Investigating Intel's Turbo Memory: Does it really work?
by Anand Lal Shimpi on June 19, 2007 3:39 PM EST- Posted in
- Laptops
Final Words
When Intel launched its fifth revision to Centrino, we were left mostly disappointed. It was the most lackluster Centrino launch we had seen since the brand's inception and it almost seemed like a platform that was released for the sake of coming out with something new every year. The sole feature we had high hopes for was Intel's Turbo Memory, but we were left sorely disappointed when we couldn't even find a use for it.
Some OEMs have publicly lashed out at Turbo Memory, stating that it basically does nothing for the user experience, which for the most part echos our findings internally. The most recent data we've put together shows that Turbo Memory can have a positive impact on battery life, however the tests that show the impact aren't as easy to come by. And honestly, savings of 8 minutes when watching a movie aren't impressive enough given the additional cost of adding Turbo Memory to a notebook (expected to be at least $100 USD).
The best results we have seen however show promise for Turbo Memory; greater than 10% increases in battery life, resulting in an extra 20 minutes of active use time are nothing to scoff at. The problem is how often and likely these scenarios are to occur vs. SYSMark-esque situations where Turbo Memory does nothing for battery life.
Based on our usage, we'd expect to conservatively see 5 - 10% increases in battery life on average for normal usage, including simply watching a movie. The improvement is there, but it's not as dramatic as we'd like to see. Today's investigation sheds a little more light on what Intel's Turbo Memory can do, and clearly it has potential.
There are two vectors Intel can scale along in order to improve the effectiveness of Turbo Memory: size and software. The size vector is simple; the larger the ReadyDrive cache, the more data you can put it in, and thus the longer the hard disk can remain asleep. The software vector may end up falling into Microsoft's lap more than Intel's, but the idea is this: the more aggressive the prefetchers are that populate Turbo Memory, the more likely you are to gain power and performance benefits.
Sony has publicly stated that at the last minute, Microsoft removed code from Windows Vista that would more intelligently populate the ReadyDrive partition in an attempt to get Vista out on time. Whether or not this is true is up for debate, but clearly there's room for improvement here. Vista's SuperFetch works quite intelligently and it would seem that tighter coupling (assuming some already exists today) between SuperFetch and Turbo Memory could yield even more positive benefits.
On the desktop the benefits are even less clear, since shaving a couple of watts off of the total system power isn't as big of a deal. There are potential performance implications, but we suspect that the ReadyDrive flash size needs to be increased dramatically and be far more aggressive in prefetching to generate real interest.
We leave today with a more hopeful outlook for Intel's Turbo Memory, but it's clear that the technology is in its infancy. We stand by our original conclusion with regards to the Santa Rosa platform, as it isn't one that you absolutely need to upgrade to, it is barely evolutionary by Intel's own standards. Turbo Memory could be nice to have, but your mileage may vary. We'd suggest waiting for the second revision of the technology, hopefully by the next Centrino launch in 2008 we will see larger flash sizes and more software optimizations for the technology.
Facebook
Twitter
RSS
31 Comments
View All Comments
casket - Wednesday, June 20, 2007 - link
"If you add more memory to laptop, you use more power, emit more heat, etc"-- Using this logic... adding ReadyBoost (which is memory) would also use more power, emit more heat, etc...
The key here is that either readyboost or memory uses less power than a spinning hard drive. I would suspect you get the same power savings with more memory as well.
yyrkoon - Wednesday, June 20, 2007 - link
I dont know about anyone else, but I am starting to resent Intel using town names of the area I grew up in as a kid. You would think they could be a little more original.PrinceGaz - Wednesday, June 20, 2007 - link
I'd say that if it reboots every 6 minutes or so to re-run the test, it isn't worth a look and is totally useless as a notebook baterry-life benchmark as it in now ay reflects real-world usage, and all results using it should be discarded. Surely a better benchmark could be found than that. Unfortunately, removing the WorldBench results make Turbo Memory seem next to useless, which is understandable as it is likely to have been mainly the reduced HD activity when rebooting that the Turbo Memory was helping with.
JarredWalton - Wednesday, June 20, 2007 - link
And yet, the mocked up WorldBench 6 test shows a rather impressive 12% increase in battery life. It seems that the startup/shutdown process at the very least gets a decent benefit (in terms of battery life) from Turbo Memory. That indicates that the power savings from putting the hard drive to sleep are definitely tangible.redly1 - Wednesday, June 20, 2007 - link
I would like to buy this and test it out with my tablet PC. Anyone know where I can buy one of these mini-PCIe cards?skaaman - Monday, June 25, 2007 - link
Here is the part# NVCPEMWR001G110You can pick them up for under $35
BD2003 - Wednesday, June 20, 2007 - link
The problem I have with the article is that in general, they are still running benchmarks that do not reflect how an actual user interacts with their laptop, and do not really reflect the benefits that turbo memory/readydrive/readyboost would have.PCMark is supposed to give a number as to how fast your computer can run a barrage of application tests - but looping it over and over does not even come close to reflecting an actual usage pattern.
Now granted, they need a *repeatable* test to have numbers that are comparable, but that does not necessarily speak of the validity of the numbers.
For the average office laptop, you'll be running outlook, word, excel etc - the amount of data actually being loaded and saved is VERY small vs. large amounts from a benchmark, and in that very common scenario, the drive would rarely have to spin up, and the battery savings would probably be much closer to the ideal of 30 mins than what their benches showed.
I do agree with them on their final conclusion - 1gb is just not enough for more than basic office tasks. In order for this to really take off, to be able to cache an entire movie, they're going to need cache on the order of 4gb. Then I think it'll really make a difference battery/performance wise.
And they really, really need to fix the driver issues.
BikeDude - Wednesday, June 20, 2007 - link
If the movie is 4GB, a 1GB cache means (ideally) you will spin up the hard drive four times to load the next GB. I doubt you'll see much benefit from a 4GB cache in such a scenario.That said, the test didn't do any read ahead tests. All the descriptions so far seem to say the technology caches stuff already read. I.e. if streaming a movie from the hard disk there's nothing that will suck it all into a cache... (grrrr, this reminds me that my Hauppague TV tuner streams everything to a 7MB file which it then plays back -- works fine as long as I don't hit the same drive with heavy IO)
sorr - Wednesday, June 20, 2007 - link
i'd just use another Gigabyte of memory i.e, 2 GB in total and hybrid drive for now, then after 2~3 years just use the SSD when it comes down in price and goes up in capacitySilthDraeth - Wednesday, June 20, 2007 - link
Page 4 mentions Windows XP. I thought I read the article, but maybe I am missing something. I thought it was purely for Vista, but XP is mentioned several times.Please explain, because I am confused. Thanks.