News
 

Bookmark and Share

(7) 

Modern graphics processors feature over a thousand of processing elements, or cores, and can use them all. Modern commercial microprocessors feature up to twelve cores, but Intel Corp.’s experimental single-chip cloud computer (SCC) features 48-cores. According to an Intel engineer, it is theoretically possible to create a CPU with a thousand of cores, the question is how to utilize those cores.

“I came up with that 1000 number by playing a Moore's Law doubling game. If the integration capacity doubles with each generation and a generation is nominally two years, then in four or five doublings from today's 48 cores, we are at 1000. So this is really a question of how long do we think our fabs can keep up with Moore's Law. If I've learned anything in my 17+ years at Intel, it's never bet against our fabs,” said Timothy Mattson, who is a principal engineer at Intel's Microprocessor Technology Laboratory, in an interview with ZDNet UK web-site.

Theoretically, Intel would be able to create a 1000-core SCC-like homogeneous multi-core central processing units (CPUs) in eight or ten years. The question is whether this is actually necessary: graphics processing units with over one and a half thousand of processing elements are available already, but they cannot run operating systems or efficiently solve truly complex problems, such those computed on modern servers. As a result, both AMD and Intel are working on multi-core heterogeneous microprocessors.“Speaking from a technical perspective, I can easily see us using 1000 cores. The issue, however, is really one of product strategy and market demands. As I said earlier, in the research world where I work, my job is to stay ahead of the curve so our product groups can take the best products to the market, optimised for usage models demanded by consumers,” added Mr. Mattson.

The prototype chip contains 24 tiles with two x86 cores per each, which results in 48 cores – the largest number ever placed on a single piece of silicon. Each core can run a separate OS and software stack and act like an individual compute node that communicates with other compute nodes over a packet-based network. Every core sports its own non-coherent L2 cache and each tile sports a special router logic that allows tiles to communicate with each other using a 24-router mesh network with 256GB/s bisection bandwidth. There is no hardware cache coherence support among cores in order to simplify the design, reduce power consumption and to encourage the exploration of datacenter distributed memory software models on-chip. Each tile (2 cores) can have its own frequency, and groupings of four tiles (8 cores) can each run at their own voltage. The processor sports four integrated DDR3 memory controllers, or one controller per twelve cores.

 

Back in the past Intel already introduced a research processor with 80-cores, but that chip, unlike SCC, even did not reach any researchers outside the company. The first research processor of Intel's Tera-Scale research project had performance of 1.6TFLOPS SP at 5GHz clock-speed.

Tags: Intel, SCC, x86

Discussion

Comments currently: 7
Discussion started: 12/28/10 02:11:58 PM
Latest comment: 12/30/10 05:04:38 PM
Expand all threads | Collapse all threads

[1-5]

1. 
Looks like Intel was beaten to the market on this one by Tilera who currently have processors for sale with 100x64bit CPUs each with L1 and L2 cache on a single chip each CPU is capable of running an operating system.
0 0 [Posted by: EDAguy  | Date: 12/28/10 02:11:58 PM]
Reply

2. 
Are you telling me that Intel managed to make a CPU with EIGHTY cores and still get it to run at a whopping 5.7GHz over 3 years ago and yet Intel tries to fob us off with crappy quad-core and hex-core running at a poxy 3.X GHz!

I would love to know what the TDP was of at chip.

How did they cool it?

If they managed 80 cores at 5.7GHz in 2007 what have they got now?
0 0 [Posted by: loadwick  | Date: 12/28/10 05:04:18 PM]
Reply
- collapse thread

 
Was just a prototype. Probably consume around 300-400W, and need nitro cooling. Probably....
0 0 [Posted by: TAViX  | Date: 12/29/10 03:37:38 AM]
Reply
 
Apparently it did 6.26GHz @ 191.79W

wikipedia:
By 2007, Intel Corporation unveiled the experimental multi-core POLARIS chip, which achieves 1 TFLOPS at 3.13 GHz. The 80-core chip can raise this result to 2 TFLOPS at 6.26 GHz, although the thermal dissipation at this frequency exceeds 190 watts.

cited url: The Arrival of TeraFLOP C...ing - 80 cores at 6.26GHz
0 0 [Posted by: jihadjoe  | Date: 12/29/10 06:55:51 AM]
Reply

3. 
yup, how will Intel manage to cool down the proc will be one of the main issue later on
0 0 [Posted by: awg1031  | Date: 12/28/10 08:22:23 PM]
Reply

4. 
If this will get the dumb ass programmers form the last 20 years to learn something more than just x86 .. this is fine by me.

But, unfortunately, in the last 2 decades, programmers showed us thousands of times that they don't know how to use multi-cores, GPUs and I'm not even talking about REAL architectural optimizations targeting a specific architecture.

I mean being able to recognize the CPU architecture and use some new advantaged introduced with that CPU. If they get their build to run 1% faster then their colleagues they brag about it to the whole cafeteria But learning to use the advantages offered by the CPU architecture and getting a 50% improvement is too much for their lazy stupid *sses. Don't you laugh! I have such an idiot standing next to me trying to sleep on the keyboard and smiling at me like a retard. Or maybe he's just gay

Today, they still rely on the compile to do the "optimizing". Sure ... my new performant build was obtained by pressing the "compile" button.

And we all know how good compilers are at sabotaging the competition and us .. the users.

In our days, they STILL check for GenuineINTEL
0 0 [Posted by: East17  | Date: 12/29/10 04:38:20 PM]
Reply

5. 
You know I just have to say this, But will it run Crysis 3 max settings?
Personally all this crap about dual,quad,hex is marketing rubbish to the average joe gamer, Bring back the Ghz wars more speed not more cores thats what we need still after all these years, My dual 480GTx cards in SLI are still holding back waiting for the freaking cpu to feed them some numbers to crunch!
Only way around it is to overclock the cpu to a faster ghz sigh....
0 0 [Posted by: ozegamer  | Date: 12/30/10 05:04:38 PM]
Reply

[1-5]

Add your Comment




Related news

Latest News

Wednesday, August 27, 2014

9:09 pm | Samsung Begins to Produce 2.13GHz 64GB DDR4 Memory Modules. Samsung Uses TSV DRAMs for 64GB DDR4 RDIMMs

Tuesday, August 26, 2014

6:41 pm | AMD Quietly Reveals Third Iteration of GCN Architecture with Tonga GPU. AMD Unleashes Radeon R9 285 Graphics Cards, Tonga GPU, GCN 1.2 Architecture

Monday, August 25, 2014

6:05 pm | Chinese Inspur to Sell Mission-Critical Servers with AMD Software, Power 8 Processors. IBM to Enter Chinese Big Data Market with the Help from Inspur

Sunday, August 24, 2014

6:12 pm | Former X-Bit Labs Editor Aims to Wed Tabletop Games with Mobile Platforms. Game Master Wants to Become a New World of Warcraft

Thursday, August 21, 2014

10:59 pm | Khronos Group to Follow DirectX 12 with Cross-Platform Low-Level API. Khronos Unveils Next-Generation OpenGL Initiative

10:33 pm | Avexir Readies 3.40GHz DDR4 Memory Modules. DDR4 Could Hit 3.40GHz This Year

12:10 pm | AMD to Lower Prices of A-Series APUs for Back-to-School Season. New Prices of AMD A-Series APUs Revealed