sYnfo

You might find the syscall tracing functionality of Cirron useful: https://github.com/s7nfo/Cirron

FYI vien [0] figured out that simply compiling with "-static -fno-pie" and _exit(0)-ing at the end puts the solution presented here to 15000 points and hence #4 on the leaderboard. Pretty funny.

[0] https://news.ycombinator.com/user?id=vient

Neat! I'll add the best solution without explicit SIMD/asm in this thread to the post after I wake up, it's a great datapoint.

14 already assumes unsigned accumulator! 255 [accumulator capacity] / (2 [shuffle-adds] * 9 [highest digit value]) ~= 14

Map vs. territory. The challenge, as defined by the system the competition runs on, is to get 3 correct responses in a row. That's it.

1) if you set BATCH_SIZE > 14 sums_acc may overflow

2) chunks with too many small numbers cannot be processed with just 2 shuffle-adds

3) (not mentioned in the post) HighLoad limits the size of the source code you can submit, so you can't put all possible values in the look-up table

To be clear, it’s not dereferencing unmapped memory, I just haven’t shown how it’s being mapped, because it’s a little complex. As I note in the post, you can imagine as if I mmap all the necessary addresses at the start of the program.

It's not quite so simple: AFAICS they have not open-sourced the training code, only one for sampling from the pre-trained model.