strf VS pdqsort

You might get interested in trying strf library instead:

If you want a formatting library that supports well char8_t and UTF, you might get interested in the one I'm developing: Strf.

You might like the strf formatting library then

You can also use https://github.com/robhz786/strf to convert utf-8 to utf-32 ( as demonstrated here).

Format strings enable the use of tools like gettex. However, with the strf formatting library, It is possible to use them without a format string.

So it is a formatting library (strf), and if one wants to make a type xyz printable, one can either specialize a template or overload tag_invoke function, like below:

The Strf formatting library may solve your problem:

There is the strf formatting library. Its current version (0.14) is not working well in CUDA, but I'm working to fix this into the next release, which should come soon. The usage would be:

strf

I found that this exists: https://github.com/orlp/pdqsort

Their sort_unstable algorithm is based on this pattern-defeating quicksort.

Closely related is pattern defeating quicksort ( https://github.com/orlp/pdqsort ), which adapts quicksort to take advantage of sorted runs. I've adapted a few quicksorts to pdqsort and seen good speedups (as people were often sorting partially sorted data)

Basically: Timsort is to mergesort as pdqsort is to quicksort

I was thinking of optimal C++ over native types. I just spoke up because if your intuition of quicksort is that 50k elements should take 20ms you’re drastically underestimating computer performance. They’re crazy fast and optimized sorting algorithms are downright scary.

Just for fun, I added pdqsort to the benchmark:

https://github.com/orlp/pdqsort

Here are some of the results on an Ivy Bridge hackintosh:

      size, qsort, inline, sort, stable_sort, pdqsort, radix7

sort_unstable is a pattern-defeating quicksort (https://github.com/orlp/pdqsort) added with RFC#1884 (https://github.com/rust-lang/rfcs/pull/1884).