Intel 32nm

[Jake_HT]

Sorry if this has been talked about before, but it's new news to me... I knew they were working on 32nm stuff, but here's some background anyways..

Going to be using LGA 1366, 32nm, 6 core (12 threads), DDR3 of course.. Claimed 22percent clock for clock vs. 45nm (not sure if that is counting i7?)

DailyTech - "Gulftown" is the Flagship of 32nm "Westmere" Line

PC Perspective - Intel 32nm Westmere CPU and Roadmap Updates

[bojangles]

All I know is that I'm putting all my money into the 32 nm process. My computer is still quite fast enough to play games on good settings and crunch movies and ZIP files in no time. By then there should be some better video cards as well. However, I am dreaming right now, because I'm looking for that perfect job...

[gingerbee]

just bought my 920 and can't wait for the upgrade fast chips too

[AkG]

Right now my OC'ed Intel q9450 is feeling fast enough...though I'm hankering for some SSD on Perc 5i goodness.
When the six core / 12 threads beasties hit, I may jump on the i7 bandwagon...till then Its All Good. :)

[matsta31]

the price for thoses will be really high I think. remeber the early days of the Q6600 ? I wonder if we will get to that level

[Jake_HT]

Originally Posted by matsta31

the price for thoses will be really high I think. remeber the early days of the Q6600 ? I wonder if we will get to that level

I'd like to see i7 pricing again.. base model that is about $350 which isn't bad for an enthusiast chip that overclocks well... But doubt it since it's a whole new architecture (32nm) so they won't be cheap! Wonder if they'll finally get out of the 2-3 GHz range for stock and jump into 3.6GHz + stock.. more cores isn't necessarily what we need since not that many applications take advantage of it! We need faster cores for the single threaded apps..

[encorp]

Originally Posted by Jake_HT

I'd like to see i7 pricing again.. base model that is about $350 which isn't bad for an enthusiast chip that overclocks well... But doubt it since it's a whole new architecture (32nm) so they won't be cheap! Wonder if they'll finally get out of the 2-3 GHz range for stock and jump into 3.6GHz + stock.. more cores isn't necessarily what we need since not that many applications take advantage of it! We need faster cores for the single threaded apps..

That's actually a bit off; I think we need more and more cores and software needs to start taking advantage of that. Audio and Film editing takes advantage of all the cores and it's amazing; we really need people to start multithreading their apps. We're already at the very edge of MHZ really on our current manufacturing processes and more cores is the most efficient way to increase "speed".

[bojangles]

Originally Posted by encorp

That's actually a bit off; I think we need more and more cores and software needs to start taking advantage of that. Audio and Film editing takes advantage of all the cores and it's amazing; we really need people to start multithreading their apps. We're already at the very edge of MHZ really on our current manufacturing processes and more cores is the most efficient way to increase "speed".

The problem is that coding for multiple cores is really hard. Parallelism is one of those things that can't be grasped because it hasn't been done since the late 80s.

[Mr.Blah]

Originally Posted by bojangles

The problem is that coding for multiple cores is really hard. Parallelism is one of those things that can't be grasped because it hasn't been done since the late 80s.

That and some apps just can't be made multithreaded efficiently, something to do with the shared memory I think.

[bojangles]

Originally Posted by Mr.Blah

That and some apps just can't be made multithreaded efficiently, something to do with the shared memory I think.

Kind of. That's what pipelining was for. It was a way to act like parallelism, but also behave like a linear process. It allowed instructions to fetch, execute and store while others were doing the same thing on a different clock cycle. It solved most of the shared memory problems and wait times to store data in a cache or the RAM. This is why GPUs have more processing power than CPUs these days.

The CPU still uses a very large cache array, while the GPU uses a very complicated pipeline architecture. However, CPUs are best for solving static instructions like math calculations and things that are already written in stone (C++ code, etc), which is why the cache plays a vital role when fetching data and instructions. I don't know how the cache is set up in today's chips, but what I know is that they do separate the L1, L2, and L3 cache in such a way that it allows higher priority to either data or instructions, depending on what the processor is designed for (I'm talking the construction of any CPU, not just a Pentium, Phenom, etc.).

The GPU are extremely valuable when it comes to dynamic instructions, etc. because it needs to calculate rapidly changing variables, like in video games. Because of its pipelining architecture, it can solve vector algebra much quicker than a CPU (solving an N x N matric by a CPU is an order of N^2), but parallelism can solve that much more quickly), which is why GPUs are becoming widely used in solving highly complex environments. It is also why we put multiple CPUs in a server. However, with today's technology, we can push a higher amount of numbers out with less GPUs, than an array of CPUs.

A computer is stupid. Seriously. It can only do one thing, but it can do it really well.

We just have to figure out where we can do it the fastest.