Intel's 925X & LGA-775: Are Prescott 3.6 and PCI Express Graphics any Faster?
by Anand Lal Shimpi on June 21, 2004 12:05 PM EST- Posted in
- CPUs
It's been such a long time since we've had as exciting a product as Intel's 925X platform arrive in our labs. The platform brings about a new CPU interface (LGA-775), a new graphics interface (PCI Express x16), a new memory interface (DDR2) and a slew of other tweaks that make for an impressive bundle of technology. Unfortunately for Intel, we are much more than just technologists - we are pragmatic technologists.
We have already shown how Intel's 925X and 915 platforms basically offer no performance increase over current generation 875P/865 platforms. The lack of performance improvement can essentially be attributed to the high latency of current DDR2 memory, combined with the lack of bandwidth utilization of DDR2-533. These two problems can and will be addressed in the future by lower latency DDR2 memory as well as Prescott's forthcoming 1066MHz FSB (which will be very well matched to a DDR2-533 memory bus). Once again, unfortunately for Intel, we are talking about present day performance and the situation isn't as perfect as it would be had we been given both of those things.
So, the launch of the 925X and 915 has come and gone, with very little excitement from the community in regards to platform performance - but are there any other diamonds in the rough to be discovered?
Alongside the LGA-775 socket interface, Intel gave Prescott a bit of a speed bump - taking it up to 3.6GHz, making it the highest clocked Intel processor available today. This article will be taking a look at the extra 200MHz and how it changes, if at all, the Prescott factor.
Then, we have this issue of PCI Express graphics; Intel has pretty much guaranteed a fast transition to PCI Express graphics cards by removing any AGP support from their 925X/915 chipsets. Intel is expecting that half of all Intel platforms will be 9xx based by the end of 2004, meaning that 50% of all of Intel's platforms shipped by the end of 2004 will not have AGP support. Like it or not, PCI Express as a graphics bus is here.
But what about performance? Both ATI and NVIDIA have been duking it out over the past several months about whose PCI Express solution is the best. And now, we're finally able to find out. Toning down the suspense a bit, you'll find that the whole PCI Express debate was really much ado about nothing, but we'll have some more explanation and benchmarks showing that in the coming pages.
With the above paragraphs, we've pretty much summed up what you can expect out of this article, but wait, there's more (cue TV salesman). This week, we will also take an in-depth look at one other feature offered by the platform and investigate the real world performance benefits of Native Command Queuing. NCQ is supported in the new ICH6 South Bridge and is claimed to improve performance significantly; we'll see what that means in the real world soon enough.
With that said and done, let's get to it.
Facebook
Twitter
RSS
39 Comments
View All Comments
Phiro - Monday, June 21, 2004 - link
Great article, good pics on the new socket.I'm glad to see PCI-E performance is within a % or two of AGP-8X, and that Nvidia & ATI are neck and neck, no big hit on either one.
I think it was clear to anyone who has been following the move to PCI-E that the onus wasn't on a performance increase on a single card - the move to PCI-E is an engineering one, not a siloed performance gain. The idea is we have a much more robust bus, we can have many cards with tons of bandwidth instead of one, and we add alot of versatility.
It's like the move from VLB to PCI - anyone remember that? PCI was a good, good standard. While graphics cards didn't make a huge jump in performance, you finally got away from those damn ISA slots.
Anyhow. I think PCI-E is a good standard, and I'm going to have it in my next system.
RyanVM - Monday, June 21, 2004 - link
Why weren't there more comparisons between equal processors on the different platforms, such as LGA775 P4E vs. S478 P4E (2.8, 3.2, etc)? It seems to me that those would better isolate the chipset.ZobarStyl - Monday, June 21, 2004 - link
I don't think AMD solutions with PCI-E will be any faster...the reason that the benches using the new chipset with DDRII were considered even ground is that the companion article on the new Intel chipsets showed there is at this point no difference between the two setups in terms of performance, only in price. This generation of PCI-E solutions based on AGP designed chips (from both camps) wasn't really built with PCI-E bandwidth in mind, so the gains on any system are likely neglible. Once chips (and games too, I would assume) can be built with the bandwidth of PCI-E in mind perhaps we will see a gain, right now let rich kids upgrade while you sit back on a much cheaper AGP solution that gives the same perf. =)CU - Monday, June 21, 2004 - link
I think ATI said they were buffers and not a bridge. I could be wrong though.elephantman - Monday, June 21, 2004 - link
I'd have to agree with justly on that last oneAlso..I believe nvidia had posted an xray of ati's pcie core which showed a bridge solution and not a fully native pcie solution as stated...maybe we'll get a response from ati on this soon
justly - Monday, June 21, 2004 - link
This quote from page two is pure rubbish."It used to be that the heatsink, not the socket's lever, was what provided the majority of force on the CPU itself to ensure proper contact with the socket."
The force exerted on the CPU by the heatsink is used to maximize heat transfer. If the heatsink force was to provide "contact with the socket" then there would be no need for a lever (at least on a ZIF socket). This would also mean that no one should worry that a CPU could burn up without a heatsink, as it would not have "contact with the socket" without the force of the heatsink pushing down on it.
mkruer - Monday, June 21, 2004 - link
To be fair I would use the P4E for rendering IF it wasn’t a power hog. But since I doen render anything movies, I guess not.mkruer - Monday, June 21, 2004 - link
Hum interesting PCI Express offers virtually no gain because of DDR-2 latencies? I wonder how much better PCI Express would be on an AMD 64 with DDR-1? You don’t have the DDR-2 latencies issues, plus because of HT, that’s Hyper Transport for you Intel people out there, I wonder if in the long run the AMD systems will perform better for the graphics card on average then any Intel chipset. Anyway this confirms my suspicion, “never buy any first generation product form either company” and in Intel’s case this time you might want to wait for the Merom, Conroe and Tukwila, chips because I think everyone should stick a fork in the P4 it’s done! (pun intended)phobs - Monday, June 21, 2004 - link
Interesting read,Bit of a error on page 22, you say "concluding our AGP vs. PCI Express performance investigation." and then go on to have 2 more pages of benchmarks...