Samsung Galaxy Tab Pro 8.4 and 10.1 Review
by Jarred Walton on March 22, 2014 9:30 PM ESTBattery Life
For battery life testing, we run the displays at 200 nits and test Internet surfing and H.264 720p video playback. In some cases the tablet OEMs have features built into the software that lock display brightness to a low (minimum) setting when battery life is less than 10%. The Galaxy Pro offerings appear to do this, though you can override the behavior in the power options. In real-world use, you can expect perhaps slightly better Internet battery life (as it's unlikely you'll be refreshing pages every 20 seconds) while the video playback results are exactly what you would do if watching a movie.
The Nexus 7 wins the WiFi testing result while the iPad Air and Mini Retina take the top two spots for the video playback (and silver and bronze in the Internet testing). It’s interesting that the two Galaxy Pro tablets are so close on the Internet results but the 10.1 does substantially better on the video playback. Either way, both tablets are at least capable of reaching their “up to 9/10 hours” advertised battery life, with perhaps a bit more if you’re willing to turn down the display brightness or shut off WiFi.
There are better tablets if you want as much battery life as possible, but given the ready availability of portable chargers and such I'm not sure it's all that critical. Gaming battery life is lower than the above results, of course, so plan on more like four to six hours of gaming (depending on the game) before needing to plug in.
Storage Performance
Having used several older Android tablets, the drop in storage performance over time can be extremely painful. With Android 4.3 and 4.4 now supporting TRIM, hopefully things will stay running a bit more smoothly over a long period of time. As it stands, we don’t have all that many results for our Android storage benchmarks (and no cross-platform test for iOS yet), but the Samsung eMMC looks to be better than most of what we’ve tested. The random write speeds in particular are nearly twice as fast as that of the Nexus 7, and we’re at least consistently beating typical hard drive performance with >1MBps random I/O. Hopefully we’ll see even faster NAND/controller solutions upcoming tablets.
Facebook
Twitter
RSS
125 Comments
View All Comments
SilthDraeth - Saturday, March 22, 2014 - link
On my note phone if I want to take a screenshot, I hold the power button and the Samsung Home button. Give that a try. Or, on my wife's note 10.1 first edition, it has a dedicated screenshot softkey that appears where your normal android home keys, etc appear.FwFred - Sunday, March 23, 2014 - link
LOL... 'Pro'. Surface Pro 2 just fell off the chair laughing.garret_merrill - Friday, October 3, 2014 - link
Really good tablets, although I would seriously consider the Note Pro series too (highly ranked by a number of sources, see http://www.consumertop.com/best-tablets/). But either way, the Samsung tables deliver fantastic quality.Brian Z - Saturday, March 22, 2014 - link
Antutu? Really... Maybe somebody kidnapped Anand and Brian. Frigging Antutugrahaman27 - Saturday, March 22, 2014 - link
Better than just posting the browser speed tests for CPU, and draw final thoughts from that, which they have gotten in a habit of doing.JarredWalton - Sunday, March 23, 2014 - link
What's wrong with running one more benchmark and listing results for it? Sheesh... most of the time people complain about not having enough data, and now someone is upset for me running AnTuTu. Yes, I know companies have "cheated" on it in the past, but the latest revision seems about as valid in its reported scores as any of the other benchmarks. Now if it wouldn't crash half the time, that would be great. :-\Egg - Sunday, March 23, 2014 - link
You do realize that Brian has, for all intents and purposes, publicly cursed AnTuTu and mocked the journalists who used it?JarredWalton - Sunday, March 23, 2014 - link
The big problem is people that *only* (or primarily) use AnTuTu and rely on it as a major source of performance data. I'm not comparing AnTuTu scores with tons of devices; what I've done is provide Samsung Galaxy Tab Pro 8.4 vs. 10.1 scores, mostly to show what happens when the CPU in the 10.1 hits 1.8-1.9 GHz. It's not "cheating" to do that either -- it's just that the JavaScript tests mostly don't go above 1.2-1.3GHz for whatever reason. Octane and many other benchmarks hit higher clocks, but Sunspider and Kraken specifically do not. It's probably an architectural+governor thing, where the active threads bounce around the cores of the Exynos enough that they don't trigger higher clocks.Don't worry -- we're not suddenly changing stances on Geekbench, AnTuTu, etc. but given the odd clocks I was seeing with the 10.1 I wanted to check a few more data points. Hopefully that clarifies things? It was Brian after all that used AnTuTu to test for cheating (among other things).
Wilco1 - Sunday, March 23, 2014 - link
The reason for the CPU clock staying low is because the subtests in Sunspider and AnTuTu only take a few milliseconds (Anand showed this in graphs a while back). That means there is not enough time to boost the frequency to the maximum (this takes some time). Longer running benchmarks like Geekbench are fine. I wouldn't be surprised if the governor will soon start to recognize these microbenchmarks by their repeated bursty behaviour rather than by their name...Of course the AnTuTu and Javascript benchmarks suffer from many other issues, such as not using geomean to calculate the average (making it easy to cheat by speeding up just one subtest) and using tiny unrepresentative micro benchmarks far simpler than even Dhrystone.
Also it would be nice to see a bit more detail about the first fully working big/little octa core with GTS enabled. Previously AnandTech has been quite negative about the power consumption of Cortex-A15, and now it looks the 5420 beats Krait on power efficiency while having identical performance...
virtual void - Monday, March 24, 2014 - link
You cannot disregard the result produced by something just because the load generated by the benchmark comes in very short burst, that is the _typical_ workload faced by these kind of devices.The result in Geekbench give you some hint how the device would handle HPC-workloads, it give you very limited information about how well it handles mobile apps. Another problem with Geekbench is that it runs almost entirely out of L1$. 97% of the memory accesses where reported as L1-hits on a Sandy Bridge CPU (32kB L1D$). Not even mobile apps has such a small working set.
big.LITTLE is always at a disadvantage vs one single core in bursty workloads as the frequency transition latency is relatively high when switching CPU-cores. Low P-state switching time probably explains why BayTrail "feels" a lot faster than what the benchmarks like Geekbench suggest. BayTrail has a P-state latency of 10µs while ARM SoCs (without big.LITTLE) seem to lie between 0.1ms - 1ms (according to the Linux device-tree information).