Athlon64 benches... G5 killer?

t'hain esh kelcht'hain esh kelch
Posted:
in Current Mac Hardware edited January 2014
I'd say, no... At 3.2 Ghz, the dual G5 still beats it... I found some nice Q3 benches:



Link



There's also a full review of the processor, but since im a gamer, I found the Q3 benches more interesting...



Still looks like the G5 might be the gaming chip choice.. *WOOhooo*
«13

Comments

  • Reply 1 of 46
    zapchudzapchud Posts: 844member
    I can't find anything about what kind of demo, and what settings they used. Was it without sound? Was the graphics really cranked up to max? Which version of Q3?



    Too bad we need duals to beat them evil ones with games. Game performance will suck on the mac regardless of what kind of chip there is in out macs, it seems...
  • Reply 2 of 46
    eugeneeugene Posts: 8,254member
    There is no 3.2 GHz Athlon 64. *Sigh*



    Apple gets 337 fps with the 2x2.0 GHz G5...using a 128 MB Radeon 9800 Pro.



    SharkyExtreme has the 2.2 GHz Athlon 64 FX-51 getting 407 fps with a 256 MB Radeon 9800 Pro.



    ...The 3.2 GHz P4 gets 391 fps.



    How in the hell did you figure the top G5 beats either PC at Q3?
  • Reply 3 of 46
    banchobancho Posts: 1,517member
    Unless they figure out a way to run OS X on the AMD chip I can't see it killing the G5 any time soon. The only worthwhile OS to run on the AMD is Linux unless you want to pop in a copy of Windows du jour to play games.
  • Reply 4 of 46
    wirelesswireless Posts: 67member
    Well... I donno when the dual 3Ghz comes out with and we have panther I think we will be on top again ^^



    Heck I think dual 2Ghz with panther will go along way.

    But you also have to remember that if a program doesn't have a G5 plug in..... its going to run only as good as if it was on a G4. even though the PMG5 is backwards compadable the older stuff isn't going to see a preformace increase.
  • Reply 5 of 46
    outsideroutsider Posts: 6,008member
    Look at the whole package with the G5. Elastic bus that runs at half the speed of the CPU, PCI-X, dual channel DDR RAM (400MHz), Altivec, etc. This is a fast package, and it'll only get better.
  • Reply 6 of 46
    programmerprogrammer Posts: 3,458member
    As an interesting data point: Lightwave just released a G5 optimized version of their software, and they claim users should typically see a 30% performance increase. That, combined with Panther, should reset the bar for what people are expecting from the G5.
  • Reply 7 of 46
    krassykrassy Posts: 595member
    Quote:

    Originally posted by Programmer

    As an interesting data point: Lightwave just released a G5 optimized version of their software, and they claim users should typically see a 30% performance increase. That, combined with Panther, should reset the bar for what people are expecting from the G5.



    do you have an idea why applications with panther shall get a performance bump??? i don't get this by now...
  • Reply 8 of 46
    placeboplacebo Posts: 5,767member
    *whew*



    I was really worrying about the Athlon64...that looked like the one that would put up some heavy resistance.
  • Reply 9 of 46
    eugeneeugene Posts: 8,254member
    Quote:

    Originally posted by Placebo

    *whew*



    I was really worrying about the Athlon64...that looked like the one that would put up some heavy resistance.



    Not until the major OEMs start shipping systems with 'em. And that won't happen until Windows XP 64-bit Edition ships from MS.



    One extreme: AMD64 stalls until the 64-bit Windows ships and the big OEMs start shipping systems.



    Another extreme: Smaller OEMs like Northgat, Alienware, Falcon Northwest feast on the emptied playing field for a few months and maybe make a name for themselves.



    Of course what actually happens will fall somewhere in between.



    IMO, the x86-64 strategy is flawed. It's a better idea from a technical standpoint to start fresh and ditch the old ISA no matter how reluctant users are to switch. Backward compatibility? Keep an x86 system in addition to buying a new 64-bit machine. Mixing the two is at the design level won't please everybody...in fact it'll drive some people away.
  • Reply 10 of 46
    placeboplacebo Posts: 5,767member
    Wait a second...the Athlon wasn't dual, was it? This isn't looking as nice as I thought...
  • Reply 11 of 46
    zapchudzapchud Posts: 844member
    Quote:

    Originally posted by Placebo

    Wait a second...the Athlon wasn't dual, was it? This isn't looking as nice as I thought...



    Correct. You'll have to go Opteron, to get duals. And of course, only the more expensive 2xx-series and upwards.
  • Reply 12 of 46
    eugeneeugene Posts: 8,254member
    Quote:

    Originally posted by Placebo

    Wait a second...the Athlon wasn't dual, was it? This isn't looking as nice as I thought...



    Nope, neither the P4 or Athlon 64 are dual capable ... at all.
  • Reply 13 of 46
    placeboplacebo Posts: 5,767member
    ...well, if the Athlon64 gets slightly better scores than the Pentium4, and the P4 is slower than the Xeon, I think we're doing pretty well, actually.
  • Reply 14 of 46
    gizzmonicgizzmonic Posts: 511member
    Benchmarks are crap, no matter where they come from. Sites like Tom's Hardware and Anandtech are just group therapy for spendthrifts who attach their masculinity to their Quake framerates.



    Their "technical writers" know nothing or next to nothing about computers, nothing at all about writing, and everything about generating bar graphs in Microsoft Excel. They also have a keen eye for breaking tiny articles into several pages in order to drive up banner views.



    The design and content of "hardware enthusiast" sites are barely a step above "miracle diet" informercials.
  • Reply 15 of 46
    eugeneeugene Posts: 8,254member
    Quote:

    Originally posted by Placebo

    ...well, if the Athlon64 gets slightly better scores than the Pentium4, and the P4 is slower than the Xeon, I think we're doing pretty well, actually.



    The Xeon isn't faster than the P4 for everything. They have more cache, but are limited to a 533 MHz FSB. In addition, the Xeons Apple measure against are 3.06 GHz whereas the P4s are 3.2 GHz. The 3.2 GHz P4 Extreme will trump everything else, and the 3.4 and 3.6 GHz models after that.



    Just look at the available numbers.



    A SINGLE 2.2 GHz Athlon 64 FX-51 beats a SINGLE 3.2 GHz P4 by a little.

    A SINGLE 3.2 GHz P4 beats a DUAL 2.0 GHz G5 by a lot.



    What does this say? I don't know really. I'd like to think it says the game is still highly unoptimized for us Mac users.
  • Reply 16 of 46
    eugeneeugene Posts: 8,254member
    Quote:

    Originally posted by Gizzmonic



    Their "technical writers" know nothing or next to nothing about computers, nothing at all about writing, and everything about generating bar graphs in Microsoft Excel. They also have a keen eye for breaking tiny articles into several pages in order to drive up banner views.



    Don't forget pretty pictures of the CPU die from multiple angles!
  • Reply 17 of 46
    leonisleonis Posts: 3,427member
    why people always use games as the benchmark to test cpus?





    If a PS2/XBox/Game Cube has higher frame rate it would mean they are the fastest computer on the planet?
  • Reply 18 of 46
    lemon bon bonlemon bon bon Posts: 2,383member
    A P4 3.2 beating the dual G5 2 gigger by alot?



    Could you post the link?



    Besides, the G5 is unoptimised from OS, from Apps, benches...



    Still the same situation it's been for almost 3 months now.



    I think I'll take any a beats b seriously when we're on Rev B dual G5s at 2.5 each, with an optimised Panther and optimised apps and their subsequent more optimised revisions...and the odd optimised bench by then.



    A beats B is a non event at the moment.



    Athlon fx 64 thing only just beats 3.2 gig Pentium 4. Are we supposed to be impressed..?



    And how can you tell 400 fps to 340 fps?



    I can't.



    Lemon Bon Bon
  • Reply 19 of 46
    ryaxnbryaxnb Posts: 583member
    Oh whoope the high-tech system gets about 13.6x the framerate anyone can actually see.
  • Reply 20 of 46
    thttht Posts: 5,447member
    Quote:

    Originally posted by Eugene

    What does this say? I don't know really. I'd like to think it says the game is still highly unoptimized for us Mac users.



    That's about right. I think it's "not optimized enough" drivers, compilers and software design. From a CPU standpoint at least, the Athlon 64 and G5 should be neck-and-neck at the same clock rate...
Sign In or Register to comment.