An often overlooked gem of AVX-512 is its (optional) conflict detection instructions. Using these enables vectorizing gather-modify-scatter operations that may alias at the element/lane level. Algorithms that have irregular data-level parallelism (DLP) as opposed to perfect or embarrassingly parallel DLP can now take advantage of the SIMD registers/FUs.

https://upcommons.upc.edu/bitstream/handle/2117/77204/VSR%20... shows how radix sort can be vectorized much more efficiently using these types of instructions.