Announcement

Collapse

How To Post News

When posting a news article please take a look at our how to Here

See more
See less

Nvidia 3080 Ti & Ampere FULL Leak: 7nm EUV & 18Gbps needed to Defeat AMD RDNA 2

Collapse
X
Collapse
First Prev Next Last
Currently Active Users Viewing This Thread: 4 (0 members and 4 guests)
 
  • Filter
  • Time
  • Show
Clear All
new posts

  • [YOUTUBE] Nvidia 3080 Ti & Ampere FULL Leak: 7nm EUV & 18Gbps needed to Defeat AMD RDNA 2



    This is starting to get me ''Amped''
    Signature
    Welcome to EHW
    Site Guide & Features
    Follow EHW On Facebook & Twitter
    Site projects supported by your donations

    Enjoying the site with no Ads ? Helps us keep EHW Ad and bloat free by purchasing a Premium Account
    CPU
    AMD Ryzen 9 3950X (16 Core/32 Thread) @ 4525/4500/4500/4350 (1.36v)
    Motherboard
    Asrock X570 Aqua (Run 783/999)
    GPU
    Quadro 1800 (Placeholder for 3080Ti Upgrade)
    Memory
    32GB Gskill Trident Z @3800Mhz (16/16/17/16/32)
    PSU
    EVGA 1600 Watt Supernova P2
    Storage
    1x 500GB Seagate Firecuda PCIe Gen4 (M.2)
    Storage
    1x 1TB Seagate Firecuda PCIe Gen4 (M.2)
    Cooling
    Custom WC
    Monitor
    Acer Predator X34 (Ultrawide)
    Case
    Be Quiet Dark Base Pro 900 V2
    Operating System
    Windows 10 Pro X64
    Collapse

  • #2
    Originally posted by ENTERPRISE View Post


    This is starting to get me ''Amped''

    ...things are definitely heating up in the 'pre-Ampere' release arena - apart from NVidia's briefing event tomorrow which may be more focused on next-gen pro cards. Also, similar info from TweakTown a few days ago.

    If all this is true, NVidia seems to re-establish a clearer line between their consumer and pro models: GA100 *Specs* - 8192 CUDA cores, 1024 Tensor Cores, 256 RT Cores. That one might tidy me over until Hopper
    Collapse

    Comment


    • #3
      Originally posted by J7SC_Orion View Post


      ...things are definitely heating up in the 'pre-Ampere' release arena - apart from NVidia's briefing event tomorrow which may be more focused on next-gen pro cards. Also, similar info from TweakTown a few days ago.

      If all this is true, NVidia seems to re-establish a clearer line between their consumer and pro models: GA100 *Specs* - 8192 CUDA cores, 1024 Tensor Cores, 256 RT Cores. That one might tidy me over until Hopper
      So you would got for the Titan RTX (Or whatever they choose to call it for the Ampere series) ?
      Signature
      Welcome to EHW
      Site Guide & Features
      Follow EHW On Facebook & Twitter
      Site projects supported by your donations

      Enjoying the site with no Ads ? Helps us keep EHW Ad and bloat free by purchasing a Premium Account
      CPU
      AMD Ryzen 9 3950X (16 Core/32 Thread) @ 4525/4500/4500/4350 (1.36v)
      Motherboard
      Asrock X570 Aqua (Run 783/999)
      GPU
      Quadro 1800 (Placeholder for 3080Ti Upgrade)
      Memory
      32GB Gskill Trident Z @3800Mhz (16/16/17/16/32)
      PSU
      EVGA 1600 Watt Supernova P2
      Storage
      1x 500GB Seagate Firecuda PCIe Gen4 (M.2)
      Storage
      1x 1TB Seagate Firecuda PCIe Gen4 (M.2)
      Cooling
      Custom WC
      Monitor
      Acer Predator X34 (Ultrawide)
      Case
      Be Quiet Dark Base Pro 900 V2
      Operating System
      Windows 10 Pro X64
      Collapse

      Comment


      • #4
        Originally posted by ENTERPRISE View Post

        So you would got for the Titan RTX (Or whatever they choose to call it for the Ampere series) ?

        ...depends on pricing. But with RTX, 2080 Ti has 4352 Cuda / 544 tensor versus Titan RTX, Quadro RTX8000 et al that have 4608 Cuda / 576 tensor (Tesla V100 is a different beast / architecture). So the much 'cheaper' (lol) 2080 Ti RTX is already very close to the full-fat RTX, and with some custom PCBs can match the Titan RTX etc via higher clocks. It only really depends on whether the extra Titan RTX VRAM and select other features are needed by the user.

        If the Ampere rumours pan out, the new top-spec G100 has 8192 Cuda and 1024 tensor vs. G102 (3080 Ti ?) at 5376 Cuda and (? tensor)...a much more dramatic difference. But Nvidia will undoubtedly charge for this extra oomph. One wildcard re. purchasing decisions is what AMD's Big Navi and Intel's Xe end up bringing to the table and at what price...another one is 'Hopper' lurking
        Last edited by J7SC_Orion; 13-05-2020, 06:12 PM.
        Collapse

        Comment


        • #5
          That is some interesting stuff!
          Wonder what the 30xx range will do folding wise, but for now I'm happy with the 2080ti.
          Signature
          Case
          Fractal Design Define 7XL
          Motherboard
          ASRock Z170 Extreme7+
          CPU
          I7 7700k
          Memory
          Corsair Vengeance RGB 32GB
          GPU
          ASUS RTX 2080Ti
          Storage
          Gigabyte Aorus RGB PCIe 1TB
          PSU
          Corsair RM850x
          Keyboard
          Corsair K95 RGB Platinum
          Mouse
          Corsair M65 RGB Elite
          Other
          Corsair MM800 RGB Polaris
          Monitor
          IIyama G-Master
          Audio
          Logitech 5.1
          Cooling
          Custom CPU and GPU Watercooling
          Case
          CoolerMaster HAF 932
          Motherboard
          ASRock B365 Pro4
          CPU
          Intel Core i3-9100F
          Memory
          Corsair Vengeance LPX 8GB
          GPU
          MSI Radeon RX 5700 XT MECH OC
          GPU
          MSI Radeon RX 5700 XT MECH OC
          Storage
          Intel 660p Series 512GB
          PSU
          Corsair HX850W
          Keyboard
          Logitech G11
          Mouse
          Logitech G500s
          Cooling
          CoolerMaster Hyper 212 Black Edition
          Collapse

          Comment


          • #6
            Originally posted by J7SC_Orion View Post


            ...depends on pricing. But with RTX, 2080 Ti has 4352 Cuda / 544 tensor versus Titan RTX, Quadro RTX8000 et al that have 4608 Cuda / 576 tensor (Tesla V100 is a different beast / architecture). So the much 'cheaper' (lol) 2080 Ti RTX is already very close to the full-fat RTX, and with some custom PCBs can match the Titan RTX etc via higher clocks. It only really depends on whether the extra Titan RTX VRAM and select other features are needed by the user.

            If the Ampere rumours pan out, the new top-spec G100 has 8192 Cuda and 1024 tensor vs. G102 (3080 Ti ?) at 5376 Cuda and (? tensor)...a much more dramatic difference. But Nvidia will undoubtedly charge for this extra oomph. One wildcard re. purchasing decisions is what AMD's Big Navi and Intel's Xe end up bringing to the table and at what price...another one is 'Hopper' lurking
            I think that this round in order to protect the Titan RTX, they really need to distance that SKU from the Ti range, otherwise aside from the additional VRAM, the Titan RTX is just lost. It will be interesting to see what RDNA 2 brings, Intel Xe wont be able to compete IMHO with AMD's and Nvidia's next offering. Not saying they will not be impressive, but last time I looked they were not even really aiming for the gaming market all that much.
            Signature
            Welcome to EHW
            Site Guide & Features
            Follow EHW On Facebook & Twitter
            Site projects supported by your donations

            Enjoying the site with no Ads ? Helps us keep EHW Ad and bloat free by purchasing a Premium Account
            CPU
            AMD Ryzen 9 3950X (16 Core/32 Thread) @ 4525/4500/4500/4350 (1.36v)
            Motherboard
            Asrock X570 Aqua (Run 783/999)
            GPU
            Quadro 1800 (Placeholder for 3080Ti Upgrade)
            Memory
            32GB Gskill Trident Z @3800Mhz (16/16/17/16/32)
            PSU
            EVGA 1600 Watt Supernova P2
            Storage
            1x 500GB Seagate Firecuda PCIe Gen4 (M.2)
            Storage
            1x 1TB Seagate Firecuda PCIe Gen4 (M.2)
            Cooling
            Custom WC
            Monitor
            Acer Predator X34 (Ultrawide)
            Case
            Be Quiet Dark Base Pro 900 V2
            Operating System
            Windows 10 Pro X64
            Collapse

            Comment


            • #7
              Well, fresh from Jensen Huang's kitchen per this mornings event: Not much on Ampere 'gaming' yet, but as expected, on data-center versions. Top Ampere data-center version seems to have 6912 Cudas (not 8192 as per earlier leaks) - for now, anyway ;-)

              That's still a lot of room for various lower-level versions, such as Titan and Ti. It seems the whole generation will run on the same base architecture (thus including 'GeForce'), but obviously w/ different Cuda, tensor counts and VRAM types (HBM2 vs GDDR) and amounts.




              Collapse

              Comment


              • #8
                It is certainly an impressive lineup, lets hope the same for the consumer hardware !
                Signature
                Welcome to EHW
                Site Guide & Features
                Follow EHW On Facebook & Twitter
                Site projects supported by your donations

                Enjoying the site with no Ads ? Helps us keep EHW Ad and bloat free by purchasing a Premium Account
                CPU
                AMD Ryzen 9 3950X (16 Core/32 Thread) @ 4525/4500/4500/4350 (1.36v)
                Motherboard
                Asrock X570 Aqua (Run 783/999)
                GPU
                Quadro 1800 (Placeholder for 3080Ti Upgrade)
                Memory
                32GB Gskill Trident Z @3800Mhz (16/16/17/16/32)
                PSU
                EVGA 1600 Watt Supernova P2
                Storage
                1x 500GB Seagate Firecuda PCIe Gen4 (M.2)
                Storage
                1x 1TB Seagate Firecuda PCIe Gen4 (M.2)
                Cooling
                Custom WC
                Monitor
                Acer Predator X34 (Ultrawide)
                Case
                Be Quiet Dark Base Pro 900 V2
                Operating System
                Windows 10 Pro X64
                Collapse

                Comment

                Working...
                X