Intel P35: Intel's Mainstream Chipset Grows Up
by Gary Key & Wesley Fink on May 21, 2007 3:45 PM EST- Posted in
- CPUs
Test Setup
| Standard Test Bed - CrossFire Test Configuration | |
| Processor | Intel Core 2 Duo QX6700 (2.66GHz, 8MB Unified Cache) |
| RAM | OCZ Reaper PC2-9200 (4x1GB) DDR2 4-4-4-10 Corsair CM3X1024 (4x1GB) DDR3-1066 8-7-7-16 |
| Hard Drive | Western Digital 150GB 10,000RPM SATA 16MB Buffer |
| System Platform Drivers | Intel - 8.3.0.1013 |
| Video Cards | 1 x MSI HD2900XT |
| Video Drivers | ATI 8.37.4.3 (HD2900XT Release Drivers) |
| CPU Cooling | Tuniq 120 |
| Power Supply | OCZ ProXStream 1000W |
| Optical Drives | Plextor PX-760A, Plextor PX-B900A |
| Case | Cooler Master CM Stacker 830 |
| Motherboards | Intel D975XBX2KR (Intel 975X) - BIOS 2692 ASUS P5K Deluxe (Intel P35) - BIOS 0304 ASUS P5K3 Deluxe (Intel P35) - BIOS 0011 MSI P35 Platinum (Intel P35) - BIOS 7345P01 Gigabyte P35-DQ6 (Intel P35) - BIOS F4 DFI Infinity P965 (Intel P965) - BIOS 424 EVGA 680i LT SLI (NVIDIA 680i LT) - BIOS P04 |
| Operating System | Windows Vista 64-bit Ultimate |
| . | |
Test conditions were maintained the same, as much as possible, over the platforms tested. Our game tests were run at settings of 1280x1024 HQ to ensure our GPU was not a bottleneck during testing. We will provide CrossFire results in our upcoming P35 roundup but preview performance numbers are available in this article.
All results are reported in our charts and color-coded for easier identification of results. We utilize new drive images on each board in order to minimize any potential driver conflicts. Our 3DMark results are generated utilizing the standard benchmark resolution for each program. We run each benchmark five times, throw out the two low and high scores, and report the remaining score. All results are run at stock speeds for this article although we will provide overclocked results in the next article.
Our choice of software applications to test is based on programs that enjoy widespread use and produce repeatable and consistent results during testing. Microsoft Vista has thrown a monkey wrench into testing as the aggressive nature of the operating system to constantly optimize application loading and retrieval from memory or the storage system presents some interesting obstacles. This along with the lack of driver maturity will continue to present problems in the near future with benchmark selections. Our normal process was to change our power settings to performance, delete the contents of the prefetch folder, and then reboot after each benchmark run. This is a lengthy process to be sure, but it results in consistency over the course of benchmark testing. All applications were run with administer privileges.
The test results we will present today are preliminary. What do we mean by this? Although the boards we are reviewing are full retail kits, their BIOS tuning continues at a rapid pace before the "official" launch on June 4th. Over the course of the last week we have tested numerous BIOS releases from each manufacturer and we've seen positive steps along the way. We honestly thought this preview would be a cake walk for ASUS until Gigabyte/MSI provided their latest BIOS releases that improved the performance of the boards up to 9% in certain areas.
We are also using early DDR3-1066 samples with memory settings at 8-7-7-16 for 1066 scores and 9-9-9-24 for DDR3-1333 results. We just received lower latency DDR3-1333 modules and will update our results in the roundup. On a side note, ASUS provided us a new BIOS for their P5K3 board that enables 1T command rates at DDR3-1066. Early testing has shown performance improvements up to 4% in memory sensitive applications. ASUS is continuing to work on the command rate timings and hopes to have 1T settings ready when low latency DDR3-1333 hits the market shortly. Expect to see an exclusive on this memory and BIOS in the next few days.
Our Intel Intel D975XBX2KR will be at a slight disadvantage, but with memory speeds set to DDR2-800 we were able to run timings at 3-4-3-8 without issue. We did not include extensive overclocking results for the CPU or memory side as time did not permit us to run each processor series on each board for the full test suite. We received seven boards late last week and will have results on several of those along with full overclocking results before Computex starts. We will also compare P35 1333/1066 DDR2 against P965 1333/1066 at the same time. Our DFI Infinity P965 is the fastest P965 board in our labs and as such is a good match for comparison.
Memory Performance
 |
| Click to enlarge |
We switched to a 4GB memory configuration for this article and future motherboard tests. The P35 chipset proves to have the fastest memory performance and best latencies at stock speeds provided the BIOS is tuned properly. We still find the 975X to offer some of the fastest memory performance when overclocked provided you can change strap settings and have very good RAM.
We noticed an 11% difference in unbuffered memory speeds and a 7% difference in latencies on the ASUS P5K Deluxe board when comparing auto to manually adjusted BIOS settings using the same standard 4-4-4-10 memory timings. Our other boards are tuned to the best possible performance that still allows the board to complete our benchmark test suite. We did not compare DDR2-1333 to DDR3-1333 for the simple fact that we currently do not have any DDR2 memory capable of 1333 speeds in a stable manner. However, we do expect DDR2-1333 RAM later this summer.
Facebook
Twitter
RSS
58 Comments
View All Comments
drewintheav - Sunday, May 27, 2007 - link
When you tested the P5K Deluxe Wifi mainboard and OCZ Reaper 9200 ddr2 memory were you able to boot up with with both modules of the reaper memory installed or did you have to boot up with a different memory and then adjust the ddr2 voltage to 2.3?I can not boot with all settings on the Asus P5K Deluxe Wifi set to default. The motherboard starts up but the screen stays black and there is no beep or POST information displayed.
Were you able to boot up no problem? I was able to boot no problem at default settings on my Asus Commando with the same OCZ Reaper 9200. Do you think I need to replace my motherboard? I also have had the pc spontaneously restart twice now.
Thanks in advance for any info or suggestions that you can provide.
Stele - Tuesday, May 22, 2007 - link
Most sites seem to list Asus's high-end boards as having 8-phase power, as per the spec sheet provided by Asus. However, I've a funny feeling that it might not be so, despite the number of MOSFET "sets" and inductors. When I was working on P5B Deluxe boards, which also supposedly sports 8-phase power, I noticed that they used the Analog Devices ADP3198 synchronous buck controller. This controller supports up to 4 phases max, which suggests that the 8 apparent phases are actually arranged in two sets of 4-phase circuitry running in parallel. If this is true, it's an unfortunate bit of misleading marketing, though it was probably due to the pressure in keeping up with gimmicky competitors touting quantity (6-phase, 12-phase, xx-phase) over quality (component/circuitry design/implementation).The presence of a 'voltage damper' setting in BIOS for the P5Ks seem to hint at the possibility of something new, however: either the presence a new PWM controller or some additional droop compensation circuitry. I'm guessing it's still an ADP3198, and hence the latter scenario. Would it be possible to find out what controller's being used on the P5K, pretty please? :P
IMHO, while the Analog PWM controllers have generally been stellar performers in their own right, they ought to start improving their products so that manufacturers would have to worry less about breaking relationships with them and jump ship - especially with, for example, Intersil having excellent analog (up to 6 phases) and digital PWM controllers.
Stele - Wednesday, May 23, 2007 - link
Now that I recall, Gigabyte too is in the habit of being rather liberal with how they count phases... in fact they're arguably one of the first to do so, along with their DPS gimmick in the 875 days. The DQ6 is listed and marketed has having 12 phases, but if I remember correctly, Gigabyte uses an Intersil ISL6327 for their 12-phase products (at least the GA-965P-DQ6 did so). This is a 6-phase controller, which means that, as in the case of the Asus designs mentioned above, the "12-phase" power claimed by Gigabyte is little more than two sets of 6 phases in parallel. Is this still the case in the P35-DQ6?If so, it'd be good to point out the reality under misleading hype, so that if nothing else, readers and potential buyers are better informed - and to underscore the fact that there are hardware sites who do know their stuff and who don't simply swallow and parrot whatever the manufacturers throw at them.
Just my 2 cents'!
shabby - Monday, May 21, 2007 - link
The loop-de-loop kicks ass on the msi board :DTA152H - Monday, May 21, 2007 - link
I agree, I don't know why, but I need it!Gary Key - Tuesday, May 22, 2007 - link
It actually works also, a lot less aluminum than the Gigabyte and ASUS solutions, yet the MCH/PWM area seemed to be within 1C of the other boards in our early testing with the Quad. Still not a big fan of the "designs" coming out but to each his own. I think the new abit P35 board as the best looking heatpipe system but then I like it old school... :)TA152H - Wednesday, May 23, 2007 - link
I don't like you any more. I'm just not sure I can relate to someone that didn't like that rollercoaster :P .I expect it probably should work pretty well. With windmills, one of the biggest considerations for the power it produces is how tall the tower is; the further from the Earth, the more wind energy it will get. So, by extension, by creating this roller coast they elevate it to a higher point, and of course by convection the hottest air will hit that spot. So, it should work out pretty well (by now you're probably scratching your head thinking "what is this idiot talking about". It's because I have no clue, but I want it, and I'm making stuff up to validate the decision like this windmill nonsense).
Old school heat pipe systems? Hmmmm, I don't remember even seeing a heatsink on anything earlier than a 486 processor, so I just think we can categorize your heatsink taste, at best as prosaic, and maybe even boring! I think this roller coaster only portends of things to come, I expect bigger ones soon, as well a hot dog stand. Motherboards seem to have become amusement parks, we have carousels (spinning fans), water equipment, towers, and now a roller coaster. Good grief.
yyrkoon - Thursday, May 24, 2007 - link
Oh, and . . . .http://www2.abit.com.tw/page/en/motherboard/mother...">http://www2.abit.com.tw/page/en/motherb...pMODEL_N...
yyrkoon - Thursday, May 24, 2007 - link
I agree with Gary, these 'windmill' and butt ugly other heatpipes from other OEMs can not touch ABITs OTES in looks. I guess that is what hapens when you pioneer a technology, and everyone copies . . .Stele - Monday, May 21, 2007 - link
While the addition of 2 more USB 2.0 ports is certainly one of ICH9's new features, doesn't ICH8 already offer 6 SATA ports? That was one of the latter's welcome improvements over the ICH7.
There also doesn't seem to be anything in the block diagrams that indicate the presence of an eSATA port. I'm guessing here, but could it be that the mention of a "port multiplier" led to some confusion? After all, the 6 SATA ports in ICH8 and 9 are actually controlled by two host controllers, with internal port multipliers that connect them to 4 and 2 ports respectively (that's why, for example, some board manufacturers label two of the SATA ports as 'secondary' and state that it is generally not advisable to connect the boot drive to them).
However, I'm guessing that the port multiplier issue came up in the context of ICH9 because apparently Intel would be using only command-based switching in ICH9's port multipliers, removing FIS (Frame Information Structure)-based switching apparently used in ICH8 (most port multipliers use both command-based and FIS-based). While FIS-based switching offers higher performance under multiple-drive loads than command-based switching, FIS-based switching is more complex and hence expensive to implement; besides that, it uses slightly more CPU resources to manage the increased command and data flow rate. As such, Intel might have chosen to use the simpler, cheaper command-based switching for ICH9. If this is true, it might be to keep costs down and because many hardware sites probably over-emphasised on CPU-utilisation when comparing SATA performance with other chipsets. Argh. Again, this was something that came up on the grapevine but I've not been able to find official sources that verify or deny this... perhaps Anandtech could shed some light?
In the event that it's true, exactly how much performance would suffer under multiple-drive read/write loads is unclear, and this is where an extensive non-RAID and RAID performance test with perhaps a full six drives (or even 3/4/5) might give some hint. On the other hand, it may be that performance would not differ much in scenarios short of an array larger than a two-drive RAID 0/1 (as demonstrated in this review), so Intel decided to dispense with what they may consider a needless luxury.