Quantcast

Jump to content

» «
Photo

When calculating the amount of FLOPS in a GCN GPU.

6 replies to this topic
nigelhere9901
  • nigelhere9901

    Gangsta

  • Members
  • Joined: 02 Feb 2013

#1

Posted 28 April 2013 - 07:48 PM Edited by nigelhere9901, 29 April 2013 - 11:21 AM.

The 7970 has 32 GCN Compute Units, Each GCN Compute Unit contains 4 SIMDs 16-wide.

4 SIMDs 16-wide per each Compute Unit = 4 X 16 = 64 SIMDs per each GCN Compute Unit

64 SIMDs X 32 Compute Units = 2048 Stream Processors, correct?

2048 (stream processors) X 0.925 (frequency in GHz) X 2 (Operations per cycle, 2 FMA) = 3788.8 GFLOPS



What does the number 2 represent? Did I label all of them correctly?

sivispacem
  • sivispacem

    Empty Pleasures and Desperate Measures since 1994

  • Moderator
  • Joined: 14 Feb 2011
  • United-Kingdom
  • Contribution Award [D&D, General Chat]
    Most Knowledgeable [Vehicles] 2013
    Best Debater 2013, 2012, 2011

#2

Posted 28 April 2013 - 08:44 PM

It signifies two floating point operations per clock cycle. This integer varies depending on the processor design and type. I think the Intel Sandy and Ivy Bridge processors were 6 (most) or 8 (Haswell) operations per clock cycle per core, for example.

nigelhere9901
  • nigelhere9901

    Gangsta

  • Members
  • Joined: 02 Feb 2013

#3

Posted 29 April 2013 - 09:44 AM Edited by nigelhere9901, 29 April 2013 - 11:21 AM.

QUOTE (sivispacem @ Sunday, Apr 28 2013, 20:44)
It signifies two floating point operations per clock cycle. This integer varies depending on the processor design and type. I think the Intel Sandy and Ivy Bridge processors were 6 (most) or 8 (Haswell) operations per clock cycle per core, for example.

Thanks for the reply, been wondering about that.

Also, do you happen to know how to calculate FLOPS in a CPU? Is it the same method? Cores * Speed in GHz * FLOPS per cycle?

sivispacem
  • sivispacem

    Empty Pleasures and Desperate Measures since 1994

  • Moderator
  • Joined: 14 Feb 2011
  • United-Kingdom
  • Contribution Award [D&D, General Chat]
    Most Knowledgeable [Vehicles] 2013
    Best Debater 2013, 2012, 2011

#4

Posted 01 May 2013 - 07:42 AM

Technically, it's Sockets * Cores Per Socket * Clock Speed Per Core * Floating-Point Operations per-cycle, but the former number is usually 1 in most desktop systems.

The actual calculation for the 7970 would be 32 * 64 * 0.925 * 2 = 3788.8 GFLOPS

nigelhere9901
  • nigelhere9901

    Gangsta

  • Members
  • Joined: 02 Feb 2013

#5

Posted 01 May 2013 - 06:34 PM

QUOTE (sivispacem @ Wednesday, May 1 2013, 07:42)
The actual calculation for the 7970 would be 32 * 64 * 0.925 * 2 = 3788.8 GFLOPS

That theory is not any different from mine, each Compute Unit has 64 stream cores, you just have to multiply the number 64 to the number of compute units and then in to speed and then into Floating Point Operations per cycle.

sivispacem
  • sivispacem

    Empty Pleasures and Desperate Measures since 1994

  • Moderator
  • Joined: 14 Feb 2011
  • United-Kingdom
  • Contribution Award [D&D, General Chat]
    Most Knowledgeable [Vehicles] 2013
    Best Debater 2013, 2012, 2011

#6

Posted 01 May 2013 - 09:11 PM

The mathematics is the same, but it's showing the process in the main sum. That way you don't have to work out total core numbers, which is relatively okay on a single GPU or server but much more difficult across distrusted computing systems.

nigelhere9901
  • nigelhere9901

    Gangsta

  • Members
  • Joined: 02 Feb 2013

#7

Posted 02 May 2013 - 03:04 PM

Alright, Thanks for your help kind sir.




0 user(s) are reading this topic

0 members, 0 guests, 0 anonymous users