Hacker News new | past | comments | ask | show | jobs | submit login

I've been trying to get to the bottom of this here: https://github.com/solvespace/solvespace/issues/972

With my 2400G the benchmark takes 5.5 seconds. With someones M1 it takes 1.3 seconds.

We still need to verify that was run at the same settings, but it looks like the M1 is going to be faster than the 5000 series APUs regardless, possibly by a large margin and I'm assuming the 5000s are between 1.4x and 2.0x the speed of the older 2400G.

It will still be interesting to see AMD on a 5nm process, and Zen 4, and with 8 core, but by then Apple will probably have an M2 on the 3nm process. You gotta compare what can be obtained today.




The 2400G is a relatively low end part that is four generations old. In the past AMD did not release high end desktop APUs, preferring customers to buy CPUs + GPUs. This is already announced to change with a 5700G being produced. https://www.amd.com/en/products/apu/amd-ryzen-7-5700g - On paper this is a 5800H in a desktop form factor with a higher max TDP and higher clock speeds.

The 5800H gets 2.5x on cpu benchmark's rating vs the 2400G. This is composed of a 50% single core and 300% multi-core improvement.

2400G: https://www.cpubenchmark.net/cpu.php?cpu=AMD+Ryzen+5+2400G&i...

5800H: https://www.cpubenchmark.net/cpu.php?cpu=AMD+Ryzen+5+2400G&i...


>> The 5800H gets 2.5x on cpu benchmark's rating vs the 2400G.

That's in large part because its 8 cores instead of 4. The test I ran makes good use of multicore, but going from 4 to 8 won't cut the time completely in half. I suspect the M1 will still beat it by a bit.

I take back my comment on availability. We ideally need to compare things on the same process node to see which design team has done a better job ;-)


The M1 is also 8 cores and benefiting from that.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: