Potential Benchmark for iPhone XR Successor Shows 4GB RAM, Moderate Performance Gains
A new Geekbench result posted this evening purportedly reveals performance data for the next-generation iPhone XR set to debut at next week's media event.
The result, spotted by forum member EugW, lists a model number of "iPhone12,1" running iOS 13.1 with a motherboard identifier of N104AP. Back in May, Bloomberg reported that the next-generation iPhone XR was internally codenamed N104, while 9to5Mac reported in July that the device would carry the model number iPhone12,1.
If legitimate, the result reveals a few details about the iPhone XR successor and its A13 chip. First, the result shows approximately 4 GB of RAM for the device, which would be an increase over the 3 GB found in the current iPhone XR and in line with predictions from noted analyst Ming-Chi Kuo. The iPhone XS and XS Max already include 4 GB of RAM, and there have not been any solid rumors suggesting their successors will see an increase.
Moving on to the A13 itself, the result indicates it continues to include six cores, presumably in an identical setup compared to the A12 with two high-performance cores and four high-efficiency cores.
The A13's high-performance cores are shown running at 2.66 GHz in today's result, compared to 2.49 GHz in the A12, leading to an approximately 12–13 percent gain in single-core performance for the A13 with a score of 5415, compared to an average 4796 for the A12 in the iPhone XR.
Interestingly, the A13's multi-core score of 11294 is nearly identical to the A12's average score of 11192, although Geekbench's developer John Poole tells us there could be some throttling due to thermal limits as similar situations have been seen with the A12 in the iPhone XS and XR, so we may have to wait for more data to see where the A13 truly tops out.
Careful observers will note oddly low figures for the L1 and L2 caches on this A13, but Poole tells us Geekbench has difficulty telling whether the cache values it reads are for the high-performance or high-efficiency cores, particularly on unreleased hardware for which the software hasn't been optimized.
While we can't confirm whether the Geekbench result is legitimate, as results certainly can be faked, all of the data appears reasonable or explainable and Poole tells us "there's nothing obviously wrong with the result."
We'll know more with the unveiling of all three of the new iPhones at Apple's media event on September 10, although Apple is unlikely to share specifics on chip speeds and RAM amounts. It won't take long, however, for additional data to surface confirming specs for the new devices.
Top Rated Comments
Between 2011-14 we were really pushing our iPhones with the many new features and apps pushing these limits (1080p then 4K video, 400+ ppi screens, and previous-gen console ports - think GTA 3/VC/SA/LCS, Bully, various NFS releases and even Bioshock).
Since 2015 I think Apple has added Portrait Mode to the iPhone and that’s it. The console port scene is dead. What other new app has really required additional horsepower from our iPhones? Pretty much all users are using some combination of push mail/social networking/music streaming/video streaming - which even an iPhone SE can do well.
Here's hoping for 6 GB 128 GB OLED iPhones!
Second, new processes offer higher performance. It’s just dumb to try to increase processor performance by relying too much on clock rate. Power consumption/dissipation = CV^2f. Increasing f also generally requires increasing V. Bad idea. It’s much better, for anything running on batteries and without a fan, to increase performance by more efficiently using each transistor (increase IPC).
This is not a new phenomena - it’s been going on for years. If all that mattered was clock rate you’d end up with something like the GaAs F-RISC research project at Rensselaer. Super-high clock rates at the time, terrible CPU performance.
[doublepost=1567486406][/doublepost] EUV should buy them something like 10-15% performance or power (I imagine they’ll optimize for power, and increase the clock rate a bit by shrinking the critical paths, while also improving IPC with bigger caches/buffers and maybe some minor micro architectural changes. Most of the new stuff will be in the co-processors, which won’t show up in current benchmark testing that isn’t optimized to use the hardware).