Article: Nehalem Performance Preview
By: RagingDragon (a.delete@this.b.c), April 10, 2009 10:19 am
Room: Moderated Discussions
slacker (s@lack.er) on 4/10/09 wrote:
---------------------------
>Vincent Diepeveen (diep@xs4all.nl) on 4/10/09 wrote:
>---------------------------
>>David Kanter (dkanter@realworldtech.com) on 4/8/09 wrote:
>>---------------------------
>>>slacker (s@lack.er) on 4/8/09 wrote:
>>>---------------------------
>>>>Also, David: perhaps it's just me, but I found it strange >to use units of "Pixels/sec
>>>>per Watt," and "BOPs/sec per Watt." To me, it would make >more sense to write Pixels/Joule
>>>>and BOP/Joule, but I can understand how that might make >less-sense to an IT capacity
>>>>planner who looks at things in terms of watts and amps.
>>>
>>>So it ultimately depends if you want to look at energy or power. For servers,
>>>I think you've made the case that energy isn't what you optimize for since it's
>>>not a first order constraint. For a notebook, it's clear that energy is a first
>>>order constraint since that what you are limited to...
>>
>>You're underestimating powerconsumption importance for servers.
>
>He got it right. Re-read the last two messages and you will agree.
>
>Energy != Power, for reference.
To clarify: power = energy used per unit time. For example 1W = 1 J/s.
---------------------------
>Vincent Diepeveen (diep@xs4all.nl) on 4/10/09 wrote:
>---------------------------
>>David Kanter (dkanter@realworldtech.com) on 4/8/09 wrote:
>>---------------------------
>>>slacker (s@lack.er) on 4/8/09 wrote:
>>>---------------------------
>>>>Also, David: perhaps it's just me, but I found it strange >to use units of "Pixels/sec
>>>>per Watt," and "BOPs/sec per Watt." To me, it would make >more sense to write Pixels/Joule
>>>>and BOP/Joule, but I can understand how that might make >less-sense to an IT capacity
>>>>planner who looks at things in terms of watts and amps.
>>>
>>>So it ultimately depends if you want to look at energy or power. For servers,
>>>I think you've made the case that energy isn't what you optimize for since it's
>>>not a first order constraint. For a notebook, it's clear that energy is a first
>>>order constraint since that what you are limited to...
>>
>>You're underestimating powerconsumption importance for servers.
>
>He got it right. Re-read the last two messages and you will agree.
>
>Energy != Power, for reference.
To clarify: power = energy used per unit time. For example 1W = 1 J/s.
Topic | Posted By | Date |
---|---|---|
Nehalem review up | David Kanter | 2009/04/07 03:43 AM |
Nehalem review up | noone | 2009/04/07 06:48 AM |
Strange jbb on Harpertown | Henrik S | 2009/04/07 08:29 AM |
Strange jbb on Harpertown | David Kanter | 2009/04/07 11:19 AM |
Strange jbb on Harpertown | Henrik S | 2009/04/07 09:33 PM |
Strange jbb on Harpertown | Chris | 2009/04/08 12:54 AM |
Strange jbb on Harpertown | Henrik S | 2009/04/08 02:40 AM |
Nehalem review up | Vincent Diepeveen | 2009/04/07 08:34 AM |
Nehalem review up | Jack | 2009/04/09 04:51 PM |
Nehalem review up | Vincent Diepeveen | 2009/04/10 01:58 AM |
Nehalem review up | Michael S | 2009/04/10 03:45 AM |
Nehalem review up | EduardoS | 2009/04/10 07:01 AM |
Nehalem review up | Michael S | 2009/04/10 07:56 AM |
Nehalem review up | Eugene Nalimov | 2009/04/10 09:12 AM |
Choice of C compiler doesn't matter much for Java... | Henrik S | 2009/04/10 10:10 AM |
Choice of C compiler doesn't matter much for Java... | EduardoS | 2009/04/10 02:49 PM |
Choice of C compiler doesn't matter much for Java... | Henrik S | 2009/04/11 07:13 AM |
Choice of C compiler doesn't matter much for Java... | EduardoS | 2009/04/11 11:30 AM |
Large pages | David Kanter | 2009/04/11 02:02 PM |
Choice of C compiler doesn't matter much for Java... | Henrik S | 2009/04/11 11:06 PM |
Choice of C compiler doesn't matter much for Java... | Paul | 2009/04/12 01:53 AM |
Choice of C compiler doesn't matter much for Java... | iz | 2009/04/12 02:59 AM |
Choice of C compiler doesn't matter much for Java... | Henrik S | 2009/04/12 07:37 AM |
Choice of C compiler doesn't matter much for Java... | EduardoS | 2009/04/12 08:08 AM |
Choice of C compiler doesn't matter much for Java... | Henrik S | 2009/04/12 09:25 AM |
Choice of C compiler doesn't matter much for Java... | EduardoS | 2009/04/12 05:24 PM |
Choice of C compiler doesn't matter much for Java... | Henrik S | 2009/04/12 10:18 PM |
Thread costs | David Kanter | 2009/04/13 12:12 AM |
Thread costs | Henrik S | 2009/04/14 02:08 PM |
Choice of C compiler doesn't matter much for Java... | Michael S | 2009/04/11 08:53 AM |
Choice of C compiler doesn't matter much for Java... | Henrik S | 2009/04/11 11:08 PM |
Nehalem review up | Vincent Diepeveen | 2009/04/11 04:50 PM |
Nehalem review up | Michael S | 2009/04/11 05:12 PM |
Nehalem review up | Vincent Diepeveen | 2009/04/12 03:01 AM |
Nehalem review up | Michael S | 2009/04/12 05:07 AM |
Nehalem review up | rwessel | 2009/04/07 02:01 PM |
Nehalem review up | slacker | 2009/04/08 09:11 AM |
Energy vs. power | David Kanter | 2009/04/08 10:11 AM |
Energy vs. power | Vincent Diepeveen | 2009/04/10 02:08 AM |
Energy vs. power | slacker | 2009/04/10 09:26 AM |
Energy vs. power | RagingDragon | 2009/04/10 10:19 AM |
Energy vs. power | David Kanter | 2009/04/10 11:47 AM |
Energy vs. power | Jack | 2009/04/10 04:44 PM |
Energy vs. power | slacker | 2009/04/10 07:00 PM |
Energy vs. power | Jack | 2009/04/10 07:31 PM |
Energy vs. power | David Kanter | 2009/04/11 12:16 AM |
Nehalem review up | rwessel | 2009/04/08 02:32 PM |
Minor font issue | gpriatko | 2009/04/07 04:35 PM |
Minor HTML issue | David Kanter | 2009/04/07 09:38 PM |
Minor HTML issue | David Kanter | 2009/04/07 09:39 PM |
Good work, i look forward to linux and SP2 numbers (NT) | PiedPiper | 2009/04/08 01:52 AM |
Nehalem review up | Joe Chang | 2009/04/10 03:59 AM |