Cache Size Impact on Performance

As we continue to look at the Athlon 64 platform with respect to Half Life 2 performance it's now time to find out how much benefit the 1MB L2 Athlon 64s gain over the 512KB L2 parts. 

Given that we've already shown Half Life 2 to be sensitive to both memory bandwidth and latency on the platform, we wouldn't be too surprised to see some pretty big differences between 512KB and 1MB L2 Athlon 64 processors.

at_canals_08
at_coast_05
at_coast_12
at_prison_05
at_c17_12
1MB L2
116.69
134.45
121.67
118.51
80.39
512KB L2
111.56
126.2
117.35
115.75
74.14

With a performance advantage as large as 8%, the 1MB Athlon 64s (and Athlon 64 FXs)  do surprisingly well under Half Life 2 when compared to their normally competitive 512KB counterparts.  While 8% alone isn't much, combine that with the advantage of a 128-bit DDR memory bus and the Socket-939 Athlon 64 platform can offer a reasonably high performance improvement over even the Socket-754 solutions. 

SSE/SSE2 Impact on Performance

Just for kicks we turned off the Athlon 64's SSE/SSE2 instruction set support to see if that impacted performance in any way:

at_canals_08
at_coast_05
at_coast_12
at_prison_05
at_c17_12
SSE/SSE2 Enabled
116.12
140.43
123.37
113.69
83.15
SSE/SSE2 Disabled
117.64
140.94
125.85
116.55
82.56

Despite minor variations in performance, it doesn't look like SSE/SSE2 is doing much for the Athlon 64 under Half Life 2.  We just had to fulfill our curiosities. 

Memory Latency Impact on Performance High End Graphics Card CPU Scaling
POST A COMMENT

68 Comments

View All Comments

  • Phantronius - Wednesday, January 26, 2005 - link

    If your gaming on a laptop, you need help. Reply
  • RockHydra11 - Wednesday, January 26, 2005 - link

    Was anyone surprised by the results, or didn't know what the answer would be already? I could make a very educated guess before I even clicked on the link. Reply
  • T8000 - Wednesday, January 26, 2005 - link

    This kind of CPU reviewing really makes me wonder if anyone plays with a $700 R850 XT-PE without anti-aliasing, anistrophic filtering and does so at 1280x1024.

    I mean, if that's all you want, why not save a cool $500 and buy a GF6600GT instead.

    It would be nice if someone reviewed CPU scaling at real gaming settings, because the 20% differences created here, may translate in only 5% with real settings, making it unnoticable during gameplay.
    Reply
  • Whiskyboy - Wednesday, January 26, 2005 - link

    I thought the artilce was a nice return to the feature for feature comparison that a shopper like myself really finds useful. I'm slighlty curious about upcoming technologies but I'm really disintereted in seeing how the brand new toy from AMD or Nvidia performs because I'm not going to suggest paying the ridiculous premiums they charge for the new junk. Seeing the effect that things like memory timings, bandwidth, cpu clock have on performance in a consistent platform make it easier for me to make recommendations to my customers for their systems. I like the Buyer's Guide articles, but in all honesty I want the charts that this article has. If you are suggesting that there should be more articles like this, I agree, but I'm not about to complain about the first article in months that actually made a useful shopper's comparison. Thanks Anand Reply
  • Marlowe - Wednesday, January 26, 2005 - link

    I would like to see the cpu scaling done with Intel cpu's too! :) Reply
  • Cybercat - Wednesday, January 26, 2005 - link

    The X850XT PE being a PCIe part, how did you use it on Socket 754 CPUs? I've not seen any Socket 754 NF4 boards yet. Reply
  • Aquila76 - Wednesday, January 26, 2005 - link

    #32 - Gamers buy PC's in orders of magnitude greater numbers than laptops. Maybe you can run Half-life 2 on your Intel Extreme Graphics, but that's nothing compared to gaming on an A64 with a decent video card and sound. Reply
  • jherber - Wednesday, January 26, 2005 - link

    where is the pentium m? MOST OF US BUY LAPTOPS THESE DAYS. Reply
  • REMF - Wednesday, January 26, 2005 - link

    roflmao:
    http://images.anandtech.com/graphs/half%20life%202...

    an Athlon64 3200+ @ 2.0GHz gets 112fps
    an Athlon64 3000+ @ 1.8GHz gets 104fps
    .'. an A64 3100+ @ 1.9GHz would get 108fps

    ...... the same as a P4 570 running at 3.8GHz, twice the speed!

    LOL
    Reply
  • bupkus - Wednesday, January 26, 2005 - link

    I'm glad to finally see this article. I've been waiting for weeks and beginning to think this article was just "vaporware". ;)

    As to the following quote:
    "If you are stuck with one of those older but still well-performing GPUs, don't bother upgrading your CPU unless it's something slower than a 2.4GHz Pentium 4 - you'd be much better served by waiting and upgrading to dual core later on."
    As this was just a tantalizing morsel of things to come, I'm looking forward to the coming weeks.
    Reply

Log in

Don't have an account? Sign up now