Dual Core Snapdragon GPU Performance Explored - 1.5 GHz MSM8660 and Adreno 220 Benchmarks
by Brian Klug on March 30, 2011 4:29 PM EST- Posted in
- Smartphones
- Snapdragon
- Qualcomm
- Adreno
- MSM8660
- MDP
- Mobile
GLBenchmark 2.0
GLBenchmark 2.0 – as its name implies – tests OpenGL ES 2.0 performance on compatible devices across multiple software platforms. The suite includes two long benchmarking scenarios with a demanding combination of OpenGL ES 2.0 effects - texture based and direct lighting, bump, environment, and radiance mapping, soft shadows, vertex shader based skinning, level of detail support, multi-pass deferred rendering, noise textures, and ETC1 texture compression. In addition, there's a large suite of subtests and feature tests.
GLBenchmark 2.0 is the best example of an even remotely current 3D game running on this class of hardware–even then this is a bit of a stretch. GLBenchmark 2.0 is still our current go-to test as it is our best best for guaging real world performance, even across different mobile OSes. Keep in mind that with GLBenchmark 2.0 we still cannot run at any resolution than native – in this case 800x480 (WVGA) – and the same applies for other devices in the suite, they're all at respective native resolutions. GLBenchmark 3.0 will fix this somewhat with the ability to render into an off-screen buffer of arbitrary size.
We never formally reviewed the T-Mobile MyTouch 4G, but have one nonetheless and have included it in our benchmark numbers a few times. Likewise, I purchased an HTC Inspire 4G for personal use which we'll review soon. The importance of these two devices is that they represent the current generation of single-core Snapdragon SoCs with Adreno 205 graphics. Comparatively, the 1.5 GHz MSM8660 with Adreno 220 is 2.2x faster than the 1 GHz MSM8655 with Adreno 205.
Interestingly enough our run through Egypt came slightly higher with Vsync on than it did off - we're just showing the margin of error here.
Pro is a less challenging test than Egypt, as it's simply the GLBenchmark 1.x main suite with OpenGL ES 2.0 features and shaders. Already we're at the framerate cap here on both MSM8660 and likely OMAP 4430. Pro likewise demonstrates huge gains from Adreno 205 to Adreno 220 - in this case 3.7x.
Facebook
Twitter
RSS
70 Comments
View All Comments
metafor - Thursday, March 31, 2011 - link
Keep in mind that as you scale to higher resolutions, you won't be clipping the 60fps limit as much.So if Adreno is capable of going higher but isn't due to the fps cap, then it won't be slower at higher resolutions.
This isn't true of Egypt from what it seems though.
Alexstarfire - Thursday, March 31, 2011 - link
I would agree when you're strictly comparing GPUs, but we're almost comparing platforms in here. The problem is that you can't run most things on mobile platforms at any resolution you want. You're stuck with native resolution in just about every case.If you're trying to figure out which GPU is better then you certainly need to take resolution out of the equation. Can't really do that with mobile devices though.
You also have to remember that performance isn't necessarily linear across resolutions, especially if there is an FPS cap.
michael2k - Thursday, March 31, 2011 - link
What? 840x480 is half the iPad's resolution! 1024x768!The iPhone is 960x640, also much higher.
The iPad->iPad 2 difference of 6.4->44.8 or 17.6->57.6 tells us the iPhone 4 should be quite competitive with the dual core Snapdragon; 5.9->42 for Egypt and 50 for GL Pro 2, and at a much higher resolution to boot.
Any phone that uses the Adeno 220 and a higher resolution (like via HDMI out), will see their scores drop in half, while the iPhone should chug along without much difference.
B3an - Thursday, March 31, 2011 - link
How can the iPhone 4 remotely compare? Dont you not mean iPhone 5?Because the Motorola Atrix 4G has about the same screen res (540 x 960) yet it performance more than 2x as well as iPhone 4 in most benches. The Atrix's CPU and GPU are not even as fast as this new Scorpion SoC.
michael2k - Thursday, March 31, 2011 - link
You're right, I meant A5 on the iPhone 5.kade1878 - Saturday, April 2, 2011 - link
So lets compare the iPhone 4 to the Motorola Atrix 4G:iPhone: 960x640 = 614400
Atrix: 960x540 = 518400
So the ratio is ~1.19 or the iPhone 4 has 19% more Pixels than the Atrix.
Now compare that to the Benchmark result:
iPhone: 5.9 fps x 614400 pixels/frame = 3.624.960 pixel/s or ~3.6 MPixel/s
Atrix: 18.7 fps x 518400 pixels/frame = 9.694.080 pixel/s or ~9.7 MPixel/s
flipside101 - Saturday, April 2, 2011 - link
its slightly off topic but does anyone hve a handle on why no one else is using the PowerVR SGX543MP2 . its not apple tech but is it possible that they have an exclusive license ?ta
dagamer34 - Saturday, April 2, 2011 - link
TI and Samsung are the only other major companies besides Apple that usually use PowerVR chips. This year, Samsung stuck an ARM-based GPU into their chip, the Exynos (ARM GPU is the Mali 400) and Ti's OMAP 4430 has so far only been used in the Blackberry Playbook. All smartphone uses of the OMAP 4xxx platform are to be launched in the 2nd half of this year.GnillGnoll - Wednesday, April 6, 2011 - link
I'm sure Intel and Renesas would disagree with your definition of "major companies", among others. And the LG Optimus 3D smartphone (with OMAP4430) will be available by the end of the month.Renesas announced a SoC with SGX543MP2, so it's certainly not Apple exclusive tech.
scofflaw - Wednesday, March 30, 2011 - link
The original MDP8655 which I have has VEE display backlight control which when enabled can really lower the battery drain when running certain apps. Does this new MDP8660 have it as well?