843fca1874
21 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
Dan Halbert
|
88c22d5052 | remove last uses of 'u' prefix | ||
|
Dan Halbert
|
0d4bc8c163 | initial v1.19.1 merge; not compiled yet | ||
Scott Shawcroft
|
bdf592089a
|
Fix .bin, .hex and .uf2 with new linker sections
Also, format perfbench output in table with reference timing from the host. |
||
|
Scott Shawcroft
|
5bb8a7a7c6
|
Improve iMX RT performance
* Enable dcache for OCRAM where the VM heap lives. * Add CIRCUITPY_SWO_TRACE for pushing program counters out over the SWO pin via the ITM module in the CPU. Exempt some functions from instrumentation to reduce traffic and allow inlining. * Place more functions in ITCM to handle errors using code in RAM-only and speed up CP. * Use SET and CLEAR registers for digitalio. The SDK does read, mask and write. * Switch to 2MiB reserved for CircuitPython code. Up from 1MiB. * Run USB interrupts during flash erase and write. * Allow storage writes from CP if the USB drive is disabled. * Get perf bench tests running on CircuitPython and increase timeouts so it works when instrumentation is active. |
||
MicroDev
|
d9d94eacca
|
run updated pre-commit | ||
Damien George
|
d7cf8a3b9d |
tests/perf_bench: Update .mpy file header to remove old unicode flag.
Signed-off-by: Damien George <damien@micropython.org> |
||
|
Damien George
|
999abbb8b5 |
tests/perf_bench: Update import tests for changes to .mpy consts.
Signed-off-by: Damien George <damien@micropython.org> |
||
|
Damien George
|
0a2895b099 |
tests/perf_bench: Skip bm_chaos test if random.randrange is unavailable.
Signed-off-by: Damien George <damien@micropython.org> |
||
|
Damien George
|
f2040bfc7e |
py: Rework bytecode and .mpy file format to be mostly static data.
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>
|
||
Jeff Epler
|
01cabb0324 |
Merge tag 'v1.18'
Boosted performance, board.json metadata, more mimxrt, rp2, samd features
This release of MicroPython sees a boost to the overall performance of the
VM and runtime. This is achieved by the addition of an optional cache to
speed up general hash table lookups, as well as a fast path in the VM for
the LOAD_ATTR opcode on instance types. The new configuration options are
MICROPY_OPT_MAP_LOOKUP_CACHE and MICROPY_OPT_LOAD_ATTR_FAST_PATH. As part
of this improvement the MICROPY_OPT_CACHE_MAP_LOOKUP_IN_BYTECODE option has
been removed, which provided a similar map caching mechanism but with the
cache stored in the bytecode, which made it not useful on bare metal ports.
The new mechanism is measured to be at least as good as the old one,
applies to more map lookups, has a constant RAM overhead, and applies to
native code as well as bytecode.
These performance options are enabled on the esp32, mimxrt, rp2, stm32 and
unix ports. For esp32 and mimxrt some code is also moved to RAM to further
boost performance. On stm32, performance increases by about 20% for
benchmarks that are heavy on name lookups, like misc_pystone.py and
misc_raytrace.py. On esp32 performance can increase by 2-3x, and on mimxrt
it is up to 6x.
All boards in all ports now have a board.json metadata file, which is used
to automatically build firmware and generate a webpage for that board
(among other possibilities). Auto-build scripts have been added for this
purpose and they build all esp32, mimxrt, rp2, samd and stm32 boards. The
generated output is available at https://micropython.org/download.
Support for FROZEN_DIR and FROZEN_MPY_DIR has been deprecated for some time
and was finally removed in this release. Instead of these, FROZEN_MANIFEST
can be used. The io.resource_stream() function is also removed, replaced
by the pure Python version in micropython-lib.
The search order for importing frozen Python modules is now controlled by
the ".frozen" entry in sys.path. This string is added by default in the
second position in sys.path. User code should adjust sys.path depending on
the desired behaviour. Putting ".frozen" first in sys.path will speed up
importing frozen modules.
A bug in multiple precision integers with bitwise of -0 was fixed in commit
|
||
|
Damien George
|
a434705700 |
tests/perf_bench: Add perf test for yield-from execution.
Signed-off-by: Damien George <damien@micropython.org> |
||
|
Damien George
|
75da124cf8 |
tests/perf_bench: Add perf tests for qstr interning and importing .mpy.
Signed-off-by: Damien George <damien@micropython.org> |
||
|
Damien George
|
ab2923dfa1 |
all: Update Python formatting to latest Black version 22.1.0.
Signed-off-by: Damien George <damien@micropython.org> |
||
|
Dan Halbert
|
748834c6ba | update to py tests and scripts due to black 22.1.0 | ||
|
Damien George
|
c0761d28fc |
tests/perf_bench: Use math.log instead of math.log2.
So MICROPY_PY_MATH_SPECIAL_FUNCTIONS is not needed for these performance tests. Signed-off-by: Damien George <damien@micropython.org> |
||
David Lechner
|
3dc324d3f1 |
tests: Format all Python code with black, except tests in basics subdir.
This adds the Python files in the tests/ directory to be formatted with ./tools/codeformat.py. The basics/ subdirectory is excluded for now so we aren't changing too much at once. In a few places `# fmt: off`/`# fmt: on` was used where the code had special formatting for readability or where the test was actually testing the specific formatting. |
||
Jim Mussared
|
cfd17f4ebe |
tests/perf_bench: Add bm_fft test.
This is mostly a test of complex number performance. The FFT implementation is from Project Nayuki and is MIT licensed. |
||
Damien George
|
73fccf5967 |
tests/perf_bench: Add some viper performance benchmarks.
To test raw viper function call overhead: function entry, exit and conversion of arguments to/from objects. |
||
|
Damien George
|
73c269414f |
tests/perf_bench: Add some miscellaneous performance benchmarks.
misc_aes.py and misc_mandel.py are adapted from sources in this repository. misc_pystone.py is the standard Python pystone test. misc_raytrace.py is written from scratch. |
||
|
Damien George
|
127714c3af |
tests/perf_bench: Add some benchmarks from python-performance.
From https://github.com/python/pyperformance commit 6690642ddeda46fc5ee6e97c3ef4b2f292348ab8 |
||
|
Damien George
|
e92c9aa9c9 |
tests: Add performance benchmarking test-suite framework.
This benchmarking test suite is intended to be run on any MicroPython
target. As such all tests are parameterised with N and M: N is the
approximate CPU frequency (in MHz) of the target and M is the approximate
amount of heap memory (in kbytes) available on the target. When running
the benchmark suite these parameters must be specified and then each test
is tuned to run on that target in a reasonable time (<1 second).
The test scripts are not standalone: they require adding some extra code at
the end to run the test with the appropriate parameters. This is done
automatically by the run-perfbench.py script, in such a way that imports
are minimised (so the tests can be run on targets without filesystem
support).
To interface with the benchmarking framework, each test provides a
bm_params dict and a bm_setup function, with the later taking a set of
parameters (chosen based on N, M) and returning a pair of functions, one to
run the test and one to get the results.
When running the test the number of microseconds taken by the test are
recorded. Then this is converted into a benchmark score by inverting it
(so higher number is faster) and normalising it with an appropriate factor
(based roughly on the amount of work done by the test, eg number of
iterations).
Test outputs are also compared against a "truth" value, computed by running
the test with CPython. This provides a basic way of making sure the test
actually ran correctly.
Each test is run multiple times and the results averaged and standard
deviation computed. This is output as a summary of the test.
To make comparisons of performance across different runs the
run-perfbench.py script also includes a diff mode that reads in the output
of two previous runs and computes the difference in performance. Reports
are given as a percentage change in performance with a combined standard
deviation to give an indication if the noise in the benchmarking is less
than the thing that is being measured.
Example invocations for PC, pyboard and esp8266 targets respectively:
$ ./run-perfbench.py 1000 1000
$ ./run-perfbench.py --pyboard 100 100
$ ./run-perfbench.py --pyboard --device /dev/ttyUSB0 50 25
|