login
Search
With Intel's recent announcement of the 64-bit extension to their x86 architecture, a discussion began on the lkml comparing Intel's new offering to AMD's existing AMD64 offering. Linux creator Linus Torvalds expressed extreme annoyance that AMD's involvement in developing this new technology was not mentioned. The Linux kernel will refer to both 64-bit x86 technologies as x86-64, though Linus suggested, "actually, I'm a bit disgusted at Intel for not even _mentioning_ AMD in their documentation or their releases, so I'd almost be inclined to rename the thing as 'AMD64' just to give credit where credit is due. However, it's just not worth the pain and confusion." Linus went on to clarify:
"What I found so irritating is that _hours_ after the Intel announcement, people were _still_ confused about whether the new intel chip was actually compatible with AMD's chips. Why the f*ck not just come out and say so, and talk about it? It took people actually reading the manuals (which didn't mention it either) to convince some people on the architecture newsgroups that yes, 'ia32e' was really the same as 'amd64' except in the small details that have always set Intel and AMD apart."
From: Linus Torvalds [email blocked] To: Kernel Mailing List [email blocked] Subject: Intel vs AMD x86-64 Date: Tue, 17 Feb 2004 17:44:33 -0800 (PST) Ok, now that Intel has finally come clean about their x86-64 implementation (see http://www.intel.com/technology/64bitextensions/index.htm?iid=techtrends+spotlight_64bit for full details), can somebody write up a list of differences? I know there are people who have had access to the Intel docs for a while now, and obviously Intel is too frigging proud to list the differences explicitly. From what I can tell from a quick look, it looks like it is basically just the 3DNow vs SSE3 thing, but I assume there are other details too. Can people who have been involved with this make a quick list for the rest of us who only got to see the final details today? (And I assume there's somebody with a few patches pending..) Thanks, Linus
From: Mikael Pettersson [email blocked] Subject: Re: Intel vs AMD x86-64 Date: Wed, 18 Feb 2004 10:56:44 +0100 Linus Torvalds writes: > > Ok, > now that Intel has finally come clean about their x86-64 implementation > (see > > http://www.intel.com/technology/64bitextensions/index.htm?iid=techtrends+spotlight_64bit > > for full details), can somebody write up a list of differences? I know > there are people who have had access to the Intel docs for a while now, > and obviously Intel is too frigging proud to list the differences > explicitly. From what I can see from these docs, Intel's "IA-32e" is very very close to the natural combination of P4 with AMD64. No hyperlink stuff, but otherwise the same. The local APIC and performance counters should be exactly as in P4 :-) What about naming? IA-64 is taken, AMD64 is too specific, Intel's "IA-32e" sounds too vague, and I find x86-64 / x86_64 difficult to type. "x64" perhaps?
From: Linus Torvalds [email blocked] Subject: Re: Intel vs AMD x86-64 Date: Wed, 18 Feb 2004 07:47:21 -0800 (PST) On Wed, 18 Feb 2004, Mikael Pettersson wrote: > > What about naming? IA-64 is taken, AMD64 is too specific, Intel's > "IA-32e" sounds too vague, and I find x86-64 / x86_64 difficult to type. > "x64" perhaps? x86-64 it is. Maybe you can remap one of your function keys to send the sequence ;) This whole "ia32" crap has always been ridiculous - nobody has _ever_ called an x86 anything but x86, and Intel is just making it worse by adding random illogical letters to the end. In contrast, x86-64 tells you _exactly_ what it's all about, and is what the kernel has always called the architecture anyway. Linus
From: Herbert Poetzl [email blocked] Subject: Re: Intel vs AMD x86-64 Date: Sun, 22 Feb 2004 03:59:57 +0100 On Wed, Feb 18, 2004 at 07:47:21AM -0800, Linus Torvalds wrote: > > > On Wed, 18 Feb 2004, Mikael Pettersson wrote: > > > > What about naming? IA-64 is taken, AMD64 is too specific, Intel's > > "IA-32e" sounds too vague, and I find x86-64 / x86_64 difficult to type. > > "x64" perhaps? > > x86-64 it is. Maybe you can remap one of your function keys to send the > sequence ;) > > This whole "ia32" crap has always been ridiculous - nobody has _ever_ > called an x86 anything but x86, and Intel is just making it worse by > adding random illogical letters to the end. > > In contrast, x86-64 tells you _exactly_ what it's all about, and is what > the kernel has always called the architecture anyway. hmm, so the current x86_64 will be changed to x86-64 or will there be x86_64 and x86-64? probably I missed something important, but AMD64 seems to be labeled x86_64 in 2.4 and 2.6 # ls linux-2.4.25/arch/ alpha/ cris/ ia64/ mips/ parisc/ ppc64/ s390x/ sh64/ sparc64/ arm/ i386/ m68k/ mips64/ ppc/ s390/ sh/ sparc/ x86_64/ # ls linux-2.6.3/arch/ alpha/ cris/ ia64/ mips/ ppc64/ sparc/ v850/ arm/ h8300/ m68k/ parisc/ s390/ sparc64/ x86_64/ arm26/ i386/ m68knommu/ ppc/ sh/ um/ TIA, Herbert
From: Linus Torvalds [email blocked] Subject: Re: Intel vs AMD x86-64 Date: Sat, 21 Feb 2004 19:12:20 -0800 (PST) On Sun, 22 Feb 2004, Herbert Poetzl wrote: > > hmm, so the current x86_64 will be changed to x86-64 or > will there be x86_64 and x86-64? No. The filesystem policy _tends_ to be that dashes and spaces are turned into underscores when used as filenames. Don't ask me why (well, the space part is obvious, since real spaces tend to be a pain to use on the command line, but don't ask me why people tend to conver a dash to an underscore). So the real name is (and has always been, as far as I can tell) x86-64. Actually, I'm a bit disgusted at Intel for not even _mentioning_ AMD in their documentation or their releases, so I'd almost be inclined to rename the thing as "AMD64" just to give credit where credit is due. However, it's just not worth the pain and confusion. Any Intel people on this list: tell your managers to be f*cking ashamed of themselves. Just because Intel didn't care about their customers and has been playing with some other 64-bit architecture that nobody wanted to use is no excuse for not giving credit to AMD for what they did with x86-64. (I'm really happy Intel finally got with the program, but it's pretty petty to not even mention AMD in the documentation and try to make it look like it was all their idea). Linus
From: Adrian Bunk [email blocked] Subject: Re: Intel vs AMD x86-64 Date: Mon, 23 Feb 2004 18:03:36 +0100 On Sat, Feb 21, 2004 at 07:12:20PM -0800, Linus Torvalds wrote: >... > Actually, I'm a bit disgusted at Intel for not even _mentioning_ AMD in > their documentation or their releases, so I'd almost be inclined to rename > the thing as "AMD64" just to give credit where credit is due. However, > it's just not worth the pain and confusion. >... In the long term, x86_64 creates more confusion: - SuSE says AMD64 [1] - RedHat says AMD64 [2] - Debian says AMD64 [3] Renaming might be some work today, but it might actually remove confusion in the future. > Linus cu Adrian [1] http://www.suse.com/us/business/products/server/sles/amd64.html [2] http://www.redhat.com/software/rhel/comparison/ [3] http://www.debian.org/ports/ -- "Is there not promise of rain?" Ling Tan asked suddenly out of the darkness. There had been need of rain for many days. "Only a promise," Lao Er said. Pearl S. Buck - Dragon Seed
From: Linus Torvalds [email blocked] Subject: Re: Intel vs AMD x86-64 Date: Mon, 23 Feb 2004 09:31:02 -0800 (PST) On Mon, 23 Feb 2004, Adrian Bunk wrote: > > In the long term, x86_64 creates more confusion: > - SuSE says AMD64 [1] > - RedHat says AMD64 [2] > - Debian says AMD64 [3] > > Renaming might be some work today, but it might actually remove > confusion in the future. Well, the thing is, I _like_ a vendor-neutral name. I think it's important to have multiple sources for a chip, and I think one of the problems with IA-64 was that it was a locked-in chip with patents and no serious competition internally (ignore the Intel mouthing about "open"). The x86 is so great partly because there's been real competition. So I think it's very important to x86-64 to have real competition to make sure nobody gets too dishonest. So AMD64 is a bad name, partly for the same reason IA32 is a horrible name (and who have you ever heard use the IA32 name except for people who are paid to do so by Intel?) What I found so irritating is that _hours_ after the Intel announcement, people were _still_ confused about whether the new intel chip was actually compatible with AMD's chips. Why the f*ck not just come out and say so, and talk about it? It took people actually reading the manuals (which didn't mention it either) to convince some people on the architecture newsgroups that yes, "ia32e" was really the same as "amd64" except in the small details that have always set Intel and AMD apart. So I don't really want to change the name. "x86-64" is a good name. I just wish there was more honesty involved, and less friggin *POSTURING*. Linus
From: Rik van Riel [email blocked] Subject: Re: Intel vs AMD x86-64 Date: Mon, 23 Feb 2004 16:25:56 -0500 (EST) On Sat, 21 Feb 2004, Linus Torvalds wrote: > I'm really happy Intel finally got with the program, With the program? They still don't have an IOMMU ;) -- "Debugging is twice as hard as writing the code in the first place. Therefore, if you write the code as cleverly as possible, you are, by definition, not smart enough to debug it." - Brian W. Kernighan
From: Linus Torvalds [email blocked] Subject: Re: Intel vs AMD x86-64 Date: Mon, 23 Feb 2004 13:36:43 -0800 (PST) On Mon, 23 Feb 2004, Rik van Riel wrote: > On Sat, 21 Feb 2004, Linus Torvalds wrote: > > > I'm really happy Intel finally got with the program, > > With the program? They still don't have an IOMMU ;) Hmm.. Let's see what their chipsets will look like for this thing. Since they don't have an integrated memory controller, they can't very well do the IOMMU on the CPU, now can they? So you can't blame them for that. Linus
From: David S. Miller [email blocked] Subject: Re: Intel vs AMD x86-64 Date: Mon, 23 Feb 2004 13:48:53 -0800 On Mon, 23 Feb 2004 13:36:43 -0800 (PST) Linus Torvalds [email blocked] wrote: > On Mon, 23 Feb 2004, Rik van Riel wrote: > > On Sat, 21 Feb 2004, Linus Torvalds wrote: > > > > > I'm really happy Intel finally got with the program, > > > > With the program? They still don't have an IOMMU ;) > > Hmm.. Let's see what their chipsets will look like for this thing. Since > they don't have an integrated memory controller, they can't very well do > the IOMMU on the CPU, now can they? You mean the PCI controller is in the CPU, else how else would you accomplish this? Or are you suggesting something else? Really, not having an IOMMU on a 64-bit platform these days is basically like pulling out one's toenails with an ice pick.
From: Linus Torvalds [email blocked] Subject: Re: Intel vs AMD x86-64 Date: Mon, 23 Feb 2004 14:08:40 -0800 (PST) On Mon, 23 Feb 2004, David S. Miller wrote: > > You mean the PCI controller is in the CPU, else how else would you > accomplish this? The IOMMU basically needs to be on the northbridge or at least in between the PCI bus an a northbridge (pretty much by definition: the bridge between IO and memory). On an Opteron, that's on-the-chip. For current Intel chips that's a separate chip. In fact, I _think_ you could actually use the AGP bridge as a strange IOMMU. Of course, right now their AGP bridges are all 32-bit limited anyway, but the point being that they at least in theory would seem to have the capability to do this. > Really, not having an IOMMU on a 64-bit platform these days is basically like > pulling out one's toenails with an ice pick. Well, as long as they had that "64-bit is server" mentality, they can honestly say that you just have to use 64-bit-capable PCI cards. Now, the "server only" mentality is obviously crap, but since we haven't even seen the chipsets designed for the 64-bit chips, we shouldn't complain. At least yet. Now, I'm not above complaining about Intel (in fact, the Intel people seem to often think I hate them because I'm apparently the only person who gets quoted who complains about bad decisions publicly), but at least I try to avoid complaining before-the-fact ;) Linus
From: David S. Miller [email blocked] Subject: Re: Intel vs AMD x86-64 Date: Mon, 23 Feb 2004 14:06:47 -0800 On Mon, 23 Feb 2004 14:08:40 -0800 (PST) Linus Torvalds [email blocked] wrote: > In fact, I _think_ you could actually use the AGP bridge as a strange > IOMMU. Of course, right now their AGP bridges are all 32-bit limited > anyway, but the point being that they at least in theory would seem to > have the capability to do this. Ok, I see. In fact, I remember some vague notion that the AGP bridge on the Athlon's could technically be used as a full-on IOMMU, especially since it was all derived from Alpha PCI chipsets which did use things this way.
Marketing
The science of marketing is basically incomprehensible to rational thinking people and it is only growing more complex as its fearless pioneers continue to push the limits and make more breakthroughs.
It is not physics, engineering, chemistry, not even economics, but marketing that is is the dominant driver behind companies like Intel. Most companies with more than 5 people, actually.
You and I would think that if they concentrated on making the best products in their field, the marketing would be just about all done for them. Not so.
Linus is way out of his league here. Someone tell him to go back to hacking kernels before he makes a bigger fool out of himself.
Marketing is a matter of degree
Selling soap would require more marketing. Technical stuff less so. The problem is that MBA's see everything as soap.
...
Yeah but most companies are marketing first and making good products second for crying out loud.
This case with Intel. They don't announce it is compatible with AMD. If they didn't announce it then it is because they don't want you to know about it (because if they did want you to know then by crickey they would let you know).
So they are trying to intentionally mislead customers about compatibility. Obviously software developers and resellers will know pretty quickly, so the answer doesn't lie there. They are trying to mislead the chipnologically challenged average person.
Why do they want to do that? Probably so they can try to continue to spew their endless tiresome rhetoric about being the leaders and AMD just copying them.
How about they instead aim to actually be leaders? All the benefit without any of the misleading and dishonesty, and they can fire 90% of the marketing department to boot.
ignorance is bliss
Average people just see "Windows" on the box, and leave it at that. They don't worry about compatability, and in this case, they'll be okay with that attitude.
If that's the case, why are t
If that's the case, why are there so many adverts on mainstream TV for PCs touting "the latest Intel Pentium 4 processor"? Average people go for what they know, and that's what's thrust in their face daily, namely Microsoft, Windows and Intel.
Nonsense
Nonsense! Average people *think* they're going to go for Microsoft, Windows and Intel, but when they get to the shop, they buy what I tell them to buy. Unless they are g4mer 1337 5cr1p+ k1dd135. Apart from them, everyone.
leaderchip
I don't think it is about who is the leader and who's not, sorry.
IMHO, Intel is more afraid to state that they will offer the same thing than AMD, but that it wont be available soon.
Let's say your a decider, you have to make a choice for your next equipments, and you want 64-bit CPUs.
- If you think there will be 2 different 64bit platforms, you will certainly wait that both are available in order to evaluate which set of instructions is better.
- If you know that both CPUs will use the s-a-m-e 64bit instructions, but that AMD did the engineering, has the knowledge, and already has several 64bit products on the shelve... THEN you will certainly be more inclined to buy AMD solution. Without waiting for Intel products.
Time to Market is the key thing nowadays.
Re: Marketing
naah - its refreshing to see someone honest for a change. Linus says and does what he believes is right without caring of it might hurt Intel's (or Microsofts or whatever company it happens to be) pride.
speak up
No, it's about time people speak up against the lies, total lack of honesty and arrogant idiocy of some of the big corporations. I demand respect from a company that might or might not receive large parts of my money, for products that have a big importance in my business. This kind of behavior doesn't give me faith at all. I expect direct and honest communication; if they can not do that *before* I even get a chance to buy a product, how can I trust them *after* I bought it, or the product itself?
Turn it like you want, marketing these days is mostly a bunch of lies. It is incomprehensible to rational thinking people, because they don't understand how ethically disabled people can make a job out of bending the truth and screwing others over. What kind of job is that, to get paid only for spreading (half) lies and misinformation?
I know not all marketing efforts should be judged this hard, after all, products need to be sold, but in my eyes, there is no excuse for this kind of dishonest and honorless behavior. Have some dignity.
People have a right, even stronger, people *should* speak out on behavior that looks unethical and unfair in their opinion.
I can't even remotely understand how you seem to call these people "fearless pioneers" and imply that this behavior is some kind of "breakthrough". This behavior was wrong, and if you don't agree with that, I believe I don't like you. :)
"science of marketing" ? well
"science of marketing" ? well, it simply cannot be put under the science tag please. get the best marketing guy on earth or beyond, and he'd still have to gamble on his next big bet, he'd never be able to predict anything for SURE. his ass is always on the line. marketing is basically chance, and seeing how the herd moves. marketing is based and left extremely to the chance. yes, the two breeds are very different - marketing and coders or rational thinkers as you would like to put it. but surely linus was talking common sense, and its not very far from marketing. common sense plus shepherding the "joe" herd is marketing. i donot see any fault of linus here. okay, he's outright brutal in his conclusions - but thats his right to free speech. everyone cannot be friggin silent abt corporate policies. i will never be heard if i were to rave and rant. well, if linus does it, intel cant run away from - that they wouldnt give a damn might be different. they'd do that anyways.
broken link
tux.org and www.tux.org is not the same
Re: broken link
Bug reports are considered flamebait comments too. I see...
re: broken link
I've fixed the link. Interestingly enough, if you check the past couple years of KernelTrap.org archives you'll see that I've always been linking to tux.org/lkml (without www).
It may be a moot point, as today it appears that tux.org was updated to redirect www.tux.org...
grammar nazi
So just to be a bit harder on you, jeremy, it's a 'moot' point. It's not a 'mute', or silent point. Heh. But that's okay, we still love ya.
Seems somebody at Intel heard you!
Though, I think it's funny... "Entirely different architectures".... On the Silicon, maybe. Instruction sets? Hardly. And if they want ultimate stability, they'd code for the common denominator. ;P
http://www.intel.com/technology/64bitextensions/faq.htm
Q9: Is it possible to write software that will run on Intel's processors with 64-bit extension technology, and AMD's 64-bit capable processors?
A9: With both companies designing entirely different architectures, the question is whether the operating system and software ported to each processor will run on the other processor, and the answer is yes in most cases. However, Intel processors support additional features, like the SSE3 instructions and Hyper-Threading Technology, which are not supported on non-Intel platforms. As such, we believe developers will achieve maximum performance and stability by designing specifically for Intel architectures and by taking advantage of Intel's breadth of software tools and enabling services.
*Other names and brands may be claimed as the property of others.
-Chad
chad@gambitnospam.net
64-bit extension technology FAQ available after keynote
Actually, the FAQ linked to above was available immediately after the IDF disclosure of the 64-bit extension techology. This should have been a basis for understanding the compatibility of the 2 implementations and it was available immediately.
How do the processors run?
A bit offtopic, but do any of you have one of these AMD64/Intel64 (probably not the latter ;) ) processors already, and if so, how do they run, speedwise and heatwise? What about stability of existing code?
AMD Opteron is wicked fast
Running 64-bit Red Hat Enterprise Linux, a dual-Opteron
box is something to behold.
Note that the plain Athlon64 has a narrow memory bus,
while the Athlon64-FX is like an Opteron w/o SMP.
Get the FX version if you want a single fast CPU.
(the wide bus does require paired memory modules BTW)
Re: How do the processors run?
One of our servers at work is an IBM eServer 325 with 1.4GHz Opteron CPUs and 2GB of RAM (soon to be 4GB). It's currently running Slackware Linux 9.1 (yes, 32bit dist, I know, but that's the company standard dist) with a custom 2.6.3 kernel and it's kicking serious ass.
I've got a Destkop Amd64 3000
I've got a Destkop Amd64 3000+ running Gentoo Linux in 64bit mode. There are still some 64bit issues around - in 99 of 100 cases some segfaults because of unsafe type handling. But most issues can be resolved quite easily.
It runs great - stability wise too. I was impressed by the speed I got for the buck.
Just my 2 cents ;)
Dash to underscore in filenames
For the one that is wondering about the remarks about dash to underscore in filenames, IIRC that used to be done because there were several getopt like systems on Unix, and a lot of people rolled their own.
A lot of them simply scanned for dash (and not space dash)
checking for space dash it no
checking for space dash it not necessary, since each argument is delivered in a seperate string in char ** argv (or $1,$2..$n if you prefer shell scripts), so checking for argv[i][0]=='-' would be enough.
MS banging heads together ?
One rumour I've heard is that MS sat Intel down and told them that if their new 64 bit extensions were not compatible with AMD's then they were not going to port their code to it.
Probably worth taking with a couple of tons of salt though.. :-)
could be
I read that Microsoft told intel they weren't going to support to x86 64 bit instruction sets and Microsoft also told intel they were already going with AMD.
The truth!
Microsoft, long before any of this was anywhere near ready, announced that they would support exactly /one/ 64-bit architecture extension, and that it would be the first viable, successful one they saw. AMD got there first.
heresay - existing P4 may already have IA_64 support
I'm not posting this on /. because I don't want to deal with the type of responses it's likely to result in because it's heresay but here goes...
So, I was speaking to a drunk guy, who was laughing his ass off because he claims that this 'new' architecture from Intel is exactly the same silicon as the P4. He explained that there is a _legitimently_ documented bit (IA_64) that everyone has been overlooking (IA_64) that isn't actually a read-only flag (IA_64) that enables the 64-bit instructions (IA_64)...in today's shipping P4s!
Would anyone be up for the challenge of writing a quick DOS program to test this out? Can't remember if you have to pop into protected mode or not to enable the flag but I'm sure someone smarter than I could figure it out...
Of course this is all just heresay...might be worth taking a few minutes to confirm or deny though...I know I'd be interested to see the results.
Cheers,
A Little Birdie
This person is confused (or h
This person is confused (or had too much to drink). There is an IA-64 flag in the CR registers for Intel processors. This register indicates exactly what it states, that the processor is an IA-64 (EPIC architecture, ie, Itanium processor) to OSes and code that are accessing the CR registers (usually 32bit programs that are running on Itanium processors).
This register has nothing to do with P4 processors, including the ones that will feature the 64-bit extension technology. Read or write this bit as much as you like.. it will have no effect (except maybe generating a GPF).
Not all P4
Only most recent P4, codenamed Prescott and dubbed 'E' version (2.8E, 3.0E, 3.2E) have dual 32-bit cores.
--
:wq
the big deals companies
did someone heard about 64-bit desktop processor from china ?
I think the real big one will come very soon. So I hope the prices will be more attractive for customers 'cause the competition becomes more hard.In any case, this is well for all of us.
China advances home-grown chips
You mean that[1] one?
[1] China advances home-grown chips