I'm surprised 10% wasn't enough - 10% bottom-line improvement in programming language implementation is normally massive. Twitter is singing from the roof-tops about 10% improvement in Java performance from the new Graal JIT compiler.
I would imagine that for code that is performance sensitive enough that a 10% improvement matters, they would be porting to a language with saner performance instead?
I'm by no means an expert on the subject, but isn't there an advantage to having a JIT compiler use LLVM?
On another note, I believe one thing that has been problematic for pypy adoption is that it does not automatically work with C extensions or Cython, and generally if someone already had performance issues with CPython, they would have written some C/Cython extensions?
It's a tool that allows you to write an entire interpreter in RPython (a subset of Python) and then have it build a native binary with a free jit compiler included, with the specifics of your language encoded within. The reference implementation for this project is a Python interpreter.
Maybe because 10% on a server is much more valuable than 10% on a client.
On a server, you’re paying for that 10%. On a client, you’re not. If it was 10% for nearly free then sure - but maintaining a separate implementation of a language is costly.
https://blog.pyston.org/2017/01/31/pyston-0-6-1-released-and...