f2040bfc7e
Background: .mpy files are precompiled .py files, built using mpy-cross, that contain compiled bytecode functions (and can also contain machine code). The benefit of using an .mpy file over a .py file is that they are faster to import and take less memory when importing. They are also smaller on disk. But the real benefit of .mpy files comes when they are frozen into the firmware. This is done by loading the .mpy file during compilation of the firmware and turning it into a set of big C data structures (the job of mpy-tool.py), which are then compiled and downloaded into the ROM of a device. These C data structures can be executed in-place, ie directly from ROM. This makes importing even faster because there is very little to do, and also means such frozen modules take up much less RAM (because their bytecode stays in ROM). The downside of frozen code is that it requires recompiling and reflashing the entire firmware. This can be a big barrier to entry, slows down development time, and makes it harder to do OTA updates of frozen code (because the whole firmware must be updated). This commit attempts to solve this problem by providing a solution that sits between loading .mpy files into RAM and freezing them into the firmware. The .mpy file format has been reworked so that it consists of data and bytecode which is mostly static and ready to run in-place. If these new .mpy files are located in flash/ROM which is memory addressable, the .mpy file can be executed (mostly) in-place. With this approach there is still a small amount of unpacking and linking of the .mpy file that needs to be done when it's imported, but it's still much better than loading an .mpy from disk into RAM (although not as good as freezing .mpy files into the firmware). The main trick to make static .mpy files is to adjust the bytecode so any qstrs that it references now go through a lookup table to convert from local qstr number in the module to global qstr number in the firmware. That means the bytecode does not need linking/rewriting of qstrs when it's loaded. Instead only a small qstr table needs to be built (and put in RAM) at import time. This means the bytecode itself is static/constant and can be used directly if it's in addressable memory. Also the qstr string data in the .mpy file, and some constant object data, can be used directly. Note that the qstr table is global to the module (ie not per function). In more detail, in the VM what used to be (schematically): qst = DECODE_QSTR_VALUE; is now (schematically): idx = DECODE_QSTR_INDEX; qst = qstr_table[idx]; That allows the bytecode to be fixed at compile time and not need relinking/rewriting of the qstr values. Only qstr_table needs to be linked when the .mpy is loaded. Incidentally, this helps to reduce the size of bytecode because what used to be 2-byte qstr values in the bytecode are now (mostly) 1-byte indices. If the module uses the same qstr more than two times then the bytecode is smaller than before. The following changes are measured for this commit compared to the previous (the baseline): - average 7%-9% reduction in size of .mpy files - frozen code size is reduced by about 5%-7% - importing .py files uses about 5% less RAM in total - importing .mpy files uses about 4% less RAM in total - importing .py and .mpy files takes about the same time as before The qstr indirection in the bytecode has only a small impact on VM performance. For stm32 on PYBv1.0 the performance change of this commit is: diff of scores (higher is better) N=100 M=100 baseline -> this-commit diff diff% (error%) bm_chaos.py 371.07 -> 357.39 : -13.68 = -3.687% (+/-0.02%) bm_fannkuch.py 78.72 -> 77.49 : -1.23 = -1.563% (+/-0.01%) bm_fft.py 2591.73 -> 2539.28 : -52.45 = -2.024% (+/-0.00%) bm_float.py 6034.93 -> 5908.30 : -126.63 = -2.098% (+/-0.01%) bm_hexiom.py 48.96 -> 47.93 : -1.03 = -2.104% (+/-0.00%) bm_nqueens.py 4510.63 -> 4459.94 : -50.69 = -1.124% (+/-0.00%) bm_pidigits.py 650.28 -> 644.96 : -5.32 = -0.818% (+/-0.23%) core_import_mpy_multi.py 564.77 -> 581.49 : +16.72 = +2.960% (+/-0.01%) core_import_mpy_single.py 68.67 -> 67.16 : -1.51 = -2.199% (+/-0.01%) core_qstr.py 64.16 -> 64.12 : -0.04 = -0.062% (+/-0.00%) core_yield_from.py 362.58 -> 354.50 : -8.08 = -2.228% (+/-0.00%) misc_aes.py 429.69 -> 405.59 : -24.10 = -5.609% (+/-0.01%) misc_mandel.py 3485.13 -> 3416.51 : -68.62 = -1.969% (+/-0.00%) misc_pystone.py 2496.53 -> 2405.56 : -90.97 = -3.644% (+/-0.01%) misc_raytrace.py 381.47 -> 374.01 : -7.46 = -1.956% (+/-0.01%) viper_call0.py 576.73 -> 572.49 : -4.24 = -0.735% (+/-0.04%) viper_call1a.py 550.37 -> 546.21 : -4.16 = -0.756% (+/-0.09%) viper_call1b.py 438.23 -> 435.68 : -2.55 = -0.582% (+/-0.06%) viper_call1c.py 442.84 -> 440.04 : -2.80 = -0.632% (+/-0.08%) viper_call2a.py 536.31 -> 532.35 : -3.96 = -0.738% (+/-0.06%) viper_call2b.py 382.34 -> 377.07 : -5.27 = -1.378% (+/-0.03%) And for unix on x64: diff of scores (higher is better) N=2000 M=2000 baseline -> this-commit diff diff% (error%) bm_chaos.py 13594.20 -> 13073.84 : -520.36 = -3.828% (+/-5.44%) bm_fannkuch.py 60.63 -> 59.58 : -1.05 = -1.732% (+/-3.01%) bm_fft.py 112009.15 -> 111603.32 : -405.83 = -0.362% (+/-4.03%) bm_float.py 246202.55 -> 247923.81 : +1721.26 = +0.699% (+/-2.79%) bm_hexiom.py 615.65 -> 617.21 : +1.56 = +0.253% (+/-1.64%) bm_nqueens.py 215807.95 -> 215600.96 : -206.99 = -0.096% (+/-3.52%) bm_pidigits.py 8246.74 -> 8422.82 : +176.08 = +2.135% (+/-3.64%) misc_aes.py 16133.00 -> 16452.74 : +319.74 = +1.982% (+/-1.50%) misc_mandel.py 128146.69 -> 130796.43 : +2649.74 = +2.068% (+/-3.18%) misc_pystone.py 83811.49 -> 83124.85 : -686.64 = -0.819% (+/-1.03%) misc_raytrace.py 21688.02 -> 21385.10 : -302.92 = -1.397% (+/-3.20%) The code size change is (firmware with a lot of frozen code benefits the most): bare-arm: +396 +0.697% minimal x86: +1595 +0.979% [incl +32(data)] unix x64: +2408 +0.470% [incl +800(data)] unix nanbox: +1396 +0.309% [incl -96(data)] stm32: -1256 -0.318% PYBV10 cc3200: +288 +0.157% esp8266: -260 -0.037% GENERIC esp32: -216 -0.014% GENERIC[incl -1072(data)] nrf: +116 +0.067% pca10040 rp2: -664 -0.135% PICO samd: +844 +0.607% ADAFRUIT_ITSYBITSY_M4_EXPRESS As part of this change the .mpy file format version is bumped to version 6. And mpy-tool.py has been improved to provide a good visualisation of the contents of .mpy files. In summary: this commit changes the bytecode to use qstr indirection, and reworks the .mpy file format to be simpler and allow .mpy files to be executed in-place. Performance is not impacted too much. Eventually it will be possible to store such .mpy files in a linear, read-only, memory- mappable filesystem so they can be executed from flash/ROM. This will essentially be able to replace frozen code for most applications. Signed-off-by: Damien George <damien@micropython.org>
238 lines
8.2 KiB
C
238 lines
8.2 KiB
C
/*
|
|
* This file is part of the MicroPython project, http://micropython.org/
|
|
*
|
|
* The MIT License (MIT)
|
|
*
|
|
* Copyright (c) 2013, 2014 Damien P. George
|
|
*
|
|
* Permission is hereby granted, free of charge, to any person obtaining a copy
|
|
* of this software and associated documentation files (the "Software"), to deal
|
|
* in the Software without restriction, including without limitation the rights
|
|
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
|
* copies of the Software, and to permit persons to whom the Software is
|
|
* furnished to do so, subject to the following conditions:
|
|
*
|
|
* The above copyright notice and this permission notice shall be included in
|
|
* all copies or substantial portions of the Software.
|
|
*
|
|
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
|
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
|
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
|
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
|
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
|
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
|
* THE SOFTWARE.
|
|
*/
|
|
|
|
// This code glues the code emitters to the runtime.
|
|
|
|
#include <stdint.h>
|
|
#include <stdio.h>
|
|
#include <string.h>
|
|
#include <assert.h>
|
|
|
|
#include "py/emitglue.h"
|
|
#include "py/runtime0.h"
|
|
#include "py/bc.h"
|
|
#include "py/objfun.h"
|
|
#include "py/profile.h"
|
|
|
|
#if MICROPY_DEBUG_VERBOSE // print debugging info
|
|
#define DEBUG_PRINT (1)
|
|
#define WRITE_CODE (1)
|
|
#define DEBUG_printf DEBUG_printf
|
|
#define DEBUG_OP_printf(...) DEBUG_printf(__VA_ARGS__)
|
|
#else // don't print debugging info
|
|
#define DEBUG_printf(...) (void)0
|
|
#define DEBUG_OP_printf(...) (void)0
|
|
#endif
|
|
|
|
#if MICROPY_DEBUG_PRINTERS
|
|
mp_uint_t mp_verbose_flag = 0;
|
|
#endif
|
|
|
|
mp_raw_code_t *mp_emit_glue_new_raw_code(void) {
|
|
mp_raw_code_t *rc = m_new0(mp_raw_code_t, 1);
|
|
rc->kind = MP_CODE_RESERVED;
|
|
#if MICROPY_PY_SYS_SETTRACE
|
|
rc->line_of_definition = 0;
|
|
#endif
|
|
return rc;
|
|
}
|
|
|
|
void mp_emit_glue_assign_bytecode(mp_raw_code_t *rc, const byte *code,
|
|
#if MICROPY_PERSISTENT_CODE_SAVE || MICROPY_DEBUG_PRINTERS
|
|
size_t len,
|
|
#endif
|
|
mp_raw_code_t **children,
|
|
#if MICROPY_PERSISTENT_CODE_SAVE
|
|
size_t n_children,
|
|
#endif
|
|
mp_uint_t scope_flags) {
|
|
|
|
rc->kind = MP_CODE_BYTECODE;
|
|
rc->scope_flags = scope_flags;
|
|
rc->fun_data = code;
|
|
#if MICROPY_PERSISTENT_CODE_SAVE || MICROPY_DEBUG_PRINTERS
|
|
rc->fun_data_len = len;
|
|
#endif
|
|
rc->children = children;
|
|
|
|
#if MICROPY_PERSISTENT_CODE_SAVE
|
|
rc->n_children = n_children;
|
|
#endif
|
|
|
|
#if MICROPY_PY_SYS_SETTRACE
|
|
mp_bytecode_prelude_t *prelude = &rc->prelude;
|
|
mp_prof_extract_prelude(code, prelude);
|
|
#endif
|
|
|
|
#ifdef DEBUG_PRINT
|
|
#if !(MICROPY_PERSISTENT_CODE_SAVE || MICROPY_DEBUG_PRINTERS)
|
|
const size_t len = 0;
|
|
#endif
|
|
DEBUG_printf("assign byte code: code=%p len=" UINT_FMT " flags=%x\n", code, len, (uint)scope_flags);
|
|
#endif
|
|
}
|
|
|
|
#if MICROPY_EMIT_MACHINE_CODE
|
|
void mp_emit_glue_assign_native(mp_raw_code_t *rc, mp_raw_code_kind_t kind, void *fun_data, mp_uint_t fun_len,
|
|
mp_raw_code_t **children,
|
|
#if MICROPY_PERSISTENT_CODE_SAVE
|
|
size_t n_children,
|
|
uint16_t prelude_offset,
|
|
uint16_t n_qstr, mp_qstr_link_entry_t *qstr_link,
|
|
#endif
|
|
mp_uint_t scope_flags, mp_uint_t n_pos_args, mp_uint_t type_sig) {
|
|
|
|
assert(kind == MP_CODE_NATIVE_PY || kind == MP_CODE_NATIVE_VIPER || kind == MP_CODE_NATIVE_ASM);
|
|
|
|
// Some architectures require flushing/invalidation of the I/D caches,
|
|
// so that the generated native code which was created in data RAM will
|
|
// be available for execution from instruction RAM.
|
|
#if MICROPY_EMIT_THUMB || MICROPY_EMIT_INLINE_THUMB
|
|
#if __ICACHE_PRESENT == 1
|
|
// Flush D-cache, so the code emitted is stored in RAM.
|
|
MP_HAL_CLEAN_DCACHE(fun_data, fun_len);
|
|
// Invalidate I-cache, so the newly-created code is reloaded from RAM.
|
|
SCB_InvalidateICache();
|
|
#endif
|
|
#elif MICROPY_EMIT_ARM
|
|
#if (defined(__linux__) && defined(__GNUC__)) || __ARM_ARCH == 7
|
|
__builtin___clear_cache(fun_data, (uint8_t *)fun_data + fun_len);
|
|
#elif defined(__arm__)
|
|
// Flush I-cache and D-cache.
|
|
asm volatile (
|
|
"0:"
|
|
"mrc p15, 0, r15, c7, c10, 3\n" // test and clean D-cache
|
|
"bne 0b\n"
|
|
"mov r0, #0\n"
|
|
"mcr p15, 0, r0, c7, c7, 0\n" // invalidate I-cache and D-cache
|
|
: : : "r0", "cc");
|
|
#endif
|
|
#endif
|
|
|
|
rc->kind = kind;
|
|
rc->scope_flags = scope_flags;
|
|
rc->fun_data = fun_data;
|
|
|
|
#if MICROPY_PERSISTENT_CODE_SAVE || MICROPY_DEBUG_PRINTERS
|
|
rc->fun_data_len = fun_len;
|
|
#endif
|
|
rc->children = children;
|
|
|
|
#if MICROPY_PERSISTENT_CODE_SAVE
|
|
rc->n_children = n_children;
|
|
rc->prelude_offset = prelude_offset;
|
|
rc->n_qstr = n_qstr;
|
|
rc->qstr_link = qstr_link;
|
|
#endif
|
|
|
|
// These two entries are only needed for MP_CODE_NATIVE_ASM.
|
|
rc->n_pos_args = n_pos_args;
|
|
rc->type_sig = type_sig;
|
|
|
|
#ifdef DEBUG_PRINT
|
|
DEBUG_printf("assign native: kind=%d fun=%p len=" UINT_FMT " n_pos_args=" UINT_FMT " flags=%x\n", kind, fun_data, fun_len, n_pos_args, (uint)scope_flags);
|
|
for (mp_uint_t i = 0; i < fun_len; i++) {
|
|
if (i > 0 && i % 16 == 0) {
|
|
DEBUG_printf("\n");
|
|
}
|
|
DEBUG_printf(" %02x", ((byte *)fun_data)[i]);
|
|
}
|
|
DEBUG_printf("\n");
|
|
|
|
#ifdef WRITE_CODE
|
|
FILE *fp_write_code = fopen("out-code", "wb");
|
|
fwrite(fun_data, fun_len, 1, fp_write_code);
|
|
fclose(fp_write_code);
|
|
#endif
|
|
#else
|
|
(void)fun_len;
|
|
#endif
|
|
}
|
|
#endif
|
|
|
|
mp_obj_t mp_make_function_from_raw_code(const mp_raw_code_t *rc, const mp_module_context_t *context, const mp_obj_t *def_args) {
|
|
DEBUG_OP_printf("make_function_from_raw_code %p\n", rc);
|
|
assert(rc != NULL);
|
|
|
|
// def_args must be MP_OBJ_NULL or a tuple
|
|
assert(def_args == NULL || def_args[0] == MP_OBJ_NULL || mp_obj_is_type(def_args[0], &mp_type_tuple));
|
|
|
|
// def_kw_args must be MP_OBJ_NULL or a dict
|
|
assert(def_args == NULL || def_args[1] == MP_OBJ_NULL || mp_obj_is_type(def_args[1], &mp_type_dict));
|
|
|
|
// make the function, depending on the raw code kind
|
|
mp_obj_t fun;
|
|
switch (rc->kind) {
|
|
#if MICROPY_EMIT_NATIVE
|
|
case MP_CODE_NATIVE_PY:
|
|
case MP_CODE_NATIVE_VIPER:
|
|
fun = mp_obj_new_fun_native(def_args, rc->fun_data, context, rc->children);
|
|
// Check for a generator function, and if so change the type of the object
|
|
if ((rc->scope_flags & MP_SCOPE_FLAG_GENERATOR) != 0) {
|
|
((mp_obj_base_t *)MP_OBJ_TO_PTR(fun))->type = &mp_type_native_gen_wrap;
|
|
}
|
|
break;
|
|
#endif
|
|
#if MICROPY_EMIT_INLINE_ASM
|
|
case MP_CODE_NATIVE_ASM:
|
|
fun = mp_obj_new_fun_asm(rc->n_pos_args, rc->fun_data, rc->type_sig);
|
|
break;
|
|
#endif
|
|
default:
|
|
// rc->kind should always be set and BYTECODE is the only remaining case
|
|
assert(rc->kind == MP_CODE_BYTECODE);
|
|
fun = mp_obj_new_fun_bc(def_args, rc->fun_data, context, rc->children);
|
|
// check for generator functions and if so change the type of the object
|
|
if ((rc->scope_flags & MP_SCOPE_FLAG_GENERATOR) != 0) {
|
|
((mp_obj_base_t *)MP_OBJ_TO_PTR(fun))->type = &mp_type_gen_wrap;
|
|
}
|
|
|
|
#if MICROPY_PY_SYS_SETTRACE
|
|
mp_obj_fun_bc_t *self_fun = (mp_obj_fun_bc_t *)MP_OBJ_TO_PTR(fun);
|
|
self_fun->rc = rc;
|
|
#endif
|
|
|
|
break;
|
|
}
|
|
|
|
return fun;
|
|
}
|
|
|
|
mp_obj_t mp_make_closure_from_raw_code(const mp_raw_code_t *rc, const mp_module_context_t *context, mp_uint_t n_closed_over, const mp_obj_t *args) {
|
|
DEBUG_OP_printf("make_closure_from_raw_code %p " UINT_FMT " %p\n", rc, n_closed_over, args);
|
|
// make function object
|
|
mp_obj_t ffun;
|
|
if (n_closed_over & 0x100) {
|
|
// default positional and keyword args given
|
|
ffun = mp_make_function_from_raw_code(rc, context, args);
|
|
} else {
|
|
// default positional and keyword args not given
|
|
ffun = mp_make_function_from_raw_code(rc, context, NULL);
|
|
}
|
|
// wrap function in closure object
|
|
return mp_obj_new_closure(ffun, n_closed_over & 0xff, args + ((n_closed_over >> 7) & 2));
|
|
}
|