Intel Opens Its Front-Side Bus 185
vivin writes "The Inquirer is reporting that Intel has opened up its FSB. Intel did this during IDF 07. What this means is that you can plug non-Intel things into the Intel CPU socket. The article says 'This shows that Intel is willing to take AMD seriously as a competitive threat, and is prepared to act upon it. In addition to this breaking one of the most sacred taboos at Intel, it also hints that engineering now has the upper hand over bureaucracy.'"
Not the first time (Score:5, Interesting)
The old Socket 7 [wikipedia.org] used to fit Intel and AMD and Cyrix.
Hell, it can even house socket 5 cpus!
Back then it wasn't a big deal to upgrade a CPU.
All the companies started changing sockets at a frantic pace and made a simple CPU update essentially mean a whole machine.
A new motherboard for the new socket but it also has new memory footprint as well so that gets replaced, and the PCIx slot won't fit my agp card.
Re: (Score:2)
I'd like more memory, but that would mean a new motherboard (it currently has all the memory installed it can take). Since I don't want to upgrade my CPU yet, it means buying a motherboard that won't let me upgrade my CPU if I want to in a few years.
Re:Not the first time (Score:5, Informative)
IIRC, the socket-7 issue was not that Intel *wanted* others to use the technology, but rather that their license agreements with various other manufacturers allowed the rest of the industry to use it.
The only reason that Intel is opening up their FSB this time around is because they will be forced to use HyperTransport [zdnet.com] if they *don't* open it up (a royalty-free deal, to boot).
Their already using AMD64 and with AMD's new processors showing promise, Intel are really scratching and clawing here. I don't have the knowledge to pick a bus based on merit but, from what I've read, Hypertransport is better. Can anyone with experience here chime in?
Do we want Hypertransport or Intel's bus? What about licensing?
Re:Not the first time (Score:5, Informative)
Do we want Hypertransport or Intel's bus? What about licensing?
HT can run with approximately twice the number of transfers per second per pin as current-generation Intel FSBs. HT is also more readily expandible to use more pins, because it's an autonegotiating variable-width bus, similar to PCI-express. It also wastes fewer pins on control signals. HT is clearly the best, technologically.
Licensing wise, HT is licensed "royalty-free" for an annual fee. I don't believe the fee is particularly large. Many chip producers have already licensed it and will license modules to connect your own chip design to it for very small fees. Such modules exist on some modern FPGAs. This is not currently true of the Intel FSB spec.
Re: (Score:3, Insightful)
I really don't think it would necessarily be heads-and-shoulders better than Hypertransport though.
Re: (Score:2)
On a different note, the Inq article mentions that "it is one of the 'thou shalt nots' of the Intel competition manual, how it forced AMD to make their own bus." I think history has shown that AMD will always end up with a better bus. For the athlon, they used the aplha e
Re: (Score:2)
That is the date that I am seeing when clicking on the link
Re: (Score:3, Funny)
Re:Not Invented Here!!!! (Score:4, Funny)
Re: (Score:2)
Re:Not the first time (Score:5, Funny)
SHyT has a nice ring to it.
Re: (Score:2)
Re: (Score:2)
Re: (Score:2)
Re: (Score:2)
Will this make it less confusing? (Score:5, Insightful)
I had an AMD Duron 800MHz that I tried to replace with an Athlon 1300MHz which should have been supported, but created a nifty column of smoke when I plugged it in. Anything that reduces that likelihood is good in my book.
Peter
Re: (Score:2)
Re: (Score:2)
No it won't.
Those days have long since passed. Socket 939 CPUs work in 939 motherboards. AM2 chips work in AM2 motherboards, etc. The socket A days had the occasional unpleasant compatibility surprises, but with decent quality motherboards, any chip would work, though perhaps at a slightly lowe
Re: (Score:2)
There were 2 types of opterons, the 940 pin (server boards only) and the newly released 939 pin compatible opterons (works in any desktop 939 pin board).. this allowed a better sliding scale in terms of price and performance with a huge motherboard base.
Myself I opted for a lower clocked opteron 939 pin and then just overclocked it to 2.4ghz, got a 300+dollar cpu for 150 bucks (dual core too).
Does this really make sense? (Score:5, Interesting)
I'm not sure how much sense this statement really makes. If they take AMD as a serious threat, wouldn't they WANT AMD to be forced to continue using their own bus? AM2 was probably a misstep, given the performance drops, giving intel the upper hand, but now they are willing to let AMD play in their sandbox - it helps AMD more than it hurts them.
I'm not complaining about the move, I just found the article a bit sparse on details and the statement at odds with common sense. Is it fully open, or does it require licensing? What is AMD's take on this news? How much re-work will be required to move AMD's processor cores to the intel bus? Will they gain performance or lose it in the translation?
Lots of questions that the Inquirer seems to totally ignore in what may be a significant development in the battle of the big boys.
Re: (Score:2)
Re: (Score:2, Insightful)
Re: (Score:1)
Re: (Score:1)
Not at ALL what you are thinking: (Score:5, Informative)
Intel is not trying to open their bus up to AMD. That is not at all the goal. First of all, access to the the Intel bus requires a license. I'm not sure Intel would even grand AMD one for a sane price. Second of all, AMD would in no way want Intel's bus. As has been the hot topic of discussion for over a year, AMD's HT (HyperTransport) point-2-point links are faster both in terms of bandwidth, and latency than Intel's FSB. HT uses less pins than Intel's bus, and HT devices are simpler, cost less, and use less power. HT is a pretty neat and effective technology. Intel's FSB on the other hand, is much the same as it was around 10 years ago. To answer your question, AMD would take a massive hit by going to Intel's POS bus. It's funny, ATM, AMD has the better bus/platform and Intel has the better core. No one here seems to realize that AMD would never be willing to throw out their main advantage right now... AM2 isn't the issue. The issue is HT. Hell, even IBM announced that Power7 will use AMD's HT links. No one will be dropping HT for the POSFSB any time soon.
Intel/AMD are only opening their sockets/buses in an attempt to get third party developers to make FPGAs, JAVAics, and other accelerators. AMD has had some luck with this, and one can buy co-processors that drop into an AMD socket today. Intel is trying to get the same benifits, but I don't really see the point until Intel can get CSI working and drop the antiquated FSB.
Re: (Score:2)
Re: (Score:2)
That works fine for a few processors (4) if you put in a really big cache. However it fails to scale as well as HT in a machine with more processors and NUMA, when you have a workload that's god good localization.
Re: (Score:2)
Re: (Score:3, Informative)
That's just wrong. AM2 was simply AMD switching to DDR2 RAM. It didn't cause a performance drop, just no immediate performance improvement over socket 939 with DDR, and there's nothing they could have done to change that, except trying to force manufacturers around the world to produce faster DDR RAM.
Even with the higher latency of DDR2, AMD still has a much faster bus, and lower latency, than Intel. And even if the oppo
Re: (Score:2)
No i'm pretty sure it's right, AM2 did have some performance drops when it first came out (compared to 939), but this is to be expected as DDR2 has a high latency hit compared to mediocre speed improvements, 533+/- FSB of DDR2 compared to 400 FSB of DDR but double the latency. It is only with going to 800FSB speed DDR2 and beyond that AM2 will s
didn't it used to be this way? (Score:3, Interesting)
And by CPU, I DON'T mean the case and everything inside
Re: (Score:2, Funny)
Yea, that'd be the "modem".
Re: (Score:2)
No, that's the "hard drive".
Re: (Score:3, Funny)
It was kinda amusing one day we were sitting in the office and some professor comes in frantic that "Somebody stole my hard drive!!!?!?!?!".
We were all sitting there thinking "What person is gonna take the time and effort to open up the machine and take the hard drive? This guy must have secret flux capacitor plans on there or something.". We get to his office and the whole computer is gone . . .
Re: (Score:2)
You could get fun add-ons like the Weitek 3167, which was a floating-point coprocessor for the 386 that was several times faster than Intel's 80387.
Re: (Score:2)
Tom
Re: (Score:2)
Even before then. I remember using an IBM PC-XT in which my dad had swapped out the stock Intel 8088 CPU with a faster-running NEC V20.
Re: (Score:2)
Re: (Score:2)
Yup, that's how they got started... Right before Intel sued them.
Because of Intel's second-supplier contract with IBM, AMD earned the right to continue using Intel's existing (Socket 7) board, but not future boards, which was the birth of the Athlon and Slot A (later Socket A) boards.
Cyrix did a little patent-tradin
Re: (Score:3, Informative)
chip speed (bus speed @ multiplier)
386dx 40 (40 @ 1x)
486dx 50 (50 @ 1x)
486dx2 66 (33 @ 2x)
486dx2 80 (40 @ 2x)
486dx4 100 (25 @ 4x, 33.3 @ 3x, even 50 @ 2x with proper cooling)
486dx4 120 (40 @ 3x)
I used to have this one but sold it:
k6-2 350 (100Mhz @ 3.5x)
AMD had more chips than this, including the k5, k6, and k6-3. I never owned any of those, so I don't remember the specs off the top of my head. After the k6-2 and k6-3 came the Socket A and Slot A Ath
Explanation please? (Score:1)
Re: (Score:2)
More precisely, Intel is taking AMD's HyperTransport seriously. AMD has already made HyperTransport available to other hardware manufacturers to build add-on chips for specialized processing or whatever else. Think of it like the Cell processor, only you and mix and match different "cells" and each "cell" is designed for a specific task (video encoding/decoding, encryption, compression, etc), making it much fa
For the motherborad section? (Score:4, Interesting)
Perhaps they think it wise to sell products that can be used even if their competitor gets a few bucks- until today didn't they effectively yield the floor for AMD motherboards to other companies?
Couldn't there be some sort of trap here? (Score:4, Insightful)
The other companies probably don't worry Intel much. VIA might make something, but I highly doubt they could manage to make anything that'd take any significant market from Intel, given what they've been releasing.
Re: (Score:3, Interesting)
But that raises the same point. The open socket could be used for something other than a processor. Like another FPGA accelerator.
Tom
Re: (Score:2)
Actually, HT isn't open. It's licensed royalty free to members of a consortium who have to pay annual membership fees.
Of course, the fact that they don't pay any per-device royalties means they can sublicense that tech to you (e.g. by including it on an FPGA) really cheaply.
Re: (Score:2)
Re: (Score:2)
A lot of it depends how quickly you change CPUs (Score:4, Insightful)
TBH, these days, for general desktop use I don't think that benefit's there any more. If you want to see a real benefit, you're best off replacing the CPU with something drastically faster. This may well involve a new motherboard and possibly new memory.
Alternatively, you upgrade the more sensible way - look at your computer needs, look to see what's causing a bottleneck currently and upgrade that. Much more cost-effective than just replacing a CPU and hoping you see a benefit.
Re: (Score:3, Insightful)
Way back when, there used to be a real benefit to upgrading your 133MHz PC to 200MHz and it was easy to do so just by changing the CPU.
Quite - though as a percentage that was a significant upgrade.
In the days when every MHz counted, we all clawed to be at the cutting edge because upgrading really made a noticeable difference (not just to games, but the speed of everyday activities). Now the effect is less noticeable except in games as a FPS increase or the ability to turn on extra effects.
I remember a lecturer at Uni asking us if we thought that the 200MHz CPU speeds of the time would increase, citing Moore's Law and questioning whether
Re: (Score:2)
Re: (Score:2)
Wait until you see the minimum system requirements for Microsoft Word 2017...
Re:A lot of it depends how quickly you change CPUs (Score:5, Informative)
100GHz is probably pushing it. You'll note that we haven't seen a huge increase in clock speeds recently, but rather continuing increases in instructions per cycle. I'd guess we'll reach a plateau somewhere around the 10GHz mark.
Moore's Law will soon hit a much more fundamental law: physics. You can't keep shrinking transistors like they are at the moment; it was predicted that we'd reach the limit years ago (yes, I too remember the advent of 200MHz desktop processors, and thinking they couldn't get much faster), but the fact we haven't so far doesn't mean we won't. Moore's Law demands a shrinking by a factor of 1.4 every 18 months. We're currently on 45nm. This gives us the following trend:
end 2008 - 32nm
start 2010 - 22nm
end 2011 - 16nm
start 2013 - 12nm
end 2014 - 8nm
start 2016 - 6nm
end 2017 - 4nm
4 nanometres is only 38 atomic radii of silicon. It seems unlikely that a transistor this small could be produced. Therefore, as long as we continue to use silicon transistors (and no promising alternative that solves this issue exists right now) we will see the end of Moore's Law within the next 10 years. I'm sure of it.
And an end of Moore's Law will not only slow GHz increases, but also will slow the adoption of larger numbers of cores, because without shrinking transistors the only way to increase number of cores is by having a larger die size, which is more expensive and requires larger chip size, which requires larger system board size, which requires larger case size, which consumers don't like.
Re: (Score:2)
4 nanometres is only 38 atomic radii of silicon.
Correction: It's the Van der Waals radius that's important, not the atomic radius. A 4nm length of crystalline silicon will contain just 19 atoms. Seems even more unlikely we'll get there now.
Re: (Score:2)
There was a time when (almost) all that counted was the switching power. These days leakage power is coming close, from a certain temperature on it becomes even dominant. Now imagine how this picture will look like at 4nm when no significant fabrication technology change happens.
Re: (Score:2)
See? Already a 50% improvement in processing power.
Re: (Score:2)
Re: (Score:2)
Fast
Cheap
Good
Pick two of three.
Re: (Score:2)
I agree with you-- fairly soon we are going to be into areas where quantum effects and simple atomic size are going to be problems. Barring a fundamental change in technology (some sort of single electron transister), I suspect you are right.
Re: (Score:2)
And what determines the number of transistors at minimum component cost, other than the size of the transistors? Using current fabrication techniques, AFAIK the cost of a fixed area of die is pretty much constant. Therefore, a decrease in feature size of sqrt(2)
Re: (Score:2)
Re: (Score:2)
Ah, the bad old days.
Re: (Score:2)
It sure made overclocking easier...
Re: (Score:2)
Of course people like that do need a fast PC and lots of RAM, to keep up with all the malware they will be running.
FPGAs, anyone? (Score:3, Interesting)
Re: (Score:2)
The reason it's a response to AMD (Score:4, Informative)
And yes, the bus speed matters. I've seen neural net tests in which Woodcrest, for example, does much better at 1333MHz using four cores than you'd see at 1066MHz. That's the same architecture except for bus speed. AMD's memory bandwidth is still better, though they lag in other areas.
I don't know whether, or how much, you'll see that bus bandwidth matter in the typical slashdotter workload (games).
Re: (Score:2)
How fast would a neural net run if you coded it into one or more FPGAs and had a few dual core cpus feeding them data?
It does open up some interesting options.
nVidia users HT in Intel chipsets (Score:3, Interesting)
Re: (Score:2)
When your motherboard comes with an extra HT socket into which you will be able to plug in an "acceleration coprocessor" (read: GPU/Physics processor), you'll see the value of bus bandwidth. PCI-Express is already fully utilized on high end video cards (for burst traffic), and the latency does not allow a pcie device to be used as a coprocessor, just a batch processor of relatively large jobs
I like Intel but... (Score:3, Insightful)
When they have to spell it out for you what their actions supposedly "hint" at, you know you're reading quite a silly PR spin on the matter.
Conquering Heroes? (Score:2)
Some encouragement of competition. "We'll complete as long as we're winning."
I wonder if other companies will decide to get into the desktop CPU markets and use this as a starting point.
Unsupported conclusion (Score:2)
In addition to this breaking one of the most sacred taboos at Intel, it also hints that engineering now has the upper hand over bureaucracy
No decisions involving that much money are left to engineers.
Engineers are the people who say, "You know what would be cool?" and then lay out an idea. The bean counters study it, perform an analysis, and then decide if there is money in it. If there is, then the idea is given a green light. If not, no matter how cool the idea is - it gets buried.
Remember, we'r
a lot of companies (Score:2)
How useful is this really? (Score:2)
Re: (Score:2)
"Does this "opening" include CSI as well, (pause for dramatic effect, put on sun glasses)....or will anyone who accepts this be stepping into rapidly obsolete technology?" BAHWAAAAAAAaaa.
Re: Intel Opens Its Front-Side Bus (Score:4, Insightful)
Re: (Score:2)
Re: (Score:1, Flamebait)
Re:wow (Score:5, Insightful)
so why would anybody want to plug in an AMD processor there unless it was hugely cheaper or more powerful?
For starters, intel's frontside bus is just that, a good old-fashioned FSB that hasn't changed much in years.
AMD's processors have something completely different. Not only is it physically incompatible, it's actually "Hypertransport" which is marketing speak for a chip-to-chip interconnect [wikipedia.org]. Look at all the big iron manufacturers supporting it. Note no intel. AMD has been shipping these processors since 2003. Intel's (incompatible) equivalent isn't due out until 2008. Other manufacturers have been shipping CPUs with similar interconnects since the mid 1990s (UltraSPARC, MIPS).
AMD processors implement NUMA [wikipedia.org] via this interconnect. Each CPU can have its own local memory. On an intel system, all processors compete for bandwidth over the shared FSB
This is why Opteron/Athlon 64 systems scale well past 2 processors. This is also why it will be easier to make e.g. graphics processors that fit in AMD motherboards.
intel processors may currently do better on selected synthetic benchmarks and niche applications. AMD, however, has a far more sophisticated, modern and scalable platform. Intel set sail on the itanic.
Re: (Score:2)
Re: (Score:2)
Re: (Score:3, Insightful)
This looks like an AMD fanboy if I ever saw one.
Re:wow (not?) (Score:2, Interesting)
But it sure is good. It may encourage others to make CPUs without the need to develop their own chipsets, FSBs, motherb
AMD vs. Intel, but not so literally. (Score:5, Informative)
That was a while ago, but I suspect it's coming to fruition or perhaps gaining more traction, if only now Intel is saying "me too."
http://news.zdnet.com/2100-9595_22-528221.html [zdnet.com]
Re: (Score:2)
Technically, HyperTransport is not a (shared) bus but a point-to-point link, just like PCI Express, Serial ATA, etc.
Re: (Score:2)
Re: (Score:1)
Re: (Score:1)
How about some open source hardware company take this up and develop a LinChip?
With openbios and a mips style chip designed for linux.... imagine the possibilities...
Wish I could plug one of my old alpha processors into this thing.
Re: (Score:2)
I am the great OpenCores genie! Your wish has been granted: OpenRISC 1000 core [opencores.org].
Re: (Score:3, Informative)
Re: (Score:2)
I'm not sure if this is supposed to be +1 Funny or not, but...
WinChip lives on [wikipedia.org] in the VIA C7 series of chips. I've got lots of them around (in firewalls and other embedded style devices). They are dog-slow, however: about half as much work accomplished per clock speed as a PIII.
Their big advantage is power consumption, and therefore size. They're used in Mini-ITX [wikipedia.org] systems, which are about the size of a CD jewelbox, and are easily available without CPU fans (or very small fans for the faster models).
Re: (Score:2, Interesting)
Open98
this is was coolest tool to strip down Win98 with, WARNING: applications that depend on internet explorer will break! http://snoopy81.ifrance.com/rom2.htm [ifrance.com]
Eh, um, no. (Score:3, Informative)
Use the subjunctive (Score:2)
If you simply say 'if...was', then we assume it might actually have happened at some point in the past, but you just aren't sure, whereas what you're really trying to say is that it might happen at some point in the future. So, use 'were'.
Re: (Score:2)
No, it wasn't. It was incredibly flaky. I go back and try using old OSes from time to time, and it was just a month ago I tried 98 once again...
The slightest thing would cause it to crash... un-plug a USB device at the wrong time, and BSOD. Hell, even pull out a floppy disk or CD before the light goes completely off, and you're better-off rebooting than trying to get out of it.
If a single process was using a lot of resources, the system would be so incredibly unresponsive that you
Re: (Score:2)
Re: (Score:2)
No, it didn't. It had the Explorer shell, unlike NT 3.51, but NT4 was NOT Plug-and-play, it did not have a device manager, driver installation, system management, and the like, were nothing like 9x. Tasks which should be simple, like installing a sound-card driver were 10-step processes. The interface for setting an IP address was alien enough that I know many people kept setting a static IP address for their dial-up modem, and couldn't figure out how to show or ch
Re: (Score:2)
If they had rebuilt it on an Unix base, they would've been on a weaker position: applications and skills would be easily ported between OS's, which would mean people wouldn't be forced to use MS' products like they are now.
...). Sticking with win32 is what allows them to keep doing tha
MS' business plan has been to lock people into their products as much as possible (cfr. Office, DOS, Windows itself, Internet Explorer,
Re: (Score:2)