News
 

Bookmark and Share

(28) 

Intel Corp. may have another trump in its sleeves, which has never been discussed before. Apparently, the company has a feature called central processing unit (CPU) Core Multiplexing Technology, which is already supported by its mainboards. Unfortunately, nobody knows for sure what does it do, but some believe that it actually boosts performance of single-threaded applications on multi-core processors.

The most recent release notes for version 1304 BIOS update for Intel Desktop Board B975XBX mainboard state that “CPU Core Multiplexing Technology BIOS setup option” has been removed from main page”, which should be a confirmation that either the technology that has never been discussed before is in development, is available in certain not introduced chips or has been abandoned from certain processors without being enabled.

Neither Intel, nor press have never talked about the CPU Core Multiplexing Technology, however, visitors of forums at XtremeSystems.org web-site dedicated to overclocking and tweaking believes that the technology was intended to boost performance in single-threaded applications on multi-core processors.

“We will support the disabling of one core in BIOS in a future BIOS rev.,” said Daniel Snyder, a spokesman for Intel Corp., when asked about the background of the technology. This means that once one core is disabled, the whole 2MB or 4MB cache reservoir on microprocessors that have shared level-two (L2) cache will be usable by one processing engine, which should boost performance in applications that cannot take advantage of two executing cores.

It is highly-likely that the feature will only work on the upcoming Core 2 processors code-named Conroe, which have shared L2 cache between its cores. It is also likely that the capability will allow quad-core chips to act like two dual-core processors in situations when four processing engines cannot be used efficiently.

It is uncertain how the CPU Core Multiplexing Technology correlates with Intel Advanced Smart Cache tech that allows one of two processing cores to use the entire memory reservoir if necessary while the other is idle and whether the two features carry different names while performing the same operation.

Recently it was reported that Intel’s arch-rival Advanced Micro Devices may introduce a feature that would increase performance of single-threaded applications on multi-core microprocessors.

Discussion

Comments currently: 28
Discussion started: 06/27/06 11:36:57 AM
Latest comment: 08/25/06 02:26:20 PM
Expand all threads | Collapse all threads

[1-1]

1. 
It could disable 1 core and raises multiplier of the other core. This would mean the active core would have the full 4 MB of L2 cache plus higher clockspeed while not exceeding the thermals.
0 0 [Posted by:  | Date: 06/27/06 02:15:05 PM]
Reply
- collapse thread

 
Doesn't work that way.
Its very likely a software approach that makes multiple cores seem like one virtual one.

I suspect it could be calling a hardware virtualization function...Which could explain why AMD's "anti-Hyperthreading" only works on Socket AM2 dual-core CPUs. (since they have AMD Pacifica virtualization technology).

To the OS, it'll seem like one core, even though it could actually be 2, 4, etc physical cores.
(to make it work, you need a driver and BIOS support).

The idea is to try to improve single threaded application performance. (Because most programmers still think in this way). This approach is easier on the programmer (in some respects) as they can continue to think in terms of single-threaded. (If you're a game programmer, you know how hard it is to write and optimise for multi-core CPUs).

Anyway, I'm still curious of the performance this offers in real life.

Sure the idea sounds OK, but does it actually do what those Marketing people say it does? Or is this another bit of fluff?...We need proof in the form of benchmarks! :-)
0 0 [Posted by:  | Date: 06/28/06 04:50:13 AM]
Reply
 
AMD is using the software approach to actually use both cores to become one. It was called Anti-Hyperthreading or Reverse Hyperthreading...the official name of it, I'm not sure. Intel on the other hand wants to just disable 1 core...now what will they do with that one core is still a mystery. Could they up the speed? Maybe. But just going from 2mb to 4mb cache just doesn't seem like a well thoughtout plan.

From the technical stand point I'd give thumbs up to AMD. In real world non-benchmarking test has yet to be seen as to which tech is actually better.

My guess is AMD.
0 0 [Posted by:  | Date: 06/28/06 06:30:02 PM]
Reply

[1-1]

Add your Comment




Related news

Latest News

Thursday, August 28, 2014

12:22 pm | AMD Has No Plans to Reconsider Recommended Prices of Radeon R9 Graphics Cards. AMD Will Not Lower Recommended Prices of Radeon R9 Graphics Solutions

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