Understanding Qualcomm's Snapdragon 810: Performance Preview
by Joshua Ho & Andrei Frumusanu on February 12, 2015 9:00 AM EST- Posted in
- SoCs
- Qualcomm
- Mobile
- Gobi
- Snapdragon 810
Final Words
In light of everything, it seems that Snapdragon 810 was not as the rumors claimed. In my experience, I didn’t notice any of the development devices getting hotter than what I’d come to expect from a modern SoC. In most cases, it appears that CPU performance is about what we’d expect from a cluster of four Cortex A57s at 2 GHz, although there are a few anomalous results that could be a concern. If anything, it’s clear that the CPU isn’t really an area of weakness on the Snapdragon 810, especially with all of the work that Qualcomm has done for an energy aware scheduler to maximize the performance and efficiency of their big.LITTLE implementation.
Outside of the CPU, it’s evident that Qualcomm will retain their traditional lead in the modem and RF space, as OEMs will continue to adopt parts of RF360 along with Qualcomm modems and transceivers to ensure maximum performance on flagship smartphones and other high-end mobile devices. I don’t believe any other company will really be able to beat Qualcomm in this space, as they strongly emphasized just how well-validated their modems are and the extent to which they implement standards properly to work with operators around the world without issue.
While my time with the Snapdragon 810 hasn’t revealed any significant issues, the real concern here seems to be more along the lines of the GPU performance. While ALU performance and compute performance in general are significantly improved with the Adreno 430, the performance uplift doesn’t really seem to be as large as one might hope. Although Qualcomm is trying to sell the idea of a 4K tablet with the Snapdragon 810, it feels as if it’s too early to try and drive such high resolutions when the GPU can’t handle it. In order to see an appreciable increase in performance this year, it’s likely that OEMs will need to stay with 1080p or at most QHD display resolutions to really deliver improved graphics performance for gaming and other GPU intensive use cases.
As we’ve mentioned before, it seemed that Qualcomm stumbled a bit with the launch of Apple’s A7 SoC. While it seemed that Snapdragon 810 might have relatively little competitive advantage over other SoCs, in the past few months it’s become clear that Qualcomm has been leveraging their strengths to ensure that they remain a strong choice for SoCs this year. Although the GPU and memory subsystem appear to be a bit weak, overall 2015 remains promising for Android flagships, even if an OEM can’t design their own SoC.
Facebook
Twitter
RSS
119 Comments
View All Comments
aryonoco - Friday, February 13, 2015 - link
Yes, that sentence is totally meaningless.JoshHo - Sunday, February 15, 2015 - link
I didn't write the Geekbench analysis, I'm currently looking into the issue.randymorrisplano - Friday, February 13, 2015 - link
You guys who say 2 or 4k is too much for anything under 6" displays, are seriously are not taking the near future of ubiquitous VR on our handsets. Putting the display that close to the eyes, with magnifying optics, makes it a whole new ballgame.Gigaplex - Friday, February 13, 2015 - link
If I was going to do that, I'd use a VR headset, rather than holding my phone over my eyes.68k - Friday, February 13, 2015 - link
Interesting that Aarch32 get slightly better integer score in Geekbench compared to Aarch64. The lack of HW support for AES and SHA-1 in earlier Aarch32 capable CPUs and the fact that earlier 32 vs 64-bit comparisons has not been done on the same CPU-uarch made it tricky to directly compare results between Aarch32 and Aarch64.Adjusting for the difference in clock frequency between Exynos 5433 and Snapdragon 810, Aarch32 is about 12% fast. Removing the AES result which is an outlier in favor for Exynos, the performance lead for Aarch32 is still about 5%.
Aarch64 seem to do better in the MT cases compared to ST cases, the average lead for Aarch in all ST cases with AES removed is 16%.
dragonsqrrl - Friday, February 13, 2015 - link
So many awesome reviews and previews from Anandtech in the past week. Keep up the good work!lilmoe - Friday, February 13, 2015 - link
At this point of software optimization, I still believe big.LITTLE Core Migration is the way to go. Software isn't yet up to task for GTS, most of that complexity should be handled by hardware.fivefeet8 - Friday, February 13, 2015 - link
Your GFXbench3.0 driver overhead benchmarks seems to be off for the Shield Tablet. Unless maybe Android 5.x is causing a degradation there.sonicmerlin - Friday, February 13, 2015 - link
So how many bands will this new modem be able to support? And why do Apple phones always seem to support more LTE bands than the competition?aryonoco - Friday, February 13, 2015 - link
1) Depends on how many filters and transceivers the OEM fits the phone with. The baseband makes it easier to support more but the actual band support would still be OEM dependant.2) Because Apple does not shy away from high BoM and can cram as much filters and transceivers as they want in order to reduce the number of SKUs. Android manufacturers (unfortunately) don't think like that.