Next-Generation Intel Chipsets May Drop PCI Bus
As far as we're concerned, PCI can't die quickly enough. Intel began working on the standard 20 years ago and made it the preferred interconnect standard for second-generation Pentium systems as early as 1994. By 1999-2000, modern motherboards had all but dropped ISA (Industry Standard Architecture) and typically included just one slot per board. The then-new PCI standard supported a wide range of features ISA couldn't and offered 4x the bandwidth of the EISA bus.
The principle problem with PCI was its inability to scale either bit size or clockspeed. 64-bit PCI used a significantly larger physical slot, which made it more expensive, while the number of bus lines made increasing the base clockspeed tricky. Where consumer products were concerned, transfer speeds topped out at 133MB/s. This limitation led to the development of AGP, which was essentially a point-to-point PCI bus that supported additional features like sideband addressing and GART.
PCI Express x16 offers more than 6x the bandwidth of PCI-X, but uses a smaller slot
Modern devices—even PCI Express x1 devices—offer between 50-300 percent more bandwidth than PCI, depending on whether or not the PCI Express slot is a first or second-generation device. By the time PCI-Express 3.0 is finished, a single x1 connection will offer up to 800MB/s of bandwidth—6x more than first-generation PCI.
Backwards Compatibility Concerns:
The good news for consumers is that Intel's decision to drop PCI support should be all-but painless and may even improve peripheral performance in some cases. It's less common than it used to be, but some motherboard manufacturers still hang spare SATA/Ethernet/USB2 ports off the PCI bus, even though doing so adds latency and potentially reduces performance.
This decision may not sit well with users who rely on PCI slots for additional ports or video cards, but moving away from PCI is still a good idea, even if it penalizes small groups of people. The vast majority of add-in cards today are still built using PCI, but even a single mechanical hard drive can saturate its 133MB/s bus in certain circumstances. USB 3, next-generation FireWire, and RAID arrays are similarly pinched for bandwidth; we've reached the point where the PCI bus imposes a noticeable performance penalty on nearly every type of add-in card.
Unfortunately, the market as a whole is stuck in a reverse chicken/egg scenario. The majority of add-in cards are manufactured using PCI because it's the universal standard that everyone has and that people are most comfortable with. Because of this, manufacturers continue to use it, and thus perpetuate the cycle. Intel's clean break, when/if the company makes one, won't end PCI compatibility—third party manufacturers will continue to provide bridge chips—but it will send a signal to the computer industry as a whole that it's time to move on.
Next-generation products like SSDs, USB3, and even SATA 6G are only useful if their performance isn't handicapped by this sort of issue. If getting rid of PCI is the price we pay to ensure external devices are just as fast as their internal counterparts, we judge the trade well worth it.
|
Via: Kingofgng | News Archive
| Tags:
Intel,
RAID,
PCI Express,
pci,
FireWire,
USB3,
SATA 6G,
Series 6 Chipsets
|
|
This would not be a surprise at all since PCI-E x1 devices are widely available for any application along side the PCI variants. It also helps that there have been boards sprinkled with these diminutive interconnects for a couple of years now.
(Edit: I did not mean to imply in industry has interests in interfacing devices with pigs.) |
|
Very true. PCI-e devices seem to be far more common in every store I've been in lately |
News:
|
Anybody thinking raid 0 on a Single slot SSD on a PCI X slot. This is something I would toss my motherboard out the window for. USB 3.0 eh not so much. |
|
On a PCI X or PCI-Express? The fastest PCI-X HDD controller card I'm aware of was a 133MHz, 64-bit controller. I had one and an accompanying motherboard, but fast as it was, that's still just 1.06GB/s of bandwidth. Also, remember the other drawback of PCI-X. If a PCI-X slot shares bandwidth with a PCI slot and the PCI slot is running a 32-bit card, the PCI-X slot was automatically constrained to 33MHz as well. The only solution to that was to buy a motherboard that used multiple PCI controllers. |
|
As far as I am concerned this is a good thing. I also am much more satisfied with the performance of peripherals on a USB3 or a E-SATA outlet. The advantages of USB 3 is it is completely backwards compatible. As for PCI I use nothing in my PCI slots everything is PCI Express. The bandwidth on the boards and with the equipment it connects is so more advantageous than PCI that I see no point in the protocol anymore. The main thing here is the bandwidth as well as the limitations of PCI. As processors become more and more multi core, and we have memory that is faster and faster the limitation drags everything backwards. The bandwidth advantages of PCI express are 6 to 8 times the amount of PCI. So PCI is needed no more at least in my eyes. Anyone using PCI components that could replace them with PCI Express ones would therefore gain from the upgrade. The saying time is money is very relative to society currently as it is basically the state of all these advances in technology. The more you can get done in the least amount of time thanks to these upgrades is the value of it all. Of course as fast as everything moves today equipment wise keeping up can be a pricey undertaking. So you have to choose the right components and peripherals. Either way PCI to me is a dead outlet, and therefore wasted space. Which is just that nothing more than a waste, not to mention the energy advantages of PCI Express and components which use it. |
|
Joel, I think MrBrownSound meant PCIe. I run into a lot of people who abbreviate it PCIx, mostly out of the onomatopoeia. We run into the same problem with SATA 6G: some people call it SATA 3, confusing it with the still-current SATA 3G (SATA II). Personally I think we should just all go to Cro-Magnon pictograms: PCI Express would be a group of hunters on a hill, then spears flying downward, then an ox. PCI-X, on the other hand, would be a group of hunters, the sun rising above a hillock, then a flowering plant near a river. Much simpler. As the article mentioned, any motherboard manufacturer worth its salt would provide some legacy support; heck, they still include floppy disk and PATA connectors. But shuffling it off to a subsidiary place on the mainboard would provide the impetus for peripheral manufacturers to retool and produce PCIe x1 versions of their PCI cards. So, all in all, I think it's a good move on Intel's part-- even though it makes my state-of-the-art system just a little more obsolete. |
|
Clemsnide: I think your idea for Cavemangrams is fabulous. I hereby declare this concept to be "HotHardware Approved" *attaches gold star* |
|
The other nice thing about getting rid of PCI (hopping back on topic) is eliminating latency. One of the not-so-fun issues with the bus is that multiple devices have to wait their turn. Since PCIe is a point-to-point topology, there's no such restriction. |
|
Not to mention, PCI Sig Express will announce PCI-E 3.0 by mid 2011. |
stuff on Hot Hardware
Loading...
Loading...
Loading...
