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?

Index Yonah vs. Dothan
Comments Locked

135 Comments

View All Comments

  • Missing Ghost - Wednesday, November 30, 2005 - link

    Why no EM64T???
    They should add this, or I'll buy Turions.
  • fitten - Thursday, December 1, 2005 - link

    Do you really *use* 64-bit software today? or just run it to say you run it? or just dream of running 64-bit software? I think Intel is pretty much right-on with what they said about 64-bit in the mobile market. I don't know of anyone who would really do anything with 64-bit right now other than just "have it". I have it at home because I write software that I test on both 32-bit and 64-bit platforms. Other than that, I have no use for 64-bit software yet. I don't run massive databases, I don't run massive CFS/CFD simulation codes. I don't run GIS software where I worry about having the entire world in memory mapped to the nearest centimeter. 32-bit is still fine. I'd like to have a 64-bit laptop myself, but that's so I could develop/test the software I write and not for much other reason.

    Also, 64-bit is more transistors which means more power draw.
  • tfranzese - Thursday, December 1, 2005 - link

    Business users I've seen tend to hold on to laptops for quite some time, and when they are done with them they sometimes end up in another groups hands where they can use it for hosting/serving small applications, and not limited to legacy software/OSs.

    I think it's a big misstep to not engineer 64-bit extensions into Yonah. As I mentioned earlier, almost every processor being sold today is a 64-bit desktop or server CPU. With that kind of penetration, it's only a matter of time (which is fast approaching) when 64-bit Windows development will pick up speed. Vista is getting very close (~1 year) and this chip isn't even released yet.
  • Shintai - Thursday, December 1, 2005 - link

    Business also dont tend to upgrade early. The larger the slower basicly.

    So a 32bit desktop and laptop will be fine the next 5 years or more. Alot still uses windows 2000 and havent even moved to XP and 2003 server.

    Just because the ubergeek can get Vista before xmas 2006 doesn´t mean any business will implement it.
  • stateofbeasley - Thursday, December 1, 2005 - link

    Again, the problem is the assumption that Vista is x64 only - that is wrong. Vista has concurrent x86 and x64 builds. The assumption is that Microsoft will make all software x64 once Vista is out - that is also a foolish assumption to make, given that MS has said nothing about moving office to x64 only.

    Businesses are also going to be very slow to adopt 64-bit OSes for clients. Where I work we upgraded to Windows XP last month. Our IS department isn't planning to roll out Vista any sooner than 2008 - they want at least one service pack (preferably two) and a few months to validate.

    People at AnandTech tend to view these things from the enthusiast standpoint, which is far different than the business standpoint. What makes sense from the enthusiast standpoint is often idiocy from the perspective of a department responsible for maintaining a corporate infrustructure comprising hundreds or thousands of machines.
  • BrownTown - Thursday, December 1, 2005 - link

    32 or 64 bits is just marketing stuff. What matters is performance, if a 32bit processor can put out the same performance as a 64bit one then its just as good in my book. Also, people arent gonna go buy Vista as soon as it comes out, it mostly be sold only in new computers. And by the time it comes out Intel should have Mermon ready which does have the 64bit extensions. Im sure Intel considered this and figured that the added transisters were to much to account for the benefit.
  • Scarceas - Wednesday, November 30, 2005 - link

    I think the mobile market could REALLY benefit from two different cores...

    A low-power core for most of the time, that will extend battery life while providing enough performance for web browsing and word processing... and a higher performing core for when the performance is needed.

    Pipe dream?
  • Furen - Thursday, December 1, 2005 - link

    Two different cores on the same package? That's what speedstep is for. If you dont need the power you run at low clock speeds and clock up when you do. This way you dont duplicate logic.
  • miketheidiot - Wednesday, November 30, 2005 - link

    i thinks its interesting that pepole are freaking out here because a top end intel dual core managed to come close to AMD's bottom of the line dual core chip. I think that says alot about intel now days.
  • Hikari - Wednesday, November 30, 2005 - link

    Ahh, yes, a dual core mobile cpu using less power comes out close in speed (faster, the same, and sometimes slower, depending on the test) to a low-end desktop dual-core. ;)

Log in

Don't have an account? Sign up now