6Gbps Performance

I installed the Intel SSD 510 in a 15-inch 2011 MacBook Pro as well as a 15-inch 2010 MacBook Pro to put together a 3Gbps vs. 6Gbps performance comparison. I turned to Xbench for some quick and dirty performance data:

SATA Performance—XBench 1.3
Intel SSD 510 250GB 3Gbps (2010 15-inch MBP) 6Gbps (2011 15-inch MBP) 6Gbps Advantage
4KB Sequential Write 157.8 MB/s 192.2 MB/s +21.8%
256KB Sequential Write 182.0 MB/s 257.1 MB/s +41.3%
4KB Sequential Read 32.5 MB/s 32.7 MB/s 0.0%
256KB Sequential Read 197.3 MB/s 315.6 MB/s +60.0%
4KB Random Write 47.8 MB/s 49.0 MB/s +2.5%
256KB Random Write 186.4 MB/s 260.9 MB/s +40.0%
4KB Random Read 14.5 MB/s 13.4 MB/s -7.6%
256KB Random Read 149.7 MB/s 207.3 MB/s +38.5%

As you'd expect, there's no real benefit to the new 6Gbps interface for random operations (particularly at low queue depths). Sequential speeds are much improved however. Xbench shows up to a 60% increase in performance in sequential operations.

You'll note that the absolute numbers are pretty low to begin with. A 128KB sequential read of the Intel SSD 510 on our desktop Sandy Bridge SSD testbed pulls nearly 400MB/s. On the new MacBook Pro we can't get more than 320MB/s.

Our sequential Iometer tests are run at a queue depth of 1 so there's no advantage there. The only explanation I can come up with (assuming Xbench's test is accurate) is that Apple may be aggressively implementing SATA controller power management under OS X. Capping the link's performance or aggressively putting it to sleep could reduce performance at the benefit of increasing battery life.

The other thing I noticed was that performance on the 13-inch MBP using Xbench was a bit lower than the 15-inch MBP. Take a look at these numbers:

SATA Performance—XBench 1.3
Intel SSD 510 250GB 13-inch 2011 MBP 15-inch 2011 MBP
4KB Sequential Write 155.3 MB/s 192.2 MB/s
256KB Sequential Write 184.8 MB/s 257.1 MB/s
4KB Sequential Read 30.4 MB/s 32.7 MB/s
256KB Sequential Read 201.8 MB/s 315.6 MB/s
4KB Random Write 49.6 MB/s 49.0 MB/s
256KB Random Write 183.9 MB/s 260.9 MB/s
4KB Random Read 13.9 MB/s 13.4 MB/s
256KB Random Read 144.9 MB/s 207.3 MB/s

I only noticed this with the Intel SSD 510, the Crucial RealSSD C300 and Vertex 3 both performed identically between the 13 and 15-inch MBPs. I'm not sure what's going on here at all, although I suspect that it's somehow related to the issues users have been having with some of these drives (more on this below).

SSD Recommendations

Where does all of this discussion about SSDs leave us? Unfortunately recommending an SSD for the new MacBook Pro today is pretty difficult but I'll try my best.

If you're the conservative type and just wants something that for sure works with little to no concern about absolute performance, the Apple SSDs are probably the safest bet. You'll get a drive that's much faster than a hard drive, fully supported by Apple and with TRIM support. Yes, that's right, OS X finally has TRIM support but Apple only enables it on it's own branded SSDs. To Apple's credit, given the number of problems I've seen with SSDs over the past couple of years it makes sense to lock down and only support drives you've validated. On the flip side however, Apple should be validating and working with controller makers to ensure all drives work under OS X. Making as much money as Apple does, I don't buy the "we didn't have the time/resources" argument.

If you are going down the Apple SSD path, at least the 128GB drive isn't super ridiculously priced, although I'm less comfortable recommending the 256GB version unless you can get it at $500.

Now if you want to get a faster SSD or actually take advantage of the 6Gbps interface, things get more complicated. I've heard reports of users having issues with the Intel SSD 510 and Crucial RealSSD C300. I've tested both drives as well as the OCZ Vertex 3 in three different MacBook Pros, and in all cases the drives worked perfectly. They were all detected as 6Gbps drives and all performed well. I should note that while I couldn't get the Vertex 3 Pro to work in the 2010 MacBook Pro, the Vertex 3 worked just fine in the 2011 MacBook Pro.

SATA Performance—XBench 1.3
13-inch 2011 MBP Crucial C300 256GB Intel SSD 510 250GB OCZ Vertex 3 240GB
4KB Sequential Write 239.0 MB/s 155.3 MB/s 319.9 MB/s
256KB Sequential Write 217.2 MB/s 184.8 MB/s 257.8 MB/s
4KB Sequential Read 35.1 MB/s 30.4 MB/s 33.3 MB/s
256KB Sequential Read 248.3 MB/s 201.8 MB/s 311.8 MB/s
4KB Random Write 175.0 MB/s 49.6 MB/s 247.8 MB/s
256KB Random Write 226.6 MB/s 183.9 MB/s 290.0 MB/s
4KB Random Read 19.1 MB/s 13.9 MB/s 21.1 MB/s
256KB Random Read 239.0 MB/s 144.9 MB/s 304.0 MB/s

SATA Performance—XBench 1.3
15-inch 2011 MBP Crucial C300 256GB Intel SSD 510 250GB OCZ Vertex 3 240GB
4KB Sequential Write 239.3 MB/s 192.2 MB/s 316.5 MB/s
256KB Sequential Write 218.8 MB/s 257.1 MB/s 282.0 MB/s
4KB Sequential Read 34.8 MB/s 32.7 MB/s 34.2 MB/s
256KB Sequential Read 245.1 MB/s 315.6 MB/s 306.7 MB/s
4KB Random Write 160.5 MB/s 49.0 MB/s 240.5 MB/s
256KB Random Write 227.5 MB/s 260.9 MB/s 311.3 MB/s
4KB Random Read 18.7 MB/s 13.4 MB/s 20.9 MB/s
256KB Random Read 238.2 MB/s 207.3 MB/s 303 MB/s

The Vertex 3 is the fastest drive out of the aforementioned three, but its availability and firmware maturity are both unknowns at this point. If you have to buy today and are ok with the chance that the drive may not work (given other experiences online, although I haven't seen problems), Intel's SSD 510 is likely a good runner up (at least for the 15-inch, the C300 seems to perform better on the 13).

As far as the reports of incompatibilities with these drives are concerned, I'm not really sure what's going on. I've been hammering on all of the drives, putting the system to sleep/waking it up, and haven't encountered any failures or high latency IO operations (stuttering) yet. That's not to say that these problems won't appear over time (I'm currently doing long term testing to figure that out now), but just that I haven't seen them yet.

If you are having issues with the Intel SSD 510, Crucial RealSSD C300 or anything else please email me (link at the top of the page) the following information:

1) What are the full specs of your MBP? Any upgrades?

2) Tell me about your SSD. Is it new out of box? Have you done anything to the drive? What model, firmware revision, etc...

3) Describe the symptoms of the issue—beachballs, data corruption, etc...? What do you have to do create the issue?

4) Is the drive detected as a 6Gbps drive or a 3Gbps drive?

5) Take me through your drive installation procedure, did you just pop it in, partition and install OS X?

6) Any visible damage to the SATA flex cable when you installed the drive?

7) Have you tried exchanging the SSD or MBP? Any difference in behavior?

We haven't seen any issues on three different 2011 models that we've been testing here extensively with the Intel SSD 510, Crucial RealSSD C300, OCZ Vertex 3 and OCZ Vertex 2. I realize a number of you are having issues so the more details I can get the better.

Apple's SSD Strategy The GPU Comparison
POST A COMMENT

197 Comments

View All Comments

  • IntelUser2000 - Friday, March 11, 2011 - link

    You don't know that, testing multiple systems over the years should have shown performance differences between manufacturers with identical hardware is minimal(<5%). Meaning its not Apple's fault. GPU bound doesn't mean rest of the systems woud have zero effect.

    It's not like the 2820QM is 50% faster, its 20-30% faster. The total of which could have been derived from:

    1. Quad core vs. Dual core
    2. HD3000 in the 2820QM has max clock of 1.3GHz, vs. 1.2GHz in the 2410M
    3. Clock speed of the 2820QM is quite higher in gaming scenarios
    4. LLC is shared between CPU and Graphics. 2410M has less than half the LLC of 2820QM
    5. Even at 20 fps, CPU has some impact, we're not talking 3-5 fps here

    It's quite reasonable to assume, in 3DMark03 and 05, which are explicitely single threaded, benefits from everything except #1, and frames should be high enough for CPU to affect it. Games with bigger gaps, quad core would explain to the difference, even as little as 5%.
    Reply
  • JarredWalton - Friday, March 11, 2011 - link

    I should have another dual-core SNB setup shortly, with HD 3000, so we'll be able to see how that does.

    Anyway, we're not really focusing on 3DMarks, because they're not games. Looking just at the games, there's a larger than expected gap in the performance. Remember: we've been largely GPU limited with something like the GeForce G 310M using Core i3-330UM ULV vs. Core i3-370. That's a doubling of clock speed on the CPU, and the result was: http://www.anandtech.com/bench/Product/236?vs=244 That's a 2 to 14% difference, with the exception of the heavily CPU dependent StarCraft II (which is 155% faster with the U35Jc).

    Or if you want a significantly faster GPU comparison (i.e. so the onus is on the CPU), look at the Alienware M11x R2 vs. the ASUS N82JV: http://www.anandtech.com/bench/Product/246?vs=257 Again, much faster GPU than the HD 3000 and we're only seeing 10 to 25% difference in performance for low detail gaming. At medium detail, the difference between the two platforms drops to just 0 to 15% (but it grows to 28% in BFBC2 for some reason).

    Compare that spread to the 15 to 33% difference between the i5-2415M and the i7-2820QM at low detail, and perhaps even more telling is the difference remains large at medium settings (16.7 to 44% for the i7-2820QM, except SC2 turns the tables and leads by 37%). The theoretical clock speed difference on the IGP is only 8.3%, and we're seeing two to four times that much -- the average is around 22% faster, give or take. StarCraft II is a prime example of the funkiness we're talking about: the 2820QM is 31% faster at low, but the 2415M is 37% faster at medium? That's not right....

    Whatever is going on, I can say this much: it's not just about the CPU performance potential. I'll wager than when I test the dual-core SNB Windows notebook (an ASUS model) that scores in gaming will be a lot closer than what the MBP13 managed. We'll see....
    Reply
  • IntelUser2000 - Saturday, March 19, 2011 - link

    I forgot one more thing. The quad core Sandy Bridge mobile chips support DDR3-1600 and dual core ones only up to DDR3-1333. Reply
  • mczak - Thursday, March 10, 2011 - link

    memory bus width of HD6490M and H6750M is listed as 128bit/256bit. That's quite wrong, should be 64bit/128bit.

    btw I'm wondering what's the impact on battery life for the HD6490M? It isn't THAT much faster than the HD3000, so I'm wondering if at least the power consumption isn't that much higher neither...
    Reply
  • Anand Lal Shimpi - Thursday, March 10, 2011 - link

    Thanks for the correction :)

    Take care,
    Anand
    Reply
  • gstrickler - Thursday, March 10, 2011 - link

    Anand, I would like to see heat and maximum power consumption of the 15" with the dGPU disabled using gfxCardStatus. For those of us who aren't gamers and don't need OpenCL, the dGPU is basically just a waste of power (and therefore, battery life) and a waste of money. Those should be fairly quick tests. Reply
  • Nickel020 - Thursday, March 10, 2011 - link

    The 2010 Macbooks with the Nvidia GPUs and Optimus switch to the iGPU again even if you don't close the application, right? Is this a general ATI issue that's also like this on Windows notebooks or is it only like this on OS X? This seems like quite an unnecessary hassle, actually having to manage it yourself. Not as bad as having to log off like on my late 2008 Macbook Pro, but still inconvenient. Reply
  • tipoo - Thursday, March 10, 2011 - link

    Huh? You don't have to manage it yourself. Reply
  • Nickel020 - Friday, March 11, 2011 - link

    Well if you don't want to use the dGPU when it's not necessary you kind of have to manage it yourself. If I don't want to have the dGPU power up while web browsing and make the Macbook hotter I have to manually switch to the iGPU with gfxCardStatus. I mean I can leave it set to iGPU, but then I will still manually have to switch to the dGPU when I need the dGPU. So I will have to manage it manually.

    I would really have liked to see more of a comparison with how the GPU switching works in the 2010 Macbook Pros. I mean I can look it up, but I can find most of the info in the review somewhere else too; the point of the review is kind of to have it all the info in one place, and not having to look stuff up.
    Reply
  • tajmahal42 - Friday, March 11, 2011 - link

    I think switching behaviour should be exactly the same for the 2010 and 2011 MacBook Pros, as the switching is done by the Mac OS, not by the Hardware.

    Apparently, Chrome doesn't properly close done Flash when it doesn't need it anymore or something, so the OS thinks it should still be using the dGPU.
    Reply

Log in

Don't have an account? Sign up now