If I have a method that works better than your method (let's say, simply traverse the range backwards),
smoke
Whenever I see a post going like "splitting the range is a good idea and not an issue at all" after all the uncountable and obvious proofs to the contrary, I do 50 pushups, to compensate for the 41% extra steps required to solve the same problem in 2 ranges.
smoke
After adapting my own kernel to load/store stuff using L2 (instead of only once, before and after all the jumps) I reached 9.7 GK/s on RTX 4090 (64 jump points, DP 32), which was an increase of 75% in speed, and I haven't even tried to do micro-optimizations on it, like before.
smoke...
You are always the best, but you never publish anything. Use your great brain for something more than criticism—that's my advice. Words mean nothing if your actions don’t reflect what you say.
Come on, publish "K=1.0 (at DP>0)", show off!
50% criticism, 50% mockery, 0% code, those are your metrics.
And I predict that in the next message, you will copy my joke!