Welcome, Guest. Please login or register.

Author Topic: New PowerPC 970FX, 24.5 Watts at 2GHz.  (Read 6390 times)

Description:

0 Members and 1 Guest are viewing this topic.

Offline VidarL

  • Newbie
  • *
  • Join Date: Jan 2004
  • Posts: 4
    • Show all replies
    • http://www.langberget.com
Re: New PowerPC 970FX, 24.5 Watts at 2GHz.
« on: January 22, 2004, 09:25:36 PM »
You can't compare those numbers with Intel and AMD numbers.. Those are typical power usage. Intel and AMD use TDP- Therman Design Power. The absolute maximum power they can draw.

I believe MicroDesignResources' estimation of a TDP close to 90W for a 2Ghz G5 (0.13 micron) processor is close to the truth. Which is why Apple delayed the introduction of a 1U Xserve-G5 until 90nm G5s were available.. AMD have had Opterons in 1U servers from day one.


Vidar
 

Offline VidarL

  • Newbie
  • *
  • Join Date: Jan 2004
  • Posts: 4
    • Show all replies
    • http://www.langberget.com
Re: New PowerPC 970FX, 24.5 Watts at 2GHz.
« Reply #1 on: January 23, 2004, 06:58:35 PM »
Quote
No, TDP and absolute maximum are two diferent figures, the absolute maximum is usually quite a bit (up to 30 Watts) higher and is virtually impossible to find, at least from Intel. Absolute maximum is a theoritical figure which may be impossible to reach in any case.

They all quote some form of average figure.


Sorry, but you are wrong.

Intel and AMD have a different definition of TDP IIRC, as Intel quotes the maximum power usage when using a power virus, while AMD is quoting the maximum power the CPU can theoretically consume:

Quote
Thermal Design Power (TDP) is measured under the conditions of TCASE Max, IDD Max, and VDD=VID_VDD,
and include all power dissipated on-die from VDD, VDDIO, VLDT, VTT, and VDDA.
 

Offline VidarL

  • Newbie
  • *
  • Join Date: Jan 2004
  • Posts: 4
    • Show all replies
    • http://www.langberget.com
Re: New PowerPC 970FX, 24.5 Watts at 2GHz.
« Reply #2 on: January 23, 2004, 09:36:25 PM »
Quote
Thermal Design Power, Ptdp
Maximum sustained power, across a set of realistic applications, drawn under normal operating conditions, nominal Vcc and realistic ambient (use) temperature.


Ok, so they Intel determine TDP by using a number of applications instead of a power virus. The fact remains that the TDP Intel gives out is MUCH higher than average power consumption. If IBM gave out a TDP number, it would be a lot higher.

Vidar