Page 3 of 4 FirstFirst 1234 LastLast
Results 21 to 30 of 31

Thread: AMD vs. Intel Processor Discussion

  1. #21
    Join Date
    May 2008
    Location
    UK
    Posts
    465

    Default

    Quote Originally Posted by alexforcefive View Post
    Sooooo... not to derail this interesting debate about graphics drivers, but does anyone have any thoughts about processors? I've been out of the loop for a while, but I've been reading up and it seems like the intel core2 duo e8500 gives the best bang for my buck. Would that be a fair assessment? It seems to still outperform triple- and quad-core processors, but how long will that last? Are multi-core optimised applications/games going to be really common any time soon? If I was to go with more cores, which would you suggest?

    Is bridgman right about AMD vs Intel power consumption?
    Bridgman is correct about the power consumption, AMD's stuff draws more on the CPU and less on the MB. Over all it all evens out in the end.

    CPU wise if you overclock it the Q6600 is still one of the best CPU's to go for in terms of value for money as it easily hits 3GHz+ if you have a decent cooler on it.

  2. #22
    Join Date
    Aug 2007
    Posts
    6,607

    Default

    You can expect that this CPU goes much higher too. That's 45nm already and 3.16 ghz is surely _not_ the limit.

  3. #23
    Join Date
    Apr 2008
    Location
    Saskatchewan, Canada
    Posts
    460

    Default

    Quote Originally Posted by Aradreth View Post
    Bridgman is correct about the power consumption, AMD's stuff draws more on the CPU and less on the MB. Over all it all evens out in the end.
    From what I remember of the comparative power measurements I've seen, 65nm AMD machines take a bit more power than comparable 65mm Intel machines, and substantially more power than 45nm Intel machines. Certainly the host chipset in my AMD Linux box seems to be a space heater, though it does have reasonable integrated graphics so that's some justification for taking a fair amount of power.

    Would be interesting to see some definitive power numbers though, as I'm looking at building a low-power 24/7 server to stick in the basement. As it is my Linux box spends most of its time underclocked from 2.6GHz to 1GHz, so for most things raw CPU performance is now pretty much irrelevant.

  4. #24
    Join Date
    Oct 2007
    Location
    Toronto-ish
    Posts
    7,383

    Default

    Yeah, my main point was "make sure you are comparing apples to apples", ie that just comparing CPUs is not sufficient when one CPU includes the memory controller and the other does not.

  5. #25
    Join Date
    Jan 2007
    Location
    Germany
    Posts
    2,114

    Default

    The Athlon X2 4850e @ 2,5 GHz has a TDP of 45W. I don't know any CPU with lower TDP. If you don't even need the performance, you can go with the Athlon X2 4050e @ 2,0 GHz which does need even less power.

  6. #26
    Join Date
    Apr 2008
    Location
    Saskatchewan, Canada
    Posts
    460

    Default

    Quote Originally Posted by d2kx View Post
    The Athlon X2 4850e @ 2,5 GHz has a TDP of 45W. I don't know any CPU with lower TDP. If you don't even need the performance, you can go with the Athlon X2 4050e @ 2,0 GHz which does need even less power.
    That sounds pretty good; if I'd realised how little time my CPU would spend at full clock speed I'd have got something slower than the 5000+ that's in there .

  7. #27
    Join Date
    May 2008
    Location
    UK
    Posts
    465

    Default

    Quote Originally Posted by movieman View Post
    From what I remember of the comparative power measurements I've seen, 65nm AMD machines take a bit more power than comparable 65mm Intel machines, and substantially more power than 45nm Intel machines. Certainly the host chipset in my AMD Linux box seems to be a space heater, though it does have reasonable integrated graphics so that's some justification for taking a fair amount of power.

    Would be interesting to see some definitive power numbers though, as I'm looking at building a low-power 24/7 server to stick in the basement. As it is my Linux box spends most of its time underclocked from 2.6GHz to 1GHz, so for most things raw CPU performance is now pretty much irrelevant.
    I've not really kept up with anything passed 65nm (at which point I think AMD set was using slightly more...). Yeah the drop to 45nm will make the intel preferable although the cost difference might be fairly large (I've not been paying attention).

    Quote Originally Posted by Kano
    You can expect that this CPU goes much higher too. That's 45nm already and 3.16 ghz is surely _not_ the limit.
    Oh lord no you could probably get it to almost 4GHz but applications that can benefit from a CPU running at 4Ghz instead of 3 probably benefit from 2 extra cores more then the bump in speed.

  8. #28
    Join Date
    Oct 2007
    Posts
    370

    Default

    Quote Originally Posted by Aradreth View Post
    I've not really kept up with anything passed 65nm (at which point I think AMD set was using slightly more...). Yeah the drop to 45nm will make the intel preferable although the cost difference might be fairly large (I've not been paying attention).


    Oh lord no you could probably get it to almost 4GHz but applications that can benefit from a CPU running at 4Ghz instead of 3 probably benefit from 2 extra cores more then the bump in speed.
    you can even get the yorkfield's to 6ghz...

  9. #29
    Join Date
    May 2008
    Location
    UK
    Posts
    465

    Default

    Quote Originally Posted by Redeeman View Post
    you can even get the yorkfield's to 6ghz...
    Pfft 6 is easy try 8GHz. Point is 6GHz can only be achieved with extreme setups this is an everyday setup we are talking about, big difference.

  10. #30
    Join Date
    Dec 2006
    Posts
    222

    Default

    Quote Originally Posted by Aradreth View Post
    Oh lord no you could probably get it to almost 4GHz but applications that can benefit from a CPU running at 4Ghz instead of 3 probably benefit from 2 extra cores more then the bump in speed.
    Clock scaling and ccore scaling are 2 completely different and unrelated problems.

Posting Permissions

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