Asus P5N32-SLI: Dual x16 - What Dreams Are Made On . . .
by Gary Key on October 27, 2005 12:05 AM EST- Posted in
- Motherboards
Ethernet Performance
The current motherboard test suite includes LAN performance measurements. All of these boards utilize PCI Express controllers with the only difference being the supplier of the core logic.
The Windows 2000 Driver Development Kit (DDK) includes a useful LAN testing utility called NTttcp. We used the NTttcp tool to test Ethernet throughput and the CPU utilization of the various Ethernet Controllers used on the nForce4 Ultra motherboards.
We set up one machine as the server; in this case, an Intel box with an Intel CSA Gigabit LAN connection. Intel CSA has a reputation for providing fast throughput and this seemed a reasonable choice to serve our Gigabit LAN clients.
At the server side, we used the following Command Line as suggested by the VIA whitepaper on LAN testing:
All standard Ethernet tests were performed with standard frames and the NVIDIA Active Armor suite disabled unless otherwise noted. Gigabit Ethernet supports Jumbo frames as well and will provide a further reduction in CPU overhead.
We added a further test scenario in which ActiveArmor was enabled on the Asus P5N32-SLI Deluxe board via the new 6.82 platform driver set. The throughput numbers increased by almost 3% while the CPU utilization dropped by over 7% with the standard settings enabled in the application. We also enabled Jumbo frames with ActiveArmor resulting in an increase in throughput numbers by 5% while the CPU utilization dropped by over 12%. We will be adding this benchmark testing to our standard test suite along with providing more information regarding the NVIDIA firewall solution in the near future. I highly recommend that if you have a NF4 based board, you should utilize ActiveArmor in its current configuration.
The current motherboard test suite includes LAN performance measurements. All of these boards utilize PCI Express controllers with the only difference being the supplier of the core logic.
The Windows 2000 Driver Development Kit (DDK) includes a useful LAN testing utility called NTttcp. We used the NTttcp tool to test Ethernet throughput and the CPU utilization of the various Ethernet Controllers used on the nForce4 Ultra motherboards.
We set up one machine as the server; in this case, an Intel box with an Intel CSA Gigabit LAN connection. Intel CSA has a reputation for providing fast throughput and this seemed a reasonable choice to serve our Gigabit LAN clients.
At the server side, we used the following Command Line as suggested by the VIA whitepaper on LAN testing:
Ntttcps - m 4 ,0, -a 4 - l 256000 - n 30000On the client side (the motherboard under test), we used the following Command Line:
Ntttcpr - m 4 ,0, -a 4 - l 256000 - n 30000At the conclusion of the test, we captured the throughput and CPU utilization figures from the client screen.
All standard Ethernet tests were performed with standard frames and the NVIDIA Active Armor suite disabled unless otherwise noted. Gigabit Ethernet supports Jumbo frames as well and will provide a further reduction in CPU overhead.
We added a further test scenario in which ActiveArmor was enabled on the Asus P5N32-SLI Deluxe board via the new 6.82 platform driver set. The throughput numbers increased by almost 3% while the CPU utilization dropped by over 7% with the standard settings enabled in the application. We also enabled Jumbo frames with ActiveArmor resulting in an increase in throughput numbers by 5% while the CPU utilization dropped by over 12%. We will be adding this benchmark testing to our standard test suite along with providing more information regarding the NVIDIA firewall solution in the near future. I highly recommend that if you have a NF4 based board, you should utilize ActiveArmor in its current configuration.
Facebook
Twitter
RSS
70 Comments
View All Comments
Kensei - Friday, October 28, 2005 - link
I just wanted to say that I REALLY appreciate the wonderful combination of a person who is a very, very good writer and technologist. This extremely rare combination makes him one of the best technical writers I've come across in the past 20 years.It's not too hard to find people who are technically competent but very hard to find someone who can communicate well and knows what the hell they're talking about (ask anyone who has been to college). Quite frankly, he sets a standard that I think all AnandTech writers (ok... all technical writers) should strive to eventually achieve. This level of expertise typically takes years of practice to acquire even among the talented. Can't wait for his next article.
To quote the first post..."Mixing philosophy, classical literature and computer hardware reviews? Gotta love it."
Kensei
Gary Key - Monday, October 31, 2005 - link
I greatly appreciate the comments. This was my third article and hopefully I improve with each one although you have now placed a great deal of pressure on me. ;->The next article series will be a multiple board review. I am learning how to convey several different messages in a very condensed form. It will be different than this last article so I would appreciate comments, good or bad. I try my best to listen to the readers and follow up on suggestions.
I have two very good editors in Wes and Karen so it really is a team effort at AnandTech. I still have a great deal to learn and in fact will be taking a composition course this winter to improve my skills.
Kensei - Thursday, November 3, 2005 - link
You are welcome. I don't think you need a composition course so I'd be interested in hearing how much you learned once it's over. Hopefully I'm wrong, but you may be disappointed by the course. If this is a college course, you may find that people in English departments don't quite get technical writing. It's different (although not totally different) than writing good short stories.Keep up the good work and I look forward to your future articles.
Kensei
screwtech02 - Friday, October 28, 2005 - link
So let me get this straight... In "theory" i can run my 820 at a 250fsb or 4.0, with a ddr700 rating?? And the board will recognize both the cores?? I'm tempted to get this board, but after having the previous one from ASUS, i'm scared to death, it was a HORRIBLE overclocker, max i could get was 230fsb, and lousey mem performance.... But if you say this board is different, i may try one....Gary Key - Saturday, October 29, 2005 - link
Email me please and I can forward some testing results to you along with additional information.NegativeEntropy - Friday, October 28, 2005 - link
Please check your USB/Firewire/Ethernet throughput graphs for their use of MB (MegaByte) vs Mb (Megabit).Nice board :)
Gary Key - Friday, October 28, 2005 - link
I have corrected the charts. Thank you for noticing the issue. Sometimes you view something so much that you miss the obvious. :)noac - Friday, October 28, 2005 - link
I read that you thought most would fit - "an excellent amount of room for alternative cooling solutions". Im wondering more specifically if the Scythe Ninja will fit with/without the optional fans. BTW did you test them, the fans? Wondering how much noise they make and if they work well.Gary Key - Friday, October 28, 2005 - link
I do not have the Ninja although I know where to get one for a test. :) I received the optional fans a couple of days ago from Asus (tried to get them before publishing but it did not work out). I will try them this weekend and respond to your questions. They are designed to be used with watercooling or phase change setups. The stock Intel 840EE cooler (upgraded from other Pentium D units) provided enough air flow in the area to keep the MOFSETs cool. The aftermarket coolers I used provided more than enough air flow and fit great within the CPU area. Let me know if you need a listing of these heatsinks.yacoub - Thursday, October 27, 2005 - link
That's a freakin' awesome (if expensive) board!Btw THANK YOU THANK YOU THANK YOU for finally showing just how greatly sound enabled impacts the framerates on boards with on-board audio. Amazing that 17-19% of your CPU's power can be sapped by a stupid audio chip, especially when that turns into ~15fps drop in some games. Ugh.