NVIDIA 680i: The Best Core 2 Chipset?
by Gary Key & Wesley Fink on November 8, 2006 4:45 AM EST- Posted in
- CPUs
Memory Performance
The AMD AM2 has essentially removed concern about the Memory performance of chipsets by providing a low-latency memory controller directly on the processor. Intel continues to integrate the memory controller in their chipsets, and the Intel Core 2 chipsets achieve competitive memory performance and low latency with caching schemes and read-ahead algorithms. Because Intel has done such an excellent job of providing stellar memory performance in the 975x/P95 chipsets, any chipset that hopes to compete with Intel would have to perform similarly in memory controller performance.
To assess the effectiveness of the NVIDIA 680i chipset we measured memory performance with Everest 3.50 from Lavalys and compared results to the top-end Intel 975X chipset.
The results of memory performance on the NVIDIA 680i are truly impressive compared to the 975X. NVIDIA has clearly produced a competitive memory controller for Intel Socket 775, a task which has eluded other chip makers who have tried to compete on this platform. Results can only be called equivalent in any of the Everest benchmarks.
Another widely used measure of latency and memory bandwidth is ScienceMark 2.0.
ScienceMark confirms the results with Everest 3.5. NVIDIA has built a memory controller in the new 680i chipset that is every bit as good as the outstanding Intel memory controller in the 975X. This is not a minor achievement.
The final confirmation of memory controller performance with the 680i chipset comes with SiSoft Sandra 2007. The most common measurement is buffered or Standard Memory Bandwidth.
The AMD AM2 has essentially removed concern about the Memory performance of chipsets by providing a low-latency memory controller directly on the processor. Intel continues to integrate the memory controller in their chipsets, and the Intel Core 2 chipsets achieve competitive memory performance and low latency with caching schemes and read-ahead algorithms. Because Intel has done such an excellent job of providing stellar memory performance in the 975x/P95 chipsets, any chipset that hopes to compete with Intel would have to perform similarly in memory controller performance.
To assess the effectiveness of the NVIDIA 680i chipset we measured memory performance with Everest 3.50 from Lavalys and compared results to the top-end Intel 975X chipset.
| Everest 3.5 Memory Performance | ||||
| Chipset | Read | Write | Copy | Latency |
| NVIDIA 680i | 8045 | 4865 | 5506 | 54.8ns |
| Intel 975x | 7751 | 4868 | 5512 | 52.3ns |
The results of memory performance on the NVIDIA 680i are truly impressive compared to the 975X. NVIDIA has clearly produced a competitive memory controller for Intel Socket 775, a task which has eluded other chip makers who have tried to compete on this platform. Results can only be called equivalent in any of the Everest benchmarks.
Another widely used measure of latency and memory bandwidth is ScienceMark 2.0.
| ScienceMark 2.0 Memory Performance | ||
| Chipset | Latency (512 byte stride) | Memory Bandwidth |
| NVIDIA 680i | 37.12ns | 5449.37 MB/s |
| Intel 975x | 37.81ns | 5430.69 MB/s |
ScienceMark confirms the results with Everest 3.5. NVIDIA has built a memory controller in the new 680i chipset that is every bit as good as the outstanding Intel memory controller in the 975X. This is not a minor achievement.
The final confirmation of memory controller performance with the 680i chipset comes with SiSoft Sandra 2007. The most common measurement is buffered or Standard Memory Bandwidth.
| Sandra 2007 Standard Memory Performance | ||
| Chipset | INT (Integer) | FLT (Float) |
| NVIDIA 680i | 5969 | 5944 |
| Intel 975x | 5949 | 5953 |
Facebook
Twitter
RSS
60 Comments
View All Comments
yyrkoon - Thursday, November 9, 2006 - link
From my little experience with an Asrock board that can use this program, it WILL adjust clock frequency on the fly, however I think that voltage changes need be done only by rebooting. Reguardless whether I'm remembering correctly, I'm fairly certain atleast one possible change needs to be done during, or after a reboot, could be thinking of clock multiplier maybe ?Pirks - Thursday, November 9, 2006 - link
that sucks. guess I'll have to wait till nVidia makes 100% nonreboot-OC mobo, or on-the-fly-OC mobo where you just click a couple of buttons in Windows and voila - your machine turns from quiet office machine to a Crysis fireball, and vice versa - I can dream, can't I? ;)ssiu - Wednesday, November 8, 2006 - link
Since NVIDIA claims the 680i has better FSB overclock than the 650i's, and the 680i results are on par with the mainstream P965's, I am afraid that the 650i's would be significantly worse than the DS3s/P5Bs. In other words, I am afraid that the 650i's are not really a new competitive option for budget/mainstream overclockers.yyrkoon - Wednesday, November 8, 2006 - link
I dont think any true enthusiast is going to be buying a mid range board(chipset) to begin with. If the Intel numbering shceme is anything like the AM2 numbering scheme, the 650i will probably have less availible PCI-E lanes as well, and would be a major factor in my personal decission in buying any such hardware, and I know I'm not alone ;)Jedi2155 - Wednesday, November 8, 2006 - link
I don't think your definition of enthusiast is wholly correct but rather the Manufacturer idea of enthusiasist. I personally think many enthusiasists do indeed have a limited budget, and after seeing the pricing of Asus 680i board, I think mid-range is the way to go...hoping for a cheap < $250 680i board >_>.yyrkoon - Wednesday, November 8, 2006 - link
Yeah, He wasnt talking about true enthusiasts though, I realize this after re-reading his post.One a side note, that if my board brand of choice suddenly went away (ABIT), I would seriously consider buying a Gigabyte board, but the DS3 doesnt seem to be making a lot of people happy in the stability category. What I'm trying to say here, is that perhaps the board MAY not OC as well, but that according to what I've read (reviews, forum posts, and A LOT of newegg user reviews), it couldnt do much worse than the Gigabyte board in this area.
The second question I'd be asking myself, is WHO THE HELL is EVGA . . . we all know they make Video cards (probably the best for customer support for nVidia products).
I'm definately interrested in the 680i chipset, but i think my brand of choice for MANY years now would remain the same, and that I'll be sticking with ABIT :)
Gary Key - Wednesday, November 8, 2006 - link
1. The reference board is designed and engineered by NVIDIA. Foxconn manufactures the boards for the "launch" partners that include BFG and others. Asus, Abit, DFI, Gigabyte, and others will have their custom designed boards out in a few weeks.2. The Abit board is very interesting, here is pic of it - http://img474.imageshack.us/img474/2044/in932xmaxy...">Abit 680i - ;)
yyrkoon - Thursday, November 9, 2006 - link
Didnt even know there was one this close to release gary, lol thanks for the link. Judging by the 5 SATAII connectors, previously released ABIT boards, and what LOOKS like an eSATA connector on the back panel, I suppose this board will support eSATA, and possibly a SATA PM ?Stele - Friday, November 10, 2006 - link
That Abit 680i board looks very interesting indeed... if nothing else because it looks like it sports a digital PWM power supply circuitry similar to that used by DFI in the latter's LANParty UT NF590 SLI-M2R motherboard (the Pulse PA1315NL coupled inductor array is a dead giveaway, as it is designed for use only with Volterra's VT11x5M digital PWM circuitry).Unfortunately more information on such circuitry is proving very difficult to find (Volterra themselves restrict their product details and datasheets to design partners only) ... it'd be great to know how such a power circuit compares in performance and capabilities over the traditional PWM-MOSFET-based ones.
Curiously, the Abit 680i seems to have dropped the AudioMax daughter board.
yyrkoon, I'm guessing the 5th SATA II and the eSATA port are there courtesy of an SiI3132 controller - which is likely the little square IC under the upper heatpipe, just beside the audio connector block. As such, the usual capabilities and features of the said IC would apply, I think :)
yyrkoon - Wednesday, November 8, 2006 - link
I'd just like ot point out that DualNet technology is NOT true NIC Teaming, or rather Link agrregation(802.11a/d I think).When I first heard about DualNet I was extremely excited, since I had been doing TONS of research on NIC bonding etc, but after doing some homework, I found that DuelNet only supports out going packets. It was my hope that you could link two of these boards via a regular GbE switch, and get instant 2GbE connections, but this is not the case(unless they've recently redone DualNet).
Now to the question: Since SATA port Multiplier HBAs require a specific SIL chip(s) on the device they communicate with (to give full speeds of a true RAID), what are the chances that nVidia boards will work with these devices ?
In the past, I've seen two AM2 boards that have a built in SIL chip with eSATA connectors on the board back panel (ABIT, and Asus), but onboard SIL 'chipsets' seem to be rather limited(as in only supporting PM support on two SATA connections). I'd personally REALLY like to see this technology standardized, so it doesnt matter WHAT SATA controller chipset you're using. I also think that once nVidia realizes that PM support onboard is a major plus, and once they implement it, they COULD be taken seriously by many Intel fans.
Also, some Intel chipset fans believe that Intel chipsets are best for a rock solid system (for the record, I'm not one of these people), I guess we'll see if nVidia will change thier minds.