Results 1 to 7 of 7

Thread: AMD Radeon Instinct MI60 and MI50 accelerators announced

  1. #1
    HEXUS.admin
    Join Date
    Apr 2005
    Posts
    30,050
    Thanks
    0
    Thanked
    1,939 times in 680 posts

    AMD Radeon Instinct MI60 and MI50 accelerators announced

    The world’s first 7nm data centre GPUs deliver “supercharged compute performance”.
    Read more.

  2. #2
    Senior Member
    Join Date
    Apr 2004
    Location
    Geneva, Switzerland
    Posts
    325
    Thanks
    0
    Thanked
    22 times in 12 posts

    Re: AMD Radeon Instinct MI60 and MI50 accelerators announced

    How this compares with Vega 64 (in TFLOPS)?
    Well Vega 64 has 25.3 TFLOPS (FP16) and this one has 29.5 TFLOPS FP16, so 16% improvement?
    or 12.7 TFLOPS (FP32) vs 14.7 for the new one so 16% better

    These are not great numbers or I am doing something wrong?
    The more you live, less you die. More you play, more you die. Isn't it great.

  3. #3
    Senior Member
    Join Date
    May 2014
    Posts
    1,701
    Thanks
    103
    Thanked
    223 times in 160 posts

    Re: AMD Radeon Instinct MI60 and MI50 accelerators announced



    *cleans self up*

    Ahem, that's pretty impressive. Liking the Hive system with the Infinity Fabric ring, would like to know more.

  4. #4
    Moosekateer CAT-THE-FIFTH's Avatar
    Join Date
    Aug 2006
    Location
    Not here
    Posts
    29,637
    Thanks
    3,336
    Thanked
    4,664 times in 3,598 posts
    • CAT-THE-FIFTH's system
      • Motherboard:
      • Less E-PEEN
      • CPU:
      • Massive E-PEEN
      • Memory:
      • RGB E-PEEN
      • Storage:
      • Not in any order
      • Graphics card(s):
      • EVEN BIGGER E-PEEN
      • PSU:
      • OVERSIZED
      • Case:
      • UNDERSIZED
      • Operating System:
      • DOS 6.22
      • Monitor(s):
      • NOT USUALLY ON....WHEN I POST
      • Internet:
      • FUNCTIONAL

    Re: AMD Radeon Instinct MI60 and MI50 accelerators announced

    Quote Originally Posted by darcotech View Post
    How this compares with Vega 64 (in TFLOPS)?
    Well Vega 64 has 25.3 TFLOPS (FP16) and this one has 29.5 TFLOPS FP16, so 16% improvement?
    or 12.7 TFLOPS (FP32) vs 14.7 for the new one so 16% better

    These are not great numbers or I am doing something wrong?
    Think of this card as 14NM Vega but with expanded INT4,INT8 and FP64 throughput and 4 stacks of HBM2 instead of 2:

    https://www.anandtech.com/show/13562...ed-by-7nm-vega

    With respect to accelerator features, 7nm Vega and the resulting MI60 & MI50 cards differentiates itself from the previous Vega 10-powered MI25 in a few key areas. 7nm Vega brings support for half-rate double precision – up from 1/16th rate – and AMD is supporting new low precision data types as well. These INT8 and INT4 instructions are especially useful for machine learning inferencing, where high precision isn’t necessary, with AMD able to get up to 4x the perf of an FP16/INT16 data type when using the smallest INT4 data type. However it’s not clear from AMD’s presentation how flexible these new data types are – and with what instructions they can be used – which will be important for understanding the full capabilities of the new GPU. All told, AMD is claiming a peak throughput of 7.4 TFLOPS FP64, 14.7 TFLOPS FP32, and 118 TOPS for INT4.
    It probably still has 4096 compute cores as before,so most of the FP32 TFLOPs increase is probably through better IPC,higher clockspeeds,etc.


    Those despicable Elk,stealing the pond weed!

  5. #5
    Cinnamon Roll Ozaron's Avatar
    Join Date
    Jan 2017
    Location
    Norfolk
    Posts
    591
    Thanks
    75
    Thanked
    32 times in 31 posts
    • Ozaron's system
      • Motherboard:
      • MSI X570 Unify
      • CPU:
      • Ryzen 3700X
      • Memory:
      • 32GB Patriot Blackout @ 3800 CL16
      • Storage:
      • Toshiba X300 4TB (2), Samsung 850 Evo 500GB
      • Graphics card(s):
      • Sapphire R9 Fury Nitro
      • PSU:
      • Seasonic M12-II 620w
      • Case:
      • Corsair Obsidian 500D
      • Operating System:
      • W10 Enterprise 64bit
      • Monitor(s):
      • BenQ GW2765HT
      • Internet:
      • 2.5 MB/s ↓ 0.86 MB/s ↑ ~20ms

    Re: AMD Radeon Instinct MI60 and MI50 accelerators announced

    IF links on GPU. Come on AMD, roll through the business products, earn some money, and give us a viable IF m-GPU consumer solution on 7nm which smokes RTX for less outlay.

  6. #6
    Long member
    Join Date
    Apr 2008
    Posts
    1,885
    Thanks
    63
    Thanked
    325 times in 230 posts
    • philehidiot's system
      • Motherboard:
      • Father's bored
      • CPU:
      • Cockroach brain V0.1
      • Memory:
      • Innebriated, unwritten
      • Storage:
      • Big Yellow Self Storage
      • Graphics card(s):
      • Semi chewed Crayola Mega Pack
      • PSU:
      • 20KW single phase direct grid supply
      • Case:
      • Closed, Open, Cold
      • Operating System:
      • Cockroach
      • Monitor(s):
      • The mental health nurses
      • Internet:
      • Please.

    Re: AMD Radeon Instinct MI60 and MI50 accelerators announced

    I think that the previous gen stuff was already well optimised for FP16 and FP32 throughput so the selling point here is the power consumption and the new feature set as well as the reduced cost of ownership.

    There is a big issue about CUDA being like herpes in this arena and so the overall cost of switching is a lot more than just the cost of the hardware. Nvidia also have some other software advantage from what I can tell which is likely a function of market share.

    Nvidia have however shot themselves in the foot. Anyone checked out the latest Nvidia drivers T&Cs for consumer GPUs? The Licence Agreement stops them being used in datacentres - something which is open to defintion and could really just say "not for commercial number crunching". This may put off a lot of small players and turn them to AMD. At which case the software development rate will increase massively as it's the smaller companies that actually innovate whereas Nvidia... well... let's just say their development methods are a little old school.

  7. #7
    Senior Member
    Join Date
    Jul 2016
    Location
    My happy place
    Posts
    226
    Thanks
    70
    Thanked
    16 times in 14 posts
    • afiretruck's system
      • Motherboard:
      • Gigabyte X399 Designare Ex
      • CPU:
      • AMD Threadripper 1900X
      • Memory:
      • Corsair 32GB 3200MHz
      • Storage:
      • 2x 250GB NVMe + 2x 1TB SATA
      • Graphics card(s):
      • RX Vega 64 + GTX 970
      • PSU:
      • Corsair RMi 850
      • Case:
      • Fractal Design Define R6
      • Operating System:
      • Linux Mint 19
      • Monitor(s):
      • Screeny

    Re: AMD Radeon Instinct MI60 and MI50 accelerators announced

    Quote Originally Posted by Ozaron View Post
    IF links on GPU. Come on AMD, roll through the business products, earn some money, and give us a viable IF m-GPU consumer solution on 7nm which smokes RTX for less outlay.
    This would be a logical step forward, but it remains to be seen how well gaming performance scales with multiple GPUs on IF.

    It would be awesome if they could make a viable MCM gaming GPU, but I just don't think it'll work as well as Zen has for them.

Thread Information

Users Browsing this Thread

There are currently 1 users browsing this thread. (0 members and 1 guests)

Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts
  •