2283b6d68f
This change makes it so the compiler and persistent code loader take a mp_compiled_module_t* as their last argument, instead of returning this struct. This eliminates a duplicate context variable for all callers of these functions (because the context is now stored in the mp_compiled_module_t by the caller), and also eliminates any confusion about which context to use after the mp_compile_to_raw_code or mp_raw_code_load function returns (because there is now only one context, that stored in mp_compiled_module_t.context). Reduces code size by 16 bytes on ARM Cortex-based ports. Signed-off-by: Damien George <damien@micropython.org> |
||
---|---|---|
.. | ||
mpy_cross | ||
Makefile | ||
README.md | ||
gccollect.c | ||
main.c | ||
mpconfigport.h | ||
mphalport.h | ||
mpy-cross.vcxproj | ||
qstrdefsport.h |
README.md
MicroPython cross compiler
This directory contains the MicroPython cross compiler, which runs under any Unix-like system and compiles .py scripts into .mpy files.
Build it as usual:
$ make
The compiler is called mpy-cross
. Invoke it as:
$ ./mpy-cross foo.py
This will create a file foo.mpy which can then be copied to a place accessible
by the target MicroPython runtime (eg onto a pyboard's filesystem), and then
imported like any other Python module using import foo
.
Different target runtimes may require a different format of the compiled bytecode, and such options can be passed to the cross compiler.
If the Python code contains @native
or @viper
annotations, then you must
specify -march
to match the target architecture.
Run ./mpy-cross -h
to get a full list of options.
The optimisation level is 0 by default. Optimisation levels are detailed in https://docs.micropython.org/en/latest/library/micropython.html#micropython.opt_level