Disk Controller Performance
With the variety of disk drive benchmarks available, we needed a means of comparing the true performance of the wide selection of controllers. The logical choice was Anand's storage benchmark first described in Q2 2004 Desktop Hard Drive Comparison: WD Raptor vs. the World. The iPeak test was designed to measure "pure" hard disk performance, and in this case, we kept the hard drive as consistent as possible while varying the hard drive controller. The idea is to measure the performance of a hard drive controller with a consistent hard drive.
We played back Anand's raw files that recorded I/O operations when running a real world benchmark - the entire Winstone 2004 suite. Intel's iPEAK utility was then used to play back the trace file of all IO operations that took place during a single run of Business Winstone 2004 and MCC Winstone 2004. To try to isolate performance differences to the controllers that we were testing, we used the Maxtor MaXLine III 7L300S0 300GB 7200 RPM SATA drive in all tests. The drive was formatted before each test run and a composite average of 5 tests on each controller interface was tabulated in order to ensure consistency in the benchmark.
iPeak gives a mean service time in milliseconds; in other words, the average time that each drive took to fulfill each IO operation. In order to make the data more understandable, we report the scores as an average number of IO operations per second so that higher scores translate into better performance. This number is meaningless as far as hard disk performance is concerned, as it is just the number of IO operations completed in a second. However, the scores are useful for comparing "pure" performance of the storage controllers in this case.
The performance patterns hold steady across both Multimedia Content IO and Business IO, with the ULi, ATI, and Silicon Image based disk controllers providing the fastest IO operations followed by the on-board NVIDIA nForce4 SATA controllers. The performance generated by the ULi and ATI IDE controller logic is particularly excellent, while the SATA performance of both is up to 12% better when compared to the nForce4 chipset. The SATA performance of the Silicon Image 3132 is very competitive with the core logic chipsets in our tests.
With the variety of disk drive benchmarks available, we needed a means of comparing the true performance of the wide selection of controllers. The logical choice was Anand's storage benchmark first described in Q2 2004 Desktop Hard Drive Comparison: WD Raptor vs. the World. The iPeak test was designed to measure "pure" hard disk performance, and in this case, we kept the hard drive as consistent as possible while varying the hard drive controller. The idea is to measure the performance of a hard drive controller with a consistent hard drive.
We played back Anand's raw files that recorded I/O operations when running a real world benchmark - the entire Winstone 2004 suite. Intel's iPEAK utility was then used to play back the trace file of all IO operations that took place during a single run of Business Winstone 2004 and MCC Winstone 2004. To try to isolate performance differences to the controllers that we were testing, we used the Maxtor MaXLine III 7L300S0 300GB 7200 RPM SATA drive in all tests. The drive was formatted before each test run and a composite average of 5 tests on each controller interface was tabulated in order to ensure consistency in the benchmark.
iPeak gives a mean service time in milliseconds; in other words, the average time that each drive took to fulfill each IO operation. In order to make the data more understandable, we report the scores as an average number of IO operations per second so that higher scores translate into better performance. This number is meaningless as far as hard disk performance is concerned, as it is just the number of IO operations completed in a second. However, the scores are useful for comparing "pure" performance of the storage controllers in this case.
The performance patterns hold steady across both Multimedia Content IO and Business IO, with the ULi, ATI, and Silicon Image based disk controllers providing the fastest IO operations followed by the on-board NVIDIA nForce4 SATA controllers. The performance generated by the ULi and ATI IDE controller logic is particularly excellent, while the SATA performance of both is up to 12% better when compared to the nForce4 chipset. The SATA performance of the Silicon Image 3132 is very competitive with the core logic chipsets in our tests.
Facebook
Twitter
RSS
23 Comments
View All Comments
Gary Key - Tuesday, April 4, 2006 - link
This item was changed along with the sound reference to Abit that two of us missed a few times at 3:40 this morning. Sorry about the issues! :)
We do have another bios to test today, so far it has fixed the Firewire and Marvel Ethernet throughput issues. Time to test stability and overclocking.
ashishkochaar - Sunday, September 24, 2017 - link
I had tried doing so with the same software but I was unable to get access for<a href="https://www.anandtech.com/show/1983">Anand... Services.
Ryan Norton - Tuesday, April 4, 2006 - link
Seriously, I love AT and their reviews are consistently great, but I bought into the A8R-MVP hype and was completely let down. I don't OC my ass off so my disappointment isn't quite the same as someone who wants to run a 3000+ at 325 HTT at 2.8GHz blah blah but still. Not saying AT is at fault, ASUS mostly is: just that no amount of praise can overcome the perception of RD480 boards in the PC enthusiast world now. ESPECIALLY praise for OCability =^)bob661 - Tuesday, April 4, 2006 - link
I heard that there are some pretty pissed off owners of this board out there. ATI is new to the chipset game and they'll need some time to mature like every other manufacturer out there.Ryan Norton - Tuesday, April 4, 2006 - link
Yeah, and like I said, I'm not one of them, since I really don't OC much. I was more excited about the layout and passive chipset cooling, which HAS lent itself to a very quiet PC in my Antec P180. Still (and I've got little evidence to back this statement up) the indelible sense of disappointment has crept into my overall appraisal of the board. I replaced an MSI Neo4 Platinum with it and would probably go back to that board were I able to replace its chipset fan (a real leafblower sound-alike) with a passive solution, but my 7800GTX hangs right over that area. The BIOS is very counterintuitively laid out, and not being able to choose which PCIe x16 slot the video card sits in is also annoying.You should go read the A8R-MVP section of the Asus website forums (finding them is a PITA since there are few static links available over thre) and read the bitching. I think most of the AT forumgoers' collective experiences with the board ended up here:
http://forums.anandtech.com/messageview.aspx?catid...">http://forums.anandtech.com/messageview...amp;thre...
bob661 - Tuesday, April 4, 2006 - link
Thanks for the link.seanp789 - Tuesday, April 4, 2006 - link
The final words page has a link at the bottom to ethernet performance. a page 14 that does not appear to exist.JarredWalton - Tuesday, April 4, 2006 - link
The article was modified from being 16 pages originally to being 13 pages -- no content was changed, but the layout was modified. You probably just saw the article in a transitory state. Sorry.Patrese - Tuesday, April 4, 2006 - link
Great review, it seems that the manufacturers are using Anandtech as beta testers for BIOS... :) Is it really too hard to release a mobo with a properly working BIOS? It seems to be happening everytime...BTW, this board is too purple to be an Abit, as stated on the last page: "In the on-board audio area, the Abit board offers"
Visual - Tuesday, April 4, 2006 - link
WTF is a video shunt card?