ASRock 939SLI32-eSATA2: ULi Dual x16 SLI
by Gary Key on March 2, 2006 12:15 PM EST- Posted in
- Motherboards
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 I/O 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 I/O operation. In order to make the data more understandable, we report the scores as an average number of I/O 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 I/O operations completed in a second. However, the scores are useful for comparing "pure" performance of the storage controllers in this case.
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 I/O 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 I/O operation. In order to make the data more understandable, we report the scores as an average number of I/O 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 I/O operations completed in a second. However, the scores are useful for comparing "pure" performance of the storage controllers in this case.
Facebook
Twitter
RSS
46 Comments
View All Comments
UJMA - Sunday, March 5, 2006 - link
I see, I'm still interested to see how this Epox board overclocks, I look forward to the Anantech review. If its priced similar to the Asrock Sli but with better voltage options I will get one despite it being x8 x8 ... thanks for the info.UJMA - Saturday, March 4, 2006 - link
fantastic!!! I rate Epox boards highly, I'm waiting for that particular board to make an appearance in the UK ... I look forward to your results!Redrider - Saturday, March 4, 2006 - link
I am looking to build a system for my 15 year old son who does video editing as his system stressing function, not gaming. We do video editing on my own aging but still quite nice FIC AU13max, Athlon2500+, All-in-Wonder 9700pro, 1GB (2x 512)PC2700, system that I built 3 years ago (my only other previous build). I want to build a system that will be good for video editing primarily but provide for gaming should his gaming interest change from his Playstation2 to his PC. I would build my own system and pass my old system down to him like I did last time, but really like the DVR/home theater I have set up with my TV, JVC 9010VBK receiver, and AIW AGP card.Anyway, things sure have changed since my last build! I could use a bit of guidance. I am considering this board and would like advice on the least expensive (as a baseline, I will work my way up from there budgetarily) CPU, memory, video card, etcetera that would serve the aforementioned needs.
To add a bit of complexity to my question (I hope this off topic diversion is ok) I had been considering a DFI LP UT NF4 Ultra-D mainly for the future potential if he gets into overclocking and such as well as the cool factor with a uv lighted case. Some reviews gave this poor marks for stability at the default settings which sent me looking elsewhere like here. Does the X2 support of the ASRock 939SLI32 warrant going with a dual core and this board for multitasking capability?
Thanks for your assistance.
dab - Saturday, March 4, 2006 - link
my $.02I just RMA'd a defective Ultra-D. The power requirements are very high, as it is capable of severely overvolting your hardware. It is also a very advanced board and may be difficult to use in many situations. Read at dfi-street.com before purchasing system components if you're serious about this avenue.
Perhaps he would be better off with a less demanding, more user friendly board like the Asrock board or an Asus offering.
Redrider - Saturday, March 4, 2006 - link
Thanks for the heads up. I was a bit apprehensive about the reviews referencing compatibility issues on the DFI. This ASRock seems interesting. Asus seems like people either love'm or hate'm. I tend away from mainstream as evidenced by my FIC Mobo which appears to be one of the last of the line. I guess I'll keep on looking to see what I come up with.If I go with the ASRock any component suggestions? Any other specific components that I should avoid?
Live - Friday, March 3, 2006 - link
Great to see the new way of presenting the gaming benchmarks. The "min" numbers are especially useful. Nice and easy to understand as well. Keep up the good work! I hope you will continue to use this in all your gaming benches. With the reports/speculation of Nvidias next high end offering being close to ATIs X1900XTX in the sense that it will beat it in some and loose in others this extra info might be the decisive factor.Missing Ghost - Thursday, March 2, 2006 - link
I don't like it. The layout is not very good. The chipset heatsinks look crappy. It seems like the southbridge heatsink is too high and will be in the way of expansion cards. And why a 20 pin power connector? I want 24 pins, especially because this board supports sli. I think I can find better for this price, but maybe that's because I don't care about 16x pcie slots.kelim - Thursday, March 2, 2006 - link
Can anyone confirm what (if any) Zalman HSFs are compatible with this motherboard?Gary Key - Friday, March 3, 2006 - link
Zalman CNPS-9500 - YesZalman CNPS-7700 - No
Zalman CNPS-7000 - I do not have this item but looking at the measurements it would be extremely close, taking the measurements off the 7700 unit in place it might fit but just as easily might not.
kelim - Saturday, March 4, 2006 - link
Thank you good sir. The 9500 is what I'll be coupling with this baby.