A New Socket and New Chipsets

There’s no nice way to put this: Sandy Bridge marks the third new socket Intel will have introduced since 2008. The first was LGA-1366 for the original Nehalem based Core i7. In 2009 we got LGA-1156 for Lynnfield, later updated with support for the dual-core Clarkdale CPUs launched in 2010. Next year, Sandy Bridge will launch with LGA-1155.

The CPU and socket are not compatible with existing motherboards or CPUs. That’s right, if you want to buy Sandy Bridge you’ll need a new motherboard.

As is the case today, there are two lines of chipsets for consumer desktops: H and P series. The H series supports Sandy Bridge’s on-die graphics, while the P series is strictly for discrete graphics.

At launch we’ll have P67 and H67 based motherboards, both of which are in testing right now. A quarter later we’ll see value H61 motherboards added to the mix.

Chipset Comparison
  P67 H67 H61 P55 H57 H55
CPU Support Sandy Bridge LGA-1155 Sandy Bridge LGA-1155 Sandy Bridge LGA-1155 Lynnfield / Clarkdale LGA-1156 Lynnfield / Clarkdale LGA-1156 Lynnfield / Clarkdale LGA-1156
CPU PCIe Config 1 x 16 or 2 x 8 PCIe 2.0 1 x 16 PCIe 2.0 1 x 16 PCIe 2.0 1 x 16 or 2 x 8 PCIe 2.0 1 x 16 PCIe 2.0 1 x 16 PCIe 2.0
RAID Support Yes Yes No Yes Yes Mp
USB 2.0 Ports 14 14 10 14 14 12
SATA Total (Max Number of 6Gbps Ports) 6 (2) 6 (2) 4 (0) 6 (0) 6 (0) 6 (0)
PCIe Lanes 8 (5GT/s) 8 (5GT/s) 6 (5GT/s) 8 (2.5GT/s) 8 (2.5GT/s) 6 (2.5GT/s)

With P67 you lose integrated graphics but you gain the ability to run two PCIe x8 cards off of the CPU. You also get fully unlocked memory multipliers with P67, whereas H67 is locked to whatever official DDR3 speeds Intel supports with Sandy Bridge (currently DDR3-1333).

Both H67 and P67 support 6Gbps SATA, however only on two ports. The remaining 4 SATA ports are 3Gbps. Motherboard manufacturers will color the 6Gbps ports differently to differentiate.

There’s no native USB 3.0 support on these chipsets, but most motherboard makers are looking to third party solutions to enable USB 3 on Sandy Bridge boards.

The other major (and welcome) change is the move to PCIe 2.0 lanes running at 5GT/s. Currently, Intel chipsets support PCIe 2.0 but they only run at 2.5GT/s, which limits them to a maximum of 250MB/s per direction per lane. This is a problem with high bandwidth USB 3.0 and 6Gbps SATA interfaces connected over PCIe x1 slots. With the move to 5GT/s, Intel is at feature parity with AMD’s chipsets and more importantly the bandwidth limits are a lot higher. A single PCIe x1 slot on a P67 motherboard can support up to 500MB/s of bandwidth in each direction (1GB/s bidirectional bandwidth).

With native 6Gbps SATA support, the faster PCIe interface will be useful for any third party USB 3.0 controllers.

Original Nehalem and Gulftown owners have their own socket replacement to look forward to. In the second half of 2011 Intel will replace LGA-1366 with LGA-2011. LGA-2011 adds support for four DDR3 memory channels and the first 6+ core Sandy Bridge processors.

A New Architecture The Roadmap & Pricing
Comments Locked

200 Comments

View All Comments

  • tatertot - Tuesday, August 31, 2010 - link

    Can you also confirm whether or not the GPU turbo was also disabled?
  • DanNeely - Saturday, August 28, 2010 - link

    Do you think Intel will be sharing preliminary performance/pricing data on LGA 2011 by the time that the first LGA 1155 parts start shipping? I'm on 1366 now and would like to know if staying on the high end platform will be a reasonable option or if there isn't any point in holding off for another 6 months on my upgrade.
  • Anand Lal Shimpi - Saturday, August 28, 2010 - link

    I wouldn't expect any near-final LGA-2011 performance data until Q2 next year, well after the LGA-1155 launch.

    Take care,
    Anand
  • Casper42 - Saturday, August 28, 2010 - link

    2 things jumped out at me

    1) No USB3 - Major FAIL. Putting USB3 in an Intel chipset will drive huge adoption rates rather than this limping in BS by manufacturers today. Not to mention that for Hard Drives, USB2 has been a bottleneck for a long time whereas only top end SSDs today are maxing out SATA3

    2) 2 chips with Quad Core and no HT that are identical except for Clock speed and one of them is essentially the 400 and the other is the 500? WTF? Call them the 2410, 2420, 2430, etc. That gives you like 8 or 9 speed bins for that family. Whomever is doing the numbering at Intel needs a swift kick to the head to get them back on track mentally as things just get more and more confusing. You have the i3/i5/i7 today, why not just change it to:
    i2 = Dual Core no HT/Turbo
    i3 = Dual Core with HT and/or Turbo
    i4 = Quad Core no HT/Turbo
    i5 = Quad WITH
    i6 = Six without
    etc
    As it stands now we have i5 with both dual and quad core and i7 with 4 and 6. just doesnt make sense.
  • dertechie - Saturday, August 28, 2010 - link

    That's quite the IPC improvement there. Not quite Netburst to Core 2 but a lot more than I expected (I was expecting something on the order of 5%, with most gains coming from ramping clocks with the extra headroom of 32nm).

    Question is, do I want the i5-2500K more than I loathe Intel's motherboard department? I'm seeing them bring out new sockets almost as often as new processor families, which really, really does not make me confident in the socket's future.

    I will wait at least for Bulldozer benches before buying whatever makes sense at that time (okay, probably weighted in AMD's favor). I've lasted 4 years on this Pentium D, I can live another half of one.
  • IntelUser2000 - Saturday, August 28, 2010 - link

    Why do some people still compare Netburst vs. Core 2? The Pentium 4 generation was a clock speed focused that that FAILED to realize its clock speed potential so it looked really bad compared to Core 2.

    Compared to Core Duo Core 2 was only 15-20% faster. Sandy Bridge manages to do another 20%, which is really good in a generation, yea?
  • ssj4Gogeta - Saturday, August 28, 2010 - link

    Pentium D to SB will be such a huuuuge jump, lol.
  • neslog - Saturday, August 28, 2010 - link

    Your excellent article was exciting to read. Thank you!

    I noticed a small typo on the Windows 7 Gaming Performance page in the first line under the Data Recovery chart : "Clock for clock...to the i7{5} 760..."
  • ET - Saturday, August 28, 2010 - link

    I think that the integrated graphics here are a game changer. Sure nobody will look to them for serious gaming, but finally they're at a point where if you buy any CPU you will be able to play most games, even if at low settings. I'll be looking forward especially to the mobile CPU's. With Bobcat around the corner, I guess next year we will finally see mainstreams notebooks become capable of some game playing, which will be great (and bad for NVIDIA).
  • Exodite - Saturday, August 28, 2010 - link

    What I'd like to see is something like Nvidia's Optimus make it to the desktop. With both AMD and Intel going for on-chip integrated graphics the market is practically begging for a unified standard for graphics switching.

    The next-generation IGPs look to be competent enough for anything but high-end gaming, which means I should be able to power down my discrete graphics card completely most of the time. The end result would be significant reductions in noise generation, power usage and heat emissions.

    Having discreet graphics cards reduced to basically connector-less, slot-in cards for on-demand co-processing seems the logical step.

Log in

Don't have an account? Sign up now