Slashdot Mirror

actually the intel nucs are produced by intel and with intel branding. http://www.intel.com/content/w...

and this is the email support for intel nucs http://www.intel.com/support/m...

if they do not provide the support they claim to be providing then it's false advertising and downright fraud. of course, if you're selling tech you get away with that just like that.

actually the intel nucs are produced by intel and with intel branding. http://www.intel.com/content/w...

and this is the email support for intel nucs http://www.intel.com/support/m...

if they do not provide the support they claim to be providing then it's false advertising and downright fraud. of course, if you're selling tech you get away with that just like that.

Yeah, but ISAs are all but over, and they are over in x86-land.

They're not "over" to compiler writers and assembler-language programmers.

IS != ISA, HTH HAND

It would only help if it were true. What are your definitions of "instruction set" and "instruction set architecture", and what citations can you give that would make those definitions worth taking seriously, as opposed to, for example, Intel's use of "instruction set" and Intel's use of "instruction set architecture"?

Yeah, but ISAs are all but over, and they are over in x86-land.

They're not "over" to compiler writers and assembler-language programmers.

IS != ISA, HTH HAND

It would only help if it were true. What are your definitions of "instruction set" and "instruction set architecture", and what citations can you give that would make those definitions worth taking seriously, as opposed to, for example, Intel's use of "instruction set" and Intel's use of "instruction set architecture"?

From the Intel website:

Previous versions of Intel Anti-Theft Technology enabled authorized IT or service personnel to send a coded "poison pill" over the Internet to completely disable a lost or stolen computer and help prevent access to its encrypted data and deter theft. New Intel AT 3.0 enables the poison pill to be sent as an encrypted, authenticated SMS message by an authorized administrator over a 3G cellular network as well within moments after a missing laptop is turned on. When recovered, the PC can be similarly re-activated with another message. Its new Locator Beacon capability gives authorities the ability to pinpoint a missing laptop using GPS technology on select 3G modems.

Presumably this 3G radio can transmit as well as receive. I tried to find more informative datasheets but Intel's website sucks and I couldn't find more on it.

That won't work.

There's a good breakdown on infowars about why it won't work:

http://www.infowars.com/91497/

But you can't just take what's on infowars without a grain of salt, so here's a video on intel's website where they substantiate everything, but with a positive spin

http://www.intel.com/content/w...

We need open hardware. The hardware being made in the factories is not trustworthy.

For the majority who won't click links and read articles, the gist is, there's a 3G radio antenna and a special dedicated processor inside of your CPU, and it can be used to either take complete control of your device, or to destroy it. All the details are there in Intel's marketing material.

"Secret" 3G Intel Chip Gives Snoops Backdoor PC Access

vPro processors allow remote access even when computer is turned off

Paul Joseph Watson | Infowars.com | September 26, 2013

http://www.infowars.com/91497/

Intel Core vPro processors contain a "secret" 3G chip that allows remote disabling and backdoor access to any computer even when it is turned off.

Although the technology has actually been around for a while, the attendant privacy concerns are only just being aired. The "secret" 3G chip that Intel added to its processors in 2011 caused little consternation until the NSA spying issue exploded earlier this year as a result of Edward Snowden's revelations.

In a promotional video for the technology, Intel brags that the chips actually offer enhanced security because they don't require computers to be "powered on" and allow problems to be fixed remotely. The promo also highlights the ability for an administrator to shut down PCs remotely "even if the PC is not connected to the network," as well as the ability to bypass hard drive encryption.

"Intel actually embedded the 3G radio chip in order to enable its Anti Theft 3.0 technology. And since that technology is found on every Core i3/i5/i7 CPU after Sandy Bridge, that means a lot of CPUs, not just new vPro, might have a secret 3G connection nobody knew about until now,"reports Softpedia.

Jeff Marek, director of business client engineering for Intel, acknowledged that the company's Sandy Bridge" microprocessor, which was released in 2011, had "the ability to remotely kill and restore a lost or stolen PC via 3G."

"Core vPro processors contain a second physical processor embedded within the main processor which has it's own operating system embedded on the chip itself," writes Jim Stone. "As long as the power supply is available and and in working condition, it can be woken up by the Core vPro processor, which runs on the system's phantom power and is able to quietly turn individual hardware components on and access anything on them."

Although the technology is being promoted as a convenient way for IT experts to troubleshoot PC issues remotely, it also allows hackers or NSA snoops to view the entire contents of somebody's hard drive, even when the power is off and the computer is not connected to a wi-fi network.

It also allows third parties to remotely disable any computer via the "secret" 3G chip that is built into Intel's Sandy Bridge processors. Webcams could also be remotely accessed.

"This combination of hardware from Intel enables vPro access ports which operate independently of normal user operations," reports TG Daily. "These include out-of-band communications (communications that exist outside of the scope of anything the machine might be doing through an OS or hypervisor), monitoring and altering of incoming and outgoing network traffic. In short, it operates covertly and snoops and potentially manipulates data."

Not only does this represent a privacy nightmare, it also dramatically increases the risk of industrial espionage.

The ability for third parties to have remote 3G access to PCs would also allow unwanted content to be placed on somebody's hard drive, making it easier for intelligence agencies and corrupt law enforcement bodies to frame people.

"The bottom line? The Core vPro processor is the end of any pretend privacy," writes Stone. "If you think encryption, Norton, or anything else is going to ensure your privacy, including never hooking up to the web at all, think again. There is now more than just a ghost in the machine."

Facebook @ https://www.facebook.com/paul....
FOLLOW Paul Joseph Watson @ https://twitter.com/PrisonPlan...
--
http://www.intel.com/content/w...

I've seen bugs in chips all the time. Most of the time people have to write bad software to account for the bugs in the chips. You aren't seeing most of the CPU bugs because OS programmers are seeing them and fixing them in drivers which you never touch. Take a look at errata: http://www.intel.com/content/dam/www/public/us/en/documents/specification-updates/xeon-e5-family-spec-update.pdf

Hey, now that Intel is trying to sell quarks NICs, we could be looking at a real crunch in the IPv6 space... (and, at a tray price of over $9/unit, large atoms and even most molecules becoming enormously expensive.)

The problem was, originally, that the CPU itself did not have an NX bit

It doesn't need one, if a system actually implements protection according to the spec. Check http://www.intel.com/Assets/en... , section 3.4.5.1. (Page 3-16, vol. 3A). If you're still in doubt, check the original 80386 manual, http://css.csail.mit.edu/6.858... (page 109).

because you could *read* program code and why would you want to do that except to execute it

Well, read and execute are two separate permissions even on unix systems :) (eg. you cannot read a file, but you can order the system to execute it). There is a whole range of applications for read-only buffers, not only for execution, specially if eg. my application deals with DMA transfers. On modern PCI Express systems, this makes even more sense.

Yes, and in 2001 no x86 CPUs were physically capable in hardware of marking executability in the LDT.

I actually find that quite hard to believe. The LDT was introduced with the 80286, in 1981. If you check both manuals I mentioned, you'll find indication that you cannot store a TSS in the LDT and some other special descriptor types. Not code/data ones. That would actually *void* the initial purpose of the LDT, which was providing a poor man's protection mechanism without a paging system. My memory isn't what it used to be, and sometimes I do get some things wrong. It happens. But I've spent over 10 years programming mainly in x86 assembly (covering the end of the 90's), and - while I may not recall all the specifics, I still remember some stuff . The drawbacks of using LDTs have more to do with memory consumption and system complexity than anything else. If you have information that support your claim, please share :)

I'm not spouting anything, you are.
No one but you has said there is anything fundamentally wrong with it.

Here's a description, the architecture is in section 3. Point out the flaws, oh mighty one.
https://software.intel.com/en-...

In fact, I guarantee if someone made a hard drive with a controller with an mSATA slot for adding a SSD and offered the controller to be setup as pass-through (act as two drives) or caching (SSD keeps a cache of platter), it would sell like crazy.

This already exists. It's called Intel Smart Response Technology and it's been available on motherboards since it was release three years ago in 2011. It works with both mSATA and standard SATA attached drives.

Most people just haven't paid the extra $100-200 to buy an SSD to cache their HD not to mention the technical know-how required to install the drive and setup the BIOS and software correctly.

What we need is systems that are sold with this already built in so users don't have to do it manually. But that adds $100-200 cost to the system and many shoppers look at the price tag first when they're buying a new computer :-(

You might want to double check that:
https://downloadcenter.intel.c...

Intel® Graphics Media Accelerator Driver for Windows* 7(exe) Installs graphics driver version 15.12.75.4.1930 (8.15.10.1930) for the integrated graphics controller of Intel® Chipsets for Windows 7*.
***********
Intel® Graphics Media Accelerator Driver for Windows* 7 64 (exe) Installs 64bit graphics driver version 15.12.75.4.64.1930 (8.15.10.1930) for the integrated graphics controller of Intel® chipsets for Windows 7. OS: Windows 7 (64-bit)*

The Intel Galileo board has 8 GPIO pins, but these are not nearly as useful as on an Arduino or Raspberry Pi because they are actually multiplexed through I2C rather than connected directly to the processor, and thus are much slower to read or toggle than on other project boards. Is the same true of the MinnowBoard Max, or does it have real GPIO? This might not matter if you're going to use it as a router or NAS, but for embedded projects it can make a big difference.

Intel Releases $99 "Minnowboard Max," An Open-Source Single-Board Computer

http://slashdot.org/submission...

##

"Not to be outflanked by rivals, Intel has released the $99 Minnowboard Max, a tiny single-board computer that runs Linux and Android. It is completely open source - you can check out the firmware and software here(1) - and runs a 1.91GHz Atom E3845 processor."

http://www.minnowboard.org/mee...

http://newsroom.intel.com/comm...

http://techcrunch.com/2014/04/...

(1) http://www.minnowboard.org/

Intel Releases $99 "Minnowboard Max," An Open-Source Single-Board Computer

http://slashdot.org/submission...

"Not to be outflanked by rivals, Intel has released the $99 Minnowboard Max, a tiny single-board computer that runs Linux and Android. It is completely open source - you can check out the firmware and software here(1) - and runs a 1.91GHz Atom E3845 processor."

http://www.minnowboard.org/mee...

http://newsroom.intel.com/comm...

http://techcrunch.com/2014/04/...

(1) http://www.minnowboard.org/

What you fail to mention is the fact you could have probably built most if not all of an AMD 6 core system for the cost of the i7-860 alone, and if one were to go one notch down to the quads (which lets face it software just hasn't kept up with hardware and even more triple cores spend more time at idle than under load) then one could have easily built the entire system. The 8 cores were built just to say they could and frankly have never been priced competitively, no different than those 5Ghz chips they released not too long ago.

My oldest boy has an AMD hexacore, 8Gb of RAM, a 1Tb HDD and an HD7750, the whole system ended up costing something like $375 after MIRs. It kicks ass at gaming, transcoding, hell it'll do anything your average user will be able to think up for a PC to do and do so quite well and cost a grand total of $70 more than your i7-860 BY ITSELF without so much as a stick of RAM or anything according to Intel.

So if you want to sit here and argue that you are one of the 1% that actually NEED every MHz of speed you can get, which until we see benches done that are compiled with GCC I wouldn't trust the benches BTW but that is a different story, then fine, do so. But the bang for the buck is so far in AMD's camp right now it isn't even funny, you can choose from several quad cores including fully unlocked for less than a Pentium Dual, and if all you care about is power the AMD Jaguars spank the Intel Atoms on performance while using less than 25w for a quad. AMD is just a crazy deal ATM which is why I've had no complaints when it comes to being AMD exclusive, the customers get great performance at a great price.

Intel DN2820FYK is selling for $140 and comes with an infrared sensor.

I have OpenELEC 4.0 beta (version 3.95.1) running off a 4GB USB stick I had lying around - no need to buy an SSD. Infrared sensor worked out of the box with my Harmony Smart Control remote.

Do the new AMD64-architecture assembly-language opcodes to do AES encryption and decryption count?

http://en.wikipedia.org/wiki/A...

http://www.intel.com/content/w...

Of course, there's also ARM. It's not new, of course, but programming ARM in assembly language is kind of a recent developmen (though I'd conservatively estimate that at least 20% of assembly-language ARM code is probably malware).

In theory, you can even do JVM assembly. It's kind of pointless and masochistic, but people have done it just to say they have. ;-)

The box looks like it is based on the Intel Next Unit of Computing, but at a much lower price point. A bare "kit" of an NUC without a drive is more expensive. It should be able to run Linux after the Chrome bootloader issue is addressed.
http://www.intel.com/content/w...

Ick.

Its Haswell http://ark.intel.com/products/...

Encoding was added to the VAAPI interface, but was never supported by Intel hardware. There's not much sense implementing a protocol when there's no hardware to interface with. You may be looking for the Intel Media SDK, which wasn't made publicly available until the middle of last year.

The vast majority of code shops compiling windows source use the Microsoft compile

My understanding is that there are still many major apps that use the Intel compiler. The Intel compiler produces the very fastest code (as long as you run that code on a chip that offers "GenuineIntel" as the CPUID string).

I agree with GP that the tests used in benchmarking should all be themselves tested to make sure that this problem is not present. If Photoshop turns out to be compiled with Intel, then don't use Photoshop in the benchmark.

And I don't seriously think that Intel would punish web sites that only run benchmarks that don't screw non-Intel chips. (If they do, that's even more reason to hate Intel.)

Intel's compiler was a rigged setup back in 2002...and that all changed around 2006 with VS8.

Intel's compiler is still rigged. Check out this URL. I can't copy the text because it is a bitmap image of text. It basically says "non-Intel chips may not perform well with the output of this compiler, and if that happens you can't complain about it because we warned you".

http://software.intel.com/en-us/articles/optimization-notice#opt-en

Seriously, how did this drivel get modded up on Slashdot?

Personally, I think a sentence that says the Intel C compiler is no longer rigged because Microsoft shipped Visual Studio 8 is pretty much "drivel".

All the newer Intel SSDs have that exact feature. Built in hardware based encryption with the keys stored in the SSD's controller. The keys are completely inaccessible to the PC's CPU.

Combine that with a HDD password (the ATA/IDE password command that has been around since forever.) And this type of attack is pretty much impossible. The user has to input the HDD password through the BIOS before the disk becomes accessible (the SSD stores the password in its internal memory and won't allow read/write operations until the password is provided). You would need to get the user's disk password somehow.

My employer exclusively uses Intel SSD's for our corporate laptops for this reason.

All the newer Intel SSDs have that exact feature. Built in hardware based encryption with the keys stored in the SSD's controller. The keys are completely inaccessible to the PC's CPU.

Combine that with a HDD password (the ATA/IDE password command that has been around since forever.) And this type of attack is pretty much impossible. The user has to input the HDD password through the BIOS before the disk becomes accessible (the SSD stores the password in its internal memory and won't allow read/write operations until the password is provided). You would need to get the user's disk password somehow.

My employer exclusively uses Intel SSD's for our corporate laptops for this reason.

No kidding. Set up a file server with NFS and use an Intel NUC at the TV installed with xbmc (and/or mythtv.) Intel themselves has instructions for setting up their NUC with xbmc using Linux Mint. The newer NUCs even have an IR receiver built in so all you need is a MCE remote (or a Harmony) and you're set.

Further examples:

Eye-fi cards are SD cards containing a WiFi module, which can be a quick way to get photos off a camera.

Intel Edison is an SD-sized computer with WiFi and Bluetooth: http://www.intel.com/content/www/us/en/do-it-yourself/edison.html

USB storage drives can be tiny too: http://www.gizmodo.co.uk/2013/10/worlds-smallest-usb-stick-squeezes-64gb-into-a-tiny-silvery-peanut/

Genuine question - where are these devices? Has any physical evidence of them been detected? Has anyone found one? I'm not sceptical that they did it, I think it's entirely possible. I'm just curious if there's any physical evidence that's been found yet...?

Intel Core vPro with anti theft capability? I read a while ago that these processors have a complete OS on board, with working GPRS, but I can't find that article anymore.

I've owned two fairly new laptops recently, one with an AMD A8-4500M ($400) and one with an Intel Core i7-2630QM ($830).

...but even the i7 up to Sandy Bridge is, in my experience, not much better than equivalent higher-end chips in laptops made four years ago

An I7-2630QQM is a 3 year old sandy bridge chip, it launched Q1'11. I don't know why you would expect 3 year old chips to be much faster than 4 year old chips, especially if you bought it recently. I mean, there are 2 generation of newer Intel processors out, and have been since Q2'13. Heck, if there's a 2 1/2-3 year old chip in the laptop when you bought it the manufacturer is probably doing other stupid things that were contemporary at the time like putting 5400 rpm drives in the laptop and less than 4 gig of RAM at which point it wouldn't be any surprise that it's slower than expected.

Most of how a computer feels isn't from how fast the CPU is for most tasks anymore, it's about having sufficient RAM and fast enough disk (usually an SSD) to not have to wait long for data to load. That's is a big part of the reason why so many people say that CPUs are fast enough now. The number of problems that are computationally constrained is much smaller than it used to be, especially for the typical laptop user. If you were upgrading today and looking for something faster (and for $830 I'd hope you could do better than a 3 year old chip), I'd say to look for something with an SSD. At $830 you can probably find one and at $1000 you certainly could, and it'll feel faster and have better battery life to boot.

intel is already doing it.

and besides, this is about higher end chips.

Intel makes their high end chips exclusively in the US. Overseas fabs make lower tier chips.

the wiki article is not the full truth. some higher end chips are made here but that's NOT what the issue is about. you can't build entire systems from US based parts anymore. it simply can't be done. most of your parts (usually all) are not US made. and your pc board is not just one single high-end chip.

You seem to be conflating cost and efficiency with technical capability. It usually doesn't make any sense for mass produced consumer level electronics to be made in the US. It would be horrendously expensive, quantities would be relatively limited and no one would buy them. That doesn't mean the capability isn't there. If an F-35 could be made from the ground up in the United States (which is obviously can be, as rare earth magnets are the only thing at issue here) your desktop PC's motherboard could be if there was some reason for it.

I tried to punt the details here toward the references provided, but you raise a good question: why not just use the lifetime percentage exposed at attributed 202/0xCA "Percent Lifetime Remaining". There's two problems with that data.

First off, that SMART attribute hasn't been consistent since the drive was released. See M500 960GB MU03 SMART Issue as one observation about the biggest firmware change. I believe that happened after the Tech Report review. The fact that Crucial changed exposing wear data over the life of the drive is itself enough to get it booted from some companies as an immature product.

But let's say you consider that ancient history now. The other side of the complaints here is that the M500 doesn't give wear data in terms of bytes written. If you have two M500 drives that show identical wear data as measured by 202/0xCA, what does that tell you about their respective workloads? Unfortunately, it doesn't tell you anything useful for that purpose without more context. And that's a critical failure for the standard way such things are rated and evaluated now.

Intel publishes white papers for the recommended drive in TFA like DC S3500 Series RAID Workload Characterization, and that gives a lot of data about how to compare production deployments against drive specifications. I did exactly that for their earlier drives in the blog article I referenced.

There's just not quite enough data available from a Crucial M500 to do a similar analysis on it. "Erase count" is really an implementation detail specific to the drive; you can't compare those across different manufacturers. The most useful standard that aims to eliminate the workload specific aspect from lifespan ratings is JESD218. That also looks at lifetime in terms of terabytes written. There are some really fundamental detaisl that so far seem missing on Crucial's drives. You can back out write data from some of the other statistics, but without a hard published spec for such things I don't consider that very useful.

"Does the Intel® Core i7 Desktop Processor support Error Correction Code (ECC) memory?

The Intel® Core i7 Desktop Processors typically do not support ECC memory. ECC memory is usually used on servers and workstations, rather than on desktop platforms. This is mainly due to the price premium of ECC memory and chipset support. Check with your desktop board manufacturer to see if ECC memory is enabled on your board."

Only for very small values of 'workstation'.

http://www.intel.com/support/processors/sb/CS-029913.htm

I did not look at the actual numbers claimed nor what they are. But a factor of 7 between a GPU and a 32 core intel system is not impossible. My BS alarm trip around a factor of 20 for a 2 processor system.

If you look at state of the art nvidia GPU, you pick a tesla K10, ( http://www.nvidia.com/object/tesla-servers.html ). You get about 4T.5flop/s single precision of performance and a bandwidth of 320GB/s. The flop is realistic for compute intensive (read dense mat mul) and the bandwidth is never reached. Probably 250GB/s is more reasonnable.

On the CPU side, if you peak a Xeon E5 such as this one ( http://ark.intel.com/products/64595/ ), you need 4 of them to get to 32 cores. you get 32core*2.6Ghz*8floatpersimd = 665Gflop/s which is actually realistic for dense kernel such as matmul. and 4*50GB/s bandwidth. But in practice you difficulty reach 30GB/s per processor so 120GB/s aggregated.

So the GPU is about 7.5 times faster floating point wise and 2 times faster bandwidth wise. but here we are talking peak, and practical performance varies a lot from application to application and depending if you can use your architecture properly. But overall for some well chosen kernel a factor of 10 still seems not too unreasonnable.

It doesn't matter. Either there's an airgap, where nothing can get out regardless, so it doesn't matter, or their's a hop along the path you don't control so the security of your device doesn't matter.

If you have an Intel processor, then there is already a radio backdoor built in. See http://www.intel.com/content/www/us/en/enterprise-security/what-is-vpro-technology-video.html

Then again, Intel's 330 is notorious for not getting along with T60/T61 Thinkpads.

That seems more like a problem with the Thinkpad, not the SSD.

We were discussing reliability of SSDs.

Then again, Intel's 330 is notorious for not getting along with T60/T61 Thinkpads.>/quote>

With stock firmware from Lenovo, SSDs are unsupported on T60/T61's. PERIOD. The are some third party firmware hacks that promise more stability. But, in general, it's luck of the draw on those machines.

Then again, Intel's 330 is notorious for not getting along with T60/T61 Thinkpads. It happened to me as well - something about its power management didn't get along with my T61; it would randomly freeze the system for about 30 seconds, and no combination of registry hacks and/or driver upgrades or downgrades would fix it.

The workaround was to replace the drive with a Samsung 840. No more freezeups. The Intel drive went into one of my desktops, where it has worked flawlessly.

As for my OCZ experience, good riddance. I had one of their PSUs pop one day. As usual in this situation, it was caused by crap capacitors. Naturally, it was a couple of months out of warranty.

That's a nice anecdote, considering the Pentium M didn't come out until 2003.
Perhaps it was a P3?

You're right, it was a Pentium III-M, not a "Pentium M"

The Intel compilers do NOT "phone home" for licensing. What they do "phone home" for is to send anonymous usage data. When you install, you're asked if you want to opt in to this - it is not enabled by default. Licensing is done entirely locally for single-user licenses. See http://software.intel.com/en-us/articles/software-improvement-program for more information.

OK, so you have found two applications where it isn't usable.

In computers it is on the other hand very usable. Take a look at an i7-920
With a core voltage at ~1V and a TDP of 130W you have about 130A circling around there in total.
Even with a relatively small resistivity of 5mohm/cm you have a lot of losses in the conductive paths in the chip at currents like that.
It is not an insignificant improvement in battery life on laptops and phones and the reduction in cooling in desktops and server racks isn't something that should be ignored either.

The XEON Phi has vastly greater SIMD capability than any Cray or SPARC architecture. In stock now.

The 4770K has an Intel HD 4600, not an Iris Pro 5200. The nVidia GPU is faster than the 4600 in the CPU tested.

The only 4770 series chip to feature Iris Pro is the 4770R.

Reference: http://ark.intel.com/products/family/75023

I take it they never looked here? TBB works with clang... sort of.

Hmm, odd - I use a desktop PC with a Sandy Bridge i5 at work and the Intel HD graphics drivers (from here: http://downloadmirror.intel.com/22627/a08/Win64_152815.zip) work just fine under Windows 8.1. Admittedly that's via DVI rather than HDMI, as my monitor doesn't have an HDMI input.

Tell that to intel:
http://software.intel.com/en-us/android

I read the original article, but I don't see any part where someone recorded what was going out the speaker and looked at it. If someone is sending data over audio, it will show on a scope. Clearly that's not going to do much unless the receiving side has some kind of modem code listening for it.

Then there are claims like "It seemed to send TLS encrypted commands in the HostOptions field of DHCP packets." Attacking via DHCP packets is plausible; DHCP clients get told a lot of things they're supposed to do, and some of the older vendor-specific extensions are very insecure. But TLS? TLS isn't used within the DHCP protocol itself. There's a way to store DHCP configuration info in an LDAP server and have a DHCP server access it via LDAP.

If someone is seeing strange DHCP packets, and reloading the BIOS won't help, it's possible that what's going on involves an attack via the network controller. The fancier network controller parts now have CPUs and EEPROM. This may be an attack which puts code in the network controller which in turn patches the BIOS.

The people studying this need to list exactly what network ICs the machines involved are using. Some network devices are too dumb to be used as an attack vector, but some have whole protocol stacks, WiFi support, remote administration support, etc. It would not be surprising if those were attackable.

I've expected attacks via network controllers for years. That's been used to attack servers. There's a known attack on PCI controllers which can survive rebooting and reloading the BIOS.

If the machine has wireless networking hardware and the attack exploits the network controller, it may be able to do wireless networking even if the user thinks they have the hardware disabled. Time to open up the machine, clip onto the JTAG port on the network controller, and read out the device memory with a JTAG debugger. Compare the dumps with other machines.

I'm curious as to exactly what 2 watt processors can compare to a 3.2 GHz P4 from 2003.

Have you even seen the benchmarks for the new Intel Atom Z3770?

I'm curious as to exactly what 2 watt processors can compare to a 3.2 GHz P4 from 2003.

So? gcc has much better support for C++11 and C++14

Much better? Maybe "a tad better" And the things icpc is missing are not so important. But that wiki (while the best reference for it that I know of) is out of date, so if you are comparing the latest version of each, I think you'd find that they are fairly compatible.