view the rest of the comments
Google Pixel
The World's Google Pixel community!
This community is for lemmings to gather and discuss all things related to the Google Pixel phone and other related hardware. Feel free to ask questions, seek advice, and engage in discussions around the Pixel and its ecosystem.
We ask you to be polite when addressing others and respect Lemmy.world's rules.
NSFW content is not allowed and will immediately get you banned.
It also goes without saying that self-promotion of any nature and referral links are not allowed. When in doubt, contact the mod team first.
Also, please, no politics.
For more general Android discussions, see !android@lemmy.world.
This community is not in any way affiliated with Google. If you are looking for customer support regarding your Pixel phone, look here instead: https://support.google.com/pixelphone/
There's no way the in order A53 from 2012 gets even close to the performance of the OoO A78 from 2020.
Didn't know one is in-order and the other is OoO. The A53 is still being used for new products by Nvidia in 2020 (Bluefield-2). So there must be some merit to it or Nvidia is cheaping out on stuff
The BlueField-3 uses the A78 and unfortunately I don't have one to test. I'm basing everything I know based on conference talks. I do know apparently the A78 does not have working performance counters for perf which makes it a pain to debug.
That being said, a 2023 Mid-end Xeon gets you up to 60Gbps TCP single flow (100Gbps ConnectX-6 NIC) So maybe that's a better comparison? Might need to account for all the other x86 optimizations
Also, I think the bottleneck for TCP processing is branching, not memory access. So I'm not sure if OoO execution would help much. Would the A78 have improved branch predictors?
A53 is used for low-power and low-cost applications... It's a "good enough" CPU that has really good performance/area.
Perfect performance counters for OoO is really hard.
OoO also makes BP more useful. An OoO processor without BP isn't very useful because there aren't that many instructions between branches... So, generally, modern OoO processors dedicate far more resources to BP.