We first reported about VIAs problems with PCI in early December 2001. When combined with a VIA-board, ATA/133 adaptors and fast SCSI cards can not live up to their performance expectations. In January 2002 VIAs first patch appeared on the firms support website, aimed at users of Promise cards. Of course we checked if this patch really helps and maybe solves problems with other cards.
VIAs problems with its PCI implementation surfaced with the move to Ultra-ATA/133. The maximum speed of the interface here increases to a theoretical maximum of 133 MBytes/s. Currently, Maxtor is also the only vendor to actually ship these drives, named DiamondMax D540X and D740X.
To fully use the speed of the interface of these drives, companies like Promise, Highpoint and ACARD offer PCI cards with Ultra-ATA/133-chips. These controllers fully consume the bandwidth of PCI: As with Ultra-ATA/133 PCI has a theoretical maximum of 133 MBytes/s. As with many other storage related units, vendors here define one megabyte to be one million bytes, and not 1048576 bytes. Therefore, in more technical units, the theoretical maximum is 127,2 MBytes/s.
In addition to that, Ultra160-cards for SCSI peripherals have long exceeded the limitations of the PCI bus, as their theoretical maximum is 160 MBytes/s.
In our tests with the maximum burst rate offered by todays hard drives, only motherboards equipped with chipsets by Intel, SiS and ALi showed decent performance. VIAs flaws were found with board designed for Intels and AMDs CPUs alike.
Hard Drive Overhead
While constantly reviewing ATA/100 hard drives we saw interface speeds of up to87 MBytes/s. These speeds can only be achieved when the drive transfers data to and from its fast buffers, but also affect real world performance. This is especially true if you copy large files within one drive, as we will see a little later in this story.
For our storage reviews we normally use Tyans Trinity motherboard, it comes with VIAs MVP3 chipset.
You can't really expect ATA/100 to deliver more than these 87 MBytes/s. On the one hand, taking 1024 as a factor, the interface only gives you maximum speeds of 95,4 MBytes/s. On top of that, apart from the actual data commands and status information has to be transferred, which narrows the bandwidth even more.
With Ultra-ATA/133 cycles have shortened from 40 ns (ATA/100) to 30 ns. Data is transferred the rise and fall of the signal. The interface has a theoretical maximum of 127,2 MBytes/s. Not taking the overhead into account, Ultra-ATA/133-drives should be able to transfer about 100 MBytes/s in burst mode.
The speed while doing sequential transfers from the hard drive media itself is actually much lower than that. High end IDE drives max out at about 40 MBytes/s currently. If you consider the overhead, these drives can only push older Ultra-ATA/66-controllers to their limits.
Benchmarks: Burst Mode
For these tests we used Maxtors DiamondMax D540X and D740X with the Promise- and Highpoint-controllers. The other components are listed in the "Test Setup" section, found to the right of this text.
To do some compatibility checks, we also ran the same set of tests with nine motherboards equipped with chipsets by Intel, VIA, ALi and SiS. As many boards feature the same PCI controllers, we only did some quick cross checks with other chipsets, e.g. VIAs KT266A that all showed the same behavior.
Motherboards with the Intel chipsets i815, i820 and i845 offered the PCI performance we expected. The Promise Ultra133 TX2 card with the Maxtor drives was able transfer between 109 and 117 MBytes/s. Even if one considers the overhead that's a very good result. Highpoints RocketRAID 133 still gives you 95 to 100 MBytes/s. Motherboards with SiS and ALi chipsets showed similar results.
Chipset | Highpoint RocketRAID 133, Maxtor D540X | Highpoint RocketRAID 133, Maxtor D740X | Promise Ultra133 TX2, Maxtor D540X | Promise Ultra133 TX2, Maxtor D740X |
|---|---|---|---|---|
| ||||
ALi Alladin Pro5 | 95,0 MBytes/s | 95,9 MBytes/s | 96,3 MBytes/s | 96,1 MBytes/s |
Intel 815 | 96,0 MBytes/s | 97,6 MBytes/s | 113,0 MBytes/s | 115,2 MBytes/s |
Intel 820 | 94,9 MBytes/s | 95,4 MBytes/s | 108,9 MBytes/s | 114,9 MBytes/s |
Intel 845 | 97,6 MBytes/s | 100,5 MBytes/s | 114,5 MBytes/s | 117,4 MBytes/s |
SiS 645 | 94,2 MBytes/s | 96,7 MBytes/s | 107,1 MBytes/s | 108,0 MBytes/s |
VIA MVP3 | 74,1 MBytes/s | 76,6 MBytes/s | 63,8 MBytes/s | 63,5 MBytes/s |
VIA KT133A | 76,1 MBytes/s | 77,5 MBytes/s | 78,4 MBytes/s | 78,2 MBytes/s |
VIA P4X266A mit VT8233 | 79,7 MBytes/s | 81,2 MBytes/s | 90,3 MBytes/s | 90,1 MBytes/s |
VIA P4X266A, VT8233A | 64,8 MBytes/s | 62,6 MBytes/s | 72,3 MBytes/s | 72,6 MBytes/s |
As the table shows, burst performance significantly drops when these ATA/133 cards are plugged into a motherboard with VIAs chipsets. The Promise Ultra133 TX2 there only offers between 64 MBytes/s (VIA MVP3) and 90 MBytes/s at best (VIA P4X266A with VT8233 Southbridge). Highpoints PCI card shows similar effects. Even when the chip HPT372-Ultra is integrated with the motherboard as with the Shuttle part we used, there's no more than 65 MBytes/s tranferred. This motherboard is equipped with VIAs P4X266A chipset, including the VT8322 as a southbridge.
Please note: The burst transfers given here are completely independent from the CPU used and its clock speed. Even the slowest CPU we used, an AMD K6-2 at 400 MHz, has a much higher bandwidth than the bottlenecks named PCI or IDE bus.
ATA/133: IDE-Timing
To check the timing within the IDE bus itself we attached the cards by Promise and Highpoint to our Tektronix TLA704 Logic-Analyzer . Despite the bad performance with burst transfers we found the actual cycle timing to be correct. The Promise Ultra133 TX2 and Highpoints RocketRAID 133 transfer data within cycles of 30ns as per the specification of ATA/133.
If this is so, why do VIA motherboards only give you 64 to 90 MBytes/s effectively? The answer lies within the many breaks these systems take during bursts.
Normally, a burst should be performed continuously and without any interruption. The above pictures shows a burst like this, recorded using the Promise Ultra133 TX2 and and Intel-845-motherboard. The whole burst here is performed correctly. The length of a burst, however, can differ depending on the data transferred.
With VIA boards, this high speed transfer from the cache of a hard drive is constantly interrupted within a couple of µs. It has then to be re-initiated, as the next picture shows. Therefore, the effective burst rate drops to 64 to 90 MBytes/s at best.
In contrast to chipsets from Intel, SiS and Ali, VIAs products seem to have difficulties with maintaining high transfer rates close to the maximum speed of PCI for a longer time. As with ATA/133 PCI has a theoretical maximum bandwidth of 127,2 MBytes/s. It seems fair to conclude that VIAs implementation of a PCI bus must be the reason for the problems found.
To check the signaling with a VIA chipset we used VIAs P4XB motherboard. It is equipped with VIAs P4X266A chipset, using VT8233 as a southbridge. This VIA chipset was the best of the worst when we measured the transfer rates with ATA/133 bursts.
ATA/133: PCI-Timing
By use of a PCI probe with our logic analyzer we also checked what was happening within the PCI bus during theses transfers. With an Intel 845 based system we found a constant flow of data, whereas with VIA boards these transfers are interrupted all the time.
To take these scores, we made Maxtors DiamondMax D740X work with the Promise Ultra133 TX2 in burst mode.
After these 24 packets are transferred, a new address gets requested. The PCI bus can only transfer blocks of 96 bytes of data within one burst with this solution.
With Intels chipsets being able to transfer 1024 packets within one burst, this makes a whole transfer of 4096 bytes. As a consequence, Intels chipsets gain a higher transfer rate overall on their PCI bus than VIAs chipset.
SCSI-RAIDs and PCI
The timing checks we did explain, why ATA/133 cards perform so bad with VIA chipsets. These new high speed adapters max out the bandwidth of the PCI bus and VIAs solution can not keep up with that.
This effect can also be found with other PCI cards. We also checked the PCI transfers taking place using Adaptecs SCSI-RAID-2100S. This card is designed for Ultra160 SCSI and easily outperforms PCI.
For a real world test we set up four pieces of Fujtsus Ultra160 hard drive MAM3184MP as a RAID-0 stripe set. These drives spin their platters at 15.000 rpm and offer sequential transfers from the disc media at 54 MBytes/s. They are among the fastest available hard drives at the moment.
In a RAID-0 configuration the SCSI adapter combines the physical hard drives to one logical drive. Data is distributed across the physical drives in consecutive blocks. This enables parallel reads and writes which in the end boosts throughput. In theory the maximum transfer rate of every physical drive nicely adds up, but you still loose a little performance due to the overhead included in managing the RAID itself.
With Adaptecs SCSI-RAID-2100S one can adjust the block size of the RAID. 128 KBytes are set per default, the minimum size is 8 KBytes. Taking the maximum of 128 KBytes, a file of 512 KBytes is distributed among all four hard drives in our test configuration. This speeds up transfers significantly, for every drive reads or writes one segment simultaneously.
This performance boost is most noticeable when working with large consistent files, as every drive is working with sequential reads or writes. When working with a lot of small files, access time of the hard drives used becomes the bottleneck. In this situation even a RAID-0 configuration shows the performance of single drive at best.
SCSI: Benchmarks
To not measure the performance of one single drive with our Quad-RAID-0 we set the block size to a multiple of 128 KBytes for the read tests. This guarantees that every one of the four hard drives is working as hard as possible during the benchmarks.
As every single drive delivers up to 54 MBytes/s transfers, the bandwidth of Adaptecs-RAID-2100S with Ultra160-SCSI is eaten up completely with this configuration already. To keep up the flow of data to and from the drives, the card features a cache of 32 MBytes. As a consequence, this RAID card is able to fully load the PCI bus in our setup.
We took the following scores using MSIs 845 Pro2 (845 chipset) and VIAs P4BX (P4X266A) motherboards with this same SCSI-RAID.
Intel 845 | VIA P4X266A | |
|---|---|---|
For all tests: Adaptec SCSI-RAID-2100S with four Fujitsu MAM3184MP, RAID-0 | ||
sequential reads max. | 113,6 MBytes/s | 72,9 MBytes/s |
sequential reads average | 110,9 MBytes/s | 72,3 MBytes/s |
sequential reads min. | 106,2 MBytes/s | 70,8 MBytes/s |
tecMark Read | 23,6 MBytes/s | 21,0 MBytes/s |
tecMark Write | 32,7 MBytes/s | 24,0 MBytes/s |
tecMark Copy | 31,4 MBytes/s | 25,7 MBytes/s |
copying a 2 GByte file | 101 Sekunden | 133 Sekunden |
With the MSI motherboard the RAID-0 sequentially reads data with up to 114 MBytes/s. This performance is maintained over nearly the whole capacity of the RAID: the minimum speed only drops to 106 MBytes/s. Even with burst transfers from the cards cache we found the same results.
This looks much worse with the VIA motherboard. Our RAID there only delivers a maximum of 72 MBytes/s with sequential reads. Although the system also sticks with this speed over almost the whole capacity, a lot of the potential of the RAID is wasted. To be more precise: If you spend more than 2300 Dollars for a RAID system like this, you loose 34 per cent of the performance when this RAID has to deal with a VIA chipset.
Even with everyday tasks the differences are shuttering. If you copy a file of 2 gigabytes on the RAID systems, the Intel solution finishes 30 per cent faster then a VIA motherboard.
SCSI: PCI-Timing
Again, we looked into the PCI traffic with our logic analyzer. The results of the SCSI-RAID are in line with the effects seen with ATA/133 peripherals. The transfers over VIAs PCI bus get interrupted, whereas the Intel motherboards have much longer bursts.
As with the ATA/133 cards the above picture shows, that VIAs PCI bus only transfers blocks of 96 bytes within one burst.
And once again: The Intel chipset transfers 4096 bytes of actual data within one burst and only then asks for a new address.
Stability Issues
According to a lot of feedback from readers, the problems we found with VIAs PCI implementation may also be the root cause for a lot of the stability issues reported for VIA chipsets in the past. We came to this conclusion, as a lot of the effects disappeared as soon as the "unofficial" patch was applied (see next page).
One of our readers was reporting of a lot of crashes with his Elitegroup K7VZA (KT-133A chipset). In combination with Creatives Soundblaster Live Player 5.1 his system crashed whenever some sound was played for a longer time. Whether he was listening to MP3 files via WinAMP or using PowerDVD to watch a DVD movie or trying to play Quake III - his machine would crash after a couple of minutes. After he installed the patch, the system would run fine for hours. Several readers of Kyle Bennetts HardOCP sent him similar reports when Kyle followed up on our story.
We also got mail from a musician who reported that his VIA chipset (KT-266A with MSIs K7T-266 Pro2 R/U) would prevent him from getting any professional work done. He uses Creamwares DSP board Luna II. Cards like this are often used in professional audio production, since their signal to noise ratio and overall sound quality is far superior over off-the-shelf soundcards. Furthermore, they offer lower latencies by circumventing Microsofts DirectX driver model by using special drivers. These drivers interface with software samplers like GigaSampler and virtual studios like Cubase.
We visited his studio to hear the effect in person. When installed fresh out of the box with VIAs latest 4-in-1-drivers the machine would not play one single note from a keyboard correctly over a software sampler. The sound was often interrupted and had a number of clearly audible "hiccups".
A system like this works a little different from the familiar MIDI sounds of a budget soundcard. The external keyboard here only tells which notes to play, and the software sampler creates the sound requested by use of a library and the CPUs processing power. All the soundcard does is a D/A conversion. As a consequence, the system relies on a constant flow of data across the PCI bus while the note is played. As the rest of the setup was working fine, the problem could not have been caused by software or drivers.
After we installed the unofficial latency patch the effect described completely disappeared. Whether we played one single note with a number of instruments or went through complex songs with up to 64 note polyphony and dozens of instrumenst - not a single note was wrong.
The two examples described show that the way VIA implements the PCI bus is far more than a performance issue. The problems also occur with professional applications or while gaming.
The "unofficial"
PCI Latency Patch
It was not VIA, but independent programmer George Breese of Networking Resources from New York who first came up with a patch for some of VIAs problems with the PCI bus. George often posts in the independent forums at VIAHardware, who also offer the patch as a direct download.
Please note: This is not an "official" patch supplied by VIA or any motherboard manufacturer. You may use it at your own risk. To date, we could not verify if there are any stability issues implied through longer burst cycles. However, we did not see any crashes or incompatibilities after applying this patch. But, taking its severe modifications into account, this is not completely impossible. You should read the files included in the download before going any further.
The patch deals with PCI Latency, among other things. This PCI Latency sets the number of cycles, that one PCI-Busmaster-Device can request the bus for exclusive use, before releasing it. This minimum amount of clock cycles is set, so PCI performance will not decrease too much, if burst transfers are interrupted too often. On the other hand, the latency timer also prevents one device from making exclusive use of the bus for too long. After the PCI latency during one burst has passed, every other device can request usage of the bus. The burst is then cancelled immediately.
The PCI-Latency-Patch with Version 0.19 mainly changes the following settings by setting registers in the northbridge:
Turns off options "PCI Delay Transaction" and "PCI Master Read Caching" (Registers 70, Bit 1 and 2).
Sets Arbitration-Timer of the PCI-Controller to 96 clock cycles. One typical BIOS-default is 32 clocks. This new setting is made to work around the older IDE bug in VIAs 686B southbridge (Register 75, Bit 0-2 or 0-3, depending on chipset).
The VIA PCI controller's "PCI Latency" timer, which is normally used to guarantee the CPU at least a specified number of PCI clock cycles when accessing the PCI bus, is set to zero. (Register 0D)
The CPU is removed from PCI priority rotation. Ordinarily, the CPU can be guaranteed access to the PCI bus after one to three other devices have used the bus. (Register 76, bits 4 and 5, and bit 7 on older chipsets).
We did a quick cross check with this patch using the Promise Ultra133 TX2 and a few motherboards. It all resulted in better burst transfers.
Chipset | No Latency-Patch | With Latency-Patch |
|---|---|---|
Promise Ultra133 TX2 and Maxtor DiamondMax D740X | ||
VIA MVP3 | 63,5 MBytes/s | 84,1 MBytes/s |
VIA KT133A | 78,2 MBytes/s | 93,4 MBytes/s |
VIA P4X266A | 90,1 MBytes/s | 100,9 MBytes/s |
As burst transfers are still not en par with Intel chips they still are 32 per cent higher now than without the patch.
Checking the PCI timing with the logic analyzer we found that now bursts with VIA chipsets transferred 32 packets of data. Only then the bus is released. Without the patch, this was only 24 packets of data. These longer bursts explain the increase in performance.
Playing around with the patch a little more we found that even audio applications can gain a great benefit from it. One system with a professional DSP sound card for studio use lost all the drops of notes it showed before. Without the patch, one single note played by a software sampler was audibly interrupted frequently. This effect disappeared after applying the patch. It's another indication, that PCI transfers got interrupted to often.
VIAs official patch, Version 1.01
Under the section "Drivers" VIA was offering a patch at its support site VIA Arena for two weeks only. However, the question was "Do you use a Promise RAID PCI card?" If this is so, the patch promises to "increase the burst rate." As VIA did not mention the performance and stability issues found recently, this can only be viewed as an attempt to conceal the real PCI problems. According to VIA the patch works with all versions of Windows. What exactly this patch does is not documented by VIA.
In our lab, however, this patch really makes a difference with Promise cards. With VIAs own motherboard P4XB (P4X266 chipset) burst transfers went up to 113,3 MBytes per second from 90,1 MBytes/s without the patch. We were using the Promise Ultra 133 TX2 for this test. This is the basic version of the adaptor which not offers any RAID functionality. Even there VIAs patch shows its effect.
As given in the pictures above, our Logic-Analyzer again showed what happens: VIA increased the burst length from 24 to 120 blocks of data, before the bus is released. This explains the significant performance increase. George Breeses Patch, on the other hand, only increases the burst length to 32 blocks of data.
Limitations of the VIA patch, Version 1.01
But in contrast to George Breeses universal solution VIAs patch only helps a limited number of people: It only works with Ultra-ATA-cards by Promise. Even when patched, the performance of a VIA chipset with ATA/133 cards by HighPoint or ACARD is unchanged and poor.
Chipset | ACARD AEC-6280 | Highpoint RocketRAID 133 | Promise Ultra133 TX2 |
|---|---|---|---|
All scores taken with Maxtors DiamondMax D740X | |||
VIA KT266A without Patch | 87,7 MByte/s | 83,3 MByte/s | 83,5 MByte/s |
VIA KT266A with Patch | 87,7 MByte/s | 83,7 MByte/s | 104,2 MByte/s |
VIA P4X266A without Patch | 89,6 MByte/s | 81,2 MByte/s | 90,1 MByte/s |
VIA P4X266A with Patch | 89,7 MByte/s | 81,2 MByte/s | 111,3 MByte/s |
In addition, there is another limitation of the patch VIA won't tell about: It only increases performance with chipsets that feature VIAs V-Link technology. VIA uses V-Link since the release of the Apollo Pro266. The highspeed chip-to-chip bus V-Link can sustain transfer rates of up to 254 MByte/s and interfaces between the North- and the Southbridge. Older chipsets like the KT133A or MVP3 do not offer higher burst transfer rates with VIAs patch. These chipsets connect the Southbridge to the Northbridge as a PCI device.
Therefore VIAs patch does not solve the problem of the weak PCI performance of all of VIAs chipsets. At least, one can completely remove the patch through Windows' control panel.
We checked back with VIA, and they promised to come up with a better solution. The patch version 1.01 vanished from their sites, however, the links to the file itself are still working. On Friday, February 01, 2002, VIA finally came up with version 1.04, described on the next page.
Update: VIAs official patch, Version 1.04
According to VIA, the new version of their patch will increase performance with RAID cards from ACARD, Adaptec and Highpoint and not only with Promise-cards anymore. We did a few test with all these cards. In addition to that, we also checked the new patch with the Advance 29133, another Ultra-ATA/133-PCI-Controller, which is not on VIAs list yet.
This time, the results are more satisfying. The increase in burst transfer rates is between 20 to 30 MBytes/s with all cards. This brings VIAs PCI-Bus to the level of performance found with Intels chipset. Even with the Advance card these results can be obtained.
PCI card | No Patch [MBytes/s] | Patch 1.04 [MByte/s] |
|---|---|---|
All scores taken with Maxtors DiamondMax D740X and VIAs P4XB Motherboard (P4X266A chipset) | ||
ACARD AEC-6280 | 89,6 | 106,5 |
Adaptec 29160 | 78,2 | 104,5 |
Advance 29133 | 82,9 | 105,8 |
HighPoint RocketRAID 133 | 81,2 | 99,9 |
Promise Ultra133 TX2 | 90,1 | 111,3 |
In addition to this, VIAs patch 1.04 now works with older chipsets not featuring the V-Link-Bus as well. We checked this with a KT133A and a MVP3. Burst transfers with the KT133A went up to 108,3 MBytes/s from 78,2 MBytes/s. The MVP3 even scored 102,2 MBytes/s with the patch, and 64,1 without it. We took these scores with the Promise Ultra133 TX2.
However, it remains to be seen whether the new patch also remedies some of the stability issues many readers have reported.
As of Friday, February 01, 2002, VIA has not posted the patch to either VIA ARENA or VIAtech.com. So, for the time being, tecCHANNEL.DE will be hosting the patch here.
Over the following weekend VIA posted this patch to VIA Arena here. However, the filename changed from "viapfd.zip" to "rpp1.01.zip". We did a file compare of the files in these archives, and they are identical. Just to avoid further confusion, we replaced the file on our server with VIAs.
This piece of software was made by VIA, not tecCHANNEL.DE. Use it at your own risk. However, we did not see a single crash or loss of data when doing our tests in the lab.
Update:Conclusion
VIAs problem with PCI performance affects motherboards for Intel- and AMD-CPUs alike. VIA only adapts the northbridge to new processors and normally uses the same southbridge for all chipsets of one generation. However, with VIAs new V-Link-Designs, the southbridge also features all of the PCI interface. With our tests, the same PCI problems were found up to the latest southbridge VT8233A. The older chipsets, without V-Link, showed the same effects.
The whole problem is the bad PCI performance of VIAs chipsets. In theory, and according to the datasheets, there is a maximum bandwidth of 133 MBytes/s. In practice, there is 65 to 90 MBytes/s left of it. Intel chipset offer between 110 to 119 MByte/s. Chipsets by SiS and ALi fall in between these two extremes.
Especially for ATA/133 cards this makes VIAs chipsets a "no-go". With a single drive, you may not see the effect as heavily as here. However, these affordable RAID cards are very popular for setting um cheap stripe sets, optimized for performance. With two hard drives delivering 40 MBytes/s, this setup already gets slowed down by VIA chipsets. Depending on the motherboard, there's not 80, but around 60 MBytes/s left.
SCSI-RAIDs with Ultra160 drives are no solution either, as the problem lies within the PCI bus and not the hard drive interface. We found significant performance decreases here as well.
VIAs quietly released Promise RAID Performance Patch only helps user that have a Promise card and a VIA chipset with V-Link technology. This was quickly followed by version 1.04, which boosts performance with all RAID cards tested so far and seems like an OK workaround.
For the time being, we can not recommend unpatched VIA chipsets for professional users who demand high performance from their hard drives and think about setting up RAID configurations. This includes video editing, small- and medium-business servers and workstations for graphics- and audio-editing.
The problems found, especially with the frequent interruptions of data transfers on the PCI bus of VIA's chipsets, may also be responsible for many of the compatibility issues found with their products in the past as the feedback from a lot of readers showed. Most of them were happy after installing the "unofficial" patch by George Breese. We can only hope that VIAs official patch 1.04 will have the same effect. (cvi/nie)
Test Setup
| |
Motherboard 1 | Tyan Trinity ATX S1598 |
|---|---|
Processor | Super Socket 7 |
Chipset | VIA MVP3 |
BIOS | V1.04a 052199 |
Motherboard 2 | Elitegroup K7VZA Rev. 3.0 |
Processor | Socket A |
Chipset | VIA KT133A |
BIOS | 3.3b 09/20/01 |
Motherboard 3 | Shuttle AV45GTR |
Processor | Socket 478 |
Chipset | VIA P4X266A & VT8233A |
BIOS | v6.00PG 11/06/01 |
Motherboard 4 | VIA P4XB |
Processor | Socket 478 |
Chipset | VIA P4X266A & VT8233 |
BIOS | --- |
Motherboard 5 | MSI 845 Pro2 |
Processor | Socket 478 |
Chipset | Intel i845 |
BIOS | --- |
Motherboard 6 | Siemens D1127 |
Processor | Slot 1 |
Chipset | Intel i820 |
BIOS | v4.06 Rev. 1.05.1127 05/25/00 |
Motherboard 7 | |
Processor | |
Chipset | ALi Alladin Pro5 |
BIOS | |
Motherboard 8 | MSI 645 Ultra |
Processor | Socket 478 |
Chipset | SiS 645 |
BIOS | --- |
Motherboard 9 | Asus A7M266-D |
Processor | Dual Socket A |
Chipset | AMD-760 MPX |
BIOS | --- |
Harddisk 1 | Maxtor DiamondMax D540X Model 4G120J6 |
Capacity | 120 GByte |
Interface | Ultra-ATA/133 |
Harddisk 2 | Maxtor DiamondMax D540X Model 4G160J8 |
Capacity | 160 GByte |
Interface | Ultra-ATA/133 |
Harddisk 3 | Maxtor DiamondMax D740X Model 6L40J2 |
Capacity | 40 GByte |
Interface | Ultra-ATA/133 |
Harddisk 4 | Maxtor DiamondMax D740X Model 6L80J4 |
Capacity | 80 GByte |
Interface | Ultra-ATA/133 |
Harddisk 5 | IBM Deskstar 60GXP Model IC35L040AVER07-0 |
Capacity | 40 GByte |
Interface | Ultra-ATA/100 |
Harddisk 6 | Fujitsu MAM3184MP |
Capacity | 18,4 GByte |
Interface | Ultra160-SCSI |
PCI-Controller 1 | HighPoint RocketRAID 133 |
Interface | Ultra-ATA/133 |
Firmware | v2.1 |
PCI-Controller 2 | Promise Ultra133 TX2 |
Interface | Ultra-ATA/133 |
Firmware | v2.20.0050.10 |
PCI-Controller 3 | ACARD AEC-6280 |
Interface | Ultra-ATA/133 |
Firmware | --- |
PCI-Controller 4 | Promise Ultra100 |
Interface | Ultra-ATA/100 |
Firmware | v2.00 (Build 12) |
PCI-Controller 5 | Adaptec SCSI-RAID 2100S |
Interface | Ultra160 SCSI |
Firmware | v001.35 |