It's beyond amazing we can still innovate on something like a memory allocator using hardware tricks that have been available for nearly 40 years. Leave no stone unturned!
We thought similarly about cache performance, but weren't able to find specific examples (most of the slow benchmarks we dug into were due to unoptimized allocator performance rather than poorer caching).
Informally I think one of the reasons for this is that in long running problems, allocations returned from malloc end up being pretty random rather than contiguous -- as allocations are freed they are put in freelists, and freelists are designed more for temporal locality rather than spatial.
BTW, this is really cool project. Do you envision any difficulties of merging this into jemalloc?
In terms of contrasts it'd be like trying to merge Ruby with Python.. this project's approach stands independently. It may be better to ask what features it can gain from merging with something like jemalloc