Disk Controller Performance

With so many chipsets and brands of storage controllers on current Athlon 64 boards, we standardized on Anand’s storage benchmark, first described in Q2 2004 Desktop Hard Drive Comparison: WD Raptor vs the World, as a standard means of measuring disk controller performance. To refresh your memory, 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 of all the IO operations that take place during a single run of Business Winstone 2004 and MCC Winstone 2004. To try to isolate performance difference to the controllers that we were testing, we used Seagate 7200.7 model SATA and IDE hard drives for all tests.

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 should not be used to report hard disk performance 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.

iPeak Business Winstone Hard Disk I/O

iPeak MM Content Creation Hard Disk I/O

The ULi is a really excellent performer in iPeak tests, with performance in league with the ATI SB450 that we recently tested in our Sapphire motherboard review. The ULi M1567 was among the highest iPeak measurements that we have yet seen in IDE and on-board SATA. While the SATA controller of the ULi 1567 is not the SATA 2 used by the NVIDIA nForce4, its performance is even faster than nF4 when running our stock SATA drive.

In past benchmarking, IDE has provided the slowest IO performance in this roundup. However, ULi and ATI IDE break that trend, with IDE performance being the best that we have measured since we have been testing with iPeak.

There are no additional SATA/SATA2 controllers on the ULi M1695 Reference Board 2, but for IDE or SATA disk storage, the ULi M1567 delivers outstanding storage performance.

Overclocking Comparison USB, Firewire & Storage Performance
Comments Locked

46 Comments

View All Comments

  • AMDScooter - Friday, August 5, 2005 - link

    ^^^ Same. My OC'd S754/Clawhammer plays all current games fine. Seeing as none of the titles I play currently can take advantage of SMP now anyway I am really in no rush to migrate. That combined with the fact my X800 XTPE on the AGP bus still has plenty of bandwidth to spare. Also, the lack of NV drivers for all games to be able to take advantage of 2 video cards makes me lean more for the ATI chipset soloution anyway. My2c..
  • MarkB - Friday, August 5, 2005 - link

    How about using the OCZ memory volatage booster card for the overclocking tests.. would be crazy to see performance at 400 FSB and high clocked ram.
  • SpaceRanger - Friday, August 5, 2005 - link

    I thought the OCZ Memory thing was just a voltage stabilizer, not a booster. Maybe I am getting the 2 modules confused..
  • Lonyo - Friday, August 5, 2005 - link

    Nah, I'm fauirly sure it adds voltage adjustments up to either 3.2 or 3.5v.


    "The OCZ DDR Booster with patent-pending PowerClean technology supplies “cleaner” power to the installed memory modules and allows increasing their voltage above the rated one"

    http://www.xbitlabs.com/articles/memory/display/oc...">http://www.xbitlabs.com/articles/memory/display/oc...

    "in the extreme right position, the memory receives a voltage of 3.9v."

    It would be a little unfair since no other tests have been run with the booster, but it would be nice to get a sneak peek at possible performance of very high speed RAM with AMD64 and a high FSB. Some nice OCZ VX in there with the booster and 3.5v or so would be something worth seeing.
  • nserra - Friday, August 5, 2005 - link

    Wesley Fink there are some questions unanswered, yet.

    The performance in IDE and SATA is impressive.
    Does it have SATA NCQ?

    You should also ask about this riser card, because the final version must have 3 PCIe 16X slots, with 2 working has 8X, I doubt that the riser card is a good working solution, because if I put the board in a case how can I connect the monitor cables or even insert the cards on the riser ?

    Also how does it have 2 PCIe x4 (or x2) if it has only 20 PCIe lanes, or does this mean only one will work in 4X mode and 2 in 2X mode?

    Also ask about when we should expect mobo’s with those chipset start selling?
    Example: http://www.asrock.com/product/product_939Dual-SATA...">http://www.asrock.com/product/product_939Dual-SATA...
  • Wesley Fink - Friday, August 5, 2005 - link

    Yes, ULi tells me this south bridge board does support NCQ - as do the coming M1573 and M1575 south bridges.

    I do not know the final solution on the riser card. This is a Reference Board for qualification. Manufacturers will decide what they wish to implement. As I stated in the review I do agree the riser is not a likely production feature.

    As you can see in the BIOS picture on page 4, the options are 1 x4 or 2 x2 - total 4 lanes added to the 16 equals 20. ATI actually has 22 lanes in their chipset and use the extra 2 lanes for communication between north/south bridge.
  • joex444 - Friday, August 5, 2005 - link

    Notice that in the BIOS screenshot it says:
    1x16 1x4
    1x16 2x2
    2x8 1x4

    So, you have a choice of running 1 x4 card or two x2 cards.

    Can you run x4 cards in an x4 slot at x2 speed? Heck, where are the x4 cards anyways, can't say I've actually seen an x4 slot on a board before, either.
  • jpkomm - Friday, August 5, 2005 - link

    I asked ASrock's US sales division the same thing. They said the "939Dual-SATA2" motherboard will not be available in the US market. Of course, I'm not too sure if that is unshakable or not. They may or many not release it here; however, they may do it but just in a different flavor. Your guess is as good as mine. I love the reviews pumping up this chipset, but I have yet to find anything solid as to US releases. Guess I will just sit patiently and wait.
  • lsman - Friday, August 5, 2005 - link

    OCworkbench.com review this board as these jumpers are for
    "FUTURE_CPU_PORT"...Socket M2..
    so may be the board to look for..
    http://www.ocworkbench.com/2005/asrock/reviews/939...">http://www.ocworkbench.com/2005/asrock/reviews/939...
  • Xenoterranos - Friday, August 5, 2005 - link

    Anyone know where/when to get one of these. This is exactly what I need, as I and probably thousands of you have an AGP card and don't want to spring for PCIe yet.

Log in

Don't have an account? Sign up now