We are excited to announce the v0.5.1 release of Pyston, our high performance Python JIT.
This minor release passes all SciPy tests and is on average about 15% faster than 0.5.0. In addition several bug fixes and compatibility improvements got merged.
Performance related changes:
We released recently a blog post about our baseline JIT and inline caches. This release brings a lot of improvements in this area, some of the changes are:
- the number of ICs slots is now variable. Before we specified for every IC how many slots it has and how large they should be (all slots in a IC had the same size). This often led to higher memory usage than necessary. We changed it now to a fixed size of memory which will than get filled with variable size slots whenever a new slot is required and there is space left in the IC. In addition this makes our IC size estimates in the LLVM tier more accurate because they are now based on the number of bytes we required in the bjit tier.
- the interpreter reuses the stack slots (internally called vregs) assigned to temporary values which are only live in a basic block. This reduces stack usage which saves memory and made Pyston faster.
- better non null value tracking, stack spilling, duplicate guard removal and much more temporary values will get held in registers
- the bjit and ICs can now use callee-save register which removes a lot of spilling around calls
- added a script which allows to inspect jited code directly from `perf report`.
- usage with `make perf_<testname>`
- our codegen and analysis passes now work on the vreg numbers which allows us to use arrays as internal data structures instead of hash tables which makes the code easier to understand and faster
- faster reference counting pass in the code generator of the LLVM tier
startup performance benchmarks:
This benchmarks show that the startup time improved significantly. Part of this comes from the numerous bjit improvements mentioned above (the chart also contains a direct comparison between the bjit performance of the different releases).
steady state benchmarks:
There are still a lot of low hanging fruit and we still have a huge amount of ideas for (performance) improvements for future releases.
The next months we will use to make Pyston ready for usage at dropbox – this is going to be very exciting 🙂
Finally, we would like to thank all of our open source contributors who have contributed to this release, and especially Nexedi for their employment of Boxiang Sun, one of our core contributors who helped greatly with the SciPy support.
- Cullen Rhodes
- Long Ang
- Lucien Chan