Memory Latency & Bandwidth Performance

Given AMD's on-die memory controller, memory latencies should be reduced significantly as well as bandwidth efficiency improved a bit. In order to validate these hypotheses we turn to ScienceMark 2.0 to give us an indication of memory latency and bandwidth performance:

Although the Pentium 4 and the Athlon 64 FX have the same amount of theoretical memory bandwidth, the Athlon 64 FX comes out ahead by a significant margin thanks to the on-die memory controller.

Memory latency is reduced significantly over the Athlon XP thanks to the on-die memory controller, although there is much to be said about Intel's 865/875 memory controllers by looking at the latency comparison seen above.

Here we have the same comparison as before, just with the performance measured in CPU clocks and not ns.

Intel's Preemptive Strike - Pentium 4 Extreme Edition Business Application Performance
Comments Locked

122 Comments

View All Comments

  • Anonymous User - Tuesday, September 23, 2003 - link

    Anand runs the Content Creation benchmark without the bugfix patch?!?! WTF? Like that's fair... Without the patch, it doesn't use SSE properly with the Athlons...

    And the FX 51 benches are completely bogus, because he used an nForce3-based motherboard.

    They've got issues, and the Via boards outperform
    them significantly. Hello? Anand?

    http://www.tech-report.com/reviews/2003q3/athlon64...

    "Notice here the contrast between the Athlon 64 FX with the K8T800 and with the nForce3 Pro. With the K8T800, the Athlon 64 FX is arguably the fastest system overall in the viewperf suite. The nForce3 Pro, however, seems to limit performance quite a bit."
  • Anonymous User - Tuesday, September 23, 2003 - link

    #9 Which planet are you on?
  • Anonymous User - Tuesday, September 23, 2003 - link

    Great news for the Linux users:-) I'm seeing a lot of Windows users switching to Linux and using transcode or cinelerra:-)
  • Anonymous User - Tuesday, September 23, 2003 - link

    Good thing you are not biased at atll, #4
  • Anonymous User - Tuesday, September 23, 2003 - link

    Eat it #6 amd fan boy
  • Anonymous User - Tuesday, September 23, 2003 - link

    yes, you're right #4, they're biased. just like all the other tech sites praising the new amd chip. they're obviously all wrong.... go away
  • Anonymous User - Tuesday, September 23, 2003 - link

    Still can't decide. Leaning Intel... I've had better experience with Intel.. but next year When XP64 shipes......
    Guess I will stick with my trusty 386..
  • Anonymous User - Tuesday, September 23, 2003 - link

    BIASED BIASED BIASED BIASED BIASED

    The P4EE whoops new AMDs chip and you say is "The Pentium 4 EE manages to regain some lost ground for Intel, but not enough". YOU ARE CRAZY!!!!!! The Prescott will DEMOLISH AMD once and for all. Btw, get some more benchmarks. Q3 and UT2003 are OLD GAMES using DX8. Run Battlefield and other memory/cpu entensive games.

    AMD fanboys can't cry about their chip is slower but cheaper either.

    Worst biased site ever. Just because they kissed your butt and showed you the cpu's a year in advance you shove your nose up AMDs socket.

    BIASED BIASED BIASED BIASED BIASED
  • Anonymous User - Tuesday, September 23, 2003 - link

    What people tend to forget is that 3200+ is the INITIAL speed from the first batch of CPU's. As with the XP the speed will increase rather rapidly as well as die-quality and tweaks/performance fixes. Athlon XP debuted at what, 1500+ (?) and now ends at 3200+. The A64 going to 90nm will yield some neat increases in available speeds (4800+ anyone?) ;)
  • Anonymous User - Tuesday, September 23, 2003 - link

    wtf no 640x480 game benchmarks?

Log in

Don't have an account? Sign up now