circuitpython/tests/micropython/import_mpy_native_x64.py

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

118 lines
2.9 KiB
Python
Raw Normal View History

# test importing of .mpy files with native code (x64 only)
try:
import usys, uio, uos
uio.IOBase
uos.mount
except (ImportError, AttributeError):
print("SKIP")
raise SystemExit
if not (usys.platform == "linux" and usys.maxsize > 2 ** 32):
print("SKIP")
raise SystemExit
class UserFile(uio.IOBase):
def __init__(self, data):
self.data = memoryview(data)
self.pos = 0
def readinto(self, buf):
n = min(len(buf), len(self.data) - self.pos)
buf[:n] = self.data[self.pos : self.pos + n]
self.pos += n
return n
def ioctl(self, req, arg):
return 0
class UserFS:
def __init__(self, files):
self.files = files
def mount(self, readonly, mksfs):
pass
def umount(self):
pass
def stat(self, path):
if path in self.files:
return (32768, 0, 0, 0, 0, 0, 0, 0, 0, 0)
raise OSError
def open(self, path, mode):
return UserFile(self.files[path])
# these are the test .mpy files
# fmt: off
user_files = {
# bad architecture
all: Remove MICROPY_OPT_CACHE_MAP_LOOKUP_IN_BYTECODE. This commit removes all parts of code associated with the existing MICROPY_OPT_CACHE_MAP_LOOKUP_IN_BYTECODE optimisation option, including the -mcache-lookup-bc option to mpy-cross. This feature originally provided a significant performance boost for Unix, but wasn't able to be enabled for MCU targets (due to frozen bytecode), and added significant extra complexity to generating and distributing .mpy files. The equivalent performance gain is now provided by the combination of MICROPY_OPT_LOAD_ATTR_FAST_PATH and MICROPY_OPT_MAP_LOOKUP_CACHE (which has been enabled on the unix port in the previous commit). It's hard to provide precise performance numbers, but tests have been run on a wide variety of architectures (x86-64, ARM Cortex, Aarch64, RISC-V, xtensa) and they all generally agree on the qualitative improvements seen by the combination of MICROPY_OPT_LOAD_ATTR_FAST_PATH and MICROPY_OPT_MAP_LOOKUP_CACHE. For example, on a "quiet" Linux x64 environment (i3-5010U @ 2.10GHz) the change from CACHE_MAP_LOOKUP_IN_BYTECODE, to LOAD_ATTR_FAST_PATH combined with MAP_LOOKUP_CACHE is: diff of scores (higher is better) N=2000 M=2000 bccache -> attrmapcache diff diff% (error%) bm_chaos.py 13742.56 -> 13905.67 : +163.11 = +1.187% (+/-3.75%) bm_fannkuch.py 60.13 -> 61.34 : +1.21 = +2.012% (+/-2.11%) bm_fft.py 113083.20 -> 114793.68 : +1710.48 = +1.513% (+/-1.57%) bm_float.py 256552.80 -> 243908.29 : -12644.51 = -4.929% (+/-1.90%) bm_hexiom.py 521.93 -> 625.41 : +103.48 = +19.826% (+/-0.40%) bm_nqueens.py 197544.25 -> 217713.12 : +20168.87 = +10.210% (+/-3.01%) bm_pidigits.py 8072.98 -> 8198.75 : +125.77 = +1.558% (+/-3.22%) misc_aes.py 17283.45 -> 16480.52 : -802.93 = -4.646% (+/-0.82%) misc_mandel.py 99083.99 -> 128939.84 : +29855.85 = +30.132% (+/-5.88%) misc_pystone.py 83860.10 -> 82592.56 : -1267.54 = -1.511% (+/-2.27%) misc_raytrace.py 21490.40 -> 22227.23 : +736.83 = +3.429% (+/-1.88%) This shows that the new optimisations are at least as good as the existing inline-bytecode-caching, and are sometimes much better (because the new ones apply caching to a wider variety of map lookups). The new optimisations can also benefit code generated by the native emitter, because they apply to the runtime rather than the generated code. The improvement for the native emitter when LOAD_ATTR_FAST_PATH and MAP_LOOKUP_CACHE are enabled is (same Linux environment as above): diff of scores (higher is better) N=2000 M=2000 native -> nat-attrmapcache diff diff% (error%) bm_chaos.py 14130.62 -> 15464.68 : +1334.06 = +9.441% (+/-7.11%) bm_fannkuch.py 74.96 -> 76.16 : +1.20 = +1.601% (+/-1.80%) bm_fft.py 166682.99 -> 168221.86 : +1538.87 = +0.923% (+/-4.20%) bm_float.py 233415.23 -> 265524.90 : +32109.67 = +13.756% (+/-2.57%) bm_hexiom.py 628.59 -> 734.17 : +105.58 = +16.796% (+/-1.39%) bm_nqueens.py 225418.44 -> 232926.45 : +7508.01 = +3.331% (+/-3.10%) bm_pidigits.py 6322.00 -> 6379.52 : +57.52 = +0.910% (+/-5.62%) misc_aes.py 20670.10 -> 27223.18 : +6553.08 = +31.703% (+/-1.56%) misc_mandel.py 138221.11 -> 152014.01 : +13792.90 = +9.979% (+/-2.46%) misc_pystone.py 85032.14 -> 105681.44 : +20649.30 = +24.284% (+/-2.25%) misc_raytrace.py 19800.01 -> 23350.73 : +3550.72 = +17.933% (+/-2.79%) In summary, compared to MICROPY_OPT_CACHE_MAP_LOOKUP_IN_BYTECODE, the new MICROPY_OPT_LOAD_ATTR_FAST_PATH and MICROPY_OPT_MAP_LOOKUP_CACHE options: - are simpler; - take less code size; - are faster (generally); - work with code generated by the native emitter; - can be used on embedded targets with a small and constant RAM overhead; - allow the same .mpy bytecode to run on all targets. See #7680 for further discussion. And see also #7653 for a discussion about simplifying mpy-cross options. Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
2021-09-05 22:28:06 -04:00
'/mod0.mpy': b'M\x05\xfe\x00\x10',
# test loading of viper and asm
'/mod1.mpy': (
all: Remove MICROPY_OPT_CACHE_MAP_LOOKUP_IN_BYTECODE. This commit removes all parts of code associated with the existing MICROPY_OPT_CACHE_MAP_LOOKUP_IN_BYTECODE optimisation option, including the -mcache-lookup-bc option to mpy-cross. This feature originally provided a significant performance boost for Unix, but wasn't able to be enabled for MCU targets (due to frozen bytecode), and added significant extra complexity to generating and distributing .mpy files. The equivalent performance gain is now provided by the combination of MICROPY_OPT_LOAD_ATTR_FAST_PATH and MICROPY_OPT_MAP_LOOKUP_CACHE (which has been enabled on the unix port in the previous commit). It's hard to provide precise performance numbers, but tests have been run on a wide variety of architectures (x86-64, ARM Cortex, Aarch64, RISC-V, xtensa) and they all generally agree on the qualitative improvements seen by the combination of MICROPY_OPT_LOAD_ATTR_FAST_PATH and MICROPY_OPT_MAP_LOOKUP_CACHE. For example, on a "quiet" Linux x64 environment (i3-5010U @ 2.10GHz) the change from CACHE_MAP_LOOKUP_IN_BYTECODE, to LOAD_ATTR_FAST_PATH combined with MAP_LOOKUP_CACHE is: diff of scores (higher is better) N=2000 M=2000 bccache -> attrmapcache diff diff% (error%) bm_chaos.py 13742.56 -> 13905.67 : +163.11 = +1.187% (+/-3.75%) bm_fannkuch.py 60.13 -> 61.34 : +1.21 = +2.012% (+/-2.11%) bm_fft.py 113083.20 -> 114793.68 : +1710.48 = +1.513% (+/-1.57%) bm_float.py 256552.80 -> 243908.29 : -12644.51 = -4.929% (+/-1.90%) bm_hexiom.py 521.93 -> 625.41 : +103.48 = +19.826% (+/-0.40%) bm_nqueens.py 197544.25 -> 217713.12 : +20168.87 = +10.210% (+/-3.01%) bm_pidigits.py 8072.98 -> 8198.75 : +125.77 = +1.558% (+/-3.22%) misc_aes.py 17283.45 -> 16480.52 : -802.93 = -4.646% (+/-0.82%) misc_mandel.py 99083.99 -> 128939.84 : +29855.85 = +30.132% (+/-5.88%) misc_pystone.py 83860.10 -> 82592.56 : -1267.54 = -1.511% (+/-2.27%) misc_raytrace.py 21490.40 -> 22227.23 : +736.83 = +3.429% (+/-1.88%) This shows that the new optimisations are at least as good as the existing inline-bytecode-caching, and are sometimes much better (because the new ones apply caching to a wider variety of map lookups). The new optimisations can also benefit code generated by the native emitter, because they apply to the runtime rather than the generated code. The improvement for the native emitter when LOAD_ATTR_FAST_PATH and MAP_LOOKUP_CACHE are enabled is (same Linux environment as above): diff of scores (higher is better) N=2000 M=2000 native -> nat-attrmapcache diff diff% (error%) bm_chaos.py 14130.62 -> 15464.68 : +1334.06 = +9.441% (+/-7.11%) bm_fannkuch.py 74.96 -> 76.16 : +1.20 = +1.601% (+/-1.80%) bm_fft.py 166682.99 -> 168221.86 : +1538.87 = +0.923% (+/-4.20%) bm_float.py 233415.23 -> 265524.90 : +32109.67 = +13.756% (+/-2.57%) bm_hexiom.py 628.59 -> 734.17 : +105.58 = +16.796% (+/-1.39%) bm_nqueens.py 225418.44 -> 232926.45 : +7508.01 = +3.331% (+/-3.10%) bm_pidigits.py 6322.00 -> 6379.52 : +57.52 = +0.910% (+/-5.62%) misc_aes.py 20670.10 -> 27223.18 : +6553.08 = +31.703% (+/-1.56%) misc_mandel.py 138221.11 -> 152014.01 : +13792.90 = +9.979% (+/-2.46%) misc_pystone.py 85032.14 -> 105681.44 : +20649.30 = +24.284% (+/-2.25%) misc_raytrace.py 19800.01 -> 23350.73 : +3550.72 = +17.933% (+/-2.79%) In summary, compared to MICROPY_OPT_CACHE_MAP_LOOKUP_IN_BYTECODE, the new MICROPY_OPT_LOAD_ATTR_FAST_PATH and MICROPY_OPT_MAP_LOOKUP_CACHE options: - are simpler; - take less code size; - are faster (generally); - work with code generated by the native emitter; - can be used on embedded targets with a small and constant RAM overhead; - allow the same .mpy bytecode to run on all targets. See #7680 for further discussion. And see also #7653 for a discussion about simplifying mpy-cross options. Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
2021-09-05 22:28:06 -04:00
b'M\x05\x0a\x1f\x20' # header
b'\x20' # n bytes, bytecode
b'\x00\x08\x02m\x02m' # prelude
b'\x51' # LOAD_CONST_NONE
b'\x63' # RETURN_VALUE
b'\x00\x02' # n_obj, n_raw_code
b'\x22' # n bytes, viper code
b'\x00\x00\x00\x00\x00\x00' # dummy machine code
b'\x00\x00' # qstr0
b'\x01\x0c\x0aprint' # n_qstr, qstr0
b'\x00\x00\x00' # scope_flags, n_obj, n_raw_code
b'\x23' # n bytes, asm code
b'\x00\x00\x00\x00\x00\x00\x00\x00' # dummy machine code
b'\x00\x00\x00' # scope_flags, n_pos_args, type_sig
),
# test loading viper with additional scope flags and relocation
'/mod2.mpy': (
all: Remove MICROPY_OPT_CACHE_MAP_LOOKUP_IN_BYTECODE. This commit removes all parts of code associated with the existing MICROPY_OPT_CACHE_MAP_LOOKUP_IN_BYTECODE optimisation option, including the -mcache-lookup-bc option to mpy-cross. This feature originally provided a significant performance boost for Unix, but wasn't able to be enabled for MCU targets (due to frozen bytecode), and added significant extra complexity to generating and distributing .mpy files. The equivalent performance gain is now provided by the combination of MICROPY_OPT_LOAD_ATTR_FAST_PATH and MICROPY_OPT_MAP_LOOKUP_CACHE (which has been enabled on the unix port in the previous commit). It's hard to provide precise performance numbers, but tests have been run on a wide variety of architectures (x86-64, ARM Cortex, Aarch64, RISC-V, xtensa) and they all generally agree on the qualitative improvements seen by the combination of MICROPY_OPT_LOAD_ATTR_FAST_PATH and MICROPY_OPT_MAP_LOOKUP_CACHE. For example, on a "quiet" Linux x64 environment (i3-5010U @ 2.10GHz) the change from CACHE_MAP_LOOKUP_IN_BYTECODE, to LOAD_ATTR_FAST_PATH combined with MAP_LOOKUP_CACHE is: diff of scores (higher is better) N=2000 M=2000 bccache -> attrmapcache diff diff% (error%) bm_chaos.py 13742.56 -> 13905.67 : +163.11 = +1.187% (+/-3.75%) bm_fannkuch.py 60.13 -> 61.34 : +1.21 = +2.012% (+/-2.11%) bm_fft.py 113083.20 -> 114793.68 : +1710.48 = +1.513% (+/-1.57%) bm_float.py 256552.80 -> 243908.29 : -12644.51 = -4.929% (+/-1.90%) bm_hexiom.py 521.93 -> 625.41 : +103.48 = +19.826% (+/-0.40%) bm_nqueens.py 197544.25 -> 217713.12 : +20168.87 = +10.210% (+/-3.01%) bm_pidigits.py 8072.98 -> 8198.75 : +125.77 = +1.558% (+/-3.22%) misc_aes.py 17283.45 -> 16480.52 : -802.93 = -4.646% (+/-0.82%) misc_mandel.py 99083.99 -> 128939.84 : +29855.85 = +30.132% (+/-5.88%) misc_pystone.py 83860.10 -> 82592.56 : -1267.54 = -1.511% (+/-2.27%) misc_raytrace.py 21490.40 -> 22227.23 : +736.83 = +3.429% (+/-1.88%) This shows that the new optimisations are at least as good as the existing inline-bytecode-caching, and are sometimes much better (because the new ones apply caching to a wider variety of map lookups). The new optimisations can also benefit code generated by the native emitter, because they apply to the runtime rather than the generated code. The improvement for the native emitter when LOAD_ATTR_FAST_PATH and MAP_LOOKUP_CACHE are enabled is (same Linux environment as above): diff of scores (higher is better) N=2000 M=2000 native -> nat-attrmapcache diff diff% (error%) bm_chaos.py 14130.62 -> 15464.68 : +1334.06 = +9.441% (+/-7.11%) bm_fannkuch.py 74.96 -> 76.16 : +1.20 = +1.601% (+/-1.80%) bm_fft.py 166682.99 -> 168221.86 : +1538.87 = +0.923% (+/-4.20%) bm_float.py 233415.23 -> 265524.90 : +32109.67 = +13.756% (+/-2.57%) bm_hexiom.py 628.59 -> 734.17 : +105.58 = +16.796% (+/-1.39%) bm_nqueens.py 225418.44 -> 232926.45 : +7508.01 = +3.331% (+/-3.10%) bm_pidigits.py 6322.00 -> 6379.52 : +57.52 = +0.910% (+/-5.62%) misc_aes.py 20670.10 -> 27223.18 : +6553.08 = +31.703% (+/-1.56%) misc_mandel.py 138221.11 -> 152014.01 : +13792.90 = +9.979% (+/-2.46%) misc_pystone.py 85032.14 -> 105681.44 : +20649.30 = +24.284% (+/-2.25%) misc_raytrace.py 19800.01 -> 23350.73 : +3550.72 = +17.933% (+/-2.79%) In summary, compared to MICROPY_OPT_CACHE_MAP_LOOKUP_IN_BYTECODE, the new MICROPY_OPT_LOAD_ATTR_FAST_PATH and MICROPY_OPT_MAP_LOOKUP_CACHE options: - are simpler; - take less code size; - are faster (generally); - work with code generated by the native emitter; - can be used on embedded targets with a small and constant RAM overhead; - allow the same .mpy bytecode to run on all targets. See #7680 for further discussion. And see also #7653 for a discussion about simplifying mpy-cross options. Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
2021-09-05 22:28:06 -04:00
b'M\x05\x0a\x1f\x20' # header
b'\x20' # n bytes, bytecode
b'\x00\x08\x02m\x02m' # prelude
b'\x51' # LOAD_CONST_NONE
b'\x63' # RETURN_VALUE
b'\x00\x01' # n_obj, n_raw_code
b'\x12' # n bytes(=4), viper code
b'\x00\x00\x00\x00' # dummy machine code
b'\x00' # n_qstr
b'\x70' # scope_flags: VIPERBSS | VIPERRODATA | VIPERRELOC
b'\x00\x00' # n_obj, n_raw_code
b'\x06rodata' # rodata, 6 bytes
b'\x04' # bss, 4 bytes
b'\x03\x01\x00' # dummy relocation of rodata
),
}
# fmt: on
# create and mount a user filesystem
uos.mount(UserFS(user_files), "/userfs")
usys.path.append("/userfs")
# import .mpy files from the user filesystem
for i in range(len(user_files)):
mod = "mod%u" % i
try:
__import__(mod)
print(mod, "OK")
except ValueError as er:
print(mod, "ValueError", er)
# unmount and undo path addition
uos.umount("/userfs")
usys.path.pop()