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 decided to try 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. After copying this file to our RAM disk, we recorded the time to write 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.

Firewire & USB Performance

Possibly the most striking finding in our Firewire and USB throughput tests is the performance of a hard drive connected to Firewire 800. Gigabyte is the only SLI board to feature Firewire 800, and they have used Firewire 1394b on their top boards for almost a year. If you wonder why Firewire 800 matters, just look at the data. Our benchmarks show Firewire 800 at 40% to 55% faster than a drive connected to the more common Firewire 400, and about 16% faster than USB 2.0. The Firewire 800 drive even approaches performance of the IDE drive on the nVidia controller.

Our test is just one of many throughput tests, but in this benchmark, it is clear that the VIA Firewire 400 is faster than TI's 1394a chip.

All of the SATA solutions also slightly outperform IDE in our timed copy from RAM disk. We did not have SATA 2 drives to test with the onboard nVidia SATA2 or the MSI Sil3132, but it is still interesting that throughput with a SATA 1 drive is still a bit faster on the SATA 2 controllers than on SATA 1. We are looking forward to testing the SATA 2 controllers with true SATA 2 drives, which should begin appearing in the next few weeks.

Disk Controller Performance Ethernet Performance
Comments Locked

108 Comments

View All Comments

  • fozzymatic - Tuesday, March 1, 2005 - link

    "So, is SLI worth the cost and the effort? For some, the answer will be a definite no. The SLI boards still cost a great deal, setting up the system is still a daunting task, and the cost of two top-of-the-line video cards will be just too much for many to consider SLI to be a real option."

    I still do not understand why this argument is so popular. Why is the general assumption that purchasers of SLI capable boards will immediately want to jump into a dual-card config? The idea is flexibility. Sure, 2 6800's are expensive now, but they will inevitably get cheaper. So why not buy one now and then profit form your forward thinking later down the line when the price of a second card is cut in half and there are more SLI-supported games available. I concede that the mobos are 50$ more than a non-SLI board but, for 50$, I'll take the enhanced upgrade path. Out of the gate the SLI boards are the fastest single or double-card NF4 mobos available, so whats to lose?
  • justly - Monday, February 28, 2005 - link

    Wesley, well done, although I have to admit I skipped over some of the pages describing the individual boards as I am not personnaly intrested in buying a SLI system.

    One thing about the bar graphs, it could have been a little easier to compare between a single card and SLI if you had used split bars like in this graph
    http://images.anandtech.com/reviews/video/ATI/rade...
    using the top half of the bar for single card and the bottom for duel cards.

    It would also be nice to see a comparasion of disk controller, firewire and USB performance (and anything else that is chipset specific) using all the different brand chipsets.

    I don't think you are the person that does power supply reviews, but with all the concerns recenty about power supplies it would also be nice to see an article that not only describes some of the differences in power supplies but what components draw power from what rails and how much they draw (I have seen power supply guides that give an idea of how many total watts is needed but very little information on how those watts are divided up between rails).

    One last thing, I have a little problem with this statement "the ability of a motherboard to run at much higher than stock speeds tells you something about the quality of components used in a motherboard". If every motherboad had a perfect BIOS and they all had the same overclocking options then your statement could be true, but that is not the case. Would you call all Intel branded motherboards poor quality just because Intel doesn't put overclocking options in their motherboards BIOS? What if an OEM decided to use one of these great overclocking boards in a prebuilt system and the only change they made to the board was to eliminate the overclocking options from the BIOS, is that board now poor quality?


  • Viper4185 - Monday, February 28, 2005 - link

    Well well well, seems you are right. The MSI nForce 4 Ultra board in Australia even has 1x PCI Express slot...

    http://www.msi.com.tw/program/products/mainboard/m...

    Does anyone know which boards support Firewire 800 (1934b)?

    Also to Wesley, thanks for the reply, do you have a rough idea when the nForce 4 Ultra comparison would be available?
  • falcc - Monday, February 28, 2005 - link

    There seems to be different version of MSI's SLI boards depending on where you live. In Australia the SLI board is a MSI K8N Diamond. The interesting thing about this board is that it has two PCI Express x1 slots. as well as the two x16 slots for SLI. It also has a wlan option.
  • falcc - Monday, February 28, 2005 - link

  • ChineseDemocracyGNR - Monday, February 28, 2005 - link

    #43, I'm aware it needs a PHY, but I always thought it worked the same way as it did since the nForce3-250Gb, with no PCI-E involved.

    I checked out the manual for the MSI K8N Diamond and ASUS A8N-SLI, from them:

    MSI
    "Dual LAN
    ? Supports dual LAN jacks
    - 1st LAN supports 10/100/1000 Fast Ethernet by nForce4 SLI
    - 2nd PCI Express LAN supports 10/100/1000 Fast Ethernet by Marvell 88E8053"

    ASUS
    "nForce4 built-in Gbit MAC with external Marvell PHY :
    - NV ActiveArmor
    - NV Firewall
    - AI NET2"

    I couldn't find a reference that the chipset LAN is tied to PCI-E.
  • ajmiles - Monday, February 28, 2005 - link

    Excellent, thanks Wesley. Every response I've had from now has been, quote:

    "With regards to the overclockability, it has AI Overclock, PEG link, and other options, the extent of the overclockability was not promised and unfortunately some customers expect amazing overclocking abilities when the 1T overclock is still a good feature and is overclocking in action."

    Perhaps what you would expect them to say when their board clocks more than 60mhz lower than some competitors.

    If you could keep me apprised of their response either here or at amiles(at)gmail.com that'd be great. Thanks again.
  • JoKeRr - Monday, February 28, 2005 - link

    I really wish MSI could pump a bit more voltage for the ram, 2.85 is a bit low, especially considering the Asus is giving 3V and DFI is giving 4V!! Guess if u want to run your good old BH5 sticks at 250mhz 2-2-2-7, DFI will be the way to go. But I really liked the MSI mobo. o well, guess u can't have everything.
  • JoKeRr - Monday, February 28, 2005 - link

  • Wesley Fink - Monday, February 28, 2005 - link

    #6 & #56 - I saw the same behavior with the A8N-SLI Deluxe during our testing, and I shared my results with Asus. I forwarded your comments and my own to the Asus A8N-SLI BIOS and Engineering team.

Log in

Don't have an account? Sign up now