Intel's Core i7 870 & i5 750, Lynnfield: Harder, Better, Faster Stronger
by Anand Lal Shimpi on September 8, 2009 12:00 AM EST- Posted in
- CPUs
Discovery: Two Channels Aren't Worse Than Three
Intel told me something interesting when I was out in LA earlier this summer: it takes at least 3 cores to fully saturate Lynnfield's dual-channel DDR3-1333 memory bus. That's three cores all working on memory bandwidth intensive threads at the same time. That's a pretty stiff requirement. In the vast, vast majority of situations Lynnfield's dual channel DDR3 memory controller won't hurt it.
Move up to 6 or 8 core designs and a third memory channel is necessary, and that's why we'll see those processors debut exclusively on LGA-1366 platforms. In fact, X58 motherboards will only need a BIOS update to work with the 6-core 32nm Gulftown processor next year. P55 looks like it'll be limited to four cores and below.
Because of this, Lynnfield's memory bandwidth and latency cores are actually quite similar to Bloomfield. I used Everest to look at memory bandwidth and latency between a Core i7 975 and Core i7 870 (Lynnfield):
Lynnfield's memory controller is good, easily as good as what's in Bloomfield if not slightly better.
Both processors turbo'd up to 3.46GHz, indicating that Everest's memory test uses no more than two threads. The 975 ran DDR3-1066 memory (the highest it officially supports), while the 870 used DDR3-1333. The faster memory gave the 870 the advantage. Since we're not taxing all four cores, Lynnfield is at no disadvantage from a bandwidth perspective. Surprisingly enough, even SiSoft Sandra (which does use four cores for its memory bandwidth test) shows Lynnfield's dual-channel DDR3-1333 memory controller as equal to Bloomfield's triple-channel DDR3-1066 interface.
| SiSoft Sandra 2009.SP4 | Intel Core i7 975 | Intel Core i7 870 |
| Aggregate Memory Bandwidth | 17.8 GB/s | 17.3 GB/s |
Long story short? Lynnfield won't be memory bandwidth limited with DDR3-1333 for the overwhelming majority of usage cases.
Facebook
Twitter
RSS
343 Comments
View All Comments
yacoub - Tuesday, September 8, 2009 - link
lol, what a stupid comment. yes it's "cheating" to benchmark the processor the way it comes out of the box, which also happens to be how it is used in the real world environment.Voo - Tuesday, September 8, 2009 - link
Well there are many users who don't bother with overclocking so the tests aren't "illegal" or anything.But I tend to agree that most users who would be interested in buying an i7 920 or i7 860 would overclock it, so turbo mode wouldn't help at all, as we see with the OC results.
I'm curious if PCI-e on die is the only problem and if we'll see new chips who benefit from turbo mode even when overclocked. After all the principle behind turbo mode doesn't change if you overclock, does it?
james jwb - Tuesday, September 8, 2009 - link
IF that's true, i'm not at all happy with this review. But i'll wait for someone else to confirm this for obvious reasons... anand, confirm!Voo - Tuesday, September 8, 2009 - link
You read the text, didn't you? It was mentioned several times..james jwb - Tuesday, September 8, 2009 - link
i don't have time to read through all of it right now, was just flicking through and immeditaly thought to ask the question. I will read it fully later on, though.Hence why i asked the question. You say "it", as in which way, benches had turbo, benches didn't?
snakeoil - Tuesday, September 8, 2009 - link
yes again, turbo was on for all the benchmarks which is illegal and biased.maxxcool - Tuesday, September 8, 2009 - link
yes, the federal government says making a feature that makes your product better is legal.JarredWalton - Tuesday, September 8, 2009 - link
Illegal and biased? Yes, Intel is illegally making their CPUs run better at all workloads for normal users that don't overclock. Someone should arrest them! What would be biased is to test these CPUs in a fashion that artificially limits performance. Sure, it would be nice to see performance compared with and without Turbo enabled, but generally there's not enough time to run every potentially interesting test scenario.snakeoil - Tuesday, September 8, 2009 - link
there you go, finally you said it.all the benchmarks have at least 600 mhz over the processor's stock speed.
that is outrageous, then if you want to compare the result with phenom 2 you have to overclock phenom 2 at least 600 mhz over stock speed.
just to be fair
Anand Lal Shimpi - Tuesday, September 8, 2009 - link
The processor's stock speed is variable according to the workload it's running, that's what turbo mode does. AMD will enable similar functionality in 2011. This is the out-of-box performance of Lynnfield. Turbo mode is a feature of the processor as it has been since the mobile Penryn days (and more recently Nehalem). There's no reason to disable it as no end user would, unless you want to make Intel look worse for some reason.We also ran Turbo on vs. off numbers in the review: http://anandtech.com/cpuchipsets/showdoc.aspx?i=36...">http://anandtech.com/cpuchipsets/showdoc.aspx?i=36...
Take care,
Anand