ATI’s Crossfire: Best Overclocker on the Market?
by Wesley Fink on September 27, 2005 12:05 AM EST- Posted in
- CPUs
Firewire and USB Performance
It is really difficult to put together a simple, repeatable, and consistent test to measure USB and Firewire Performance. Since our goal was to make this a standard part of motherboard testing, we needed a benchmark that was reasonably simple to run and that would also provide consistent results on the same test bed. We finally determined that an external USB 2.0, Firewire 400, and Firewire 800 hard disk might be a sensible way to look at USB and Firewire throughput.
Our first efforts at testing with an IDE or SATA drive as the “server” yielded very inconsistent results, since Windows XP sets up cache schemes to improve performance. Finally, we asset up a RAM disk as our “server”, since memory removed almost all overhead from the serving end. We also managed to turn off disk caching on the USB and Firewire side by setting up the drives for “quick disconnect” and our results were then consistent over many test runs.
We used just 1GB of fast 2-2-2 system memory set up as a 450MB RAM disk and 550MB of system memory. Our stock file was the SPECviewPerf install file, which is 432,533,504 bytes (412.4961MB). After copying this file to our RAM disk, we measured the time for writing from the RAM disk to our external USB 2.0 or Firewire 400 or Firewire 800 drive using a Windows timing program written for AnandTech by our own Jason Clark. The copy times in seconds were then converted into Megabits per second (Mb) to provide a convenient means of comparing throughput. Higher Rates therefore mean better performance.
Perhaps the biggest surprise in our testing was the poor performance of USB 2.0 on the ATI Crossfire AMD. ATI had promised improvement in USB performance in the SB450 compared to the earlier SB400, but we could see little improvement in our USB 2.0 tests. ATI responded that our USB 2.0 tests measured sustained throughput, which is relevant in USB operations only with applications like the USB 2.0 hard drive that we use for this test. ATI claims that burst USB 2.0 throughput has been improved in the SB450 to near the same levels of competitive USB 2.0 peak performance. We could not confirm these claims with any test procedures. Perhaps more important, ATI is aware of the issues with USB 2.0 performance and these will be fully corrected – sustained and peak performance – in the SB600 south bridge. It appears that this issue of USB performance may also be corrected by combining the ATI RD480 northbridge with the just released ULi M1575 Southbridge.
Since our ramdisk/apptimer File Copy is measuring sustained throughput, we also compared performance of ATI IDE/SATA/Sil SATA2 using this same test procedure. The performance of ATI IDE remains excellent, but SATA and SATA 2 performance are very competitive, but not standout as in the iPeak storage benchmarks of the same controllers.
It is really difficult to put together a simple, repeatable, and consistent test to measure USB and Firewire Performance. Since our goal was to make this a standard part of motherboard testing, we needed a benchmark that was reasonably simple to run and that would also provide consistent results on the same test bed. We finally determined that an external USB 2.0, Firewire 400, and Firewire 800 hard disk might be a sensible way to look at USB and Firewire throughput.
Our first efforts at testing with an IDE or SATA drive as the “server” yielded very inconsistent results, since Windows XP sets up cache schemes to improve performance. Finally, we asset up a RAM disk as our “server”, since memory removed almost all overhead from the serving end. We also managed to turn off disk caching on the USB and Firewire side by setting up the drives for “quick disconnect” and our results were then consistent over many test runs.
We used just 1GB of fast 2-2-2 system memory set up as a 450MB RAM disk and 550MB of system memory. Our stock file was the SPECviewPerf install file, which is 432,533,504 bytes (412.4961MB). After copying this file to our RAM disk, we measured the time for writing from the RAM disk to our external USB 2.0 or Firewire 400 or Firewire 800 drive using a Windows timing program written for AnandTech by our own Jason Clark. The copy times in seconds were then converted into Megabits per second (Mb) to provide a convenient means of comparing throughput. Higher Rates therefore mean better performance.
Perhaps the biggest surprise in our testing was the poor performance of USB 2.0 on the ATI Crossfire AMD. ATI had promised improvement in USB performance in the SB450 compared to the earlier SB400, but we could see little improvement in our USB 2.0 tests. ATI responded that our USB 2.0 tests measured sustained throughput, which is relevant in USB operations only with applications like the USB 2.0 hard drive that we use for this test. ATI claims that burst USB 2.0 throughput has been improved in the SB450 to near the same levels of competitive USB 2.0 peak performance. We could not confirm these claims with any test procedures. Perhaps more important, ATI is aware of the issues with USB 2.0 performance and these will be fully corrected – sustained and peak performance – in the SB600 south bridge. It appears that this issue of USB performance may also be corrected by combining the ATI RD480 northbridge with the just released ULi M1575 Southbridge.
Since our ramdisk/apptimer File Copy is measuring sustained throughput, we also compared performance of ATI IDE/SATA/Sil SATA2 using this same test procedure. The performance of ATI IDE remains excellent, but SATA and SATA 2 performance are very competitive, but not standout as in the iPeak storage benchmarks of the same controllers.
Facebook
Twitter
RSS
40 Comments
View All Comments
n00b1e - Tuesday, September 27, 2005 - link
Great article, but how about benchmarking real apps on the overclocked settings and comparing the result to the non-overclocked ones instead of just comparing the highest attainable memory/bus speed overclocks?Quanticles - Tuesday, September 27, 2005 - link
Another bought review..."The ATI Crossfire AMD has every option a serious overclocker could wish for."
How about the option to use a CRT? I like to use 1600x1200 at 85 Hz.
Wesley Fink - Tuesday, September 27, 2005 - link
A 7800GTX or X1800 can easily do 1600x1200 at 85 Hz - and probably outperform X850XT Crossfire. It's all a matter of perspective.In addition, Derek has already said the next gen (X1800), due out in less than 2 weeks, does not have this limitation in Crossfire mode. That's why he did not recommend Crossfire X850/X800 and said to wait a short while. THAT Crossfire solution will also work on this board.
ChronoReverse - Tuesday, September 27, 2005 - link
Red Herring. We're talking about the motherboard and how wellit can overclock the cpu). The graphics card is irrelevant (and the limitation on the xfire cards themselves not the motherboard).Myrandex - Tuesday, September 27, 2005 - link
2nd page:The various ATI Radeon Xpress 200 north bridges can also be combined with ULi south bridges. The current ULi 1573 provides all the features of the ATI BS450 except integrated Gigabit Ethernet.
should be SB450
Wesley Fink - Tuesday, September 27, 2005 - link
I have spoken witrh ATI and several mfgs this morning to update board availability. Between today and the 2nd week of October we should see RETAIL Crossfire motherboards appear from DFI, Gigabyte, ECS, MSI, Asus and a few others. RETAIL availability means you will be able to buy them at New Egg or other e'tailers at that time.X850XT Master Cards are expected to be for sale RETAIL tomorrow, September 28th, with X800 Master Cards several weeks away.
I have a Gigabyte Crossfire AMD in my hands as I write this. It is the release Vewrsion 1.0 board and I received the release BIOS this morning.
eastvillager - Tuesday, September 27, 2005 - link
"yeah, we know our usb performance sucks on SB400, we're fixing it in SB450""Yeah, we know our usb performance sucks on SB450, we're fixing it in SB600"
prediction:
"Yeah, we still don't have USB 2.0 working properly on SB600, wait till SB700, when USB 3.0 comes out and we'll be ok."
Kind of hard to understand how they can do just about everything else on the mobo correctly, but continually screw up USB 2.0. USB 2.0 is a commodity at this point, it is just suppose to work, with no worries, etc.
I use USB 2.0 on a daily basis, it really isn't an area I'm willing to slack on.
Leper Messiah - Tuesday, September 27, 2005 - link
Hm. I'm getting a new mobo soon (as in the next 2 weeks). Is this a paper launch, or will we see single slot solutions out there soon? nVidia has set a precedent with the instant availiblity and massive volume (relatively, I mean they're selling below MSRP for a reason) of their 7800 series. It could be more damaging than delaying the R520 if they don't have it and this mobo out STAT.Would be kinda funny though...for years I've run nVidia chipsets and ATi graphics. Looks like it might get reversed...
allnighter - Tuesday, September 27, 2005 - link
Agreed. Not that I'm referring to AT's conclusions being questionable in any way, shape or manner, I know they say what they see, but it's pretty much obvious that ever manufacturer/vendor simply handpicks any given piece of hardware that is sent to AT for review, since they all know that AT is pretty much the most trusted site. Although I appreciate early previews we get here, I'm a much bigger fan of reviews of retail products. That's about what you'll be able to buy, right away or in just a couple of weeks. Many of these reference pieces are on steroids and simply never materialize in real world performance.Other than that - a very good write up, as usuall.
TehSloth - Tuesday, September 27, 2005 - link
Well mates, this sure does look nifty, but remember what happened to the RS480, which also received Anand's accolades as the best overclocking reference board ever, they couldn't release it right. The Gigabyte board that they talk about in the article was never actually released, and I have a long chain of correspondence with them as it got pushed back more and more. MSI, ECS, and Jetway were the only manufacturers that delivered, and they disabled all the OCing options. Psshhhah!