CrossFire Xpress 3200: RD580 for AM2
by Wesley Fink on June 1, 2006 12:05 AM EST- Posted in
- Motherboards
Network
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 AMD 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:
On the client side (the motherboard under test), we used the following Command Line:
At the conclusion of the test, we captured the throughput and CPU utilization figures from the client screen.
The PCIe Gigabit LAN on the ATI is capable of about 35% faster speed than the performance we have measured with PCI Gigabit LAN used on some motherboards. ATI provides a single Marvell PCIe Gigabit controller, compared to dual Gigabit LAN on the competing NVIDIA 590 chipset. All of the on-board PCIe Ethernet controllers seem to exhibit high CPU utilization, but you should keep in mind that the CPU usage we measure is an extremely artificial number which measures the worst case of a continuous Gb transmission. With broad-band connections needing no more than 100Mb Ethernet, the real-world CPU usage will be much lower than these test results. Throughput and CPU utilization for the ATI AM2 were competitive with results from other boards.
USB and Firewire Performance
USB has been a problem area for the ATI SB450 chipset, but it has not been a major issue with the ULi M1575 Southbridge. To test performance of USB and Firewire on the ATI CrossFire Xpress 3200 AM2 we ran our standard USB throughput test using an external USB hard drive. For Firewire tests an external Firewire 400 or 800 hard disk is used for testing
Our test method uses a RAM disk as our "server" since memory removes almost all overhead from the serving end. We also turn off disk caching on the USB and Firewire side by setting up the drives for "quick disconnect". Our results are then consistent over many test runs.
We used 2GB of fast system memory, set up as a 450MB RAM disk and the balance as system memory. Our stock file is the SPECviewPerf 8.01 install file which is 432, 533, 504 bytes (412.4961MB). After copying this file to our RAM disk, we measure the time for writing from the RAM disk to our external USB 2.0 or Firewire 400 or Firewire 800 drive using an internally developed Windows timing program. The copy times are then converted into Megabits per second (Mb) to provide a convenient means of comparing throughput. Higher rates therefore mean better performance.
A red bar is used for SB600 USB performance and orange bars represent competing chipsets. Blue bars represent Firewire performance.
SB600 lived up to its promise, scoring in the same performance range as competing USB solutions. That is, ATI SB600 is a bit faster than the Uli M1575 in USB 2.0 performance and slightly slower than NVIDIA USB 2.0 performance. At current SB600 performance levels you should see no difference in USB 2.0 performance between NVIDIA and ATI SB600.
ATI chose the excellent VIA VT6307 for Firewire on the reference board. Firewire 400 performance is excellent compared to competing Firewire chips. Keep in mind that the manufacturer can choose whatever Firewire chip they choose to use on NVIDIA and ATI AM2 motherboards. Neither chipset includes native Firewire support.
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 AMD 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, ‹client IP› -a 4 -l 256000 -n 30000
On the client side (the motherboard under test), we used the following Command Line:
NTttcpr -m 4, 0, ‹server IP› -a 4 -l 256000 -n 30000
At the conclusion of the test, we captured the throughput and CPU utilization figures from the client screen.
The PCIe Gigabit LAN on the ATI is capable of about 35% faster speed than the performance we have measured with PCI Gigabit LAN used on some motherboards. ATI provides a single Marvell PCIe Gigabit controller, compared to dual Gigabit LAN on the competing NVIDIA 590 chipset. All of the on-board PCIe Ethernet controllers seem to exhibit high CPU utilization, but you should keep in mind that the CPU usage we measure is an extremely artificial number which measures the worst case of a continuous Gb transmission. With broad-band connections needing no more than 100Mb Ethernet, the real-world CPU usage will be much lower than these test results. Throughput and CPU utilization for the ATI AM2 were competitive with results from other boards.
USB and Firewire Performance
USB has been a problem area for the ATI SB450 chipset, but it has not been a major issue with the ULi M1575 Southbridge. To test performance of USB and Firewire on the ATI CrossFire Xpress 3200 AM2 we ran our standard USB throughput test using an external USB hard drive. For Firewire tests an external Firewire 400 or 800 hard disk is used for testing
Our test method uses a RAM disk as our "server" since memory removes almost all overhead from the serving end. We also turn off disk caching on the USB and Firewire side by setting up the drives for "quick disconnect". Our results are then consistent over many test runs.
We used 2GB of fast system memory, set up as a 450MB RAM disk and the balance as system memory. Our stock file is the SPECviewPerf 8.01 install file which is 432, 533, 504 bytes (412.4961MB). After copying this file to our RAM disk, we measure the time for writing from the RAM disk to our external USB 2.0 or Firewire 400 or Firewire 800 drive using an internally developed Windows timing program. The copy times are then converted into Megabits per second (Mb) to provide a convenient means of comparing throughput. Higher rates therefore mean better performance.
A red bar is used for SB600 USB performance and orange bars represent competing chipsets. Blue bars represent Firewire performance.
SB600 lived up to its promise, scoring in the same performance range as competing USB solutions. That is, ATI SB600 is a bit faster than the Uli M1575 in USB 2.0 performance and slightly slower than NVIDIA USB 2.0 performance. At current SB600 performance levels you should see no difference in USB 2.0 performance between NVIDIA and ATI SB600.
ATI chose the excellent VIA VT6307 for Firewire on the reference board. Firewire 400 performance is excellent compared to competing Firewire chips. Keep in mind that the manufacturer can choose whatever Firewire chip they choose to use on NVIDIA and ATI AM2 motherboards. Neither chipset includes native Firewire support.
Facebook
Twitter
RSS
71 Comments
View All Comments
LoneWolf15 - Thursday, June 1, 2006 - link
Not that anyone will necessarily do so, but will RD580 support the building of Socket 939 boards as well?JarredWalton - Thursday, June 1, 2006 - link
RD580 socket 939 boards have already been made -- well, at least one of them has been made. http://www.anandtech.com/mb/showdoc.aspx?i=2752">DFI CFX3200-DR It is doubtful that we will see many more socket 939 boards using the chipset, since AM2 is basically going to replace socket 939 as fast as AMD can make it happen.LoneWolf15 - Thursday, June 1, 2006 - link
On Page 1, the table for the RD580 shows (8) SATA2 ports and dual-gig ethernet. The board specs on page two on the other hand, show 4 SATA2 ports, and single gig ethernet, but only if a PHY (i.e., Marvel or someone else) is used.Apparently ATI has added 4 additional SATA ports via Silicon image on the reference board; but I don't call that a feature of RD580. What am I missing here? The table on page 1 seems to contradict what is listed on page 2.
Wesley Fink - Thursday, June 1, 2006 - link
We agree with you. The chipset has 4 SATA2 ports and the extra 4 ports come from 3132 Silicon Image controllers. I will try to edit the image.LoneWolf15 - Friday, June 2, 2006 - link
Thanks. Also, what about FireWire? I think your article said that neither nVidia nor ATI has native Firewire (additional VIA/other vendor chipset required), but RD480 and RD580 are listed on your opening table as having 1/2 Firewire ports respectively.Stele - Friday, June 2, 2006 - link
I think the opening table is just a platform chart that divides the target markets of each chipset. On the first column is the target price range of a certain motherboard range. The second column identifies which chipset is meant to cover that particular range. The third column then explains the primary target market for that particular range. Lastly the right-most column briefly describes the features such a motherboard in that particular range should have.Wesley Fink - Friday, June 2, 2006 - link
You are correct, Stele. With that said I now think a better way to handle this and remove confusion is to go back to the original chart and clarify that this is recommendations in the text. Thanks.Stele - Friday, June 2, 2006 - link
Oh you're welcome. Looks like our replies to him were posted at the same time :PYes I think that's a great idea, otherwise after all the editing you're not going to have very much on that chart anymore! Soon we'll have people saying "$250 for a chipset? Then what's the motherboard going to cost??" ;)
Wesley Fink - Friday, June 2, 2006 - link
The feature chart is from ATI literature and was a listing of recommended configurations for various market segments. I have changed the SATA and Gigabit LAN and will remove the Firewire, since it is not chipset specific for either nVidia or ATI. There is an excellent VIA Firewire controller on the Reference board, though we would rather see Firewire 800 which is very fast but disappearing from new board introductions.Stele - Friday, June 2, 2006 - link
Probably because of
1) poor OS support - even Microsoft noted that Vista would not support 1394b at launch
2) poor device support - the majority of appliances and peripherals seem to be quite happy at 1394a with no signs of an imminent and/or major switchover to 1394b
so motherboard manufacturers probably thought "what the heck" and decided to keep costs low for now by sticking to the 1394a controllers, which are likely cheaper than their 1394b counterparts. Furthermore, the 1394a solutions are tried and tested, hence they also avoid unpleasant design surprises that may require time and effort to redesign around... resources which could be better used elsewhere for now.