The next-gen MacBook Pro with Retina Display Review
by Anand Lal Shimpi on June 23, 2012 4:14 AM EST- Posted in
- Mac
- Apple
- MacBook Pro
- Laptops
- Notebooks
Thunderbolt Performance
Apple’s 2011 Macs were the first to enjoy Thunderbolt, an interface co-developed with Intel that carries PCIe and DisplayPort over a single cable. As it derives most of its revenue from mobile, Apple wasted no time in bringing its Thunderbolt Display to market. A single Thunderbolt cable could bring Gigabit Ethernet, Firewire 800, high-speed mass storage, external audio and display to an otherwise IO-deprived MacBook Air.
At a high level, Thunderbolt is pretty easy to explain. The current implementation of Thunderbolt pairs four PCIe 2.0 lanes with DisplayPort, offering a maximum bandwidth of 2GB/s in either direction in addition to DP bandwidth. The Thunderbolt interface itself can deliver 10Gbps of bandwidth in each direction, per channel. The physical Thunderbolt port is compatible with mini DisplayPort to allow for the use of mini-DP displays as well as Thunderbolt chains. Each Thunderbolt port can carry up to two Thunderbolt channels, although one channel is typically reserved for DisplayPort duties.
In the past we measured a maximum of 1GB/s of unidirectional bandwidth for a single Thunderbolt channel in addition to video bandwidth over DisplayPort. There’s no shipping device that will deliver this sort of performance, I needed to outfit a Promise Pegasus with a handful of SSDs to truly saturate the bus.
In the 2012 Macs Apple, like the rest of the PC industry, has switched to using Intel’s 2nd generation Thunderbolt controllers codenamed Cactus Ridge.
The Retina MacBook Pro uses a four-channel Cactus Ridge controller and drives two Thunderbolt ports with it. Each port can drive a mini-DP display or a Thunderbolt chain with a mini-DP/Thunderbolt Display at the end of or in it. The rMBP can actually drive a fourth panel (counting the integrated Retina Display) via the integrated HDMI port although that’s not an officially supported configuration.
Unlike most other implementations, Apple hangs the Cactus Ridge controller off of the Ivy Bridge CPU rather than the PCH. The GeForce GT 650M in the system only gets the use of 8 PCIe 3.0 lanes instead of the full 16, but with PCIe 3.0 this is not an issue (it wouldn’t be an issue with PCIe 2.0 either to be honest).
I performed the same test as before to test if maximum bandwidth has gone up since switching to Cactus Ridge. Initial results remained unchanged, I was able to get north of 900MB/s to an array of SSDs in the Pegasus connected to a single Thunderbolt port. Now with two Thunderbolt on the rMBP however I was able to create a second chain of devices. I only have a single Pegasus so I resorted to chaining a LaCie Little Big Disk (SSD) and Elgato Thunderbolt drive. The combination of the two isn’t anywhere near as fast as the SSD array in the Pegasus but it allowed me to push the limits of the controller even more:
1380MB/s, over copper, to the rMBP. I suspect if I had another Pegasus SSD array I’d be able to approach 1800MB/s, all while driving video over the ports. Apple may limit the internal storage expansion of the rMBP but you still have a path to expansion for storage of large media files and other archives. And it’s very fast.
Unfortunately Thunderbolt behavior is still not perfect, although it is improved compared to previous Macs. If you write to Promise’s Pegasus for long enough while playing audio through Apple’s Thunderbolt Display you will still drop audio frames. Subjectively it seems to take longer to trigger this phenomenon but it does still happen. On my early 2011 MacBook Pro the problem has gotten so bad that I’ll even drop other USB packets for devices connected to the Thunderbolt Display. If I’m writing to the Pegasus I’ll miss keystrokes and the mouse will jump around until the high-speed write is complete. So far I haven’t had anything this bad happen on the Retina MBP but it took a while for this behavior to manifest on my early 2011 model so we’ll see what happens. I’m not sure what the fix will be for these types of issues as it seems there’s no good quality of service assurance for PCIe devices residing on Thunderbolt. As Thunderbolt was supposed to be as transparent as possible, it’s not surprising that even QoS overhead is nonexistent but it’s something that is clearly necessary. I’m not sure this is Apple’s fault as I’ve seen similar behavior under Windows. I suspect it’s something that Intel is going to have to figure out a way to address.
Facebook
Twitter
RSS
471 Comments
View All Comments
Mumrik - Monday, June 25, 2012 - link
Anand, on page 4 you categorize the rMBP as a consumer device: "At 220 pixels per inch it’s easily the highest density consumer notebook panel shipping today.", but back on page 2 you made a deal of of calling it a pro "appliance" and pointed out that it wasn't a consumer device.
Other than that - this DPI improvement really needs to get moving. It's been so many years and we've essentially been standing still since LCDs took over and the monitor business became a race towards the bottom. IPS, high DPI and native support for it in software PLEASE. 120hz would be nice too.
dwade123 - Monday, June 25, 2012 - link
I don't understand why Apple doesn't take advantage of their lead in Thunderbolt. This machine screams for E-GPU with GTX 670!Spunjji - Tuesday, June 26, 2012 - link
Probably because right now the user experience would be poor. See Anand's comments about sound and USB cutting out when high-bandwidth transfers are occurring. That would be catastrophic mid-game and would definitely lead me to return the hardware as unfit for purpose. Apple have had their slip-ups but they rarely release hardware that is unfit for purpose.inaphasia - Monday, June 25, 2012 - link
Does Apple have some sort of exclusive deal (ie monopoly with an expiration date) on these displays, or can anybody (HP, Asus, Lenovo etc) use them if they want to?wfolta - Monday, June 25, 2012 - link
In recent years, Apple has been the King of the Supply Chain due to Tim Cook. He's now the CEO. I doubt that there will be many retina 15" screens available for Apple's competitors for a year or more.Even if Apple didn't lock up the supply chain, Apple's competitors have been running towards lower resolutions, or the entertainment-oriented 16:9 1920x1080 (aka 1080p), so it will take them a while to pivot towards higher-density displays even if they were growing on trees.
Constructor - Thursday, June 28, 2012 - link
Apple has been paying huge sums (in the Billions of Dollars!) to component manufacturers in advance to have them develop specific components such as this one, even paying for factories to be built for manufacturing exclusively for Apple for a certain time.It is also possible that Apple has licensed certain patents from various (other) manufacturers for their exclusive use which might preclude open-market sales of the same components even after the exclusive deal with Apple is up, because the display manufacturer may not be able to keep using these same patents.
In short: The chances for PC manufacturers to get at them just by waiting for them to drop into the market eventually don't look too good.
After all, none of the other Retina displays have appeared in other products yet. And the iPhone 4 is already two years old.
So either the non-Apple-supplying component manufacturers or the PC builders will have to actually pay for their own development. And given their mostly dismal profit margins and relatively low volumes in the premium segment, I wouldn't hold my breath.
Shanmugam - Monday, June 25, 2012 - link
Anand and Team,Excellent review again.
When is the MacBook Air Mid 2012 review coming? I really want to see the battery life improvement, I can see that it almost tops out at 8Hours for light work load for 13" MBA.
Cannot wait!!!
smozes - Monday, June 25, 2012 - link
Anand states: "[E]nough to make me actually want to use the Mac as a portable when at home rather than tethered to an external panel. The added portability of the chassis likely contributes to that fact though."I work with an external display at home, and given that there are none yet at this caliber, I'm wondering about doing away with the external display and working only with the rMBP. In the past I've always needed external displays for viewing more info, and I'm curious if this is no longer necessary.
Has anyone tried doing away with an external display and just using the rMBP on a stand with a mouse and keyboard? Since the display includes more info than a cinema display, and given healthy eyesight, would this setup be as ergonomic and efficient?
boeush - Monday, June 25, 2012 - link
For several years, I've been using 17'' notebooks with 1920x1200 displays. That resolution had been more than enough for the 17'' form factor; having even such a resolution on a 15'' screen is going overboard, and doing it on an 11'' tablet is just plane bonkers. I don't see the individual pixels on my laptop's screen, and I'd wager neither would most other people unless they use magnifying lenses.I really don't get the point of wasting money on over-spec'ed hardware, and burning energy pushing all those invisible pixels.
I'd rather have reasonable display resolutions matched to the actual physiological capabilities of the human eye, and spend the rest of the cost and power budgets on either weight reductions, or better battery life, or higher computing performance, or more powerful 3G/4G/Wi-Fi radios, etc.
The marketing-hype idiocy of "retina displays" now appears to be driving the industry from one intolerable extreme (of crappy pannels with sup-par resolutions) right into the diametrically opposite insanity -- that of ridiculously overbuilt hardware.
Why can't we just have cost-effective, performance-balanced, SANE designs anymore?
darkcrayon - Monday, June 25, 2012 - link
Reminds me of comments when the 3rd gen iPad screen was introduced. You have a review which both subjectively (from an extremely experienced user) and objectively from tests shows this is the best display ever for a laptop. Yet people ignore all of that and say it's a waste... I think it would be a waste if it didn't actually... You know... Provide a visibly dramatic level of improvement. And its better to make a large jump bordering on "overkill" than to make tiny incremental steps with something like display resolution- fragmentation/etc being what it is,