The Sandy Bridge Review: Intel Core i7-2600K, i5-2500K and Core i3-2100 Tested
by Anand Lal Shimpi on January 3, 2011 12:01 AM ESTThe 6-series Platform
At launch Intel is offering two chipset families for Sandy Bridge: P-series and H-series, just like with Lynnfield. The high level differentiation is easy to understand: P-series doesn’t support processor graphics, H-series does.
There are other differences as well. The P67 chipset supports 2x8 CrossFire and SLI while H67 only supports a single x16 slot off of the SNB CPU (the chip has 16 PCIe 2.0 lanes that stem from it).
While H67 allows for memory and graphics overclocking, it doesn’t support any amount of processor overclocking. If you want to overclock your Sandy Bridge, you need a P67 motherboard.
6Gbps
Had SSDs not arrived when they did, I wouldn’t have cared about faster SATA speeds. That’s how it worked after all in the evolution of the hard drive. We’d get a faster ATA or SATA protocol, and nothing would really change. Sure we’d eventually get a drive that could take advantage of more bandwidth, but it was a sluggish evolution that just wasn’t exciting.
SSDs definitely changed all of that. Today there’s only a single 6Gbps consumer SSD on the market—Crucial’s RealSSD C300. By the middle of the year we’ll have at least two more high-end offerings, including SandForce’s SF-2000. All of these SSDs will be able to fully saturate a 3Gbps SATA interface in real world scenarios.
Intel's DP67BG—The blue SATA ports on the right are 6Gbps, the black ones are 3Gbps
To meet the soon to be growing need for 6Gbps SATA ports Intel outfits the 6-series PCH with two 6Gbps SATA ports in addition to its four 3Gbps SATA ports.
I dusted off my 128GB RealSSD C300 and ran it through a bunch of tests on five different platforms: Intel’s X58 (3Gbps), Intel’s P67 (3Gbps and 6Gbps), AMD’s 890GX (6Gbps) and Intel’s X58 with a Marvell 9128 6Gbps SATA controller. The Marvell 91xx controller is what you’ll find on most 5-series motherboards with 6Gbps SATA support.
I ran sequential read/write and random read/write tests, at a queue depth of 32 to really stress the limits of each chipset’s SATA protocol implementation. I ran the sequential tests for a minute straight and the random tests for three minutes. I tested a multitude of block sizes ranging from 512-bytes all the way up to 32KB. All transfers were 4KB aligned to simulate access in a modern OS. Each benchmark started at LBA 0 and was allowed to use the entire LBA space for accesses. The SSD was TRIMed between runs involving writes.
Among Intel chipsets I found that the X58 has stellar 3Gbps SATA performance, which is why I standardize on it for my SSD testbed. Even compared to the new 6-series platform there are slight advantages at high queue depths to the X58 vs. Intel’s latest chipsets.
Looking at 6Gbps performance though there’s no comparison, the X58 is dated in this respect. Thankfully all of the contenders do well in our 6Gbps tests. AMD’s 8-series platform is a bit faster at certain block sizes but for the most part it, Intel’s 6-series and Marvell’s 91xx controllers perform identically.
I hate to be a bore but when it comes to SATA controllers an uneventful experience is probably the best you can hope for.
Facebook
Twitter
RSS
283 Comments
View All Comments
hmcindie - Monday, January 3, 2011 - link
Why is that Quick Sync has better scaling? Very evident in the Dark Knight police car image as all the other versions have definite scaling artifacts on the car.Scaling is something that should be very easy. Why is there so big a difference? Are these programs just made to market new stuff and no-one really uses them because they suck? So big scaling differences between codepaths make no sense.
JarredWalton - Monday, January 3, 2011 - link
It looks to me like some of the encodes have a sharpening effect applied, which is either good (makes text legible) or bad (aliasing effects) depending on your perspective. I'm quite happy overall with the slightly blurrier QS encodes, especially considering the speed.xxxxxl - Monday, January 3, 2011 - link
I've been so looking forward to SB...only to hear that H67 cant overclock CPU?!?!?!?!Disappointed.
digarda - Monday, January 3, 2011 - link
Who needs the IGP for a tuned-up desktop PC anyway? Some for sure, but I see the main advantages of the SB GPU for business laptop users. As the charts show, for desktop PC enthusiasts, the GPU is still woefully slow, being blown away even by the (low-end) Radeon 5570. For this reason, I can't help feeling that the vast majority of overclockers will still want to have discrete graphics.I would have preferred to dual core (4-thread) models to have (say) 32 shaders, instead of the 6 or 12 being currently offered. At 32nm, there's probably enough silicon real estate to do it. I guess Intel simply didn't want the quad core processors to have a lower graphics performance than the dual core ones (sigh).
Pity that the socket 2011 processors (without a GPU) are apparently not going to arrive for nearly a year (Q4 2011). I had previously thought the schedule was Q3 2011. Hopefully, AMD's Bulldozer-based CPUs will be around (or at least imminent) by then, forcing intel to lower the prices for its high-end parts. On the other hand, time to go - looks like I'm starting to dream again...
Exodite - Monday, January 3, 2011 - link
Using myself as an example showing the drawback of limiting overclocking on H67 would be the lack of a good selection of overclocking-friendly micro-ATX boards due to most, if not all, of those being H67.Granted, that's not Intel's fault.
It's just that I have no need for more than one PCIe x16 slot and 3 SATA (DVD, HDD, SSD). I don't need PCI, FDD, PS2, SER, PAR or floppy connectors at all.
Which ideally means I'd prefer a rather basic P67 design in micro-ATX format but those are, currently, in short supply.
The perfect motherboard, for me, would probably be a P67 micro-ATX design with the mandatory x8/x8 Crossfire support, one x1 and one x4 slot, front panel connector for USB 3, dual gigabit LAN and the base audio and SATA port options.
Gigabyte?
Anyone? :)
geofelt - Monday, January 3, 2011 - link
The only P67 based micro-ATX motherboard I have found to date is theAsus P8P67-M pro. (or evo?)
Any others?
Rick83 - Monday, January 3, 2011 - link
There's also a non-pro P8P67-M.Keep in mind though, that the over-clocking issue may not be as bad as pointed out. There are H67 boards being marketed for over-clocking ability and manuals showing how to adjust the multiplier for CPUs... I'm not yet convinced over-clocking will be disabled on H67.
smilingcrow - Monday, January 3, 2011 - link
Major bummer as I was going to order a Gigabyte H67 board and an i5-2500K but am put off now. They seem to over-clock so well and with low power consumption that it seemed the perfect platform for me…I don’t mind paying the small premium for the K editions but being forced to use a P67 and lose the graphics and have difficulty finding a mATX P67 board seems crazy!
I wonder if this limit is set in the chipset or it can be changed with a BIOS update?
DanNeely - Monday, January 3, 2011 - link
Quick Sync only works if the IGP is in use (may be fixable via drivers later); for anyone who cares about video encoding performance that makes the IGP a major feature.mariush - Monday, January 3, 2011 - link
On the Dark Knight test...Looking at the Intel software encoding and the AMD encoding, it looks like the AMD is more washed out overall, which makes me think there's actually something related to colorspaces or color space conversion involved....
Are you guys sure there's no PC/TV mixup there with the luminance or ATI using the color matrix for SD content on HD content or something like that?