The Qualcomm Snapdragon S4 (Krait) Preview Part II
by Anand Lal Shimpi on February 22, 2012 11:40 PM EST- Posted in
- Smartphones
- Snapdragon
- Qualcomm
- Krait
- Mobile
- Tegra 3
- Tablets
- NVIDIA
GPU Performance
Prior to today there was a bug in GLBenchmark that prevented it from running on some Android 4.0.3 devices. Our Eee Pad Transformer Prime was one of those devices and thus we couldn't produce updated Tegra 3 scores using GLBenchmark. Thankfully GLBench 2.1.1 finally made it through testing/validation and includes a slightly different workload, with a number of bug fixes. Android 4.0.3 now works properly and we were able to continue our MSM8960 vs. Tegra 3 comparison. Note that the iOS build of GLBenchmark 2.1.1 is not yet available so we can't provide any iPad 2 comparisons yet.
Tegra 3's GPU performance is much improved compared to Tegra 2, and in the Egypt benchmark we see a tangible advantage over MSM8960. As we mentioned yesterday, only the first Krait SoC will use Adreno 225 - future versions will ship with Adreno 3xx, offering even better GPU performance. As the initial showdown is likely going to be Tegra 3 vs. MSM8960, this is a valid comparison.
Qualcomm and NVIDIA swap places once again when we look at the older GLBenchmark Pro test, although both perform well thanks to the lighter nature of this test.
Basemark ES 2.0 is completely dominated by Adreno however:
I'm still not totally sure why Basemark favors Adreno architectures so much but the results are what they are.
We've also been playing with Electopia, another Qualcomm-friendly test:
We do bump into Vsync limits with both the Tegra 3 and Qualcomm MDP at 800 x 480. Unfortunately Electopia doesn't allow for custom display resolutions, the only options are WVGA or native. The MDP has a native resolution of 1024 x 600 compared to the TF Prime's 1280 x 800 making a comparison at native resolutions unfair. That being said, according to Qualcomm the MSM8960 should be able to deliver around 40 fps at 1280 x 720 compared to the 24.6 fps we measured on the Transformer Prime at 1280 x 800.
Although Electopia is a game, it's still tough to tell how killer 3D titles on Android will end up performing. Oh the things I would do for an Unreal Engine 3 benchmark on Android...
Facebook
Twitter
RSS
49 Comments
View All Comments
lancedal - Thursday, February 23, 2012 - link
Hi Anand,What is the CPU voltage for the 1.5GHz?
boostern - Thursday, February 23, 2012 - link
It's been almost 10 years that I'm following you.It's always a joy to read one of your articles.
Thank you Anand, really.
Black1969ta - Thursday, February 23, 2012 - link
Tegra 2 was out before other dual cores and fell short of those later designs, it is not surprising that Tegra 3 is in the same position performance wise.Any one have a link to more news on Kal-El+, other than just name?
Is Kal-El+ a tock, to Kal-El, from Intel's Playbook?
If it is then I could see not only a process shrink down to 28nm or 32nm, but "tweaks" also.
Perhaps with the smaller process they could add a 2nd Memory channel.
The HTC One X is rumored to be a 1.5 GHz Tegra 3, instead of the 1.3Ghz in the Prime.
Lucian Armasu - Saturday, February 25, 2012 - link
If they actually really the Tegra 3+ this year (they were supposed to release the Tegra 2 3D too last year but didn't because they were late), it will probably be a quad core with at least the first core at 1.8 Ghz or even 2 Ghz, and the others a little lower.It should be at least at 2 Ghz if they want to compete with Krait. The problem is, although they were already very late with Tegra 3 to market, they also only release the tablet version first, and the phone version months later. So Krait phones will be available in Q2 this year, Tegra 3+ tablets probably in Q3, and Tegra 3+ phones late Q3 or early Q4.
If Nvidia actually managed to deliver their chips when they promised they would deliver them, I think they would be in a much better position today, because for example it would be understandable if Krait is more powerful than Tegra 3 in Q2 2012, if phones with Tegra 3 started appearing 2 quarters earlier, like they promised. But that didn't happen, so now once again Tegra 3 is late to market, just like Tegra 2 was, and the competition is already better by the time it starts to get a foothold in the market.
fteoath64 - Friday, February 24, 2012 - link
Nvidia better get to A15 very quick!. They are getting creamed by the strong competition. Here is my suggestion. Stop with the quadcore nonsense. Do a 1+1 (big.little at 2Ghz, dual ch ram), 2+1 and 3+1 for good measure. If they can make the 3+1 to turbo at 2.2Ghz with single core, it would be great.Also to find a way to retask the small core to be I/O processor when it is inactive.
curtisas - Saturday, February 25, 2012 - link
Can Qualcomm just make that device have a little less of a lip on the bottom and sell me it? It's running stock Android which is awesome, and the reference devices always have the top of the line hardware!gamoniac - Saturday, February 25, 2012 - link
I am reposting my comment on an earlier article by Brian --
The browsers are multi-threaded but javascript does not support multi-threading until the advent of web worker in HTML 5. Although the browser could load images/files with multi threads, javascript snippets on a pre-HTML 5 page only runs in one thread. Was SunSpider's benchmark written in HTML 5?
thebeastie - Monday, February 27, 2012 - link
Now I got a Sony HMZ-T1 all I really care about is how well it can handle a Bluray 13GB MKV rip of Avatar 3D that I may have on local file server or off the device it self so I can go into my bedroom and watch a 3D movie at highest quality possible with no mess or fuss of a PC.ATM iPad2 can't handle my really high end rips and I don't want to buy a laptop etc for my bedroom, I want something simple like a tablet.
superg05 - Saturday, March 10, 2012 - link
these so called standard benchmarks only show so much let me see a benchmark that shows how many cores are running for tegra 3 for example for browsing only suppose to use the companion lower core how many cores and gpu cores during the test is each different system running?