Re: Dual Core chips??

George Macdonald wrote:

On Mon, 20 Nov 2006 11:16:29 +0000, Chris <ithinkiam@xxxxxxxxx> wrote:
AMD won the performance crown over many years because it threw out the
'more cpu cycles, the faster the processor' dogma of previous
architectures. It developed more efficient processors that did more
per cycle and so its cpus preformed much better and ran a lot cooler
than Intel's electric heaters. Its dual-cores were/are exactly the
same as the signle core equivalents.

I believe it was AMD's intention to sell backed off dual cores - they
said so back before C2D came along to put a wrench in the works, and
initial product was so aligned.

Maybe, but at launch of the X2 the core speed of the top model was the
same as the single-core variant.

C2D plus price pressure forced them to a
different path, though I believe the top MHz AMD64 is still a single
core CPU.

AMD did briefly have the FX 57 which was single core and ran at 2.8GHz
versus 2.6 for top X2. This was because the gamer market (which bought
the FX cpus) wouldn't benefit from dual core. THis was true at the time,
although not any more as more games are making use of SMP. However, the
top rated FX and X2 cpus are both at 2.8GHz now.

Now that Intel has taken this onboard and released some very efficient
processors which run with slower clock cycles than the previous
pentiums (pentium Ms excluded) it has regained the performance crown
after many years of playing second fiddle to AMD.

But did they really?... play "second fiddle"?:-) I think only to the
cognoscenti - amazing what FUD, Mikey & Co. and guys in blue bunny
suits will do:-)


The fact that AMD now have a sizeable server market when 5 years ago
they didn't have /any/ is proof of that :)

.

Relevant Pages

  • Re: Deep Fritz for Core2 Duo?
    ... You can switch the free Crafty engine into running on multiple cores and it will give a fair benchmark of how system would behave with other chess engines. ... CPUs 6403 kN/s ... Only in a badly designed parallel search strategy. ... Two cores on a slow multicore against one core on a nominally twice as fast machine with the same engine would be an interesting test. ...
    (rec.games.chess.computer)
  • Re: Beyond multicore
    ... Using 200-odd pins to support a DDR-III ... device between this DRAM and the on-die Memory Controller. ... linear scaling) current 3 GHz CPUs need about 10 GBytes/sec of DRAM BW/ ... In order that each CPU core has about the same L-big ...
    (comp.arch)
  • Re: Beyond multicore
    ... Using 200-odd pins to support a DDR-III ... device between this DRAM and the on-die Memory Controller. ... linear scaling) current 3 GHz CPUs need about 10 GBytes/sec of DRAM BW/ ... In order that each CPU core has about the same L-big ...
    (comp.arch)
  • Re: [BISECTED] Lots of "rescheduling IPIs" in powertop
    ... For AMD CPUs that support MWAIT this is wrong. ... Family 0x10 and 0x11 CPUs will enter C1 on HLT. ... The core exits C1 if an interrupt is received. ...
    (Linux-Kernel)
  • Re: Advice on a multithreaded netisr patch?
    ... using the core? ... CPUs 4-7 for only network processing". ... Be careful not to migrate threads that hold locks the ... Be careful not to migrate the main boot thread. ...
    (freebsd-net)