[kimixa]

I think the issue is that people limited compute time as a proxy for difficulty.

In that case you'll hit issues on any device that performs significantly differently from that which it was tuned in.

Though I am slightly amused by people using the apple chip as an example of "high performance" in a problem that scales very well with threading.

[anthk]

Precisely a Core Duo and a custom build with -O3 -ffast-math (a Chess engine doesn't requiere anything further from integers) and -march=$YOUR_CPU_THERE can yield crazy performance speeds without needing an m4 and a great match even for masters.