I don't think anyone at NASA thinks that it will be NASA to benefit from this research. The US government's research projects are generally funded to provide pioneering foreward looking technologies that no private company would invest in developing until 10+ years from now. So that way when private industry does need that technologythey already have something to get started from.
The one exception of course is development of new weapons and military systems.
From a pure security standpoint, he is probably doing fine actually. The market share for Win98 Internet connected systems is now lower than Linux. Its such a small target and there are enough API differences between it and WinXP that the only viruses that will infect it are 10+ years old.
Now from a functionality standpoint... Win98 will be so limited on software choices at this point that its really not worth it. No modern browsers support it so you can't even browse the web really. Not to mention the horrible instability that we all have forgetten about.
I mostly agree with you but you have to consider that unfortunately there are a LOT of XBox systems out there and if a game dev wants to target that audience (which is a lot bigger than the PC gaming audience) then DX is required... no OpenGL API support on XBox (big surprise.)
This is why all the major game engines support both DX and OpenGL.
It is true that the kernel is expected to load and run the ACPI bytecode in a trusted context... but your assumption that the BIOS is gone after the OS bootloader runs is inaccurate. SMM keeps BIOS code code resident forever and running at a higher privilege level than your OS kernel. And its impossible for your kernel to see what SMM is doing unlike ACPI which is pretty easy to inspect,
Your BIOS already owns the platform and getting rid of ACPI won't change that, it will just make it more difficult to firmware engineers (like me) to support all OSes with 1 firmware image.
I agree that ACPI sucks in a lot of ways, but you must admit that there is something to be said for a standard that has enabled WinXP (10+ year old OS) and brand new stuff like Win8.1 and all the countless Linux releases in between to run on practically any PC regardless of it being brand new or 10 years old.
IMO the trend towards having special firmware for each OS is disturbing and limits the universal and reusable PC. A lot of this is being driven by Google and thier insistence that Chrome OS systems be shipped without Legacy BIOS or UEFI support (locked down coreboot that only accepts OSes signed by Google unless run in "developer mode", btw even in developer mode you can't install a new coreboot payload to enable UEFI or legacy BIOS boot).
Seriously where should you more worried about NSA exploits1) a de-compilable and OS visible byte code that controls thermal and power management or 2) An invisible micro controller firmware that converts signals from your scan matrix laptop keyboard into P/S 2 signaling?
Seriously dude, I write firmware for a living... I know a thing or two about what it does and the state of Linux's ACPI stack.
Honestly Shuttleworth's reasoning "Binary blobs can contain NSA exploits" is completely irrelevant to ACPI since ACPI byte-code can be completely de-compiled back in to the original source language making it very easy for security researchers to detect any funny business.
Honestly the modern PC has several microcontrollers in it that contain code that the primary CPU never even sees. I personally would consider those a much bigger security threat than ACPI.
So lets ask ourselves... why does he really want to get rid of ACPI? The answer is pretty simple, it going to take a lot of coding effort to get the Linux ACPI stack ready to fully support ACPI 5.0 and Connected Standby found on a lot of brand new laptops. This is just a feeble attempt to mask the fact that puring all his resources in dumb projects like Mir and Unity doesn't leave much left to keep up to date on new open PC platform standards.
The thing is there is a non-trivial number of computer users that used Win9x extensively and then 2000/XP and everything else after that who are used to that "old GUI". Honestly I think that old GUI is much better suited to any task that is complex enough to require the user to operate multiple different applications together to achieve a higher goal. I suspect that your teenage daughter's most complex computing task is typing her school papers. She probably doesn't create a whole lot of diagrams and pictures to go with them so she probably only ever has to look at Word and not do any context switching.
Really the users that do complex work flows involving multiple applications at once are Microsoft's core audience which for whatever reason they seem to have mostly forgotten about. Just to put things in to perspective, that kind of user is often referred to as a "power user" now... I remember when the term power user meant something meaningful.
And the thing is, it would be sooooo easy for Microsoft to make the "power users" happy. Here are the simple changes that would make everyone love Win8:
1. Bring the Start Menu back as an option. You don't have to make it the default, just make it an option.
2. Optionally allow Metro apps to run in a window on the desktop
3. Optionally allow the user to disable the charm bar
4. Allow the user to select between the Win8 Modern theme, Win7 Aero theme, or Windows classic theme.
Give the user the choice of how he/she wants the GUI to look and everyone will flock to Win8. It seems that Microsoft has forgotten one of Bill Gate's most important lessons, the power of the default.
If anyone from Microsoft is reading this, really guys please do this. The PC industry is in the shitter right now because of your arrogance NOT because of the iPad. The entire industry including you and including me would be better off if people started buying PCs again instead of $150 android tablets, the typical ~$400 PC + new software licenses to go along with it pumps a lot more money in to just about everyone's pocket (except maybe Apple and Google).
In truth current gen PCIe SSDs appear to the OS as a PCIe bus connected AHCI controller with a single disk that supports TRIM. There makes it completely transparent... it works exactly the same as a SATA SSD from a software perspective.
Pretty soon we will start seeing next gen PCIe SSDs that expose themselves as an NVMe controller instead of an AHCI controller. Those SSDs will be backwards incompatible with AHCI but the command protocol and DMA interface enables extreme parallism so we will see pretty incredible performance for those SSDs. From a software stack perspective they use a new NVMe host controller and a new command set (ATA commands are completely gone!) So you need new drivers for it. They have OSS Win7/8/8.1 drivers available for NVMe but due to kernel limitations only the Win8/8.1 version of the driver is capable of supporting TRIM (Maybe that is where you got confused.) Win8.1 also have a NVMe driver in-box from Microsoft.
Don't worry though, AHCI PCIe/SATA Express SSDs will be with use for a very long time esp. since Win7 is rapidly turning in to the next WinXP (the version that everyone likes and uses despite Microsoft's best efforts.)
Speaking as someone who has been visiting this site daily for over 10 years, honestly I don't know what the hell they are thinking. If they want different fonts than make the make the article title sans serif and the article body serif like the really old slashdot from the 90s, not this bullshit of two slightly different sans serif fonts that clash with each other.
Oh I almost forgot: They even got the wrong fucking green color!
When one considers the US Consumer Price Index, $79 in 2004 dollars is $97.43 in 2013 dollars. Most of the cost associated with Amazon Prime is transportation, and gasoline certainly hasn't gotten any cheaper. The $99 price tag seems reasonable, $119... not so much.
All the newer IntelSSDs 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.
So... TFA says that the end of Moore's law will result in a ton of new innovations aimed at... making computers faster??? Last time I checked making computers faster is what Moore's law is all about.
I think a better title would be "End of Traditional Silicon/CMOS Technology Forcing Radical Innovation to Keep Moore's Law Going!"
Maybe I'm alone here, but I honestly think this is a really good idea. I personally own a Windows 8 tablet as well as an android tablet and android smartphone and have found myself thinking on several occasions how much more useful the Win8 system would be if I could run Android on it as well.
I agree with other posters here that Android 4.x as it exists today isn't a good desktop OS... but honestly it would not take a ton of extra work to make a desktop friendly interface for it. The Android 4.x UI changes slightly depending on if the device is a smartphone or a tablet, why couldn't it have a "desktop" UI mode?
Honestly all Google has to do it get rid of Chrome OS as a separate entity, merge the desktop functionality of Chrome OS into Android while keeping the ability to use 3rd party software sources and call it Android 5.0. If Google makes such a product honestly I think it would be devastating to Microsoft as well as the Windows ecosystem.
No, it's not truly free unless it comes with exactly zero mysterious binary blobs calling home (or NSA, which may be the same thing).
If that's the criteria then its pretty much impossible for these laptops to meet it. That coreboot firmware is going to carry microcode updates for the CPU which are encrypted and signed by Intel so it would be impossible to replace them with free microcode. I bet the EC and the bluetooth and the hard disk controller are still running the original binary blobs too.
But don't tell RMS, he hasn't realized how much embedded firmware has proliferated in the modern PC compared to the 1990's when the LinuxBIOS (now coreboot) project started.
I'm just as happy as very other Linux user out there about the Intel drivers starting to get competitive... but I'm pretty sure the reason Intel's management is dropping big bucks on Linux graphics driver development is Andriod not SteamOS. SteamOS is probably a pleasant nice to have they they get without any large amount of extra investment.
The only problem I have with BitCoin at the moment is that it isn't something you want to hold on to.
Yup absolutely. Bitcoin isn't money, its more like a virtual commodity that people speculate on.
Lets look at the 3 properties of money and see how Bitcoin stacks up:
A unit of account
A store of value
A medium of exchange
For #1, very few banks offer BTC checking accounts and when I go to any store near my house, all the goods I see there are priced in USD, not BTC. So BTC doesn't meet #1. Next lets look at #2, BTC fluctuates in value so rapidly that as you point out, it can't be used as a reliable mechanism for storing wealth. Finally for #3, there are some very specific online markets where very specific goods can be bought with BTC, but overall BTC doesn't really cut it. Lets look at my basic human needs: food, water, shelter. When I buy food at the grocery store, they expect me to pay them in USD. The water company expects my water bill to be paid in USD. When I bought my house, the transaction was conducted in USD.
If the USD price of red apples goes up by 50% next time I go shopping, I can reliably use that as a signal that red apples are in short supply right now and opt to buy yellow ones instead. If the price of red apples goes up by 50% in BTC, I would think it was a reflection on BTC exchange rates, I wouldn't see it as a signal of a red apple shortage.
I know I'm gonna be down-voted, but seriously BTC isn't money. And it never will be until its possible to do the things I describe above using it.
Actually check out Haswell's die configuration, the integrated graphics takes up about 2 times more area than the L3 cache. Also, look at how dense the transistors are in the GPU area, looks as dense or maybe even more dense than the cache. It wouldn't surprise me if graphics are a source of manufacturing problems in addition to L3 at this point.
Actually it appears that Intel removed the A20 line starting with Haswell.
Check out page 271 of the Intel System Programmers Manual Vol. 3A from June 2013. Notice the following excerpt: "The functionality of A20M# is used primarily by older operating systems and not used by modern operating systems. On newer Intel 64 processors, A20M# may be absent."
Now check out page 368 from the May 2011 version of that same document. In the same paragraph, the statement above is not present.
From this, we can infer that between May 2011 and June 2013 some new Intel chip dropped support for A20M#. In that timeframe, Ivybridge and Haswell are the only 2 chips that were released. Since Ivybridge is the same architecture as SandyBridge just manufactured on 22nm and we know that SandyBridge did have A20M#, I think its a fairly safe assumption that Haswell is the first x86 chip that has _finally_ done away with A20M#. That said, it would be nice if Intel actually said in the manual which chip was the first to remove it.
Does someone have a new Haswell system that they can do a quick DOS ASM program on to verify this? Even better, if someone has an Ivybridge system we can narrow this down.
As someone who has written and maintained complex commercial Windows software recently I can say that since Windows Vista the backwards compatibility story with Windows is not nearly as good as it used to be. Pretty much every new version of Windows since then has brought some serious changes in behavior.
With Vista the big breaking change was of course UAC which I'm sure everyone here knows about.
Windows 7 on the surface did not introduce a large amount of breaking changes when compared to Windows Vista. Probably the biggest breaking change was the need to use a new GUID in your application manifest if you didn't want your customers to be annoyed by the "Program Compatibility Assistant."
However, Win7 was the first version where 64 bit OS installations really took off. Depending on the application, making an existing 32 bit Windows application work on a 64 bit OS can be a lot of work. I'm not talking about recompiling to 64 bit here either. There are a fair number of breaking changes with regard to COM objects, esp. if you are mixing.NET and native code anywhere.
Win8 brings us Metro/Modern apps which most Windows developers have been ignoring because of lack of backwards compatibility with Win7 and a strict sandbox that makes it almost impossible to write anything other than silly casual games (Cut the Rope/Angry Birds) or an "app" that does nothing more than access a website which you could access with your web browser anyway ("Facebook app"/"Netflix app".)
For the people who write applications (not "apps") Windows 8 has a couple things that make life difficult as well. One of the big ones is how difficult it is to perform an automated installation of.NET 3.5. For those doing driver development, the addition of connected standby to Win8 has really complicated life as well.
All this adds up ever since Vista we have always had to make changes to our software to support a new OS release, wierdly enough binary compatibility between OS releases on Windows is actually becoming comparable to a typical Linux distribution. With the release cadence of Windows becoming quicker ongoing support and maintenance for commercial Windows software is quickly becoming as expensive as commercial Linux software support.
I starting to fell like a broken record here but seriously Slashdot, I would have thought that this Myth that x86 ISA somehow makes it impossible to build a low power part would be dead by now. ARM is a rather complex instruction set now that they have added SIMD and floating point support. If you look at the number of op-codes it has versus x86 they are roughly equal. Both ISAs have variable length instructions (all recent ARM designs support THUMB) so the decode logic complexity is actually pretty comparable. Also much of the decode logic is implemented in software via microcode on both ISAs.
There is nothing magical about ARM that makes it lower power. The real reason why x86 implementations are so much hotter is because designers of x86 processors have been targeting high compute performance for decades, whereas ARM has been targeting low power for decades. A quick look at Medfield benchmarks show that it is comparable in performance to ARM processors that were current when it was released. Medfield is ~4W active TDP... same as a Exynos 5 Dual ARM CPU. From what we have seen from Merrifield/Bay Trail/Haswell the next gen x86 parts are continuing along this trend.
Slashdot Mirror
I don't think anyone at NASA thinks that it will be NASA to benefit from this research. The US government's research projects are generally funded to provide pioneering foreward looking technologies that no private company would invest in developing until 10+ years from now. So that way when private industry does need that technologythey already have something to get started from.
The one exception of course is development of new weapons and military systems.
From a pure security standpoint, he is probably doing fine actually. The market share for Win98 Internet connected systems is now lower than Linux. Its such a small target and there are enough API differences between it and WinXP that the only viruses that will infect it are 10+ years old.
Now from a functionality standpoint... Win98 will be so limited on software choices at this point that its really not worth it. No modern browsers support it so you can't even browse the web really. Not to mention the horrible instability that we all have forgetten about.
I mostly agree with you but you have to consider that unfortunately there are a LOT of XBox systems out there and if a game dev wants to target that audience (which is a lot bigger than the PC gaming audience) then DX is required... no OpenGL API support on XBox (big surprise.)
This is why all the major game engines support both DX and OpenGL.
I think you meant "will they speak Mandarin or English"
It is true that the kernel is expected to load and run the ACPI bytecode in a trusted context... but your assumption that the BIOS is gone after the OS bootloader runs is inaccurate. SMM keeps BIOS code code resident forever and running at a higher privilege level than your OS kernel. And its impossible for your kernel to see what SMM is doing unlike ACPI which is pretty easy to inspect,
Your BIOS already owns the platform and getting rid of ACPI won't change that, it will just make it more difficult to firmware engineers (like me) to support all OSes with 1 firmware image.
I agree that ACPI sucks in a lot of ways, but you must admit that there is something to be said for a standard that has enabled WinXP (10+ year old OS) and brand new stuff like Win8.1 and all the countless Linux releases in between to run on practically any PC regardless of it being brand new or 10 years old.
IMO the trend towards having special firmware for each OS is disturbing and limits the universal and reusable PC. A lot of this is being driven by Google and thier insistence that Chrome OS systems be shipped without Legacy BIOS or UEFI support (locked down coreboot that only accepts OSes signed by Google unless run in "developer mode", btw even in developer mode you can't install a new coreboot payload to enable UEFI or legacy BIOS boot).
What exactly was stupid about my post? Take it you have never heard of ACPI Source Language or the Embedded Controller?
Seriously where should you more worried about NSA exploits1) a de-compilable and OS visible byte code that controls thermal and power management or 2) An invisible micro controller firmware that converts signals from your scan matrix laptop keyboard into P/S 2 signaling?
Seriously dude, I write firmware for a living... I know a thing or two about what it does and the state of Linux's ACPI stack.
Or maybe you could isolate control systems from the Internet
You know that stuxnet explicitly targeted a uranium enrichment control system that was NOT Internet connected right?
Honestly Shuttleworth's reasoning "Binary blobs can contain NSA exploits" is completely irrelevant to ACPI since ACPI byte-code can be completely de-compiled back in to the original source language making it very easy for security researchers to detect any funny business.
Honestly the modern PC has several microcontrollers in it that contain code that the primary CPU never even sees. I personally would consider those a much bigger security threat than ACPI.
So lets ask ourselves... why does he really want to get rid of ACPI? The answer is pretty simple, it going to take a lot of coding effort to get the Linux ACPI stack ready to fully support ACPI 5.0 and Connected Standby found on a lot of brand new laptops. This is just a feeble attempt to mask the fact that puring all his resources in dumb projects like Mir and Unity doesn't leave much left to keep up to date on new open PC platform standards.
The thing is there is a non-trivial number of computer users that used Win9x extensively and then 2000/XP and everything else after that who are used to that "old GUI". Honestly I think that old GUI is much better suited to any task that is complex enough to require the user to operate multiple different applications together to achieve a higher goal. I suspect that your teenage daughter's most complex computing task is typing her school papers. She probably doesn't create a whole lot of diagrams and pictures to go with them so she probably only ever has to look at Word and not do any context switching.
Really the users that do complex work flows involving multiple applications at once are Microsoft's core audience which for whatever reason they seem to have mostly forgotten about. Just to put things in to perspective, that kind of user is often referred to as a "power user" now... I remember when the term power user meant something meaningful.
And the thing is, it would be sooooo easy for Microsoft to make the "power users" happy. Here are the simple changes that would make everyone love Win8:
1. Bring the Start Menu back as an option. You don't have to make it the default, just make it an option.
2. Optionally allow Metro apps to run in a window on the desktop
3. Optionally allow the user to disable the charm bar
4. Allow the user to select between the Win8 Modern theme, Win7 Aero theme, or Windows classic theme.
Give the user the choice of how he/she wants the GUI to look and everyone will flock to Win8. It seems that Microsoft has forgotten one of Bill Gate's most important lessons, the power of the default.
If anyone from Microsoft is reading this, really guys please do this. The PC industry is in the shitter right now because of your arrogance NOT because of the iPad. The entire industry including you and including me would be better off if people started buying PCs again instead of $150 android tablets, the typical ~$400 PC + new software licenses to go along with it pumps a lot more money in to just about everyone's pocket (except maybe Apple and Google).
Citation Please.
In truth current gen PCIe SSDs appear to the OS as a PCIe bus connected AHCI controller with a single disk that supports TRIM. There makes it completely transparent... it works exactly the same as a SATA SSD from a software perspective.
Pretty soon we will start seeing next gen PCIe SSDs that expose themselves as an NVMe controller instead of an AHCI controller. Those SSDs will be backwards incompatible with AHCI but the command protocol and DMA interface enables extreme parallism so we will see pretty incredible performance for those SSDs. From a software stack perspective they use a new NVMe host controller and a new command set (ATA commands are completely gone!) So you need new drivers for it. They have OSS Win7/8/8.1 drivers available for NVMe but due to kernel limitations only the Win8/8.1 version of the driver is capable of supporting TRIM (Maybe that is where you got confused.) Win8.1 also have a NVMe driver in-box from Microsoft.
Don't worry though, AHCI PCIe/SATA Express SSDs will be with use for a very long time esp. since Win7 is rapidly turning in to the next WinXP (the version that everyone likes and uses despite Microsoft's best efforts.)
Speaking as someone who has been visiting this site daily for over 10 years, honestly I don't know what the hell they are thinking. If they want different fonts than make the make the article title sans serif and the article body serif like the really old slashdot from the 90s, not this bullshit of two slightly different sans serif fonts that clash with each other.
Oh I almost forgot: They even got the wrong fucking green color!
When one considers the US Consumer Price Index, $79 in 2004 dollars is $97.43 in 2013 dollars. Most of the cost associated with Amazon Prime is transportation, and gasoline certainly hasn't gotten any cheaper. The $99 price tag seems reasonable, $119... not so much.
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.
So... TFA says that the end of Moore's law will result in a ton of new innovations aimed at... making computers faster??? Last time I checked making computers faster is what Moore's law is all about.
I think a better title would be "End of Traditional Silicon/CMOS Technology Forcing Radical Innovation to Keep Moore's Law Going!"
Maybe I'm alone here, but I honestly think this is a really good idea. I personally own a Windows 8 tablet as well as an android tablet and android smartphone and have found myself thinking on several occasions how much more useful the Win8 system would be if I could run Android on it as well.
I agree with other posters here that Android 4.x as it exists today isn't a good desktop OS... but honestly it would not take a ton of extra work to make a desktop friendly interface for it. The Android 4.x UI changes slightly depending on if the device is a smartphone or a tablet, why couldn't it have a "desktop" UI mode?
Honestly all Google has to do it get rid of Chrome OS as a separate entity, merge the desktop functionality of Chrome OS into Android while keeping the ability to use 3rd party software sources and call it Android 5.0. If Google makes such a product honestly I think it would be devastating to Microsoft as well as the Windows ecosystem.
No, it's not truly free unless it comes with exactly zero mysterious binary blobs calling home (or NSA, which may be the same thing).
If that's the criteria then its pretty much impossible for these laptops to meet it. That coreboot firmware is going to carry microcode updates for the CPU which are encrypted and signed by Intel so it would be impossible to replace them with free microcode. I bet the EC and the bluetooth and the hard disk controller are still running the original binary blobs too.
But don't tell RMS, he hasn't realized how much embedded firmware has proliferated in the modern PC compared to the 1990's when the LinuxBIOS (now coreboot) project started.
I think your LED knowledge is a bit dated. I personally own a very nice 1680 lumen 100w equivalent LED bulb:
see here
I'm just as happy as very other Linux user out there about the Intel drivers starting to get competitive... but I'm pretty sure the reason Intel's management is dropping big bucks on Linux graphics driver development is Andriod not SteamOS. SteamOS is probably a pleasant nice to have they they get without any large amount of extra investment.
The only problem I have with BitCoin at the moment is that it isn't something you want to hold on to.
Yup absolutely. Bitcoin isn't money, its more like a virtual commodity that people speculate on.
Lets look at the 3 properties of money and see how Bitcoin stacks up:
For #1, very few banks offer BTC checking accounts and when I go to any store near my house, all the goods I see there are priced in USD, not BTC. So BTC doesn't meet #1. Next lets look at #2, BTC fluctuates in value so rapidly that as you point out, it can't be used as a reliable mechanism for storing wealth. Finally for #3, there are some very specific online markets where very specific goods can be bought with BTC, but overall BTC doesn't really cut it. Lets look at my basic human needs: food, water, shelter. When I buy food at the grocery store, they expect me to pay them in USD. The water company expects my water bill to be paid in USD. When I bought my house, the transaction was conducted in USD.
If the USD price of red apples goes up by 50% next time I go shopping, I can reliably use that as a signal that red apples are in short supply right now and opt to buy yellow ones instead. If the price of red apples goes up by 50% in BTC, I would think it was a reflection on BTC exchange rates, I wouldn't see it as a signal of a red apple shortage.
I know I'm gonna be down-voted, but seriously BTC isn't money. And it never will be until its possible to do the things I describe above using it.
Actually check out Haswell's die configuration, the integrated graphics takes up about 2 times more area than the L3 cache. Also, look at how dense the transistors are in the GPU area, looks as dense or maybe even more dense than the cache. It wouldn't surprise me if graphics are a source of manufacturing problems in addition to L3 at this point.
Actually it appears that Intel removed the A20 line starting with Haswell.
Check out page 271 of the Intel System Programmers Manual Vol. 3A from June 2013. Notice the following excerpt: "The functionality of A20M# is used primarily by older operating systems and not used by modern operating systems. On newer Intel 64 processors, A20M# may be absent."
Now check out page 368 from the May 2011 version of that same document. In the same paragraph, the statement above is not present.
From this, we can infer that between May 2011 and June 2013 some new Intel chip dropped support for A20M#. In that timeframe, Ivybridge and Haswell are the only 2 chips that were released. Since Ivybridge is the same architecture as SandyBridge just manufactured on 22nm and we know that SandyBridge did have A20M#, I think its a fairly safe assumption that Haswell is the first x86 chip that has _finally_ done away with A20M#. That said, it would be nice if Intel actually said in the manual which chip was the first to remove it.
Does someone have a new Haswell system that they can do a quick DOS ASM program on to verify this? Even better, if someone has an Ivybridge system we can narrow this down.
As someone who has written and maintained complex commercial Windows software recently I can say that since Windows Vista the backwards compatibility story with Windows is not nearly as good as it used to be. Pretty much every new version of Windows since then has brought some serious changes in behavior.
With Vista the big breaking change was of course UAC which I'm sure everyone here knows about.
Windows 7 on the surface did not introduce a large amount of breaking changes when compared to Windows Vista. Probably the biggest breaking change was the need to use a new GUID in your application manifest if you didn't want your customers to be annoyed by the "Program Compatibility Assistant."
However, Win7 was the first version where 64 bit OS installations really took off. Depending on the application, making an existing 32 bit Windows application work on a 64 bit OS can be a lot of work. I'm not talking about recompiling to 64 bit here either. There are a fair number of breaking changes with regard to COM objects, esp. if you are mixing .NET and native code anywhere.
Win8 brings us Metro/Modern apps which most Windows developers have been ignoring because of lack of backwards compatibility with Win7 and a strict sandbox that makes it almost impossible to write anything other than silly casual games (Cut the Rope/Angry Birds) or an "app" that does nothing more than access a website which you could access with your web browser anyway ("Facebook app"/"Netflix app".)
For the people who write applications (not "apps") Windows 8 has a couple things that make life difficult as well. One of the big ones is how difficult it is to perform an automated installation of .NET 3.5. For those doing driver development, the addition of connected standby to Win8 has really complicated life as well.
All this adds up ever since Vista we have always had to make changes to our software to support a new OS release, wierdly enough binary compatibility between OS releases on Windows is actually becoming comparable to a typical Linux distribution. With the release cadence of Windows becoming quicker ongoing support and maintenance for commercial Windows software is quickly becoming as expensive as commercial Linux software support.
I live in Portland, OR area and got this message at about 11pm that day. I think that puts the radius more around 1000 miles. My carrier is Sprint.
I starting to fell like a broken record here but seriously Slashdot, I would have thought that this Myth that x86 ISA somehow makes it impossible to build a low power part would be dead by now. ARM is a rather complex instruction set now that they have added SIMD and floating point support. If you look at the number of op-codes it has versus x86 they are roughly equal. Both ISAs have variable length instructions (all recent ARM designs support THUMB) so the decode logic complexity is actually pretty comparable. Also much of the decode logic is implemented in software via microcode on both ISAs.
There is nothing magical about ARM that makes it lower power. The real reason why x86 implementations are so much hotter is because designers of x86 processors have been targeting high compute performance for decades, whereas ARM has been targeting low power for decades. A quick look at Medfield benchmarks show that it is comparable in performance to ARM processors that were current when it was released. Medfield is ~4W active TDP... same as a Exynos 5 Dual ARM CPU. From what we have seen from Merrifield/Bay Trail/Haswell the next gen x86 parts are continuing along this trend.
We already have that in the UNIX world... its called Python with the dbus-python package.