Slashdot Mirror

Because the ageing pentium architecture was a mess, and they needed to redesign from scratch for the Core 2 architecture - which was a great improvement. They stopped using the pentium brand because they stopped selling chips with any pentium-based technology in.

What is the "Pentium architecture"? The microarchitecture of the original Pentium (P5) was different from the microarchitecture of the Pentium Pro/Pentium II/Pentium III (P6), and P6 was different from the microarchitecture of the Pentium 4 (NetBurst), and NetBurst was different from the microarchitecture of the Pentium M (which was, I think, P6-derived). The microarchitecture of the Core 2 (Core) was, I think, Pentium M-derived.

So there's Pentium-the-chip (P5), and there's Pentium-the-brand, which was first used with the P5 chip but was also used with chips with significantly different microarchitectures from the P5 chip.

The Pentium 350 apparently uses the Sandy Bridge microarchitecture, along with a bunch of other microprocessors, some named Core, some named Xeon, some named Celeron, and some named Pentium. Some of the ones named Pentium were launched in Q3 2011, before the Pentium 350, so "Intel Breathes New Life Into Pentium" is, to use the technical term, a "complete bullshit headline".

In February Intel bout McAfee for about $7.68 billion. So in a sense no, Intel's not next. It's Intel's turn now. Considering this, the Window 8 on ARM stuff and some other things Intel's got to be just about sick of Microsoft right now.

http://techresearch.intel.com/spaw2/uploads/files/FASTsort_CPUsGPUs_IntelMICarchitectures.pdf

Please look at the full white paper here.

While it looks like most of the instructions were one word instructions, it does seem to have a few two word instructions. So, to answer your questions, yes, in some cases, it could handle some 16-bit processing (though most instruction codes are 8-bit).

Intel's most advanced and expensive laptop processors, on sale currently and in the foreseeable near future, only support 8 GB of RAM.

Some are listed as supporting 16GB or 32GB. for example http://ark.intel.com/products/50067, http://ark.intel.com/products/52224

But yeah in general laptop users get shafted on ram because they generally only get two ram slots and even when their platform supports 8GB modules they are frightfully expensive but then IMO if you are trying to do heavy computation on laptops you are probably doing it wrong.

16 GB of RAM is an awful lot of it, by today's standards.

Currently 16GB is the max you can put in a mainstream (but not bottom of the barrel) desktop with reasonablly priced modules and afaict it's been that way for a couple of years now. Desktops based on the high end LGA1366 socket support 24GB of reasonably priced modules.

Once you go byeond 24GB you currently have to either buy frightfully expensive 8GB unregistered modules or buy a server platform that supports registered modules and/or more ram slots.

Intel's most advanced and expensive laptop processors, on sale currently and in the foreseeable near future, only support 8 GB of RAM.

Some are listed as supporting 16GB or 32GB. for example http://ark.intel.com/products/50067, http://ark.intel.com/products/52224

But yeah in general laptop users get shafted on ram because they generally only get two ram slots and even when their platform supports 8GB modules they are frightfully expensive but then IMO if you are trying to do heavy computation on laptops you are probably doing it wrong.

16 GB of RAM is an awful lot of it, by today's standards.

Currently 16GB is the max you can put in a mainstream (but not bottom of the barrel) desktop with reasonablly priced modules and afaict it's been that way for a couple of years now. Desktops based on the high end LGA1366 socket support 24GB of reasonably priced modules.

Once you go byeond 24GB you currently have to either buy frightfully expensive 8GB unregistered modules or buy a server platform that supports registered modules and/or more ram slots.

(16 GB is still the maximum amount of memory supported so I still think it's a big deal somehow ;) ).

Funny how you ignored 90% of the content of that post and latched onto the one thing that you thought you could potentially contradict me on.

You really want me to refute every portion of your post? Seriously? What sort of weird masochistic pedant are you?

The kind that hangs out at slashdot, obviously (like 90% of the other wierdos here [including you]).

But, even dumb TVs have chips!

Yes. So does my toaster, my thermostat, the remote for my car locks, and my flashlight. They do not have general-purpose CPUs, though, which is what Intel is in the business of selling.

You know that Linux runs on all of those devices too, no? And, I think Intel sells a fair bit more than GPCPUs. You're the one who interpreted 'embedded' as 'general-purpose CPU' and 'smart'; not myself. See: http://www.intel.com/p/en_US/embedded/hwsw/hardware

This story has never been about 'general purpose CPUs' and 'smart' TVs. That is precisely the error I pointed out initially.

TVs are merely display devices.

TVs are radio receivers that include a display device. Display devices which do not include a radio receiver are called "monitors." (The "tele" in "television" is not without specific, direct, and obvious meaning.)

Of course. Do you really think I don't know that? TVs are *now* merely display devices (sorry about the shorthand but I assumed that my reader would understand that I'm talking about 2010s and not 1950s). They are becoming more mere display devices with each passage of time. Who picks up radio signals (that they don't transmit to themselves via bluetooth or wifi) these days anyway?

In the laptop

That might work at your house. At mine, I use my laptop for work, and my family would not be appreciative of having their viewing habits be dependent on my work schedule. (I will not accept the notion that I'm the only man on Earth who uses a laptop computer as a computer instead of as an extension of the entertainment system...)

You've got that backwards. The display device is an extension of the computer (technically a peripheral) not vice versa. If you have too few display devices for your household, maybe you can take turns or buy more (or, gasp, do without).

Ultimately people want to use the TV as a display for their 'smart' devices.

If this is the case, then there's no point in having general-purpose CPUs in TVs, anyway. (Which I think was my general point, not yours. Glad you agree, though...)

Once again, you're the one who equated 'embedded' and 'smart' and 'general-purpose CPU'. Maybe you need to read TFS again? It says nothing of the latter two.

You have heard of sub-notebooks and tablets which run full-blown operating systems on, wait for it, special-purpose PUs (e.g., Atom, A4, ARM, etc), no? Or what about your smart phone? Do smart phones have CPUs just because they are referred to as 'smart'? Answer: no. They still run embedded chips.

This discussion is beyond ridiculous.

Ive been looking at the Xeon E3s, and Intel's knowledgebase seems to indicate they lack the hardware gpu features.

For instance, look at the E3 1270 (link). Under "Graphics specs", it says "no" to all of the graphics features, including "processor graphics".

Ive been looking at these closely for the last few weeks, and it seems you specifically need a separate gpu chipset on the motherboard to handle the graphics, as the CPU will not do it.

What? vPro exists only on non-K CPUs. Additionally, to use such "features" requires an optional driver installation.

What? vPro exists only on non-K CPUs. Additionally, to use such "features" requires an optional driver installation.

What? vPro exists only on non-K CPUs. Additionally, to use such "features" requires an optional driver installation.

Some PCIe wifi adapters contain integrated WiMAX support. Example: Intel 6250.

Reading around in the Meego Forum Thread on this topic, I found the following tidbits:

1-They are trying to dodge the MeeGo question, as asked directly in this IRC chat

2-Nokia have also noticed this, as seen by this tweet by a guy for for Qt/MeeGo at Nokia.

3-However, a Company called Novomok will provide Tizen with Qt, so...huh?

4- Also, Intel App up will be supported, and that's based on Qt apps, so yeah.

Just in case you've missed it, Intel has released a firmware update that should fix that problem.

Intel® SATA Solid-State Drive Firmware Update Tool

I was on pins and needles for them to fix it, since I've already been down the Seagate Barracuda 7200.11 Firmware SD15 path of firmware horror.
Didn't want to go there again.

Yes, but the author is just proving they don't know what Moore's Law is.

http://download.intel.com/research/silicon/moorespaper.pdf

Yes Moore's law is coming to and end. No, it doesn't have a damn thing to do with speed, yes it has everything to do with power of the chip.

A) You job in know way makes you an expert in this, so stop using it to imply you are.

B) Moor'es law is over.

Mores law ONLY applies to silicone chips. Double the number of components in the same area at the same cost. This isn't happening anymore. At least not in fabs that make consumer wafers.

I have 2.6G hz chip n my computer. It's 3 years old. That means I should be able to buy a 10.4GHz chip for the same amount of money right now. hmmm

It's getting very hard to get the metal content in fabs down below 1 part per billion.
The crack when being moved.
Electron microscopes are expensive to make, and make finer.

And eventual we will have gate problems du to quantum properties.

Will computer get more powerful? yes. Will Moore's law always be applicable? no.
BTW:
http://download.intel.com/research/silicon/moorespaper.pdf

Well, you're wrong.

ftp://download.intel.com/museum/Moores_Law/Articles-Press_Releases/Gordon_Moore_1965_Article.pdf

There's some discussion of what the trend means for prices, but the core observation is clearly about the density.

What you say may be true. I work for a startup that started in Santa Clara CA. This is their world headquarters. They have many manufacturing plants world wide. The bean counters decide where it is good to build plants based on the people and the economy. If California were so great, you would expect plenty of new plants to take advantage of the opportunity and resources there.

In reality there are NO new plants in California and resulting jobs for California. This does not mean they are not expanding and building new plants. They have been having record quarters lately with quarters over 20 Billion in revenue.

So where are the manufacturing plants that are recently built or are being built?
http://www.theinquirer.net/inquirer/news/1011245/intel-fab-israel
http://www.oregonlive.com/business/index.ssf/2010/10/intels_new_hillsboro_factory_w.html
http://newsroom.intel.com/community/intel_newsroom/blog/2011/02/18/intel-to-invest-more-than-5-billion-to-build-new-factory-in-arizona
http://semimd.com/blog/2011/09/13/intel-mum-about-capex-ireland-fab-plans/

The headquarters is here.
2200 Mission College Blvd, Santa Clara, CA 95054-1549

What have they recently built in California?
http://www.intel.com/content/www/us/en/company-overview/intel-museum.html

California has published their rated for doing business in California. Businesses shop for places that are business friendly.

California may have great opportunities, but for many the pasture is greener elsewhere.

This is only one example. There are many more.

What you say may be true. I work for a startup that started in Santa Clara CA. This is their world headquarters. They have many manufacturing plants world wide. The bean counters decide where it is good to build plants based on the people and the economy. If California were so great, you would expect plenty of new plants to take advantage of the opportunity and resources there.

In reality there are NO new plants in California and resulting jobs for California. This does not mean they are not expanding and building new plants. They have been having record quarters lately with quarters over 20 Billion in revenue.

So where are the manufacturing plants that are recently built or are being built?
http://www.theinquirer.net/inquirer/news/1011245/intel-fab-israel
http://www.oregonlive.com/business/index.ssf/2010/10/intels_new_hillsboro_factory_w.html
http://newsroom.intel.com/community/intel_newsroom/blog/2011/02/18/intel-to-invest-more-than-5-billion-to-build-new-factory-in-arizona
http://semimd.com/blog/2011/09/13/intel-mum-about-capex-ireland-fab-plans/

The headquarters is here.
2200 Mission College Blvd, Santa Clara, CA 95054-1549

What have they recently built in California?
http://www.intel.com/content/www/us/en/company-overview/intel-museum.html

California has published their rated for doing business in California. Businesses shop for places that are business friendly.

California may have great opportunities, but for many the pasture is greener elsewhere.

This is only one example. There are many more.

There are numerous ways to get superlinear speedup. Turns out that it is not that hard. There is more to parallel programming that just 'cores'. Of course, it depends on the algorithm.

eg
Matrix Multiply 101

"Your future will be ready in 20-50 years, same as last time, and before that, and before that."

True:
http://en.wikiquote.org/wiki/William_Gibson
"The future is already here -- it's just not very evenly distributed."

"Maybe if you spent less time reading SF, and more reading TFS, you'd realize that this has no connection to any of your ideas about optical communication and/or computation. "

Maybe. But, sadly, I don't read much sci-fi these days (no time). About the only sci-fi thing I read in the past few months, and coincidentally related to Intel:
http://techresearch.intel.com/newsdetail.aspx?Id=30
"The Last day of Work" by Douglas Rushkoff"

While the comments are right that for whatever reason I was not paying attention that the solar cell was not on the chip, none-the-less, what about low-power operation is not related to the idea of chips that can run on incidental light? Such projects may take multiple innovations to make happen, as is common with fundamental research. The point is that with such chips, you can build a massive system cheaply because you just drop the chips on a surface without much infrastructure (putting them into a sphere might require glue though).

In any case, documenting previous discussions can potentially serve to invalidate later patents (and I'm past the limits of my confidentiality non-disclosure agreement on that time).

Urgh - a quick google unearths nothing more than copy-pastes of this article

Anyone got something more interesting on the actual tech?

Well, a quick Google for "claremont site:intel.com" found this page, but I suspect somebody else has already discovered it and posted it here, or the site's running from that processor and somebody turned the light off, as it's responding rather slowly. From the Google summary, it's a "Near Threshold Voltage Processor".

Thanks to an AC down page:

http://software.intel.com/en-us/videos/cloud-based-ray-tracing-on-handheld-devices-at-researchintel-days-2011/

http://software.intel.com/en-us/videos/cloud-based-ray-tracing-on-handheld-devices-at-researchintel-days-2011/

It gets worse than mere poor performance. Couple NVidia chipsets with Silicon Image SATA and you get corruption.

I use chipset integrated controllers (Intel/AMD) exclusively for SATA and high quality discrete cards for SAS. Even Intel gets this stuff wrong, however. What I don't do is use third party SATA controllers, integrated or otherwise. They always suck. It's a given.

Wait for the standard you want to be integrated into the chipset or be disappointed. The chipset makers put a lot more R&D and validation into their work. That's just how it is.

I thought you'd always been able to buy 'tray' (aka OEM) variants (without the cooler), it's just that lately the tray has cost the same or even less than the retail (aka "boxed") package, so there haven't really been a point to it.

Everything you wrote is mathematically accurate, yet the actually interesting thing is exactly how big N has to get.

You know that this very question has been researched, right? I am amazed that you are intent to discuss this issue without having actually done any research in this matter.

You might want to start with this 2005 paper from Intel where they do some performance comparison for both hardware rasterization and software raytracing for various scene complexities.

That paper in particular illustrates how close we are. We are approaching the crossover point with the number of on-screen primitives right now. GPU's have done a lot to decrease the need for more primitives since then (hacks like parallax mapping and so forth,) but they are doing those things precisely because the demand for more scene detail is outpacing the ability to deliver higher primitive counts on GPU's. Piling on shaders (stream processors these days) only goes so far in delivering higher primitive counts, because their real choice is latency or bandwidth.. pick only one, even though you need both.

More data, white paper, video, source code, etc. located here: http://software.intel.com/en-us/articles/mlaa/

It's called "NVM Express", and they're working on it.

I was about to correct you regarding Intel's support for TRIM using RAID. But when I went to double-check, Intel corrected their previous statement.

Intel® Rapid Storage Technology 9.6 supports TRIM in AHCI and RAID modes for drives not part of a RAID volume. A correction was filed to update the information in the Help file, which stated TRIM was supported on RAID volumes.

Solution ID: CS-031491
Date Created: 24-Mar-2010
Last Modified: 05-May-2011

http://www.intel.com/support/chipsets/imsm/sb/CS-031491.htm

On the other hand searching for projects under the "cultural anthropology" research area leads to nowhere:

No data was returned.

I know nothing about the particular credentials of the person quoted; but Intel actually has its very own cultural anthropology research unit. Apparently, we are talking 100+ anthropologists and social scientists.

I have no idea if these are really high-powered types, or if they are basically the washouts of academia who don't want to admit that they have essentially moved into Intel's 'Theoretical Marketing' department; but Intel has way more of them than you'd expect from a chip company.

They're P-Series Core2Duos, so I'd say yes. All the Virtualization options including VT-D are enabled in the BIOS...

This is one of them: http://ark.intel.com/Product.aspx?id=35569

Should have everything needed?

They're both X-Series Thinkpads, which definitely don't disable the virtualization features, and Win7's XP Mode (which requires the virtualizaton features) works fine...

The SAS 6G and SATA 3 (6Gbps) models of SSD go up to over 500GB now. Reading that in a few minutes is no big deal. Even the SATA II Intel 320 series does 600GB and sequential reads at 270 MB/s, which would be 600GB in (600000/270 seconds) - 2222 seconds or just over 37 minutes. My laptop has a better data rate, but I use off-brand components :-). This is no problem at all.

You have to use Western Digital Caviar Black 3.5" SATA 500GB hard drive (WD5002AALX).

WTF is Thunderbolt?

http://www.intel.com/technology/io/thunderbolt/index.htm.

The SAS 6G and SATA 3 (6Gbps) models of SSD go up to over 500GB now. Reading that in a few minutes is no big deal. Even the SATA II Intel 320 series does 600GB and sequential reads at 270 MB/s, which would be 600GB in (600000/270 seconds) - 2222 seconds or just over 37 minutes. My laptop has a better data rate, but I use off-brand components :-). This is no problem at all.

A spinning rust platter isn't ever going to dish that, but if this is a job you need done and you're willing to spend ten grand, I'll take your money all day.

And let's not have the Base2 Vs Base10 argument, OK? A 2.4 percent difference isn't going to change the outcome of this one.

If you read TFA, you would have seen that the MHz may have been numerically higher but the performance was slower than the Phenom II Quad-Core. And yes, the Core i3 (Sandy Bridge version) has hardware virtualization assist. http://ark.intel.com/VTList.aspx #deniedfud

For a little balance, Intel's press release from last week:

"TOP500 Supercomputers
The 37th edition of the Top500 list, which was announced at ISC, shows that Intel continues to be a force in high-performance computing, with 387 systems or more than 77 percent, powered by Intel processors. Out of all new entries to the list in 2011, Intel powered systems accounted for close to 88 percent. More than half of these new additions are based on latest 32nm Intel Xeon 5600 series processors which now alone power more than 35% of all systems in TOP500 list, three times the amount comparing to last year."

http://newsroom.intel.com/community/intel_newsroom/blog/2011/06/20/intel-equipped-to-lead-industry-to-era-of-exascale-computing

Well Netburst has been pretty much replaced with Core, but the new 10-core Xeons run at 2.4GHz, so that's 24GHz of computer power on a single chip.

TFA probably uses this as source:

http://newsroom.intel.com/community/intel_newsroom/blog/2011/06/20/intel-equipped-to-lead-industry-to-era-of-exascale-computing

There are 50 cores in that Knight's Ferry. They could probably go to 80 by year's end.

Not all workloads translate to the specialised SIMD arrays that are modern GPUs. There is still a need for large arrays of more general-purpose computing, as well as a need for fast single core computers (not all jobs can be computed in parallel either).

I write visual effects software in C++ and in OpenCL. Where OpenCL is practical, GPUs can be 10x faster, but there are still many cases when it's too awkward or has too much overhead to use a GPU.

• Well, this one would make a good starting point, but it's only a start because it's incomplete. As usual.
• Another incomplete implementation but again it gives you a starting point.

Looks like those two are very good starting points, though, unless you've a Cray handy.

Here's my problem with AMD: I really really really want to support them by buying their products. However when I tried to upgrade my first AMD laptop, I found that their cust.care didn't want to help, their website is a shambles and i was left to do trial-and-error on eBay. Now I'm very happy with my Intel laptop. When the upgrade phase came, it went smoothly. Their website even has a helper page to find compatible CPUs for the chipset you currently have. How cool is that? As for ATI mobile gpu, I struggled to find a decent spec laptop that's got one, so I went with nVidia and apparently they have PhysX which ATI doesn't. Why make a pro-AMD person's life so hard, it is illogical.

"Intel does provide development drivers for Intel graphics to the open source community."

+1 :D

http://www.intel.com/support/graphics/sb/cs-010512.htm?wapkw=(linux)

Intel should not provide open source drivers because their graphics chips are absolutely horrible.

"Intel does provide development drivers for Intel graphics to the open source community."

+1 :D

http://www.intel.com/support/graphics/sb/cs-010512.htm?wapkw=(linux)

Care to visit the R & D facility of the world's largest chipmaker? If I twist the right arms I might even be able to get you a 6 core i7 990X Extreme to try out. If not I'm sure we can find a t shirt.
http://www.intel.com/products/processor/corei7ee/index.htm
http://www.intel.com/?en_US_01

Care to visit the R & D facility of the world's largest chipmaker? If I twist the right arms I might even be able to get you a 6 core i7 990X Extreme to try out. If not I'm sure we can find a t shirt.
http://www.intel.com/products/processor/corei7ee/index.htm
http://www.intel.com/?en_US_01

Thunderbolt IS LightPeak. The only difference is they moved the optical transceivers from the mobo to the cable itself. (smart move actually). Lightpeak never included fibre switching, just inexpensive transceivers. Moving to copper also solves the "you cant send power over fibre" problem. ...Developed by Intel (under the code name Light Peak)...

No, they're bidirectional.

See the intel brief (PDF).