Gentoo Archives: gentoo-user

From: Volker Armin Hemmann <volkerarmin@××××××××××.com>
To: gentoo-user@l.g.o
Cc: Michael Mol <mikemol@×××××.com>
Subject: Re: [gentoo-user] Re: new machine : CPU : AMD FX-4100 ?
Date: Mon, 30 Jul 2012 16:50:57
Message-Id: 1349510.FGsGETyfgl@localhost
In Reply to: Re: [gentoo-user] Re: new machine : CPU : AMD FX-4100 ? by Michael Mol
1 Am Montag, 30. Juli 2012, 10:08:24 schrieb Michael Mol:
2 > On Mon, Jul 30, 2012 at 2:16 AM, Nikos Chantziaras <realnc@×××××.com> wrote:
3 > > On 30/07/12 07:28, Michael Mol wrote:
4 > >> On Sun, Jul 29, 2012 at 11:55 PM, Nikos Chantziaras <realnc@×××××.com>
5 > >>
6 > >> wrote:
7 > >>> On 30/07/12 06:08, Michael Mol wrote:
8 > >>>> On Sun, Jul 29, 2012 at 10:50 PM, Nikos Chantziaras <realnc@×××××.com>
9 > >>>>
10 > >>>> wrote:
11 > >>>>> On 30/07/12 05:23, Philip Webb wrote:
12 > >>>>>> i5-2550K & FX-4100 both use 95 W
13 > >>>>>> (some of the more costly AMDs use 125 W ).
14 > >>>>>
15 > >>>>> Note that power savings are not important if you're not using a
16 > >>>>> laptop.
17 > >>>>> CPU
18 > >>>>> power savings on a desktop don't translate to any relevant amount of
19 > >>>>> money
20 > >>>>> on your electricity bills. This is because neither of those CPUs
21 > >>>>> really
22 > >>>>> use
23 > >>>>> 95W. That's just the thermal upper limit.
24 > >>>>
25 > >>>> To be fair, power savings are relevant if you're concerned about your
26 > >>>> electric bill, or if you're concerned about heat management in your
27 > >>>> system.
28 > >>>>
29 > >>>> Consider my dual E5345...leaving that on 24x7 appears to cost me about
30 > >>>> 90USD/mo.
31 > >>>
32 > >>> CPU power savings will transform that into a 89.9USD/mo ;-) That's what
33 > >>> I
34 > >>> mean. It's not worth much. It helps quite a bit with laptop battery
35 > >>> life.
36 > >>> But for desktops, it doesn't do anything too useful.
37 > >>
38 > >> If you really want the hard numbers, check out some place like Tom's
39 > >> Hardware or Phoronix. I forget which does the power consumption
40 > >> measurements. At some of the hardware review blogs, you can get
41 > >> numbers on idle vs full-load power consumption, as measured at the
42 > >> wall. The difference truly is striking.
43 > >
44 > > When you have full load, the CPU won't clock down. So nothing saved
45 > > there.
46 >
47 > When you're considering full load, the TDP becomes a useful estimation
48 > of relative power consumption between different processors.
49 >
50 > > If you don't have full load, the clock-down doesn't save much compared to
51 > > max clocks while idle.
52 >
53 > This is where you're wrong.
54 >
55 > http://www.tomshardware.com/reviews/ivy-bridge-benchmark-core-i7-3770k,3181-
56 > 23.html
57 >
58 > http://www.tomshardware.com/reviews/fx-power-consumption-efficiency,3060-11.
59 > html
60
61 I wouldn't trust anything Tom's publishes.
62
63 That said, Intel's 'TDP' is not really a 'TDP' - for almost a decade Intel's
64 'TDP' is not the 'real' TDP but a 'usually you won't get higher than this' -
65 until you run some really heavy stuff. Like compiling openoffice...
66
67 AMD followed suit some time ago. So both numbers are misleading at best.
68
69 That said, idle&low load consumption is fine with all CPU's. Mobos and PSUs
70 influence that numbers a lot more.
71
72 --
73 #163933