Ah yes, I forgot about that. It's going to make the naming even more confusing going forward but it may be even better for generating hype via strategic Geekbench leaks. 😉
Anyhow, that confirms it's the 13" MacBook Pro. Thanks.
Got a tip for us?
Let us know
Become a MacRumors Supporter for $50/year with no ads, ability to filter front page stories, and private forums.
First M2 benchmarks
- Thread starter EugW
- Start date
- Sort by reaction score
Anyhow, that confirms it's the 13" MacBook Pro. Thanks.
mi7chy
Suspended
Notice how it says "or" and not "and". You can only have one and not both. Only if the frequency is kept at 3.2GHz then it would be ~15% more efficient.
"+7% perf @ iso-power
or
-15% power @ iso-perf"
jav6454
macrumors Core
If you bothered to read the data, you’d see that the a15 cores managed both an increase in performance and efficiency.
is it just me or n5p seems better than n4 ? +7% vs +5 ,both at iso powerThe efficiency part done by TSMC with second gen 5nm improvments
Geekbench 5 Metal scores: 29832
browser.geekbench.com
Gfxbench 5 results
gfxbench.com
Mac14,7 - Geekbench
Benchmark results for a Mac14,7 with an Apple M2 processor.
browser.geekbench.com
Gfxbench 5 results
GFXBench - Unified cross-platform 3D graphics benchmark database
The first unified cross-platform 3D graphics benchmark database for comparing Android, iOS, Windows 8, Windows Phone 8 and Windows RT capable devices based on graphics processing power.
M2's ~30000 is pretty healthy boost in Metal over M1's ~22000. That's around a one-third increase.Geekbench 5 Metal scores: 29832
Mac14,7 - Geekbench
Benchmark results for a Mac14,7 with an Apple M2 processor.
mi7chy
Suspended
Anandtech says the same thing as the chart. It's "or" and not "and". We believe TSMC > Anandtech > you.
https://www.anandtech.com/show/1602...technology-details-full-node-scaling-for-2h22
"Compared to it’s N5 node, N3 promises to improve performance by 10-15% at the same power levels, or reduce power by 25-30% at the same transistor speeds."
Read the review of the A15. It increases both. Stop obfuscating. All your info proves is that the increase is due to more than N5P.
Performance pretty much aligns with A14 to A15 performance jump. Not surprising at all.
That slide is showing either a power decrease or a performance increase. Apple managed both showing its also due to architectural improvements.The efficiency part done by TSMC with second gen 5nm improvments
I thought that A15 and A14 use the same node (N5), while M2 and M1 use a different node (N5P vs. N5).
I believe that it is possible to increase performance and reduce consumption at the same time, but below these figures (e.g., increase performance by 4% and reduce consumption by 10%).
satcomer
Suspended
The two I’ve seen so far:
https://browser.geekbench.com/v5/compute/4981649 29832
https://wccftech.com/apple-m2-vs-m1-cpu-and-gpu-performance-leak/ 30627
We will see, but the one test I remember the most is a 40% increase in speed in video editing. Note that the project tested included ProRes footage. This is important because M2 includes a hardware ProRes accelerator whereas M1 does not.
What’s even the point. GB is no good at estimating Apple GPU performance
Scores already posted. Metal ~30600 for M2 vs. ~22200 for M1
This is roughly in line with Apple's claims.
macsplusmacs
macrumors 68030
mi7chy
Suspended
Will have to wait and see how that reflects on real world performance like Blender, Shadow of the Tomb Raider, etc.
I could be wrong, but I thought it was…ok..for the 8-10 core models. It definitely seems to fall down on the max and ultras models though.
A15 is using N5P. Which is also the reason why M2 is using the same process because Avalanche and Blizzard core performance characteristics on N5P are known quantity.