py: Provide mp_decode_uint_skip() to help reduce stack usage.
Taking the address of a local variable leads to increased stack usage, so the mp_decode_uint_skip() function is added to reduce the need for taking addresses. The changes in this patch reduce stack usage of a Python call by 8 bytes on ARM Thumb, by 16 bytes on non-windowing Xtensa archs, and by 16 bytes on x86-64. Code size is also slightly reduced on most archs by around 32 bytes.
This commit is contained in:
@@ -54,12 +54,9 @@ STATIC mp_obj_t gen_wrap_call(mp_obj_t self_in, size_t n_args, size_t n_kw, cons
|
||||
mp_obj_fun_bc_t *self_fun = (mp_obj_fun_bc_t*)self->fun;
|
||||
assert(self_fun->base.type == &mp_type_fun_bc);
|
||||
|
||||
// get start of bytecode
|
||||
const byte *ip = self_fun->bytecode;
|
||||
|
||||
// bytecode prelude: get state size and exception stack size
|
||||
mp_uint_t n_state = mp_decode_uint(&ip);
|
||||
mp_uint_t n_exc_stack = mp_decode_uint(&ip);
|
||||
size_t n_state = mp_decode_uint_value(self_fun->bytecode);
|
||||
size_t n_exc_stack = mp_decode_uint_value(mp_decode_uint_skip(self_fun->bytecode));
|
||||
|
||||
// allocate the generator object, with room for local stack and exception stack
|
||||
mp_obj_gen_instance_t *o = m_new_obj_var(mp_obj_gen_instance_t, byte,
|
||||
|
||||
Reference in New Issue
Block a user