Slashdot Mirror
PCI Express - Coming Soon to a PC Near You
Max Romantschuk writes "I've been following the emerging of PCI Express for some time now. PCI Express, previously known as "Third Generation I/O" or "3GIO", is the technology set to replace PCI. PCI has been with us for around ten years now, and is rapidly running out of bandwidth. Last week Anandtech ran an interresting story on PCI Express. The techology has previously been covered by Hexus and ExtremeTech aswell. I feel this technology looks all set to replace PCI, and we really do need some new bus technology to keep up with the bandwidth demands of today's applications. Or is this just yet another way to force us into a new upgrade cycle?"
Due to its high bandwidth, it's expected to replace AGP as well.
"Oooh, does that mean we get to kick some puffy white mad zionist butt?"
I feel this technology looks all set to replace PCI, and we really do need some new bus technology to keep up with the bandwidth demands of today's applications. Or is this just yet another way to force us into a new upgrade cycle?
Damned if you do, damned if you don't.
Let's start fresh! SATA, PCI-Express, USB2.0! Time for a clean break! Get rid of all the legacy crap. We're supposed to upgrade every three years anyway, so let's really upgrade.
Oh Shit, we all have iMac's now...
You think that I'm crazy, you should see this guy!
Excuse me for being dumb, buy why is everything going serial over parallel? I.E. Why is serial transfer faster than parallel transfer?
On Desktop, only Gigabit ethernet needs something faster than PCI and several motherboards and chipset already include that. There isn't need for anything faster.
Manufacturers might even react to this one and STOP putting damn AMR slots in motherboards.. what a waste of space they were..
:)
then again.. I haven't bought a motherboard in a year or so.. maybe they've already woken up
I am speechless! "PCI Express currently runs at 2.5Gbps, or 250MBps per lane in each direction, providing a total bandwidth of 16GBps in a 32-lane configuration."
What can I say: WOW! - Hello gigabit netcards, (multiple) extreme graphics adapters etc!
Any technology distinguishable from magic, is insufficiently advanced.
The high bandwith demands of today's application are designed to lock us into another upgrade cycle.
Just wait until the PCI group renames PCI Express to PCI just to keep things confusing to the consumer. After all, if consumers are demanding PCI Express in their computers, then just rename everything to PCI express... or however that USB fiasco works out....
I'm just wonering now if that external HD USB2 case I bought is really 1.1 or not... Grrrrr.
If telephones are outlawed, then only outlaws will have telephones.
Or is this just yet another way to force us into a new upgrade cycle?
:)
Or maybe current PCI devices don't support DRM out of the box ? Please upgrade your bus techno, so we can use all this extra bandwidth to transfer huge crypto keys to/from your hardware, just in case you want to play a copyrighted sample on your soundcard
(-1 Paranoid)
Karma cannot be described by words alone.
More than bandwidth, what I need would be a bus
that doesn't have a problem with too many extensions
because of a limited number of IRQs.
Today most mainboard come with many onboard PCI componentes. If you really are going to put in 3-5 extra PCI components in a stock PC, you usually end up in a nice game of 'let's see what order works best', or cannot use all cards together at all.
Is it what the manufacturers think we want? The traditional Hard Drive is still the main componant in the PC slowing everything down, yet the manufacturers still keep increasing CPU, and BUS speeds and increase noise and heat levels.
Open Laptop Chassis, monitor and power standards!
Ding, Ding!
Life is the leading cause of death in America.
Why does every /. story need to have some little cynical tagline at the end of the intro. Why can't people just post the story, let other's read it, and formulate their own opinions? Arrgh, it's been starting to drive me nuts. /. is starting to sound more and more like a bad TV news program every day. "Everything is quiet and safe in our little suburb. OR IS IT?!"
ISA Vesa Local Bus PCI AGP PCI Express It's 5th generation for me.
I need a Sino-Logic 16. Sogo-7 data-gloves, a GPL stealth module...
PCI 1.x = PCI 'Full Speed'
PCI Express = PCI 'High Speed'
Given that the PCI interface was introduced to the world by intel in 1992 and that we since have increased the cpu processing powers by a hundred fold (give or take a little) it is really about time that the bus catches up.
Thomas S. Iversen
PCI Express will not replace PCI. PCI will be backwards compatible, and for the convenience of OEMs PCI will be renamed PCI Express, the faster PCI Express will be henceforth be known as PCI Express Hi-Speed, and the PCI PCI Express will be known as PCI Express Full-Speed.
Someone had to...
Any technology distinguishable from magic, is insufficiently advanced.
Or is this just yet another way to force us into a new upgrade cycle?"
Short Answer: Yes.
But, hey, that keeps many of us employed...
never bring a twinkie to a food fight.
I'd say a new standard every 10 years is a pretty reasonably upgrade cycle compared to most other PC technologies...
OK, so yes we can probably live with PCI for longer (possibly much longer), but why not introduce a new standard with better potential? It maintains complete backwards compatability with regular PCI components, so manufacturers of harware don't even have to change anything. Of course another issue is motherboard cost, but there will always be new features put into successive motherboard generations that aren't in widespread use yet... like serial ATA, gigabit ethernet, etc. And there will probably be motherboards available for a lower cost without those features as well.
Is EXACTLY what's planned.
Look for mobos supporting the next generation of DRM to hit the shelves next spring...
...then I'll be happy to enter the upgrade cycle once again.
AGP is clumsy, and PCI exp. is more modular as well. It allows the insane bandwidth og AGP for everything.
And you'll be able to take REAL advantage of 1 Gbps Ethernet - and 10 Gbps once we get that =)
How are those tiny little serial connectors supposed to support the weight of my 2007 GeForce Maxx Fury 7 video blaster with its jet turbine fan? They'll snap like twigs, I tell ya!
... or does PCI-Express sound like that run-down computer store around the corner that you've 'boycotted' but still go to anyways?
Other than uncompressed HDTV (1928x1080@29.97, 4:2:2 = 124MB/s), what applications need higher than 133MB/sec? Are 3-D cards really limited by the PCI/AGP bus today? Certainly it would be nice (and reduce video card cost) to move all that on-board 3-D memory to the motherboard, but is that really a compelling enough reason all by itself?
I'm not saying that there aren't lots of uses for a faster bus, but changing to PCI was painful (Remember EISA/VESA Local FUD? Remember motherboards with four slots, not all of which actually worked? etc.) and the next change will be equally difficult. So, how many of the reasonable applications are really mainstream enough for all PCs to go through the process?
Xesdeeni
It looks like Linux developers are already working on support. Also, the Inquirer reports that PCI may kill AGP?
Or is this just another way to force an upgrade cycle?
It may well be one of the intentions of it, but one thing I don't get is that with CPU speeds and hard disk capacities where they are now, the average computer buyer (which probably is not very well represented on slashdot) no longer really needs to upgrade their computer, so changing interface/slot shape/etc won't really matter to them.
I know I'm generalising, but the only applications that really push today's computers are games (and high end scientific programs, but they're a fairly minor special case) and I would guess that most computers are not used primarily for games (ie. "serious gamers" - think families). Serious gamers will always be upgrading their computer to the latest and greatest anyway - they don't need to be forced into an upgrade cycle.
It's getting to the point now where by the time the average family decides they need to upgrade their computer, it is easier (and maybe even cheaper) to just buy the latest middle-of-the-line computer package.
I'd almost question whether the idea whole idea of upgrading is itself becoming obsolete for an average computer user?
"Because it's there." - George Mallory, when asked why he wanted to climb Mt Everest, March 18, 1923 (New York Times)
Does no one else remember the fiasco with I20, USB and IDE? These are all
"specifications" for hardware that no one needs--their only purpose is to
try to squeeze Linux out of the marketplace.
Yeah! Ban IDE! Bring back ST506! If was good enough for the PC-XT it's
good enough for me! Or good enough for you anyway.
Im waiting for PCI Express: 2.0 Full speed
------------- I didn't know she was your sister I swear!
Exactly, check out the i875 chipset design on the 3rd page of the anadtech article and everything there without using pci, with a springdale/canterwood/nforce2 even, motherboard everything but the kitchin scsi is built in, expansion cards are becoming useless on average machines as proved by the huge growth of laptops and small form factor computers. As long as the agp slot keeps up with the pace then graphics cards will be happy and pci/pci-express cards will only be useful for workstation/server machines. Can anyone actually think of a useful expansion card that wouldn't duplicate something on a new motherboard (occasional firewire ommisions and scsi excluded)?
Needed? Heck yes.
133 MHz PCI can barely keep up with 2 gigabit SAN technology - one HBA/bus is all you can get. And faster SANs are on the horizon.
Yup. I just went to look. They have the PDFs avialable, but a password is required. You can sign up for an account, but only if you are an employee of a company which is part of the consortium.
Oh, I'm sure at least a couple of Linux companies will get access to the specs. That isn't a whole lot of help to those of us who are not working on Linux. We either have to wait for the code to be completed and available from Linux (From which we then have to reverse engineer the exact process from) or hunt around until someone leaks the specs and we can snatch them on the quiet.
Don't even bother to flame me and claim that these standards bodies have a right to make money from these; its a damn specification They are funded by the hardware companies who are going to make millions of dollars in upgrades and new hardware alone. Charging a few bucks for the specs is a little on the cheap side.
Will the nickname for PCI Express be "PCI XP" ?
Tired of being "punished" by the Slashdot $rtbl since 2002. I'm now over at http://soylentnews.org/ .
It's called PCI Express because it's a bus! Express Bus! That's cute.... hahahahahhahaha....
Then it's needed, unless you really want your desktop box to have more than one main I/O bus.
Hmmmmmmmm...... Bandwidth..... Sweet life giving bandwidth .
Based on the direction in which mass-market computers are moving, the bus that gets exposed to the user is getting somewhat less important. Aside from gamers and tinkerers, and people who manage big servers, how many computer users ever have a need to open up the case?
Ten years ago it was almost a given that at some point, you (or your Computer Guy) had to add or replace one of the cards -- add Ethernet, upgrade the video, whatever. Nowadays, the hardware on-board is more than sufficient, and any of those "special" accessories you get, such as storage drives for your digital camera, or a scanner, or whatever, are more likely than not going to be USB or FireWire.
It's very likely that the mainstream desktop computer is going to move to a slotless "brick" form factor. This would have the side benefit of making it much cheaper. This form factor is available already, but it's not yet cheap because it's still considered a "specialty" unit.
I'd also be happy to see the return of the Commodore 64 form factor -- just shove everything into the keyboard. Plug in your mouse and monitor and Ethernet, and go.
Tired of FB/Google censorship? Visit UNCENSORED!
But I like to upgrade!
I usually build two computers a year. If I sell my computer every six months at 75% (which is about the going price) of its original price, I can keep up experimenting with sweet new hardware.
As an added bonus, I've built an expanding network of friends, friends' friends and practically unknown people who have been referred to me by the others. They buy my second hand computers, consult me whenever they want to buy a computer and have me build computers for them. I do it free, although sometimes I ask a steady "customer" to buy me some interesting item as a nominal fee for my services.
It's great fun! Yes, I tend to lose some money but most hobbies will cost you something.
BOO! TERRO
Hmm, let's see, on a desktop PC, you have:
some IDE controllers, each of which can push maybe 50MB/sec to the media (RAID-0) tops.
audio, keyboard, some other I/O, maybe 1 MB/sec
NIC, 10MB/sec tops
Ok, so I do the math and get 61MB/sec, or just under 1/2 the bandwidth of PCI. For 90% of the PCs out there, this is sufficient. For high end boxes, you can use 64bit or 66MHz PCI, or PCI bridges.
Tell me again why this technology is necessary?
I want to delete my account but Slashdot doesn't allow it.
Lets faces it, this is just so we can stream porn faster - everyone knows what drives technological advances. Innovation can be measured in pron per minute...
This is going to finally bring around some really miniscule systems that actually have expansion slots. Very very cool, now the size limitation to a useful system is going to be the height of the CPU cooler!
sig.
"Or is this just yet another way to force us into a new upgrade cycle?" Yesssss, and that is ALL it is. Nothing will be gained, compatibility will be lost. May as well wait until the 256 bit processors come out.
About the only stuff that has made it into the chipset are cheap soundcards (yes creative is cheap to) and some extremely cheap raid solutions. A lot of other stuff is still in one form or another on the PCI bus. Even if it is not included on a plugin board.
So yes there is a real need for it. Simple example? Raid disks. With striping (multiple disks working together) it is now very easy to saturate the PCI Bus with the cheapest disks.
Same with gigabyte ethernet.
Of course it will be a long time before any real replacement will happen if ever. If I look at some of my old boards on top of the bookclosset I can see it took a long time before ISA was off, and I also see some odd really short slots I never used or seen cards for.
MMO Quests are like orgasms:
You may solo them, I prefer them in a group.
I may be missing something here, but I have been using 64bit PCI-X on servers for some time now, it's way fast, it can support multiple gig speed nics, FC HBAs and ultra 320 fast/wide SCSI array controllers but nobody outside of server users seems to have even heard of it. Why not give existing technologies a fair crack of the whip before re-inventing the wheel...?
And I still use a few ISA-boards.. :) :p
for example an old ati-tvcard
getting hard to find motherboards with an ISA slot as it is..
well screw backwards compability.. soon we don't have analog tv-broadcasting in this country so I'll have to buy an dvb-card anyhow
This looks just as if they have taken the Infiniband spec and stripped out a lot of the bells and whistles which that had grown in order to become totally generic. Intel "back burnered" Infiniband about six months ago, so presumably switched there effort to this. It looks a good idea to me - I think we have been waiting too long for tightly-coupled serial links to reach general use. Inmos had them 18 years ago, but they never caught on then (because inmos wouldn't let people buy in to their several good ideas without also buying in to the several more bad ideas).
Serial links make system configuration much easier. They do have the slight downside that they have even wierder failure modes than traditional busses and (IME) have more soft failure modes than busses.
Consciousness is an illusion caused by an excess of self consciousness.
PCI-express is nothing other than Intel's favorite profit-making tool, version churn. there IS NO WIDESPREAD NEED FOR GREATER BANDWIDTH.
servers do not need PCI-express: they're already using PCI-X just fine, up to 1 GBps, which is plenty for any vaguely affordable IO devices. gosh, yes, it's tragic that 10G eth doesn't do so well on PCI-X, but when's the last time you saw a $40K 10GE nic at your local computer store?
AGP 8x is more than enough bandwidth for graphics - the obvious trend is towards greater intelligence and ram in the graphics card itself, which means you could probably put an ATI 9999-pro-xp on a fucking ISA bus and be happy.
the PC industry has talked itself into believing that there's an inevitability to the escalator that has allowed better hardware to trickle down to the desktop. introduce something at the high end and let the wonder of mass-production and human avarice bring it to even entry-level computers. why 150 MB/s SATA when disks are around 40, and there is by definition one disk per channel? why gigaflops on the graphics board of a business desktop that does everything in 2d?
switched fabrics are cool, though. the real figure of merit should be latency: PCI latency is the main concern for IO throughput today, and if it's not addressed in the next gen, it will have failed...
And the current PCI specs barely support the current SAN speeds...
Comment removed based on user account deletion
Does this mean that now we'll have motherboards with ISA, PCI, PCI Express (I know - they'll physically co-exist with PCI slots happily, but that doesn't alleviate the confusion to the !/. crowd) and AGPx1,2,4,8 (take your pick)? Any future motherboard that has ONLY PCI Express (this means no AGP slot, not 0 PCI slots) would be rightly considered to be less backwards compatible, and would therefore offer much less choice in terms of components, lowering its perceived market value. The perfect example here would be the seemingly impossible-to-kill ISA slot, that by any standard of geekdom should have been extinct by now. But many motherboards still have them - maybe because failure to do so would leave x% of customers unhappy and they don't want to take that risk?
Anyway, I think the exact same thing will happen to PCI Express. It looks like a cool bus design with lots of speed, and I'd like to see a system with just one type of expansion bus, but unfortunately I don't see that coming.
Black holes are where God divided by zero
Yup I was thinking of that exact motherboard when I posted, read about it on [H] this morning, but its one of the very few I've seen so I'm generalising.
While PCI Express will probably replace PCI, the transition will probably be very long.
As the Anandtech authors point out, there were still ISA slots on motherboards 10 years after the introduction of PCI. So I would expect that you'll still be able to use your PCI cards in new computers five years from now.
A pirate is walking down the street with a steering wheel attached to the front of his pants. Someone asks him what it is for.
What is his answer?
âoeI feel this technology looks all set to replace PCI, and we really do need some new bus technology to keep up with the bandwidth demands of today's applications. Or is this just yet another way to force us into a new upgrade cycle? When I look back at the explosion of technology within the past decade and the ever-continuing attempts to eradicate the bottlenecks that computer systems have had PCI Express is a breath of fresh air. For example lets take a look at processors; within the past ten years processor speeds have doubled every eighteen months if we go by Moores Law. Itâ(TM)s hard to believe it was a little over ten years ago that Intel released the First Pentium Chips. HDD speeds (physical read) have also increased dramatically from about 2 MB/s for a 635MB HDD to over 45 MB/s for a modern HDD. Graphics were given a face lift with the introduction of the AGP bus pushing the speeds of transfer up from PCIâ(TM)s 133 MB/s to 2.1GB/s however many systems are used for a LOT more than video rendering capabilities and are geared more towards storage markets were data access speed is of the utmost importance. 64 bit PCI gave us a boost to 266 MB/s transfer speeds to be used in conjunction with high speed U320 SCSI but even then we cannot take full advantage of the capabilities offered. PCI express opens up the horizons for computers letting us transfer substantial amounts of data in less time. This can only be a good thing. More Information * Shorter Time = Greater Efficiency Therefore I donâ(TM)t see this as another way to force us into the upgrade cycle but a good solid advancement in computers. Also, the good thing is that it is coming wither we like or not.
- Sig
Ik what i'm wondering about,
when PCI-Express motherboards come, and they have PCI backwards compatible ports for your old PCI cards (sound nic etc) what will happen to my AGP graphics card? I mean, am I forced to upgrade my graphics board aswell? Or do they plan on having a backwards compatible AGP 1x 2x 4x 8x bus on there aswell (since AGP is in fact just a fast PCI bus it shouldn't be too much but they didn't mention anything but PCI on anandtech)
Too bad they didn't decide to just use the existing industry-standard high-speed PCI replacement, PCI-X. Then again, Intel didn't make PCI-X, so it can't be any good, right? Just like Firewire.
Since most users are using Microsoft products, and Microsoft seems to be keen at using lots of memory and cpu cycles where sometimes not necessary, they seem to be handling the issue of forcing people into a new upgrade cycle quite well. For many of us gamers, new titles like ut2 and the coming Doom III are forcing the upgrades. Given this, I don't think that PCI Express will create more "upgrade pressure" than many people already feel.
"The best laid plans of mice and men gang oft agley..." - ROBERT BURNS
Hey, finally a post I totally agree with. All my servers are 64-bit PCI-X based, so what do I care with PCI Express.
Server hacks like the 66-MHz PCI bus speed and 64-bit-wide PCI are neither practical nor sustainable. That's why we need something different, something like PCI Express. It raises the I/O bar enough to give us another few years of unconstrained growth of the PC architecture.
Easy, automatic testing for Perl.
What PCI device are you using that is bandwidth limited & will benefit from a faster PCI bus? I don't have anything. My video card is in an AGP bus, and I would like that to be faster, but for the items in PCI slots, I really have nothing that will gain any benefit. I would much rather have faster memory, closer or in the processor.
I have come to a conclusion that one useless man is a shame, two is a law firm, and three or more is a congress -J Adams
The real PCI bandwidth is usually something like 75-90MB/sec. Depending on the chipset.
Now, add in IDE RAID cards, and SCSI cards and those along can saturate the bus. Consider that a single SCSI HD can now pump out about 70MB/sec when used in an STR intensive application.
If you think education is expensive, you should try ignorance -- Derek Bok, president of Harvard
using serial there is no having to worry about whether all the bits arrive at the same time (as there obviously is with parallel), and so the speed of transmission can be dramatically increased past the point at which it becomes faster than the "equivalent" parallel technology... bits arrive in the order they were sent - guaranteed.
:-l
I'm afraid this might add to the confusion about serial interfaces being 'faster' than parallel. While it is true that you don't have to worry about data/clock skew when using serial interfaces, enabling you to clock them faster, a parallel interface running at the same clock speed as a serial interface will always be faster in terms of data throughput. The reason for this is simple: serial == 1 bit per clock, parallel = > 1 bit per clock.
So, saying that serial is faster than the "equivalent" parallel interface is confusing, and incorrect, because one could be referring to equivalent clock rates being used for each interface, in which case parallel will provide at least twice the data throughput. On the other hand, "equivalent" could be referring to identical throughput rates, in which case the serial and parallel interfaces would provide, by definition, identical data rates.
The real advantage that PCI Express has over PCI/PCI-X is that it is a point-to-point, rather than a multi-drop, bus. This setup requires less time between pin transitions, meaning that it can be clock faster. Also, like Ethernet, a serial protocol can imbed the clock into the data stream so clock/data skew is no problem whatsoever.
Serial is not better than parallel anymore than digital is better than analog, there are just physical reasons why implementing point-to-point serial at significantly higher clock rates is easier than multi-drop parallel.
Anyone still awake?
Didn't think so
If it's not one thing, it's Steve's Mother
We realized PCI wasn't going to be fast enough years ago-- that's why pretty much every motherboard you can buy today has an AGP socket.
And even that wasn't fast enough, now we have AGP 8x.
But seriously, is PCI really not fast enough for the general consumer, once he's got an AGP socket? PCI that runs on a 66MHz bus that's 64 bits wide has existed and even been available in high-end PC class hardware for years, but few of even Slashdotters have anything other than 32 bit 33MHz PCI in our home machines. The only time I ever deal with the 64 bit PCI cards is for Sun Microsystems hardware at the office.
I don't think this is "forcing another upgrade cycle" at all-- upgrades already exist, and most of us don't have 'em.
Or is this just yet another way to force us into a new upgrade cycle?
If it's as knock-your-socks-off good as it professes to be, do you really care? I mean, those of us who like to ride the bleeding edge of the hardware world thirst for stuff like this all the time. Things like "OOH! A new [WidgetA] to play with! But, hey, it's not backwards compatible with [WidgetB]!" do not phase the dedicated.
Those who think it's good enough to merit a major hardware upgrade will do the hardware upgrade and those who don't feel they need gargantuan bandwidth for reading e-mail will stick to their current machines. I'd bet the only forcing involved will be people forcing themselves to not collapse after seeing the pricetag on one of these boards.
About the only stuff that has made it into the chipset are cheap soundcards (yes creative is cheap to) and some extremely cheap raid solutions. A lot of other stuff is still in one form or another on the PCI bus. Even if it is not included on a plugin board.
Southbridges haven't been connected to Northbridges through the PCI bus for a while now. Which means that eveyrthing that is integrated on the Southbridge does not run over PCI, but over HubLink, HyperTransport, A-Link, etc. (whatever chipset you happen to have)
And, modern integrated chipsets have IDE controllers, sound cards, network cards, and USB controllers all integrated.
Never underestimate the bandwidth of a 747 filled with CD-ROMs.
Now that's a no-brainer.
My computer is by far not a high-end box, but PCI is a (small) bottle-neck, even for me.
Let's see: 2 IDE channels, 2 disks, that's 50 MB/s each, 1 GBit network, that's peak 100MB/s. A U2W SCSI host adapter with 1 single, very fast disk is good for 70MB/s. Then there is USB2 (everything is USB2 now) and Firewire (each 50MB/s). Adds up to (peak) 370MB/s.
On almost all modern chipsets, these devices do not use the pci bus at all, unless you've put it your own add-in cards. (so, I imagine SCSI host adapter is a separate device, but IDE, USB2, and LAN should all be integrated into the southbridge, which means that they will be using whatever proprietary standard the chipset you have is using)
So, yes, you can overload the pci by adding a lot of add-in cards, but for most users, most of these items will be provided by the chipset.
Never underestimate the bandwidth of a 747 filled with CD-ROMs.
I am not bitter, I am just an undergraduate computer engineer sort of sad, because if I ever have the capability and inspiration to prototype some sort of device on my own, it will never interface with my current desktop's PCI-style bus at the time.
Does this mean I could finally use SCSI-160 drives on my desktop without having to shell out $600 for a server mobo? Way cool!
One thing that has irked me about ISA/PCI/VLB/Sbus expansion cards (all the way back to the apple ][ actually ) is how clunky it is to install these things into a PC or server.
That is, you have to crack open the case, exposing delicate bits like memory, cpu, power supplies and so on, unscrew the blanking plate (hopefully without losing the screw in the bottom of the PC) and lever the card in, with considerable force sometimes. That's fine for us techos, but daunting for Joe average, and a PC warranty nightmare.
Hopefully video / nic / other expansion cards for the desktop pc will eventually look something like a game console cartridge, ie all the electronics are safely enclosed in plastic, (with relevant cooling slots if so required.)All you need to do is find a blank slot at the back of the PC (protected by a spring loaded dust cover, super nintendo style) and ram it in. The card powers up, The BIOS/OS detects and configures the card and you're good to go!
I was hoping CompactPCI would filter down to the consumer level, as this comes close to realising this level of convenience for an expansion card. ie, the connector is at the back rather than the bottom of the card, and each card comes with a nice, convenient self-locking lever to help levering the card into place and locking it down.
Hopefully the PCI group come up with some sane "device bay" standard to make this a reality.
Perhaps the HDD/storage device manufacturers will agree on a standard hdd mounting system so we can hot-mount all our SATA devices too, without opening the box. If only..
TV tuner card? Are there any motherboards with those integrated? I also think it's a good idea to keep a generic interface, like PCI, available, "just in case". There will always be something someone wants that the mobo manufacturers didn't think of.
--
Seeing is believing; You wouldn't have seen it if you didn't believe it.
Never again will any announcement of new hardware technology be received by us geeks with the glee it once was. The only thing that comes to our minds now is "great, another opportunity for them to add DRM and phase out hardware that allows copying"
You might start seeing PCI-E in servers in the CY2005-CY2006 timeframe, after PCI-X and DDR PCI-X have run their course. This isn't something that's right around the corner, regardless of the hype.
I don't know if anyone using IE visited Anandtech's web site, but they are using adtech's adforce ads on their site, which adds what looks like actual links in the content of the page, but are actually advertising.
Boycott Anandtech!
The vast majority of users will not have any need for this kind of bandwidth for quite a while. People doing heavy graphics/video processing will like it but 99% of the public will yawn.
There are two major benefits, however.
Adoption will be fairly fast because so many facilities are built right on the motherboard today. Since much of the market never installs a PCI board, there is nothing preventing them from buying a PC based solely on this new technology, particularly since the new hardware won't be expensive.
And the economies of scale in sharing more hardware throughout the line from consumer PCs to high end servers will be good for everyone. Now we'll be able to steal more equipment from work (just kidding).
I'm watching to see when the processors start talking serial directly. Getting rid of the exotic seven thousand pin packages for processors (and their associated sockets) will be another great savings.
I think that 64-bit PCI is a good alternative to normal PCI, it is already in all the PowerMac G3/G4 motherboards and Sun motherboards, you can get an x86 one with 64-bit PCI too if you look hard enough.
Serious gamers will always be upgrading their computer to the latest and greatest anyway - they don't need to be forced into an upgrade cycle.
It's getting to the point now where by the time the average family decides they need to upgrade their computer, it is easier (and maybe even cheaper) to just buy the latest middle-of-the-line computer package.
I'd almost question whether the idea whole idea of upgrading is itself becoming obsolete for an average computer user?
I imagine what they're talking of here is upgrading the entire computer (read: buying a new). That is an "upgrade cycle" to mainstream users, which they'll do when there's enough "buzzwords" they're missing.
You can use the same expression about the serious gamers as well - they have a very rapid GFX card upgrade cycle. Powerusers do component upgrades when they are out of synch - like your video card is obsolete in 6 months while your CPU is good for a year and the hard disks two, but that is not the standard.
I still do component upgrades because it allows me to "scratch an itch" every time I feel a component is obsolete, there's been a price drop or a feature I'm missing is introduced, without buying lots of stuff I don't need (yet).
I admit it's getting less and less stuff that goes into this category, though the DVD burner I bought recently was one of them. Anything else (CPU, memory, GFX card, harddisk etc.) can wait until my next full computer - I think. So when the time comes, I'll buy a new machine from scratch, and the time from I bought my last until then will be my upgrade cycle...
Kjella
Live today, because you never know what tomorrow brings
Eveyone knows what an hassle it is/was to do some (user) developing for the PCI bus. Memberships cost like $3000/year, buying hardcopy of the specs is like $500 -> $1500 a pice (depending on exactly what you want to buy).
Fees like this put an quite hard stop for end-users to acctually develope his/her own haxxor-card (doing something kweel and fun) purely out of love for the sheer joy of building stuff (the same joy linux programmers enjoy).
You proabably think an open hardware standard is out of reach, but look back, and you'll proabably remenence that people said the same thing out open software and open standards.
I don't claim I know more than I know, and if you know you know more than I know, then by all means, let me know.
Actually pr0n may very well be the mother of invention. Why else do you think that VHS beat out BetaMax as the standard for home video tape machines : pr0n was available on VHS more often than Beta.
Pretty simple.
Then again, pr0n was also the reason I learned to tell time (parents got home from work at exactly 5:35pm each day so I could read my dad's Playboys until shortly before then and not get caught.) I was the best time-teller in the whole damn first grade.
Glonoinha the MebiByte Slayer
D'oh, I was sort of under the impression that the 64bit PCI-X slots in my server were PCI-Express ... but I guess not. What is the difference, in a nutshell?
Glonoinha the MebiByte Slayer
Do we get the option of PCI-Hut and Domino-PCI too?
will I be able to use my old NuBus cards with it?
Right - real server class and enterprise class hardware has been beyond PCI for some time now. PCI 64/66 for many years, PCI-X for a few years now has been the norm. It's hard to use a gigabit ethernet card (or a dual-port gigE) without some serious bandwidth - and shared 32/33 PCI just isn't the thing. PCI-X surely isn't the end-all of I/O busses (not even PCI-X DDR), but it is a pretty darn nice improvement over PCI 2.2.
"It's tough to be bilingual when you get hit in the head."
I had a rather interesting talk with an Intel Rep. @ SuperComm 2003.
He said that it's pretty hard to find someone who knows about this technology at Intel who isn't excited about it's promise.
You can use your current PCI devices in a PCIexpress board. No need to be forced into a upgrade cycle.
:P
AGP will stay for a awile longer, because latency of AGP slot is beter suited for graphics card anyways still.
Who upgrades there NIC,soundcard anyways just for PCIexpress?
you're just TACO in disguise, trying to cover his ass for all the servers his site has reduced to smoking heaps of slag, aren't you?
Machine9dotNet
I'm going from memory here, so please excuse any errors I make.
:)
The fundamental principle that makes PCI-Express work is not a new idea. In the not-too-distant past, this same idea, called "Differential Signaling" has been employed in such ubiquitous technologies as USB and DVI, in addition to the recently developed S-ATA.
One of the biggest problems with transmitting any signal is NOISE. This can be dealt with a number of ways: increase voltage swing, shorten transmission lines, reduce bit rate. Of course, those all go counter to what we WANT.
Differential signaling uses two wires (rather than just one), in addition to a ground signal to transmit a single serial data stream. It's called 'differential' because each of the two signal lines switches in antiphase to the other. Among its various advantages:
It reduces the effect of interference -- both signals experience the same noise, eliminating the effect.
It reduces the effects of ground bounce (ground level for sender and receiver are different due to the effects of output drivers drawing current) -- the ground is only a DC return path, while the signal is decoded entirely based on the difference between the two signal lines.
If a differential pair is made into properly shielded coax, it's possible to maintain good signal integrity over a long distance.
Parallel transmissions have to be throttled back because differences in wire length have to be dealt with. The more wires you have, the harder it is to ensure some very important things: All wires are the same length, all output drivers have the same response, all chip logic has the same delay, all output registers are clocked at the same point in the clock tree, all input buffers have the same response, etc. With only two signals to deal with, it's much easier to make sure all of these factors are under control; in fact, many ASICs and FPGAs have special "differential I/O buffers" which are designed specifically to deal with all of the above issues.
There are other advantages, but you get the idea. The effect of being able to clean up so much signal noise and eliminate the need to keep in sync with other signals makes it possible to dramatically increase bitrate. In fact, the result has been that differential serial communication has been able to surpass parallel in bit-rate and will continue to surpass it further.
Why this brilliant technology is only so recently becoming popular is that it has only now become cost-effective to produce transistors which switch fast enough to make the advantages of serial surpass the advantages of parallel. Before now, it would have been necessary to use expensive Gallium Arsenide transistors, eliminating the advantages. Transistors in chips are now so much faster than wires that it's not only faster but also cheaper to switch a few signals really fast than to try to keep several signals in sync (and noise-free).
I think we may have reached the point where the clock period is shorter than the wire delay for DS. That is, one bit hasn't traversed the wire all the way from the transmitter to the receiver before the next bit starts coming out of the transmittor.
It's an interesting technological cycle we observe here. Back when every transistor and every wire was expensive, it made sense to transmit serially, because it saved transistors. As transistors and wires became cheaper, it made sense to go parallel for more speed. Now that transistors are getting so fast and bit rates are bumping up against signal/noise limits, it makes sense once again to return to serial.
The next step is to go back to parallel, but this time, it's multiple independent differential pairs which carry data packets which are reassembled and reordered at the receiver.
Oh, and let's not forget about fiber-optics.
- IDE harddrives (up to ~60MB/s)
- AGP graphics card
- Fast ethernet LAN (10MB/s)
PCI does 133MB/s.IDE chips are onboard and don't need PCI slots.
Gigabit ethernet could be a use of buses faster than PCI but I've felt the trend is also to put them right on the mainboard. Besides, the switches are still prohibitively expensive.
AGP: We've seen that 8x AGP does not give a performance boost over 4x AGP.
I don't see a great need for PCI-X at the moment.
In order to break the I/O bottleneck for the mainstream PC, something else is required. Hence PCI Express.
Easy, automatic testing for Perl.
PCI Express, meet PCBexpress. Can you say trade mark infringement?
This comment does not represent the views or opinions of the user.
Okay.
everything needed for basic computing is on the motherboard, but once someone wants to use their computer for something specialized, it is not included.
for example: high end sound or studio sound is not included on the motherboard. i'm talking about sound cards with at least eight analog ins and outs and more than one midi port. these also work as firewire sometimes, so you may have covered it. another example is any kind of dongle card required for special applications like 3D or the sound program operating the first example.
just because most people don't need it, doesn't mean it's not needed. those who do will have the option while those that don't can get smaller form factor stuff.
you probably shouldn't have read this.
Okay, you're retarded. Look at this table. USB 1.1 supports low- and full-speed (1.5 and 12 Mbit), and USB 2.0 supports low-, full- and high-speed (1.5, 12 and 480 Mbit).
There exist confusing standards out there, but USB ain't one of 'em.
--grendel drago
Laws do not persuade just because they threaten. --Seneca
I scanned the articles checked for anything on this, but didn't find a suitable answer. Will "PCI Express" be like USB, wherein it will support the older gen hardware as well as the newer hardware - or it will only support "Express" PCI devices?
It would be very nice to maintain a PCI port that was capable of faster speeds but still able to run old devices (somewhat like AGP 2x/4x/8x or USB 1.0/1.1/2.0 ramping up, ignoring recent USB developments).
I still remember one of biggest pains in my backside was trying to run PC's that needed an old ISA device (Scanner interface, old ISA SCSI card, special controller card, whatever) which I have heard is a drag on the whole system. Nowadays, I've got only PCI and AGP, though my old but still very good ISA SCSI scanner is still plugged into my 1Ghz Duron (with a single ISA port).
Will we get the best of both worlds? If express supports normal PCI, we can replace the old stuff in a jiffy. Running mixed slots again might be a pain, though.
My current motherboard (EPoX 8K3A+) is the first motherboard I have owned that does NOT have ISA slots and it STILL has a parallel and 2 serial ports and PS/2 ports. I don't want any of this crap! I wish they had just put it all on a dual header PCI card I could rip out and burn.
I really hope that the motherboard manufacturers make a break from the past with PCI-X. The more legacy junk they include, the slower the adoption rate will be. REALLY !
-- "Most people prefer a popular myth to an unpopular truth"
The early adapters . . .
That's got to be the best pun I've seen in a long time.
Well, near-pun or Freudian slip or something.
Ok theres some valid points there with the tv tuner and the high quality sound cards, but thinking about it, theres the creative labs extigy and some generic tv tuner that connect via USB.
So in conclusion, its always nice to have a standard way of adding functionality to a pc, but excuse me while i go buy some shares in some SFF manufacturer and never use another pci slot in my life.
After sitting through two days of PCI-Express and PCI-X presentations at he pci-sig devcon.
/. paranoia.
The developers and the SIG most certainly weren't rubbing thier hands with a devilish grin saying "we got the suckers, let's lock them into a new upgrade cycle for another decade, Ha Ha Ha". The motivations for PCI Express are very compelling.
First PCI-EXPRESS is not targeted only for the desktop. It is targeted to be a general purpose bus for all class of machines and has features built-in that make it very attractive for server platforms.
Advanced RAS features
With conventional PCI you can only detect single bit errors. And nearly any such error is fatal. For PCs you would just reboot but it is a big no-no for HA servers. With PCI-Express you can detect and correct errors and since it is packet based, the corrupt packet can be retransmitted.
Built-in Hotplug.
Hot-plug in PCI was an after thought. It is built into PCI-express. The NewCard and Sever IO modules are designed to make hot-plugging very easy and user friendly. Nowadays to hutplug a pci card you have to open the chasis with the new modules you can just plug it in/out from the back of the chasis without removing the entire server off the rack. Also the newcard formfactor makes it ideal for laptops and mobile devices. PCI and PCMCIA are going to merge eventually and use the same Newcard form factor.
Backward Compatibility is maintained
You don't have to throw out your old PCI/PCI-X cards. PCI and PCI-EXPRESS are designed to co-exist. All the motherboard manufacturer would need to do is connect a PCI-EXPRESS to PCI switch from the root complex and provide slots for PCI/PCI-X devices
New and interesting design opportunities.
PCI-EXPRESS allows the PHY to be a a cable. So you can percieve a system where the rootconmplex and the io are in two or more seperate chasis connected by a cable. This will make it more intuitive for upgrades. End users wouldn't have to open thier cases all the would need to do is unplug the rootcomplex case and replace it with a new one or similary the io case or graphics case.
Also the Mini PCI-Express card is half the width of the current mini pci card. Allowing two cards to be placed inside a laptop with the same real estate. The platform design choices could be endless.
Hope this will quell the
The southbridge itself is attached to the (or one of the) PCI bus(es) provided by the northbridge. Most consumer PCs have the southbridge attached like a PCIPCI bridge on the main PCI bus with the rest of the card slots. So all those devices CAN reach the saturation point of the PCI bus attaching all of it to the northbridge.
The exception is in the case of some server architectures where there are two or more PCI busses and the southbridge with it's embedded stuff is on a seperate one from add-on cards.
Black holes are where the Matrix raised SIGFPE
Well let's see what the dictionary has to say...
The American Heritage® Dictionary of the English Language, Fourth Edition: "Computer Science. A parallel circuit that connects the major components of a computer, allowing the transfer of electric impulses from one connected component to any other."
It can ALSO mean a set of conductors connecting several components, but that's not what bus means. Hypertransport is a bus, even though it's a point to point link.
"You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
I am pretty disgusted at the quality of posts under this article. There were a few informative ones, sure, but for the most part its just been PCI "Full-Speed" and PCI-X "Hi-Speed" jokes, or people saying its not worth the upgrade even though all their objections have been countered in previous threads that they have just neglected to read.
Ha! Ass bouillon responded! I SCORE! HE FAIL IT!
OK, now we have these choices:
1) 33Mhz 32-bit PCI
2) Compact PCI
3) 66Mhz 32-bit PCI
4) 33Mhz 64-bit PCI
5) 66Mhz 64-bit PCI
6) PCI-X
7) PCI Express
8) AGP 1x, 2x, 4x, 8x
Personally, I've been rooting for 66Mhz 64-bit PCI
for a *long* time -- ever since my k6/2 the peripherials I've been using has saturated the PCI bus -- but I've never been able to justify buying a $600 SMP motherboard to get it as well as expensive components.
Yet another standard it not such a great thing -- that means more market fragmentation and less opportunity for economies of scale with PCI [whatever] components.
I just wish that they would all agree to put 66Mhz 64-bit PCI in everything rather then coming out with the new standard of the week.
and name the new standard in similar fashion as Sony follows with their playstations.
So here's to the new standard....
ISA!
I am wondering, if anybody can summerize the pros and cons of PCI Express and Infiniband
My opinion
Pro Infiniband:
- very high bandwidth (10 GBit/s soon 60 GBit/s)
- sophisticated mechanisms for clustering which avoid OS interaction
- Does PCI Express have QoS?
Pro PCI Express:
- simpler implementation
- software compatibility to PCI (is that only a buzzword or something real which would be hard to do for infiniband?)
Anybody knows more?
Thanks.
PCI has been with us for around ten years now, and is rapidly running out of bandwidth
Are you *sure* it's running out of bandwidth?
The old-time, 10-year old 33 MHz, 32-bit PCI bus is still handles 99% of all home users just fine. However, for the more bandwidth-hungry users, you can increase the width to 64 bits. Not enough? Double the frequency. Still not enough? PCI-X will run them at up to *133 MHz*.
Let's put some numbers to that. On a 32/33 bus, you're looking at a maximum real-world, sustained throughput of about 100 megabytes/second. Double the width, that's 200 megabytes/second. Double the frequency, that's 400 megabytes/second.
Alrighty, then. Nearly a half of a gigabyte per second. That's awfully tough to fill. That will handle two gigabit ethernet controllers running full-tilt, and still have enough bandwidth left over that you'd need at least an INCREDIBLY fast RAID array to fill it.
But, just for fun, let's say it's still not enough. PCI-x, at 133 MHz, will double that *again*, to a full gigabyte per second. On a single controller. You're going to have an *INCREDIBLY* tough time actually using that - you'd be very hard pressed to actually get that much to move over a network and/or disk.
Still, you need more? No sweat. Many boards offer more than one controller. With two PCI-x controllers, that's two gigabytes/second of bandwidth. Not two gigaBITS, but rather two gigaBYTES.
Tyan recently introduced a board that has four gigabit controllers, each on their own PCI-x controller, with an additional 64/133 controller, a 64/100 controller, and a 32/33 controller. Again, let's put some numbers to that:
At 100 MB/s for each of the gigE controllers, that's 400 MB/s right off the bat. Add in the 64/133 controller, that's about 1400 MB/sec. Add in the 64/100, you're looking at about 2200 megaBYTES per second.
Now, really... can *anyone* here raise their hand and say that they could actually *utilize* 2200 megabytes/second of bandwidth to the outside world, either via network or disk?
Despite all of the ideas of the sky falling, PCI has done a very good job for the last decade, and amazingly enough, is still going strong. Strong enough that it will be quite a while before it truly NEEDS to be replaced.
Now, when it *IS* replaced, I'd much rather see the interconnects being optical, not electrical. Instead of cracking open the case, shutting off the power, and trying to wedge yet another card inside (especially in low-height rackmounts), I'd much rather set the device on a shelf, and run a fiber patch cable over to the computer. No shutting down, and a whole lot more simple.
steve
Oh, you're not stuck, you're just unable to let go of the onion rings.
Or is this just yet another way to force us into a new upgrade cycle?
It is yet another way to force you into a new upgrade cycle. For the average PC, the PCI bandwidth problem isn't even a blip on the radar.
Of course, Longhorn is on the horizon. Every version of Windows since 1.0 required twice as many resources as before...
A Government Is a Body of People, Usually Notably Ungoverned
My concern is not with the hardware upgrade, but with software. Will MS purposely refuse to upgrade win 2000 to support the new PCI bus? Is this even an issue?
:P
The last thing I want to do is have to learn linux sooner than I was planning...
... there are 66MHz and 64bit variations too.
I don't think many low-end users would be saturating a 64bit/66MHz PCI bus any time soon. There's room
for GB Ethernet and a couple of 3Ware/Ultra320 cards there.
Also, if the CPU bridge supports it one can have more than one PCI bus per motherboard so increased bandwidth isn't the only reason for PCI-Express.
you must be fucking your relatives over because that is definitely *not* how it works for the rest of us (shit if you can get 75% from ebay maybe i have some things for you to sell for me)
Unfortunately even those who are looking to hang onto "legacy PCI" (ie PCI-X) for a few more years concede they will be changing to PCI-Express when the time is right; they simply maintain that, with it being new technology, the time isn't yet right.
This is what happens when you get all your tech news from Anand and ZDnet. Why the hell can't /. link to an industry reference on this sort of topic? I realize this ain't a whole lot better, but at least it's not written (entirely) by poorly informed hobbyists.
"I feel this technology looks all set to replace PCI, and we really do need some new bus technology to keep up with the bandwidth demands of today's applications."
Really? Did that take all 70 points of your IQ, or just half?
I read some of the comics and I agree, they're pretty bad.
Why not both?
I've long wondered why CPUs rely on bridge chips to talk to memory, but even at 2.5gbps you'd need several memory interfaces to keep the CPU full. So, while it would be cool to have a CPU that used a relatively high level serial interface for everything, you'd still want dozens (or maybe even hundreds) of independant ports to communicate with all the memory and other peripherals.
Firewire and "many other things" aren't on a seperate bus. Any time you have RAID on your motherboard, it is on the PCI bus (excluding Intel's ICH4R/5R, but those have another problem -- limited by Intel's backwards 266MB/s of north-south bridge interconnect bus bandwidth, which PCI Express will fix...). Any new technology that hasn't been integrated into the south bridge yet (think Serial ATA here) -- you guessed it, PCI bus. Heck, many older chipsets USED the PCI bus to connect the south bridge to the north bridge! By going to a point-to-point bus to replace PCI, you get a lot of good things done (which, had you read the article, you would have known):
1) Easier wiring on the motherboard (less pins, less wires -- the old serial vs. parallel problem)
2) More available bandwidth and EASY extention (just drop another wire -- I believe the standard supports up to 32 as of now, which (besides being an ungodly amount of bandwidth anyway) isn't even a hard limit -- there is no reason it can't be further extended)
3) A standard bus for a lot of things (not only PCI, but PCI Express can be used to connect any peripheral with it's own dedicated bus (think 10Gb Ethernet, Firewire 800, Serial ATA RAID, UW-SCSI), it can connect north bridge to south bridge, etc.) All those devices on "another bus" are on dedicated links to the south bridge, and every single one of them is different. PCI Express can standardize the link and make it much easier to manufacture the boards and much quicker to add in new tech.
4) Clearing up the IRQ situation by removing sideband interrupts and going straight to message-interrupts
5) PCI compatibility, both at the slot layer (for x1 slots) and at the OS layer (though enhanced PCI Express support may be required for some things; this isn't entirely clear yet)
There are two parts to reading. One is looking quickly and then replying. The other is understanding. Appearently, you've mastered one. Maybe, one day, for all our sakes, you'll get the second as well.
is PCI express the answer? no. neither is PCI-X :) something serial will be better and faster. can you wait or will PCI Express do untill then? i think i can wait, we'll see. i don't think this is a forced upgrade cycle. i think it's just that new ideas come up faster then they, the companies, can implement the older ones.
All that is gold does not glitter, Not all those who wander are lost.
The company you guys love to hate because you have been brainwashed by Micron. Won't be long before you are all paying Rambus to use a PCI Express solution that works as well as royalties on SDRAM and DDR(the FTC case is going badly for Micron)
Rambus Samples Industry's First Chips with RaSer PCI Express PHY Cell
PHY cell is sampling in TSMC 0.13-micron and available for licensing
Los Altos,CA - June 02, 2003 - Rambus Inc. (Nasdaq:RMBS), a leading provider of chip-to-chip interface products and services, today announced it has provided its customers with first samples of chips supporting the PCI Express(tm) interface. Rambus customers are using this chip to evaluate the RaSer(tm) physical layer (PHY) cell for PCI Express applications. The new chip can be combined with FPGAs, ASICs or other chips on PCI Express boards to be used for compliance and interoperability testing.
Rambus' PCI Express PHY evaluation chip is the first to be implemented on a TSMC 0.13-micron process and has been delivered to customers for system level testing. The chip supports four PCI Express lanes, to address x4, x8, x16 and x32-lane based PCI Express devices used in chipset, graphics, and switch-based applications for PCs, servers and communications systems. The chip meets PCI Express specifications, including the jitter requirements, and supports key functions such as Receiver Detect and Beacon Generate and Detect features.
"This chip is the first PCI Express silicon IP off our 0.13-micron process. Rambus has demonstrated its ability to deliver challenging serial interface technology on advanced processes. This early PCI Express silicon is key to enabling our customers to take advantage of the market's expected rapid adoption of the PCI Express standard," said Ed Chen, director of Design and e-Service marketing for TSMC.
TSMC leads the industry in 0.13-micron production, having taped out more than 230 product designs to its advanced 0.13-micron processes. With 100,000 plus eight-inch equivalent wafers already shipped, year-end 2003 production is projected to exceed 400,000 wafers. More than half of TSMC's 2003 0.13-micron capacity will be in 300mm-wafers.
Rambus has developed high-speed I/O solutions for its customers for over 13 years. This expertise, initially applied to the memory market, is now being applied to other chip interface markets such as PCI Express interconnects. Beyond high speed circuit design, Rambus' expertise includes signal integrity analysis, high speed package design, and board / backplane characterization as well as extensive modeling.
"We strongly believe in the importance of the PCI Express interface for next-generation chip interconnect applications," said Kevin Donnelly, vice president of the Logic Interface Division at Rambus. "We are seeing tremendous demand from our customers to bring PCI Express solutions to market quickly on TSMC's leading foundry processes."
The RaSer PCI Express PHY features low power consumption - 80mW power per lane - and a small die area. The RaSer PHY is based on a proven SerDes cell used in InfiniBand(tm)and Ethernet XAUI products. Rambus offers a configurable Physical Coding Sublayer (PCS) layer to provide customers a flexible interface to the PCI Express MAC and upper logic layers.
My question to you all is would anything be saved by slapping the USB and firewire onto PCI-3?
People who think they know everything really piss off those of us that actually do.
...Not in the sense of dropping your old modem, sound card, video card, SCSI card, DTV card, wireless card, (etc.) into a PCI-Express motherboard. Since it's not electrically compatible, you'll have to find a motherboard that offers both kinds of slots.
As far as DRM, I see it as simply an extra opportunity for DRM supporters to ship the new devices with revised firmware that may contain support for DRM. I like my old devices for that very reason; nobody heard of DRM when I bought my sound card.
Everything is fast enough, until something comes along that is faster, then the old one isn't fast enough. You don't see devices come along that use more resources than a computer is going to have... You don't see 10-gigibit ethernet on 32-bit PCI cards. It's a chicken and egg problem (but it's obvious which one has to come first).
You don't plug your 10-gigibit enthernet card into your AGP slot, nor your 6-port firewire card, HDTV-tuner, USB2, etc. Sure, video output is bandwidth hungry, and it's a good thing it's on a seperate bus, but that doesn't completely take away the need for a faster general-purpose bus.
I'll just go down to my local Worst Buy and see how many 64-bit PCI devices they have... Hmmm, none. In fact, it's difficult to find many of them anywhere you look. Also, you will notice that 64-bit PCI slots only tend to appear on 64-bit computers! That's right, either Sun, Alpha, IBM, or just dual Intel/AMD systems, but you can't find them on single processor IA32 systems. Add to that the prohibitive size of 64-bit PCI slots... I don't believe 16-bit ISA cards with a VESA extension was quite that big.
Me too, but for different reasons.
You really have to go out of your way to find an alternative. That is the main reason people don't have them, IMHO.
Slashdot gets worse every day... Pipedot: News for nerds, without the corporate slant