Pentium 4 3.46 Extreme Edition and 925XE: 1066MHz FSB Support is Here
by Anand Lal Shimpi on October 31, 2004 3:00 PM EST- Posted in
- CPUs
Does the 1066MHz FSB Improve Memory Performance?
Quite possibly the biggest feature of the 1066MHz FSB today is the fact that it runs at a clock multiple of DDR2-533's frequency. Why is that such a big feature? It's analogy time:
If two people are having a conversation and they can both talk and listen at the same rate, then the conversation will flow as smoothly as possible. If person A talks and listens slower than person B, then person B will always be waiting for person A instead of communicating as fast as possible - a frustrating situation for those that have been here before. Running a FSB and memory bus asynchronously is just as frustrating to the CPU; if the two frequencies aren't synchronous then there is an additional latency penalty incurred while transferring data between the two buses and because of that additional latency penalty, there is a reduction in usable bandwidth.
With the original 925X chipset we were a bit unhappy to see that the Pentium 4's 800MHz FSB was paired with DDR2-533, creating one of those frustrating asynchronous situations. But with a 1066MHz FSB (266MHz x 4), the 925XE can communicate synchronously with DDR2-533 (266MHz x 2), thus reducing memory latency and increasing memory bandwidth in theory. What do we see in practice? To answer this question we look to two trusted measures of memory bandwidth and latency: CacheMem and ScienceMark 2.0.
First looking at latency we see that with the 1066MHz FSB, memory latency with DDR2-533 looks like it's hardly improved. Running the FSB at 1066MHz manages to shave off a just a few clock cycles.
| DDR2-533 3-3-3-12 Latency Comparison - Cachemem | ||||
1066MHz
FSB
|
800MHz
FSB
|
Performance
Improvement
|
||
| 512-byte stride - 32MB block | 226
cycles
|
227
cycles
|
0.4%
|
|
| 1k stride - 32MB block | 239
cycles
|
241
cycles
|
0.8%
|
|
| 2k stride - 32MB block | 266
cycles
|
266
cycles
|
0%
|
|
| 4k stride - 32MB block | 311
cycles
|
311
cycles
|
0%
|
|
We look at ScienceMark and see the same basic situation but with slightly improved performance; looking at the absolute latency values in nanoseconds we see that the 1066MHz FSB manages to reduce memory latency by around 2 - 6%.
| DDR2-533 3-3-3-12 Latency Comparison - ScienceMark 2.0 | ||||
1066MHz
FSB
|
800MHz
FSB
|
Performance
Improvement
|
||
| 16-byte stride | 4.69 ns
|
5 ns
|
6.2%
|
|
| 64-byte stride | 17.5 ns
|
18.12 ns
|
3.4%
|
|
| 256-byte stride | 73.43 ns
|
75.93 ns
|
3.3%
|
|
| 512-byte stride | 75.93
ns
|
77.81
ns
|
2.4%
|
|
The reduction in latency isn't insignificant under ScienceMark, but what about its affects on memory bandwidth?
Looking at Cachemem once again we see an increase in memory bandwidth of just under 4%.
| DDR2-533 3-3-3-12 Bandwidth Comparison | ||||
1066MHz
FSB
|
800MHz
FSB
|
Performance
Improvement
|
||
| ScienceMark 2.0 | 4742.02 MB/s
|
4347.63 MB/s
|
9.1%
|
|
| CacheMem | 3455.3 MB/s
|
3324.7 MB/s
|
3.9%
|
|
ScienceMark appears more considerate of Intel's hard work and shows a 9% increase in memory bandwidth. The thing to keep in mind here is that the improvement in memory bandwidth will depend on the types of applications run, but the ScienceMark and Cachemem results should give you an indication of the range of improvements to be expected in applications that are memory bandwidth limited. In those applications that aren't currently bound by memory bandwidth, the impact will be much less.
What is important to keep in mind here is that DDR2 is still running at relatively high latencies. Even while running synchronously with the FSB, the 925XE and DDR2 combination still posts higher memory access latencies than 875/DDR400 platforms thanks to DDR2's high memory timings. We were able to run 3-3-3-12 timings on our DDR2 test platform by keeping memory voltage at a safe, but overclocked, 2.0V, but anything faster than that was too much for today's DDR2-533. It will take even lower latency DDR2 in order for even the 925XE platform to show some further performance advantages.
Given the relatively small increases in memory bandwidth and decreases in latency, the extra 66MHz of the 3.46EE will have to go a long way in order to gain any more ground for Intel. Let's see how things shape up in some real world tests.
Facebook
Twitter
RSS
63 Comments
View All Comments
GhandiInstinct - Sunday, October 31, 2004 - link
Come on Dell, cheaper, faster..give in to the grown up taste!!!I still can't fathom Dell being the top computer seller worldwide, are soccer moms buying at record highs?
Tides - Sunday, October 31, 2004 - link
i'd say ddr2 does suck when intel gets less performance with it vs an amd 939 with ddr1. what a waste of cash to have the intel branding.jimmy43 - Sunday, October 31, 2004 - link
Most people dont care whats in their computer. Intel is a brand name people trust, but if they can get a computer for less money which can do all they need, then they will. And guess what? Theyl be blown away, and theyl realize AMD slays Intel and theyl laugh at their friends who got an Intel. The reason Intel is able to hold on so well to the market is because of conservative companies like DELL and other such multi-billion dollar partnerships. I say once DELL gives in, its over for Intel. But seriosly they really need to pick it up...Zebo - Sunday, October 31, 2004 - link
Those gaming benchmarks are embarresing.A "budget" athlon 64 3400 with the "old" socket 754 single channel mem controller is putting a whoppin' on Intels top chip.Zebo - Sunday, October 31, 2004 - link
SLIMYou're forgetting DDR2 price which this needs in your so called Intel is "cheaper" comparison. If you want the same price setup you can get a FX-55 and really bring the wood.
AnonymouseUser - Sunday, October 31, 2004 - link
"why didn't anyone try to overclock this thing and see how far it'll go?"They didn't want to melt the motherboard?
knitecrow - Sunday, October 31, 2004 - link
why didn't anyone try to overclock this thing and see how far it'll go?Determinant - Sunday, October 31, 2004 - link
There is a graph missing in the "Business/General Use Performance" page.The graph for "Ahead Software Nero Express 6.0.0.3" is replaced by a duplicate of the preceding graph.
I was surprised to see the big difference when burning CDs/DVDs with different CPUs until I realized that it was the wrong graph.
I'm really interested to see how much of an impact faster CPUs make for burning CDs/DVDs because I didn't think that there would be a difference outside of the benchmark variance but since this was benchmarked it must have been noticable.
Thanks
MMORPGOD - Sunday, October 31, 2004 - link
None of you are aware of the situation Intel has over the world computing market. Yes evryone here on Anand forum is hardcore or enthusiast of computer tech and gaming for PC. But one thing none of you have a grasp on is that Intel has millions of people who do not define themselfs as ever being knowledgable to computing performance or benchmarks. Basicly all of intel is going to be on top no matter what, unless something big happens where the community who purchases these computer systems from the retail stores either sees whats going on beforehand or just wises up and reads about there current technology. Its something thats proven and works, Intel is leading the world in publications of its product more then AMD, thus they have a hand on being on the top. I am a diehard AMD fan, and there isnt to many of us out there who have been since AMD came out, but I can tell you, with all this media coverage on Intel over the past years, its engraved into evry consumers head that the next PC they get they will most likely purchase retail INtel equiped PC. AMD needs to market a little more because average people dont give a damn about benchmarks. Just my opinion about evryone who I see post above who says man Intel is toast or Intel is gone, those are benchmark comments and dont disolve the real world consumers thoughts on a PC with Intel name. How many people go into a Circuit City or Best Buy and see more AMD products then Intel? Intel leads advertisements and in store showcasing, so until someone actually gives the word to the public that AMD is better, Intel will always lead but not in performace. Cant wait for my FX-55Pythias - Sunday, October 31, 2004 - link
I really hope intel can get it back together, or we're gonna be looking at sky high processor pricing again. We need healthy competition.