Intel Yonah Performance Preview - Part I: The Exclusive First Look at Yonah
by Anand Lal Shimpi on November 30, 2005 2:50 AM EST- Posted in
- CPUs
Same Size, but Twice the Cores
Obviously the biggest improvement Yonah offers over Dothan is the fact that it’s dual core. But where things get interesting is that thanks to Yonah’s 65nm process, a dual core Yonah die is about the same size as a single core Dothan die - in other words, it costs Intel just as much to make a dual core Yonah, as it did for them to make a single core Dothan.
A major reason the die size didn’t really go up much is because although Yonah has two cores, its L2 cache size remains unchanged at 2MB. Unlike the Pentium D, Yonah’s 2MB L2 cache is not split into two discrete 1MB caches, it is actually one whole 2MB cache that is shared by both cores. This is a very important distinction, as it means that Yonah is far from just two Dothans stuck together.
There are other architectural enhancements to Yonah that will give it a performance advantage over Dothan. Below is an excerpt from our IDF coverage of Yonah, detailing what we know about the new CPU:
Making Pentium M more "Media Friendly"
All of the major performance improvements to each of Yonah's cores seem to revolve around SIMD FP and FP performance, two of the Pentium M's present day weaknesses in comparison to the Pentium 4.
The first improvement is that now all three of Yonah's decoders can decode SSE instructions, regardless of the type of instruction. Improving the decode width of the processor is a quick way to improve performance.
Next, SSE/SSE2 operations (not sure if all can be, but at least some) can now be fused using the Micro Ops Fusion engine of Yonah. At a high level, the benefit here is increased performance and lower power consumption, we'll get into architectural details of why that is when we eventually sink our teeth into Yonah next year.
Each of the two cores in Yonah have also received support for SSE3 instructions much like the Pentium 4 E [Prescott].
And finally there have been some improvements to Yonah's floating point performance, although Mooly would not say exactly what's been done. Curiously, Mooly referred to the floating point performance improvements as specifically made to improve gaming performance. Intel may have grander plans for Yonah than once thought...
The SSE/FP optimizations are all being grouped into what Intel is calling their Digital Media Boost technology, yes the names seem to get worse and worse as time goes on - but at least the functionality should be good.
We started out this article talking about the Pentium M’s shortcomings in digital media applications, and Intel has begun to address them with the architecture of Yonah, but the real question is - how effective have their efforts been?
Facebook
Twitter
RSS
135 Comments
View All Comments
bhtooefr - Wednesday, November 30, 2005 - link
Also, isn't there a way to disable the second core in BIOS?I think it's definitely possible to make your dual-core chip into a single-core for testing.
Slaimus - Wednesday, November 30, 2005 - link
No, since it is a CPU with double execution units, rather than 2 CPUs linked together.fitten - Wednesday, November 30, 2005 - link
I've not seen that stated anywhere. What I've seen is that there are two cores, two independent L1 caches, and a shared L2 cache.Anemone - Wednesday, November 30, 2005 - link
The reason it was compared against the X2 is simply because that is where the next gen Turion "may" land in performance. Power consumption in this test is nice, but not really relevant to the new Turion, nor is it relevant to the mobile arena where AMD with integrated controller does well against P-M plus external controller consumption (well though Intel is better so far).I had a feeling things were going to turn out this way. That cache on the P-M is really what makes it such a nicely performing chip. Weakening that was really the telling test in all this. It's nice that you put that test first. The dual core Turion is going to be very close in release timing to Yonah, and quite a few samples of the chip are already out there, but I'd bet AMD is keeping its cards close, as it has less of a need to prove a point.
However, from a mobile perspective AMD's use of Via and ATI chipsets really will be the telling factor, and will impact the "you get it all" bundle of a notebook. Where, after over a year, is Nvidia and a pci-e mobile chipset for AMD? Turion is almost out the door and they haven't even spoken up yet. That's probably because they won't be there when Turion releases. If Nvidia had no chipset on the desktop, the competition would be starkly different right now, and a good many folks know this to be true. So I'm expecting the dual core Turion to do incredibly well. 64 bit isn't an end all be all, but it will be a wonderful perk when Vista comes, and Vista will be here sooner than previously expected. Power consumption "may" favor Yonah, however Intel is doing what they always do, when a chip performs so-so, they push up the clockspeed. When they find out what Turion has on the table, they'll put out the EE version of Yonah to try to match it. THAT I bet, won't be so power friendly.
Intel is improving on Yonah with Conroe. But remember that the low latency L2 is what gave the Dothan its ability to stand in the A64 arena. That got lowered and we see the results. Now imagine what will happen when they "gently" increase the pipeline of Conroe vs P-M/Yonah. It'll drop a bit again. Against that you'll have architecture improvements and higher clockspeed (Conroe is expected to clock higher). That might end up making Conroe only "slightly" better than Yonah. That is why the marketing of th two can overlap, probably.
So IF (and it's not promising) Nvidia gets the NF4 into a mobile format and gets builders to use it on the new Turion dual cores, we might see some interesting things from the AMD side. If not, they stay as now, a niche market only. ATI chipsets aren't going to change that, much as they have not done much to the desktop side of things.
IF Yonah clocks at 2.6ghz you may see some competitive desktop systems to A64 X2's. It will rule the mobile roost unless the above happens for AMD. Conroe had better make some dramatic improvements to even Yonah's ability, though I'm doubtful, or putting both Yonah and Conroe on the desktop will simply hand even more of the market to AMD. On the mobile front, again unless the above happens for AMD/Nvidia on a mobile chipset, you will watch Yonah/Conroe rule the mobile roost.
:)
Griswold - Wednesday, November 30, 2005 - link
Intel just now managed to close the gap between them and AMD as far as dual core is concerned. I dont care if one is a mobile part and the other is not, mobile computing is of no interest to me and even less dual core mobiles. But it gives a good idea of what to expect.The numbers are there. Yonah isnt groundbreaking besides the fact that it is a dual core - and the desktop versions probably wont be either. Wow, thats late...
nserra - Wednesday, November 30, 2005 - link
TG Daily: What is your reason for not including support for 64-bit technology in Yonah? Why is it going to be supported only in Meron?Perlmutter: Like everything in technology or life, it is all a matter of timing. Integrating unneeded features into a processor means a waste of power consumption. Our assumption was, and still is, that 64-bit extensions are not the most important thing required from a processor, not even in the beginning of 2006. We believe this will change with Windows Vista, when applications start migrating to 64-bit, and we want to be ready then, and not a minute earlier.
Furen - Wednesday, November 30, 2005 - link
64-bit extensions = more transistors, which means higher power consumption.Donegrim - Wednesday, November 30, 2005 - link
If this is cheaper than the X2 3800, and overclocks really well on the desktop (say, 2.7-3ghz or so), then I could see myself being tempted by it. As long as the 'secret' motherboard isn't as ridiculously overpriced as current dothan desktops.Griswold - Wednesday, November 30, 2005 - link
WHat makes you think that thing will go to 2.7-3ghz? *laff*Donegrim - Wednesday, November 30, 2005 - link
Well the x2 3800 that consumes much more power (therefore is hotter) consistently goes to at least 2.5ghz, so I don't think it's unrealistic for a lower power chip to go further. Plus the FSB is nice and low, which makes for a good start with the overclocking.