KT333 mobo running PC3200 vs KT400 running PC3200

[cmdrdredd]

Anyplace do this kind of comparison? Overclocking a KT333 Mobo to run DDR400 and a KT400 mobo running the same memory and timings.

what one would yield better memory scores?

 

[cmdrdredd]

anyone?

 

[First]

It would be a dead draw, depending on the motherboards of course.

 

[mechBgon]

If you're looking for high memory bandwidth, might want to wait a bit longer for nForce2 to show up. Check out Evan's findings here: http://www.anandtech.com/chipsets/showdoc.html?i=1719&p=4 Looks like about 30% more bandwidth in TwinBank mode using DDR333, compared to KT400 using DDR333. And the latency is way lower (this is good ). Arrrgh, I want one already!

Keep in mind that the TwinBank feature requires two sticks of RAM. I notice that the review didn't test nForce2 in TwinBank mode, so its actual performance should be higher than what the graphs show... it was compared to KT333 with just one stick of RAM in each board.

 

[First]

Originally posted by: mechBgon
If you're looking for high memory bandwidth, might want to wait a bit longer for nForce2 to show up. Check out Evan's findings here: http://www.anandtech.com/chipsets/showdoc.html?i=1719&p=4 Looks like about 30% more bandwidth in TwinBank mode using DDR333, compared to KT400 using DDR333. And the latency is way lower (this is good ). Arrrgh, I want one already!

Keep in mind that the TwinBank feature requires two sticks of RAM. I notice that the review didn't test nForce2 in TwinBank mode, so its actual performance should be higher than what the graphs show... it was compared to KT333 with just one stick of RAM in each board.

Actually, Anand wrote that review. He'll also be releasing Part 2 of that review soon, while I'll be doing individual nForce2 reviews (Epox, ASUS, etc. retail boards) within the next two weeks.

 

[mechBgon]

Oops! I'm looking forward to the in-depth reviews!

 

[cmdrdredd]

well, I run Intel anyway so it makes no difference. I was looking to see if the KT400 chipset had some flaws in it

 

[mechBgon]

Chipsets probably all have flaws. Look at this one, found in the Intel MCH2 when paired with i845 or i850e:

5. Sustained PCI Bandwidth
Problem: During a memory read multiple operation, a PCI master will read more than one complete cache
line from memory. In this situation, the MCH pre-fetches information from memory in order to
provide optimal performance. However, the MCH cannot provide information to the PCI master
fast enough. Therefore, the Intel® 82801BA terminates the read cycle early to free up the PCI bus
for other PCI masters to claim.
Implication: The early termination limits the maximum bandwidth to ~90 MB/s.
Workaround: None
Status: There are no plans to fix this erratum.

(from ftp://download.intel.com/design/chipsets/specupdt/29824705.pdf)

This would annoy the heck out of me, since I have an Ultra160 SCSI card that bursts much faster than 90Mb/sec on my nForce board (up to 121Mb/sec). Then again, my KT333 board has a problem with the SCSI card being limited in burst rate, too. Particularly when the onboard USB 2.0's enabled. Nobody's perfect, I guess

 

[PUNKtotalled]

Originally posted by: cmdrdredd
well, I run Intel anyway so it makes no difference. I was looking to see if the KT400 chipset had some flaws in it

I got both a KT333 and a KT400, in real life I just can't see any improvements in performance. You simply get new features like USB2 with the new 8235 southbridge. Basically its the same...

In the near future VIA's KT333s will simply be KT400s without AGP8X support.