[camel-cdr]

> The answer, if it’s not obvious from my tone already:), is 8%.

Not if the data is small and in cache.

> The performant route with AVX-512 would probably include the instruction vpconflictd, but I couldn’t really find any elegant way to use it.

I think the best way to do this is duplicate sum_r and count 16 times, so each pane has a seperate accumulation bucket and there can't be any conflicts. After the loop, you quickly do a sum reduction for each of the 16 buckets.

[shihab]

Yeah N is big enough that entire data isn't in the cache, but the memory access pattern here is the next best thing: totally linear, predictable access. I remember seeing around 94%+ L1d cache hit rate.

[praptak]

> Not if the data is small and in cache.

Isn't it another way of saying what the author says in the previous paragraph, namely that "ideal SIMD speedup can only come from problems that are compute bound"?

If the cost of getting the input data into the cache is already large compared to processing it with the non-vectorized code, then SIMD cannot achieve meaningful speedup. The opposite of this condition (processing is expensive compared to the cost of data into the cache) is basically the definition "compute bound".