G5 slower than G4 in Xbenches?

Posted:
in Current Mac Hardware edited January 2014
I just saw the new mac-mini Xbench charts! Unbeliebable

Look athttp://www.macintouch.com/perfpack/comparison.html

If you look at the CPU and Thread bars the iMac G5 1,8 is slower than the G4 1,42 G4 mini! How is this possible? I checked my iMac with Xbench myself and i got 161! In terms of CPU and threads the G5 is slower than a G4! How can this be?

Comments

  • Reply 1 of 11
    the G4 is a great proccesor, I would pick a 2 GHz G4 over a 2 Ghz G5 anytime, the problem with the G4 has been Motorola that couldn't keep up with AMD and Intel in terms of speed. You have to remember that a G4 is an "old" processor that has been upgraded many times and the G5 is in his 2nd generation
  • Reply 2 of 11
    Most of this speed may be due to the fact that the mini is smaller, hence less time for signals to get from one place to another...
  • Reply 3 of 11
    pbpb Posts: 4,255member
    Sorry to seem somewhat rude, but would you suggest to anyone that does e.g. video editing to throw his(her) G5 for a G4?



    I am surprised that people still bother with Xbench. The general consensus is that it is a junk of benchmark, and I think that results like that do nothing else than confirming it. And when was the last time it has been updated? 2003-10-06? Hmm...
  • Reply 4 of 11
    I am not saying that the G5 is a bad processor, I am saying that the G4 is a great processor that couldn't reach very high frequencies, I don't know the technical reasons, maybe Motorola didn't have the R&D invested in the chip. A G4 vs a G5 at the same frequency is a better chip....



    (Sorry about the spelling)
  • Reply 5 of 11
    amorphamorph Posts: 7,112member
    It's not quite that simple. There are problems that G4s will handle better, and problems that G5s will handle better. The problems that G5s handle better (intensive scalar FP code, large data sets, streaming data, poorly optimized code) are common.



    It is, however, true that the G4 is a much better chip than it gets credit for being. I expect it to get a second wind when it gets an onboard memory controller, and its biggest bottleneck and obstacle to progress (MaxBus) is pulled off the motherboard.



    Freescale's doing well with it, though. Don't look at the Hz, look at the Hz/watt, to see how much it's improved over the last year or so (it's already running at or near 12:1 relative to the bus, so there's not much point clocking it higher...). I'm a lot more optimistic about its future than I was two years ago.



    Oh, and Xbench is wildly inconsistent. You'll get markedly different scores from different runs on the same machine. I wouldn't put much stock in any results that it yields.
  • Reply 6 of 11
    I understand that the G4 has been worked on longer than the G5 and has an edge. But what I find hard to believe is that the G5 has a much bigger bus speed. I think the iMac is like 600 Mhz or something. Compared to the G4's 133 Mhz or 167Mhz, the G5 should be able to make up for any kinks that still need to be worked out.



    Mike
  • Reply 7 of 11
    I have found xbench to be consistent on my mac. I set everything up the same, and the result is always between 95 and 98.
  • Reply 8 of 11
    Take a look at this article on G5 performance in relation to equiped ram. According to this article, a G5 with minimum ram (as they ship), can be up to 4 times slower than any other configuration.



    http://www.xlr8yourmac.com/G5/8GB_RA....html#storytop



    I didn't see a ram listing for the tests. Did I overlook it somewhere in the link comparing processors?
  • Reply 9 of 11
    messiahmessiah Posts: 1,689member
    Quote:

    Originally posted by aircft.sys.spec.

    Take a look at this article on G5 performance in relation to equiped ram. According to this article, a G5 with minimum ram (as they ship), can be up to 4 times slower than any other configuration.



    http://www.xlr8yourmac.com/G5/8GB_RA....html#storytop



    I didn't see a ram listing for the tests. Did I overlook it somewhere in the link comparing processors?




    4GB looks as though it's a bit of a sweet-spot.
  • Reply 10 of 11
    iposteriposter Posts: 1,560member
    Quote:

    Originally posted by hardeeharhar

    Most of this speed may be due to the fact that the mini is smaller, hence less time for signals to get from one place to another...



  • Reply 11 of 11
    Hey, regarding the xbench article:



    "If you change Apple's standard Energy Saver options to get "Highest" processor performance, the iMac G5 finally beats its cheaper siblings, but there must be some reason that's not the default, and clock speed alone should give the iMac a big advantage. In return for pushing the iMac, you're likely to get more fan noise at the very least."



    It mentions how running the iMac on 'High" the performance will make the fan louder, but are there any other set-backs? Such as wearing the chip out earlier, or something like that? I know it uses more power....



    just curious
Sign In or Register to comment.