ASUS Eee Pad Transformer Prime & NVIDIA Tegra 3 Review
by Anand Lal Shimpi on December 1, 2011 1:00 AM ESTCPU Performance
The big news with Tegra 3 is that you get four ARM Cortex A9 cores with NEON support instead of just two (sans NEON) in the case of the Tegra 2 or most other smartphone class SoCs. In the short period of time I had to test the tablet I couldn't draw many definitive conclusions but I did come away with some observations.
Linpack showed us healthy gains over Tegra 2 thanks to full NEON support in Tegra 3:
As expected, finding applications and usage models to task all four cores is pretty difficult. That being said, it's not hard to use the tablet in such a way that you do stress more than two cores. You won't see 100% CPU utilization across all four cores, but there will be a tangible benefit to having more than two. Whether or not the benefit is worth the cost in die area is irrelevant, it only means that NVIDIA (and/or its partners) have to pay more as the price of the end product to you is already pretty much capped.
The bigger benefit I saw to having four cores vs. two is that you're pretty much never CPU limited in anything you do when multitasking. Per core performance can always go up but I found myself bound either by the broken WiFi or NAND speed. In fact, the only thing that would bring the Prime to a halt was if I happened to be doing a lot of writing to NAND over USB. Keyboard and touch interrupts were a low priority at that point, something I hope to see addressed as we are finally entering the era of performance good enough to bring on some I/O crushing multitasking workloads.
Despite having many cores at its disposal, NVIDIA appears to have erred on the side of caution when it comes to power consumption. While I often saw the third and fourth cores fire up when browsing the web or just using the tablet, NVIDIA did a good job of powering them down when their help wasn't needed. Furthermore, NVIDIA also seems to prefer running more cores at lower voltage/frequency settings than fewer cores at a higher point in the v/f curve. This makes sense given the non-linear relationship between voltage and power.
From a die area perspective I'm not entirely sure having four (technically, five) A9 cores is the best way to deliver high performance, but without a new microprocessor architecture it's surely more efficient than just ratcheting up clock speed. I plan on providing a more thorough look at Tegra 3 SoC performance as I spend more time with a fixed Prime, but my initial impressions are that the CPU performance isn't really holding the platform back.
Facebook
Twitter
RSS
204 Comments
View All Comments
thunng8 - Thursday, December 1, 2011 - link
Not sure about the discrepancies, however, 2.1 is the latest version and it should be the one tested.Also, iOS 5 brought significantly faster openGL drivers, maybe PCWorld were comparing result from a while ago on the ipad2 and iOS4. All onscreen tests are also vsync limited, so the maximum they will ever score is 60fps.
offscreen is somewhat important, as some ipad2 games can render higher output via the HDMI accessory to an external device.
Anand Lal Shimpi - Thursday, December 1, 2011 - link
GLBenchmark 2.1 allows for testing at the same resolution (720p) to enable true apples to apples comparisons of GPUs. There are some slight changes in the workloads as well, so 2.1 numbers aren't directly comparable to 2.0.x numbers.That being said, the iPad 2 should never be slower than the Prime even in an older version of GLBench. I'm not entirely sure what's going on there...
Take care,
Anand
metafor - Friday, December 2, 2011 - link
A new version of PowerVR drivers was released some while back (I believe it came with iOS 5) and improved performance dramatically. That may be the issue.GnillGnoll - Friday, December 2, 2011 - link
46 fps is an old result on iPad 2. With iOS 5 the Egypt Standard test is almost permanently vsync limited at 60 fps (2.0.3 is gone from the online database, but the workload in the Egypt test hasn't changed between that and 2.1)araczynski - Thursday, December 1, 2011 - link
if this is supposed to be the next generation of the android tablets, getting slapped around by the ipad2, WHEN THE IPAD3 is 'just around the corner' makes it almost a joke of an upgrade.i don't have any love for apple (pc guy), but i'll be saving my mountain of pennies for an ipad3, rather than bother with an android tablet, have enough random issues with my free DroidX that i couldn't actually image wanting to pay for the 'experience' in a tablet.
vvk - Thursday, December 1, 2011 - link
If by "around the corner" you meant April or May of the next year than perhaps, based on your needs, you should wait but then if you wait another couple of month you could get the next gen super-duper tablet and so on and so forth. Anyway your life your choice I ain't canceling my preorder based on the Anand's review.gorash - Friday, December 2, 2011 - link
No this is not the next generation of Android, next generation is ICS or Jelly Bean. And iPad 3 is coming next summer.steven75 - Saturday, December 3, 2011 - link
Neither iPad was released in the summer.Ketzal - Thursday, December 1, 2011 - link
I'd like to congratulate on a truly superb review. Given the horribly short time you had to write it and do the testing. You did an amazing job.Your reviews are a true breath of fresh air.
The quality of your reviews make the Engadget and like websites look like total amateurs.
Basically it works like this...if you are pondering a new gadget. Wait for your review. If you say it's the one...it's the one. Buy said gadget.
Live happily ever after.
Congrats, I'll be singing your praises to everyone I know.
Ketzal
Wizzdo - Thursday, December 1, 2011 - link
You should consider getting a low-voltage brain in your next life since Anand does your thinking for you. This way your battery might last as long as the iPad2's.Anand may be good but regardless of his reviews "Happily ever after" is about 6 months in this industry.