI compute plays out
    Dylan Martin Tue 7 Jun 2022 // 19:30 UTC

    Nvidia has chosen Intel's next-generation Xeon Scalable processor, known as Sapphire Rapids, to go inside its upcoming DGX H100 AI system to showcase its flagship H100 GPU.

    Jensen Huang, co-founder and CEO of Nvidia, confirmed the CPU choice during a fireside chat Tuesday at the BofA Securities 2022 Global Technology Conference. Nvidia positions the DGX family as the premier vehicle for its datacenter GPUs, pre-loading the machines with its software and optimizing them to provide the fastest AI performance as individual systems or in large supercomputer clusters.

    Huang's confirmation answers a question we and other observers have had about which next-generation x86 server CPU the new DGX system would use since it was announced in March.

    Continue reading
  • Arm jumps on ray tracing bandwagon with beefy GPU design
    British chip designer’s reveal comes months after mobile RT moves by AMD, Imagination
    Dylan Martin Tue 28 Jun 2022 // 15:00 UTC

    Arm is beefing up its role in the rapidly-evolving (yet long-standing) hardware-based real-time ray tracing arena.

    The company revealed on Tuesday that it will introduce the feature in its new flagship Immortalis-G715 GPU design for smartphones, promising to deliver graphics in mobile games that realistically recreate the way light interacts with objects.

    Arm is promoting the Immortalis-G715 as its best mobile GPU design yet, claiming that it will provide 15 percent faster performance and 15 percent better energy efficiency compared to the currently available Mali-G710.

    Continue reading
  • Nvidia, Siemens tout 'industrial metaverse' to predict the future
    Using Pixar-derived tech to make digital twins immersive
    Tobias Mann Thu 30 Jun 2022 // 07:35 UTC

    Siemens and Nvidia don’t want manufacturers to imagine what the future will hold – they want to build a fancy digital twin that helps them to make predictions about whatever comes next.

    During a press conference this week, Siemens CEO Roland Busch painted a picture of a future in which manufacturers are besieged with productivity, labor, and supply chain disruptions.

    "The answer to all of these challenges is technology and digitalization," he said. "The point is, we have to make the digital twin as realistic as possible and bring it as close as possible to the real world."

    Continue reading
  • Meta: We need 5x more GPUs to combat TikTok, stat
    And 30% fewer new engineers this year
    Dylan Martin Thu 30 Jun 2022 // 22:30 UTC

    Comment Facebook parent Meta has reportedly said it needs to increase its fleet of datacenter GPUs fivefold to help it compete against short-form video app and perennial security concern TikTok.

    The oft-controversial tech giant needs these hardware accelerators in its servers by the end of the year to power its so-called discovery engine that will become the center of future social media efforts, according to an internal memo seen by Reuters that was written by Meta Chief Product Officer Chris Cox.

    Separately, CEO Mark Zuckerberg told Meta staff on Thursday in a weekly Q&A the biz had planned to hire 10,000 engineers this year, and this has now been cut to between 6,000 and 7,000 in the shadow of an economic downturn. He also said some open positions would be removed, and pressure will be placed on the performance of those staying at the corporation.

    Continue reading
  • Restructure at Arm focused on 'non-engineering' roles
    Meanwhile, CEO wants to vacuum up engineering talent amid return to stock market
    Dan Robinson Tue 28 Jun 2022 // 13:30 UTC

    Updated Arm today told The Reg its restructuring ahead of its return to the stock market is focused on cutting "non-engineering" jobs.

    This is after we queried comments made this morning by Arm chief executive Rene Haas in the Financial Times, in which he indicated he was looking to use funds generated by the expected public listing to expand the company, hire more staff, and potentially pursue acquisitions. This comes as some staff face the chop.

    This afternoon we were told by an Arm spokesperson: "Rene was referring more to the fact that Arm continues to invest significantly in its engineering talent, which makes up around 75 percent of the global headcount. For example, we currently have more than 250 engineering roles available globally."

    Continue reading
  • PCIe 7.0 pegged to arrive in 2025 with speeds of 512 GBps
    Although PCIe 5.0 is just coming to market, here's what we can expect in the years ahead
    Dan Robinson Wed 22 Jun 2022 // 15:30 UTC

    Early details of the specifications for PCIe 7.0 are out, and it's expected to deliver data rates of up to 512 GBps bi-directionally for data-intensive applications such as 800G Ethernet.

    The announcement from the The Peripheral Component Interconnect Special Interest Group (PCI SIG) was made to coincide with its Developers Conference 2022, held at the Santa Clara Convention Center in California this week. It also marks the 30th anniversary of the PCI-SIG itself.

    While the completed specifications for PCIe 6.0 were only released this January, PCIe 7.0 looks to double the bandwidth of the high-speed interconnect yet again from a raw bit rate of 64 GTps to 128 GTps, and bi-directional speeds of up to 512 GBps in a x16 configuration.

    Continue reading
  • Nvidia brings liquid cooling to A100 PCIe GPU cards for ‘greener’ datacenters
    For those who want to give their racks an air cut
    Dylan Martin Tue 24 May 2022 // 04:00 UTC

    Computex Nvidia's GPUs are becoming increasingly more power hungry, so the US giant is hoping to make datacenters using them "greener" with liquid-cooled PCIe cards that contain its highest-performing chips.

    At this year's Computex event in Taiwan, the computer graphics goliath revealed it will sell a liquid-cooled PCIe card for its flagship server GPU, the A100, in the third quarter of this year. Then in early 2023, the company plans to release a liquid-cooled PCIe card for the A100's recently announced successor, the Hopper-powered H100.

    Nvidia's A100 has already been available for liquid-cooled servers, but to date, this has only been possible in the GPU's SXM form factor that goes into the company's HGX server board.

    Continue reading
  • Will optics ever replace copper interconnects? We asked this silicon photonics startup
    Star Trek's glowing circuit boards may not be so crazy
    Tobias Mann Sat 18 Jun 2022 // 09:05 UTC

    Science fiction is littered with fantastic visions of computing. One of the more pervasive is the idea that one day computers will run on light. After all, what’s faster than the speed of light?

    But it turns out Star Trek’s glowing circuit boards might be closer to reality than you think, Ayar Labs CTO Mark Wade tells The Register. While fiber optic communications have been around for half a century, we’ve only recently started applying the technology at the board level. Despite this, Wade expects, within the next decade, optical waveguides will begin supplanting the copper traces on PCBs as shipments of optical I/O products take off.

    Driving this transition are a number of factors and emerging technologies that demand ever-higher bandwidths across longer distances without sacrificing on latency or power.

    Continue reading

Biting the hand that feeds IT © 1998–2022

Do not sell my personal information Cookies Privacy Ts&Cs