The increase over M3 is almost entirely due to increase in clock speed, and the effect of Geekbench 6.3 supporting SME for a small subset of tests, which leads to those tests running ~2x faster on M4. The actual IPC increase on general purpose code is small, around 3%. Apparently Apple has added SME to the M4 cores, which is cool, but makes comparison to previous cores a bit suspect unless your specific application can actually benefit from SME. Source: https://forums.anandtech.com/threads/apple-silicon-soc-threa...
1. Apple changed the design of its cores to achieve higher clock speeds without raising power. In other words, they deliberately decided to alter the design to get these results.
I'm curious how much of this is actually due to its raw compute capacities, and what can be attributed to memory/storage speeds (because geekbench results vary quite a bit if you change RAM/SSD).
Also, in how far is the iOS ARM score comparable to, say, Linux x86.
The current top results for single core performance are ~3,100 so it is, on paper, a substantial gain. The M3 in the iMac achieves around 3,053.
However, Geekbench is not that great (imo) so it does not necessarily indicate what you can expect overall performance to be or improve by between CPUs.
Readit News
1. Apple changed the design of its cores to achieve higher clock speeds without raising power. In other words, they deliberately decided to alter the design to get these results.
2. N3E is going to be a legendary TSMC node.
Could be a little bit of both.
Deleted Comment
Also, in how far is the iOS ARM score comparable to, say, Linux x86.
https://browser.geekbench.com/ios_devices/ipad ("iPad Benchmarks")
https://browser.geekbench.com/mac-benchmarks ("Mac Benchmarks")
However, Geekbench is not that great (imo) so it does not necessarily indicate what you can expect overall performance to be or improve by between CPUs.
The team at Nuvia, before they were acquired by Qualcomm, did the analysis: https://medium.com/silicon-reimagined/performance-delivered-...