LinuxQuestions.org

LinuxQuestions.org (/questions/)
-   Linux - Hardware (http://www.linuxquestions.org/questions/linux-hardware-18/)
-   -   The mysterious Intel Pentium T2060 processors (http://www.linuxquestions.org/questions/linux-hardware-18/the-mysterious-intel-pentium-t2060-processors-697349/)

alan_ri 01-14-2009 05:57 PM

The mysterious Intel Pentium T2060 processors
 
I'm currently having these processors in my laptop.If you search the web,like I did,you can find something like;
Quote:

What's strange is that the T2060 has only one mention on the whole of intel's website and that's hidden within some .pdf. If you were to their support today and ask about the T2060, they'd have no clue.
Quote:

According to the model number it should be a core duo. It looks like it just like the T2050 but with VT enabled and only 1mb of cache. They probably just call it a pentium to make it sell better because pentiums are now low end and since there's no c2d celeron yet they need more low end moible cpus
Quote:

There just isn't enough reliable information yet to give any kind of definative answer.
Quote:

First off a T2060 is a Core Duo and not a Core 2 Duo!.
Quote:

Ok, but we're agreed that is emphatically not a Pentium of any kind, right?
Quote:

Even if it is based on Core Duo architecture, it would still be nice to know if they disabled half the instruction set and made it run at full wattage all the time on battery.
Quote:

Official specs of the T2060 still seems to be shrouded in mystery. While some sites state the processor to only have 1MB cache, others claim it to have 2MB
So,since I have this laptop only for a short time now,I was wondering if anybody having this processors for some longer time could tell me a little bit more about them,because I'm having some problems just to determine what it can do and what actually it is.

DragonSlayer48DX 01-15-2009 05:15 AM

Hi, Alan~

Here's a chart from Intel showing the features and capabilities of their line of Pentium dual-core processors. The T2060 is also listed there.

And from this site:

Quote:

The Intel Pentium Dual Core T2060 is a new and unannounced Intel chip that has been mysteriously showing up in budget notebooks offered by mainstream resellers such as Best Buy and Circuit City. The T2060 is not on Intel's roadmap; similarly, neither were the budget Core Duos (T2050, T2250) and Core 2 Duo (T5200).
Hope this helps.

farslayer 01-15-2009 10:04 AM

install lshw and then try this..

lshw -C processor

Then use this chart to view the capabilities of your CPU by determining what the flags mean...
http://74.125.95.132/search?q=cache:...lnk&cd=1&gl=us



(alternatives to lshw)
dmidecode -t processor
cat /proc/cpuinfo

alan_ri 01-15-2009 10:45 AM

The output;
Code:

[alan@Alnilam ~]$ su -
Password:
[root@Alnilam ~]# lshw -C processor
  *-cpu:0               
      description: CPU
      product: Genuine Intel(R) CPU          T2060  @ 1.60GHz
      vendor: Intel Corp.
      physical id: 4
      bus info: cpu@0
      version: 6.14.12
      serial: 0000-06EC-0000-0000-0000-0000
      slot: U2E1
      size: 800MHz
      capacity: 2048MHz
      width: 32 bits
      capabilities: boot fpu fpu_exception wp
      vme de pse tsc msr pae mce cx8
      apic mtrr pge mca cmov pat
      clflush dts acpi mmx fxsr sse
      sse2 ss ht tm pbe constant_tsc
      arch_perfmon bts pni
      monitor est tm2 xtpr cpufreq
      configuration: id=0
    *-logicalcpu:0
          description: Logical CPU
          physical id: 0.1
          width: 32 bits
          capabilities: logical
    *-logicalcpu:1
          description: Logical CPU
          physical id: 0.2
          width: 32 bits
          capabilities: logical
  *-cpu:1
      physical id: 1
      bus info: cpu@1
      version: 6.14.12
      serial: 0000-06EC-0000-0000-0000-0000
      size: 800MHz
      capacity: 800MHz
      capabilities: ht cpufreq
      configuration: id=0
    *-logicalcpu:0
          description: Logical CPU
          physical id: 0.1
          capabilities: logical
    *-logicalcpu:1
          description: Logical CPU
          physical id: 0.2
          capabilities: logical
[root@Alnilam ~]#

The red line is interesting,isn't it?But it's in MHz,so what does that mean?
Also,I've set -march=pentium4 and -mcpu=pentium4 and the speed and performance is really better,so it is a Pentium then.
Just found something on the www;
Quote:

Multimedia applications require operating systems that support time-constrained
data types such as digital audio and video.
These continuous media demand timely service from the system,
and time-sharing scheduling algorithms are not sufficient.
Furthermore, simple fixed priority scheduling, used in many hard real-time systems,
does not necessarily guarantee the successful execution of arbitrary
collections of programs which may have conflicting timing requirements
or which may overload the system.
We have designed and implemented a processor capacity reservation mechanism
to allow programs to reserve the capacity they need to run.
Enforcement of reservations provides a scheduling firewall to protect programs
from competition for the processor; this is similar to the
firewall provided by memory protection, which isolates programs from
outside interference in their address spaces.
Using reservation, a system can control processor capacity allocation
in the same way that it controls discrete resources like memory
or storage space, and this prevents over-committing the processor.
Our reservation mechanism depends on a scheduling framework where
each reservation is expressed as a rate of progress
(defined as computation time per period of real time).
A rate can be associated with non-periodic programs as well as periodic programs.
An admission control policy, based on rate monotonic scheduling theory
moderates access to processor resources.
So,is there something
in the Linux kernel,a technique or something that will allow me
to control how much of a processor capacity will be used by a program?I'm not thinking about nice.

archtoad6 01-17-2009 05:26 AM

This thread is unreadable in KDE/Konqueror 3.5.8
because of horizontal scrolling caused by wide "Code:" blocks.

I don't know if the bug is in Konqueror, LQ, or vBulletin;
it doesn't matter -- I can't read & respond intelligently.

If you can see your way to editing the triggering "Code:" blocks,
I'd love to participate.

alan_ri 01-17-2009 08:35 AM

arcthoad6,I did what I can,hope you can see the thread now,but I think that no matter how wide horizontal srolling is that you should be able to see the post in your web browser.I'm not sure,I use Gnome and it was a long time ago when I've used Konqueror but I think it's got something to do with it,not vBulletin or something else.

packeteer 01-18-2009 05:30 PM

Quote:

Originally Posted by alan_ri (Post 3409931)
Also,I've set -march=pentium4 and -mcpu=pentium4 and the speed and performance is really better,so it is a Pentium then.
Just found something on the www;

This ^^ does not mean it is a Pentium class chip. It just means the optimisations better suit your CPU.

alan_ri 01-18-2009 06:00 PM

Quote:

Originally Posted by packeteer (Post 3413182)
This ^^ does not mean it is a Pentium class chip. It just means the optimisations better suit your CPU.

And how could that be?

archtoad6 01-20-2009 06:29 AM

Quote:

Originally Posted by alan_ri (Post 3411948)
arcthoad6,I did what I can,hope you can see the thread now,

Thank you, I can read it all now. (And it's useful & interesting.)

Quote:

Originally Posted by alan_ri (Post 3411948)
but I think that no matter how wide horizontal srolling is that you should be able to see the post in your web browser.

You're right, I should be able to...

Quote:

Originally Posted by alan_ri (Post 3411948)
I'm not sure,I use Gnome and it was a long time ago when I've used Konqueror but I think it's got something to do with it,not vBulletin or something else.

It's definitely a Konqueror problem -- Opera gives no trouble -- but it's also probably a vBulletin problem because the same thing happens at MepisLovers.org, which is powered by vBulletin also.

BTW, where did those quotations in your OP come from?


farslayer's post #3 was very useful & very interesting because of the differences in format & content of the output from the 3 utilities mentioned. "One" could write a short article comparing them.

salasi 01-20-2009 07:00 AM

Quote:

Originally Posted by alan_ri (Post 3408880)
Quote:Ok, but we're agreed that is emphatically not a Pentium of any kind, right?

Something is a Pentium if the owner of that name (Pentium: Intel) decide to call it a Pentium. Part of the trouble here is that what Intel used to call a Pentium is not what they currently call a Pentium.

A few years ago, Pentium was Intel's top of the range 'brand'; Pentium Ds were hot (lots of dissipation), highly clocked, long pipeline parts. When Intel introduced the 'Core' parts, it decided that it had already damaged the Pentium brand and needed a new name, hence the new parts were called something other than Pentium. But then it needed a lower perf/lower price/lower power part, it decided to re-introduce the Pentium brand (in addition to the Celeron brand, which had always been a lower end brand).

Now this Pentium was a 'core' part with a lower level of cache and at the slow end of the clock scale, but it had little architectural relationship to the earlier Pentium parts, but a very close relationship to the Core parts but with a few economies (for most people, the cache/clock speed were the biggie, but the VT might be a biggie for you, and I have difficulty in thinking that some of these reductions weren't so much to save Intel money in the production process but an effort to cripple the lower end models to stop them from cannabalising the market for Intel's more profitable versions...marketing, in the worst sense, in other words).

alan_ri 01-20-2009 08:57 AM

salasi,what you wrote is really interesting,it made me go and look a little bit deeper,so I found this;
Quote:

The first processors using the brand appeared in notebook computers in early 2007. Those processors, named Pentium T2060, T2080, and T2130[2], had the 32-bit Pentium M-derived Yonah core, and closely resembled the Core Duo T2050 processor with the exception of having 1 MB L2 cache instead of 2 MB. All three of them had a 533 MHz FSB connecting CPU with memory. "Intel developed the Pentium Dual-Core at the request of laptop manufacturers."
The source is wikipedia,so do you think that Intel made this at the request of laptop manufactures?

And one more;
Quote:

n 2006, Intel announced a plan[1] to return the Pentium brand from retirement to the market, as a moniker of low-cost Core architecture processors based on single-core Conroe-L, but with 1 MB cache. The numbers for those planned Pentiums were similar to the numbers of the latter Pentium Dual-Core CPUs, but with the first digit "1", instead of "2", suggesting their single-core functionality. Apparently, a single-core Conroe-L with 1 MB cache was not strong enough to distinguish the planned Pentiums from other planned Celerons, so it was replaced by dual-core CPUs, bringing the "Dual-Core" add-on to the "Pentium" moniker.
I would say that this is actually what you've said salasi.

The most interesting for me is this;
Quote:

Although using the Pentium name, the Pentium Dual Core is based on the Core technology, which can clearly be seen when comparing the specification to the Pentium D series. For example, the Pentium Dual Core has a maximum of 2MB of L2 Cache while the Pentium D processors can have up to 4MB of L2 Cache. But the major difference is the Pentium Dual Core processors only consume 65W peak while the Pentium D consumes a considerable 130W peak consumption which shows its relation to the Core power-saving technology. Despite having a smaller L2 cache, the Pentium dual-core has proven to be much faster than the Pentium D under a variety of CPU-intensive applications.
So I guess this mean that these processors are some sort of a mix between Pentium and Core.

archtoad6,
I can't remember at the moment were I've found all those qoutes,but typing something like T2060 in google could give you some results.Actually that's what I did right now and I've found this.Some qoutes are from there.
Now when I'm thinking about Konqueror,a long time ago when I've used it I had some problems viewing threads in it here on the LQ and that was because long horizontal scrolling lines.Maybe it's vBulletin.
I guess Konqueror don't like it,or is the other way? :) No problem with any other browser though.

salasi 01-21-2009 08:07 AM

Quote:

Originally Posted by alan_ri (Post 3415034)

The source is wikipedia,so do you think that Intel made this at the request of laptop manufactures?



Well, not really. I think Intel's primary consideration was not letting AMD run away with the low-end market. Remember not all of the 'new Pentium' products were laptop CPUs.

It probably cost Intel virtually zero (in comparison) NRE to make these parts available as all that they had to was disable bits of an existing chip/re-run the tape-out program with different parameters, and run test more slowly, so the only real consideration for them is at what price point these chips should sell.

Quote:

The most interesting for me is this;
Quote:Although using the Pentium name, the Pentium Dual Core is based on the Core technology, which can clearly be seen when comparing the specification to the Pentium D series. For example, the Pentium Dual Core has a maximum of 2MB of L2 Cache while the Pentium D processors can have up to 4MB of L2 Cache. But the major difference is the Pentium Dual Core processors only consume 65W peak while the Pentium D consumes a considerable 130W peak consumption which shows its relation to the Core power-saving technology. Despite having a smaller L2 cache, the Pentium dual-core has proven to be much faster than the Pentium D under a variety of CPU-intensive applications.

So I guess this mean that these processors are some sort of a mix between Pentium and Core.
I'd still stick with the idea that these are cut down versions of the Core parts, rather than having anything directly to with the earlier Pentium parts.

Indirectly, you can see that from the cache; the earlier, long pipeline, parts were very sensitive to pipeline stalls; hence, the need for the large caches (large for the time, anyway) as without effective caching, pipeline stalls kill the throughput of long pipeline parts.

Of course, the usual way that these things go is that new parts are software compatible with all of the 'extensions' (SSE, etc) that previous parts supported and may have more of those features added. So, you would expect, from a high level programmer's view, that the newer parts could look like the older ones.


All times are GMT -5. The time now is 11:14 AM.