News Intel Ponders Transition to 64-Bit-Only x86S Architecture

So as per the technical theory, a direct 64-bit reset state will now eliminate several stages of trampoline code to enter 64-bit operation, since booting CPUs (SIPI) starts in real-address mode today and needs a 64-bit replacement.

Intel also says that in this proposed architecture, it is possible to switch to 5-level paging without leaving a paged mode. So unnecessary legacy modes are now removed, and should lead to faster systems in the future ??

We will see how this works out though. Not very optimistic about this.
 
Last edited by a moderator:
Agree with this. Hope it happens. AMD
Should also
Me not so much. One of the many reasons I run a PC is because of backward compatibility. I still run a ton of old programsn OSes (the big issue) and games. This would be a product I'd refuse to buy because it simply wouldn't meet my computing needs. I would prefer native compute over emulation or VM any day of the week.
 
Last edited:
Finally. It's about time. There will always be whining, but it has to be done eventually. I don't think x86 can go on as is. AMD is making APU server things with ZEN4, Intel follows suit with recent announcement, ARM took it's time but there are big players like Amazon backing it up. The good old x86 needs a change or it's going to wake up in a world where it is playing a catch-up game, similarly to Intel when ZEN came out.
 
As with every news this is being overblown, just like with itanium, if intel is going to do this in the first place, they will run it alongside the normal x86 for many years, they will only completely transition if and when normal x86 sales drop to such a low point that it wouldn't make any sense for them to keep it going.
As long as intel can keep making money from x86 they will keep making money from it.
 
The only people affected those running Older software which most people would not even consider nowadays.
There are always going to be people who fight changes. You can always run the older software in a virtual environment .
That backwards compatibility is an anchor holding both Intel and Amd back.
 
Me not so much. One of the many reasons I run a PC is because of backward compatibility. I still run a ton of old 32bit programs and games. This would be a product I'd refuse to buy because it simply wouldn't meet my computing needs. I guess its possible you could use an emulation layer but I would need to see this in action and even then I would prefer native compute over emulation any day of the week.
This is a misconception. This removes many extremely archaic modes. Most of these have to do with OS/BIOS-level code, like running 1980s DOS on bare metal. It very much does not remove the modern 32-bit-apps-on-64-bit-kernel modes – quoting the whitepaper:
The 32-bit submode of Intel64 (compatibility mode) still exists
This is what you use every time you run a 32-bit app on your regular modern Windows or Linux install today.
 
This is largely removing the "Legacy Modes" defined in the current x86-64 ISA. See (from here):
Acr98aW.png


So unless you're running a 32-bit version of Windows or some other OS that runs in one of those Legacy modes, this isn't going to affect your legacy application support.

Also fun fact, you can run 16-bit apps in Long Mode (the 64-bit mode in x86-64), but the only reason why you can't in Windows is because Microsoft didn't include any 16-bit compatibility shims like they did with 32-bit apps (also probably because they figured nobody was using 16-bit apps)
 
People who are not CPU engineers or software engineers, will never realize why this is such a great idea and how much time and energy it will save to ditch all that old crap. And nobody cares if you play old games, go play them on an old computer.

I cannot wait for the day when there’s no 32-bit anything left

Back in the day IA64 didn’t really stand a chance, but an idea like that could really be something now

People don’t seem to understand by eliminating unused functions. You can eliminate tons of testing and validation, which means you can eliminate tons of cost.

What is the best part in a system? The answer is, no part— which means eliminate as many parts as possible from the system to increase quality

Make it as simple as possible for the highest quality. Dr. Deming teaches us that
 
Last edited by a moderator:
  • Like
Reactions: Geef and Mr.Vegas
And the reason they ditched those shims ecause they don’t want all the extra work that goes with supporting the old code. I wish people could understand that this is a cost issue from the developer standpoint.
The only thing this affects are developers who work on OS and system firmware level stuff. As long as the system software has the appropriate shims, it doesn't matter what "bitness" the application was designed for.

I'm sure you know, but for the other people: when a 64-bit OS with 32-bit support runs a 32-bit application, an x86-64 CPU doesn't enter a legacy mode, it enters a sub-mode of Long Mode.
 
  • Like
Reactions: King_V and bit_user
Sorry
The only thing this affects are developers who work on OS and system firmware level stuff. As long as the system software has the appropriate shims, it doesn't matter what "bitness" the application was designed for.

I'm sure you know, but for the other people: when a 64-bit OS with 32-bit support runs a 32-bit application, an x86-64 CPU doesn't enter a legacy mode, it enters a sub-mode of Long Mode.
Sorry, I didn’t mean to reply to you sorry I liked your post. I am looking at this from a lean manufacturing and design process. Basically, if you know who Sandy Munro is—I’m like that too If I can ditch parts, I’m going to. When I’m developing stuff, I regularly ditch everybody’s junk and go with the smallest set of code that gets the job done and guess what? I never have to support it because it never comes back because it works because it can be thoroughly tested.

Modern CPU architectures need to move on. x86 has lived, and it’s ready to die. Think of all the extra testing that can be done if they don’t have to test all the crap that nobody uses? Why can’t people see that?
 
Sorry

Sorry, I didn’t mean to reply to you sorry I liked your post. I am looking at this from a lean manufacturing and design process. Basically, if you know who Sandy Munro is—I’m like that too If I can ditch parts, I’m going to. When I’m developing stuff, I regularly ditch everybody’s junk and go with the smallest set of code that gets the job done and guess what? I never have to support it because it never comes back because it works because it can be thoroughly tested.

Modern CPU architectures need to move on x86 has lived, and it’s ready to die
I think Intel sorely needs to do a simplification of modern x86, because the very least this hopefully means less silicon needed to support these things that nobody uses. And if anyone wants to go "but what if I want to run MS-DOS on my Ryzen 7900X"? ... yeah good luck with MS-DOS even knowing what SATA is.

If they do go down this route, I hope this also means they do a cleanup of the instructions as well. Maybe even turn x86 into a load-store architecture as best they can, especially when you consider MOV is probably the most commonly used instruction (going by https://www.strchr.com/x86_machine_code_statistics)

didnt intel already try this with IA64? and how it went, tho back then 32bit was dominant
You could say Intel technically tried it with IA-64, but IA-64 was a completely different beast from x86. I would argue at the time, Intel wanted to capture the HPC/server market with it (there were still like a half dozen competing ISAs at the time), and x86 would remain for consumer/office use.
 
Last edited:
Also fun fact, you can run 16-bit apps in Long Mode (the 64-bit mode in x86-64), but the only reason why you can't in Windows is because Microsoft didn't include any 16-bit compatibility shims like they did with 32-bit apps (also probably because they figured nobody was using 16-bit apps)
Since you brought it up, it made me remember this.
Probably has nothing to do with what you are saying, but might be helpful for some people.
 
  • Like
Reactions: Aurn
This is a misconception. This removes many extremely archaic modes. Most of these have to do with OS/BIOS-level code, like running 1980s DOS on bare metal. It very much does not remove the modern 32-bit-apps-on-64-bit-kernel modes – quoting the whitepaper:

This is what you use every time you run a 32-bit app on your regular modern Windows or Linux install today.
This is good to know but among those 32 bit apps I run include a few legacy 32 bit OSes to run them properly as they don't work in a modern OS. From my understanding, that is an issue with this archtechture. Thus my point. I will clarify in my post.
 
Last edited:
As with every news this is being overblown, just like with itanium, if intel is going to do this in the first place, they will run it alongside the normal x86 for many years, they will only completely transition if and when normal x86 sales drop to such a low point that it wouldn't make any sense for them to keep it going.
As long as intel can keep making money from x86 they will keep making money from it.
In my opinion, the problem with Intel Itanium was that Intel wanted to market Itanium as a extremely large profit margin product - not, as an upgraded version of 80806 without legacy/obsolete technology.
Today, Intel markets Xeon as the high-margin product/alternative to the 80806 architecture.
Obviously, Intel could market a version of Xeon as a HEDT alternative to 80806 HEDT but doesn't want to do that because it is trying to protect a high-margin product.
 
Microsoft had an excellent 16-bit virtual PC and an excellent virtual 32-bit PC - but, stopped supporting them.

Oracle supports Oracle VM VirtualBox which is almost as good - but, lacks some details of 80684 PC support and has a very limited selection of virtual hardware components.

A good virtual PC application provides a GUI interface that allows you to select various PC components (CPU, HDD, keyboard, mouse, video monitor, video adapter card, BIOS, motherboard, memory, etc) and build a virtual PC in the same way you would build a physical PC.

I completely agree with Intel dropping support for legacy/obsolete CPU technology - but, I would like to see the availability of excellent virtual PC apps supporting 16-bit PCs and 32-bit PCs hardware technology. The virtual PCs should run any hardware drivers supported on IBM, Compaq and Dell PCs in the 1980s and 1990s.

*******************************

It just occurred to me... generally people involved with building virtual-pc software often poop-out after they get much, but not all, of a PC hardware component virtualized. This is an area where AI technology would be enormously helpful.
 
Last edited:
  • Like
Reactions: Mr.Vegas
Me not so much. One of the many reasons I run a PC is because of backward compatibility. I still run a ton of old programsn OSes (the big issue) and games. This would be a product I'd refuse to buy because it simply wouldn't meet my computing needs. I would prefer native compute over emulation or VM any day of the week.

You run msdos and win95 on modern intel CPUs? thats not even an option, lack of drivers and insane speeds are the main reason.
And Windows 11/10 doesn't run most legacy software as it is.
What exactly do you run on modern hardware, what 32bit and 16bit software do you run on modern Intel CPUs?
 
People who are not CPU engineers or software engineers, will never realize why this is such a great idea and how much time and energy it will save to ditch all that old crap. And nobody cares if you play old games, go play them on an old computer.

I cannot wait for the day when there’s no 32-bit anything left

Back in the day IA64 didn’t really stand a chance, but an idea like that could really be something now

People don’t seem to understand by eliminating unused functions. You can eliminate tons of testing and validation, which means you can eliminate tons of cost.

What is the best part in a system? The answer is, no part— which means eliminate as many parts as possible from the system to increase quality

Make it as simple as possible for the highest quality. Dr. Deming teaches us that

100%, i was among the first who moved to 64Bit, the last day i used 32bit OS was when 64bit winxp beta came out.
People argued with me that its too early, there is no need, no benefit [I saw immediate benefit with the 4GB of RAM that i had now showing all of it and added a second 4Gb stick].

I believe that we ar at least 2 years too late, Intel had great chance when 64bit win11 came out [killing the old 32bit version that win10 had].
The way Intel goes and plans CPUs years in advance, i have a feeling it will take 5-10 years until we see it actually happen.
 
is because of backward compatibility.
IMHO this is why it still hasn't happened.
Yes, it can improve CPU's by forgoing the x86...but also destroys decades of stuff that rely on it being that way.
The amount of time/money companies/devs would have to put into updating for only x64 is crazy high.

They would need a sizeable benefit from doing it that people would justify the change.

Change does "need" to happen but x64 isn't the only choice in the long term future.
 
IMHO this is why it still hasn't happened.
Yes, it can improve CPU's by forgoing the x86...but also destroys decades of stuff that rely on it being that way.
The amount of time/money companies/devs would have to put into updating for only x64 is crazy high.

They would need a sizeable benefit from doing it that people would justify the change.

Change does "need" to happen but x64 isn't the only choice in the long term future.

Decades of what stuff? Can you please list all the software that was made for 32bit, 16Bit and 8Bit for the old OS that ruins without issues on modern hardware and Win10/11?

Old software doesn't work on modern hardware and OSes anyway, its a known issue, they still using old machine, all the specifically made soft, be it for NASA or accounting or ATMS or whatever else, still uses old hardware and old OSes they were build for.
When something breaks technicians look up for old hardware.

You cant even install and use windows 7 on modern hardware because there are no drivers, so something even older is out of the question.

Basically this hardware change wont change anything for people that use old software.
 
I wish there were some hard numbers, like transistor count saved, or potential performance gains from the greater simplicity.