The launch of Athlon 64 has brought us 2 chipsets thus far: the nVidia nForce3 150 and VIA K8T800. As we have discussed in reviews of boards based on these chipsets, neither one really meets the specifications that we would like to see in Athlon 64 chipsets.

While VIA performs at the specified 800 Hyper Transport speed, it is hampered by lack of a real means to fix AGP/PCI lock. This severely limits the ability of VIA chipset boards to overclock, and is the most important complaint we have had with this chipset. VIA is also a 2-chip solution and the actual communication speed between the North and South Bridge chips is specified as 500MHz, which is much slower than the 1.6GHz to 3.2GHz that is used for internal communication of the other components on HyperTransport. While VIA has made a lot of splash about being the “only” chipset to implement 800 HT speed, they are really telling only part of the story, since the slower North/South bridge communications are certainly a bottleneck if VIA is correct about the impact of a slower HT speed on other chipsets. You simply cannot have it both ways.

nVidia, on the other hand, fully implements the ability to fix the PCI/AGP on nForce3-150 chipset boards. However, current 150 version chipsets cannot run with stability any faster than 600 HyperTransport. The nForce3 does offset this limitation partially with their one-chip implementation of nForce3 150. This assures the single chip is communicating with other HT components at the fastest speeds available, and is not hampered by a slower North/South bridge bus.

The practical reality is these differences in the nForce3-150 and VIA K8T800 have been impossible to measure at stock performance speeds. With the Athlon 64 memory controller on the chip, it appears the chipset has less impact on final performance, and our benchmarks with the VIA and nF3 chipsets have been virtually identical. Overclocking, on the other hand, has been quite different between the 2 chipsets. Using the same Athlon64 chip, we have been able to reach overclocks to the 230 (920FSB) range with nF3-150; VIA solutions, conversely, have never been able to reach much beyond the 214-215 range due to problems of the floating PCI/AGP speeds.

nVidia will have a new chipset in the next few months that will run at 800 HT called the nForce3-250. VIA is also rumored to have a new chipset with PCI/AGP lock in the works. Frankly, we are more skeptical as to whether or not the VIA solution will appear, since VIA has never had a chipset with PCI/AGP lock. We also believe that VIA would have implemented PCI/AGP lock if it had been doable with their current core logic in the year we all waited for Athlon64 to appear. While there is promise of better solutions from both nVidia and VIA, the reality today is neither chipset does exactly what we want.

SiS is now releasing their Athlon64 solution, which we are evaluating in this look at the SiS755 chipset. SiS does run at 800 HyperTransport, and SiS also has implemented the ability to run the PCI/AGP speed asynchronously, so it is possible to fix PCI/AGP speed. On paper, at least, SiS appears to be a better Athlon64 solution than either nForce3-150 or VIA K8T800. While it is also a 2-chip solution like VIA, the SiS755 chipset provides North/South communication using the proprietary Mutiol bus. For the 755, SiS has increased Mutiol speed to 1GHz, a higher speed with less chance of saturating the bus than the VIA solution.

A Closer Look at SiS755
POST A COMMENT

14 Comments

View All Comments

  • Googer - Thursday, December 16, 2004 - link

    Lets Bench IT! Reply
  • MoronBasher - Saturday, December 06, 2003 - link

    I have a sis 746, and 735 and i can't wait for this chipset to come out!!! Reply
  • mason - Thursday, November 27, 2003 - link

    Great review!
    Two things -
    1. The SIS reference board is almost always the fastest performing board with that particular chipset. I think it's premature to label it a winner until you can find a decent performing production board.
    2. SIS has been making great chipsets for the Athlon since the 735, only no one knew about them because they typically ran second to VIA in memory banddwidth, which was what all the major review sites cared about. The HDD performance and overclocking headroom on the 735 and 745 both outclassed the VIA boards (KT266, KT266A, KT333) of the day, but they were hard to find and few manufacturers made anything better than cut-rate boards.
    The MSI 745 Ultra and the Leadtek 735 board were possibly the best of the early generation SIS athlon boards.

    The current SIS748 chipset for the athlon 400FSB is actually very good, though again slightly slower than the KT600 is memory bandwidth.
    I just wish major sites would review the few boards that do use these chipsets, so we could start seeing higher quality boards like the DFI 748.
    Reply
  • destaccado - Thursday, November 27, 2003 - link

    buy now.....asus k8v is an awesome board, in 2 months you might as well wait another two months, and another..... Reply
  • jeeptreker - Wednesday, November 26, 2003 - link

    Purchase timing is my concern. I'm considering the AMD 64 3200+ & the Chaintech ZNF-150 w/ nForce3-150 chipset for Christmas. Am I on the edge of a change? If I wait a month or 2 will the AMD 64 3400+ and SIS755 or nForce3-250 chipsets be out? If these items won't be out for 6 mos. then I'll just be chasing technology.
    Buy now or wait? Any suggestions will be appreciated.
    Reply
  • Gimpus - Tuesday, November 25, 2003 - link

    When should we expect motherboards based on the SiS755 chipset to reach retail chanels? Reply
  • NFS4 - Tuesday, November 25, 2003 - link

    I'll wait til I see the performance of shipping boards before I jump ship...reference boards tend to be "tweaked" in some case. I'm currently lovin' my VIA K8T800 based Asus K8V Deluxe. Reply
  • justly - Tuesday, November 25, 2003 - link

    "To our surprise, SiS755 also provided the best performance in AnandTech benchmarks of any Athlon64 chipset that we have tested."

    Did this realy surprise Anandtech? it didn't surprise me.
    For quite some time SiS southbridge chips have proven to be well designed, in fact whenever disk preformance was tested SiS has had some of the best scores. The main problem SiS has had in the past was with the performance of their memory controller. So it would only make sence that when the memory controller is no longer a concern, as it is with the Athlon 64, SiS would be able to show of its southbridge performance.

    Other than your surprise about the performance I thought it was a good article. I hope Anandtech doesn't ignore future SiS (or ALi) AMD solutions like it has in the past with socket "A".
    Reply
  • Pumpkinierre - Monday, November 24, 2003 - link

    I noticed your description of the erratic booting/stability behavior when overclocking which is similar to overclocking problems described in the ipkonfig article-today's AT news post:http://www.ipkonfig.com/Articles/AMDCastrated/Page... .
    Is this due to data corruption in the HT link as a result of CPU speed being linked to the HT link speed?
    Reply
  • HammerFan - Monday, November 24, 2003 - link

    I think performance will be influenced most by how "streamlined" everything in the chipset is (i.e. IDE drivers at maximum performance, things such as LAN and RAID taken off of the PCI bus and put on the Southbridge). Reply

Log in

Don't have an account? Sign up now