Intel D975XBX: Intel brings their Bad-Axe to Market
by Gary Key on January 26, 2006 12:05 AM EST- Posted in
- Motherboards
Disk Controller Performance
With the variety of disk drive benchmarks available, we needed a means of comparing the true performance of the wide selection of controllers. The logical choice was Anand's storage benchmark first described in Q2 2004 Desktop Hard Drive Comparison: WD Raptor vs. the World. The iPeak test was designed to measure "pure" hard disk performance, and in this case, we kept the hard drive as consistent as possible while varying the hard drive controller. The idea is to measure the performance of a hard drive controller with a consistent hard drive.
We played back Anand's raw files that recorded I/O operations when running a real world benchmark - the entire Winstone 2004 suite. Intel's iPEAK utility was then used to play back the trace file of all IO operations that took place during a single run of Business Winstone 2004 and MCC Winstone 2004. To try to isolate performance differences to the controllers that we were testing, we used the Maxtor MaXLine III 7L300S0 300GB 7200 RPM SATA drive in all tests. The drive was formatted before each test run and a composite average of 5 tests on each controller interface was tabulated in order to ensure consistency in the benchmark.
iPeak gives a mean service time in milliseconds; in other words, the average time that each drive took to fulfill each IO operation. In order to make the data more understandable, we report the scores as an average number of IO operations per second so that higher scores translate into better performance. This number is meaningless as far as hard disk performance is concerned as it is just the number of IO operations completed in a second. However, the scores are useful for comparing "pure" performance of the storage controllers in this case.
Our testing results in RAID 5, 0, and 1 with the Intel ICH7R was successful, but we did not have time to properly complete testing of the other storage controllers for this article. We will have published RAID results for all tested boards in our 975X roundup along with results from the NVIDA based P5N32-SLI.
With the variety of disk drive benchmarks available, we needed a means of comparing the true performance of the wide selection of controllers. The logical choice was Anand's storage benchmark first described in Q2 2004 Desktop Hard Drive Comparison: WD Raptor vs. the World. The iPeak test was designed to measure "pure" hard disk performance, and in this case, we kept the hard drive as consistent as possible while varying the hard drive controller. The idea is to measure the performance of a hard drive controller with a consistent hard drive.
We played back Anand's raw files that recorded I/O operations when running a real world benchmark - the entire Winstone 2004 suite. Intel's iPEAK utility was then used to play back the trace file of all IO operations that took place during a single run of Business Winstone 2004 and MCC Winstone 2004. To try to isolate performance differences to the controllers that we were testing, we used the Maxtor MaXLine III 7L300S0 300GB 7200 RPM SATA drive in all tests. The drive was formatted before each test run and a composite average of 5 tests on each controller interface was tabulated in order to ensure consistency in the benchmark.
iPeak gives a mean service time in milliseconds; in other words, the average time that each drive took to fulfill each IO operation. In order to make the data more understandable, we report the scores as an average number of IO operations per second so that higher scores translate into better performance. This number is meaningless as far as hard disk performance is concerned as it is just the number of IO operations completed in a second. However, the scores are useful for comparing "pure" performance of the storage controllers in this case.
Our testing results in RAID 5, 0, and 1 with the Intel ICH7R was successful, but we did not have time to properly complete testing of the other storage controllers for this article. We will have published RAID results for all tested boards in our 975X roundup along with results from the NVIDA based P5N32-SLI.
Facebook
Twitter
RSS
34 Comments
View All Comments
BigP - Wednesday, June 21, 2006 - link
Im a self build Virgin - but I'm going in at the deep end. Intel's site makes their Dual Core stuff sound awsome!(a) Is it?(b)Should I look to spend my cash elsewhere when considering a motherboard/processor?Gary Key - Saturday, July 15, 2006 - link
This board is fine for stock performance and if you get rev-0304 it works very well with Core 2 Duo.FOXY25 - Sunday, February 4, 2007 - link
hi that are my system setting. My system sometimes make complete restart and i dont know why. I have change entire board with another and nothing. Do y think that could be in memory i have 2x DDR2 1024 MB at 800 Mhz Kingmax. thanks for answer.Foxy====== Board ======
Manufacturer Intel Corporation
Product Name D975XBX
Version AAD27094-306
Serial Number BQBX645001ND
BIOS Version BX97510J.86A.1476.2007.0119.1334
BIOS ROM Size 512 KB
BIOS Release Date 19.1.2007
====== Processor ======
Manufacturer Intel(R) Corporation
Processor Name Intel(R) Core(TM)2 CPU 6400 @ 2,13GHz (2 Cores)
Bus Speed 1067 MHz
Processor Speed 2,133 GHz
Stepping 6
Form Factor Other
Hyper-Threading Technology Status Not Supported
====== Cache ======
L1 Cache Data Cache 32 KB, Code Cache 32 KB Per Processor Core
L2 Cache 2048 KB Unified Cache (2048 KB Cache Per 2 Cores)
====== Memory ======
Error Correction Single-bit ECC
Maximum System Memory 4 GB
Memory Slots 4
---- CHAN A DIMM 0 ----
Socket Designation CHAN A DIMM 0
Current Memory Type DDR2
Installed Size No Module Installed
---- CHAN A DIMM 1 ----
Socket Designation CHAN A DIMM 1
Current Memory Type DDR2
Installed Size 1024 MB
Memory Speed 800 MHz
---- CHAN B DIMM 0 ----
Socket Designation CHAN B DIMM 0
Current Memory Type DDR2
Installed Size No Module Installed
---- CHAN B DIMM 1 ----
Socket Designation CHAN B DIMM 1
Current Memory Type DDR2
Installed Size 1024 MB
Memory Speed 800 MHz
====== Onboard Devices ======
#Device Type Ethernet
Device Description Intel (R) 82562 Ethernet Device
Device Status Enabled
#Device Type Sound
Device Description Intel(R) Azalia Audio Device
Device Status Disabled
#Device Type Other
Device Description Silicon Image 3114 SATA RAID Controller
Device Status Disabled
#Device Type Other
Device Description Texas Instruments TSB82AA2 1394A/B Controller
Device Status Disabled
====== Hard Drive ======
#Model ST3320620AS
Max. Transfer Mode UDMA 6 (ATA/133)
Active Transfer Mode UDMA 5 (ATA/100)
S.M.A.R.T. Status Enabled
Size 298,09 GB
#Model ST380811AS
Max. Transfer Mode UDMA 6 (ATA/133)
Active Transfer Mode UDMA 5 (ATA/100)
S.M.A.R.T. Status Enabled
Size 74,53 GB
JarrettV - Thursday, February 23, 2006 - link
Does this board support dolby digital live in the sigmatel audio chipset? I'm looking to replace my old SoundStorm setup.Also, does Intel High Definition = Dolby Digital Live support?
neilfeier - Wednesday, February 22, 2006 - link
Unlike most users of this motherboard that want to use the dual x8 PCIe slots for graphics, I want to use them for benchmarking a pair of x4 data acquisition boards we are developing. I want to test max rates to and from memory, as well as peer-to-peer transfers between the two boards (assuming the MCH allows this).So my question is: Do you think I can I put a x16 or x8 PCIe graphics card in the third x4 PCIe slot hanging off the south bridge? I don't care about graphics performance too much, I just want a dual monitor card that will work in that slot and leave the main two slots free.
And ideas on this would be helpful. Thanks!
Gary Key - Wednesday, February 22, 2006 - link
I will try it this weekend and report back.neilfeier - Friday, March 3, 2006 - link
Thanks Gary, I anxiously await the results of your experiment.Neil
Gary Key - Thursday, March 9, 2006 - link
Hi Neil,I had video working in this slot. I updated to the new bios release today and will test the performance in a couple of days.
Thanks,
Gary
Gary Key - Tuesday, March 28, 2006 - link
Neil,Performance is average but it works.
Gary
Missing Ghost - Monday, January 30, 2006 - link
error! That's not how pcie works! pcie is always full duplex, and never single-ended!