Inhibit vec

Implements #481 (closed).

• Optimised the way we handle inhibited particles in the density and force neighbour searches
• Make sure inhibited particles do not interact in the vectorised versions of the density and force neighbour searches

Do these changes seem reasonable to you? I just treat inhibited particles as padded elements in the vector, so I make sure they have positions outside of the cell.

added 108 commits

• 56c613c9...bc4b31a9 - 106 commits from branch master
• fbb36b6f - Merge branch 'master' into inhibit_vec
• cf0b7521 - Code formatting

Compare with previous version

added 1 commit

• eabd0020 - Improvements also to DOPAIR_SUBSET_NAIVE()

Compare with previous version

I have gone through the scalar version thus far. I agree with your improvements. What do you think of that last commit I pushed?

Yeah, that change makes sense too. I have tested it with star formation on and running with -S, but I don't know if you want to test it yourself.

That is also what I have done on the EAGLE_12 and _25. I need to try the vectorized version now.

Not putting the inhibted particles in the cache makes sense to me.

added 1 commit

• 47ca1589 - Change the condition to >= time_bin_inhibited when constructing the hydro cache.

Compare with previous version

I have made a small change >= not == since I use an extra time-bin value for some things. These particles should never appear here but let's be safe.

Any reason why no changes were applied to cache_read_particles_subset()?

Also, do you have a way of testing the vectorized version? The debugging checks inside the interaction function are only present in the scalar code.

Finally, do you know whether the cache construction with the new continue in it or the padding still vectorizes?

changed the description

added 1 commit

• af5f988f - Fixed typo.

Compare with previous version

Thanks!

added 1 commit

• bdc6671e - Fix DOPAIR_SUBSET_NAIVE() when debugging checks are enabled.

Compare with previous version

resolved all discussions

I think I missed cache_read_particles_subset(), I will do that next.

The inhibited particles will appear in the vectorised interaction function but will be masked out afterwards.

So the pair cache construction still vectorises, but the self cache construction doesn't with AVX because of the uninhibited_count variable used for indexing the array... Although when I benchmark it I get the same performance as the master branch. But looking at the vector report again shows that that loop doesn't actually get vectorised as the expected speedup is too low. The self cache construction does vectorise on COSMA7 with AVX512 though.

Thanks. Sounds good.

I am just uneasy about the inability to formally test it but don't have anything to suggest right now.

Can you remind me which cache construction function is used for the SELF and which is used for the PAIR?

cache_read_particles is the SELF and cache_read_two_partial_cells_sorted is the PAIR.

added 1 commit

• 1483f29f - Place inhibited particles out of range of neighbouring particles so no…

Compare with previous version

added 4 commits

• 6ee6efb8 - In runner_doself1_density_vec(), construct the padded positions only once for…
• 0c77373b - In runner_doself1_density_vec() do not check for r2 > 0. This is never done in…
• ab7e78da - Revert "In runner_doself1_density_vec() do not check for r2 > 0. This is never…
• 61172cf8 - Cosmetic changes.

Compare with previous version