Prior to this fix, pow(1.5, inf) and pow(0.5, -inf) (among other things)
would incorrectly raise a ValueError, because the result is inf with the
first argument being finite. This commit fixes this by allowing the result
to be infinite if the first or second (or both) argument is infinite.
This fix doesn't affect the other three math functions that have two
arguments:
- atan2 never returns inf, so always fails isinf(ans)
- copysign returns inf only if the first argument x is inf, so will never
reach the isinf(y) check
- fmod never returns inf, so always fails isinf(ans)
Signed-off-by: Damien George <damien@micropython.org>
Currently, certain mpremote filesystem operations can fail on Windows due
to a mixing of '/' and '\' for path separators. Eg if filesystem_command()
is called with a destination that ends in / then dest.endswith(os.path.sep)
will return False, which gives the wrong behaviour (it does end in a path
separator).
For similar reasons to 7e9a15966a, it's best
to use '/' everywhere in pyboard.py and mpremote, because the target device
understands only '/'. mpremote already does this, so the remaining place
to fix it is in pyboard.y, to convert all incoming paths to use '/' instead
of '\'.
This effectively reverts 57fd66b80f which
tried to fix the problem in a different way.
See also related 1f84440538.
Signed-off-by: Damien George <damien@micropython.org>
This allows the entire configuration to be defined in a single file,
including the logic for including pyboard.py and automatically versioning
based on the git tag.
Building the package works both via `python -m build` as well as
`hatch build`. `python -m build ` has the advantage of automatically
fetching all dependencies, you don't need to manually install any hatch
packages.
In order to make the versioning work, and also keep things simpler for end
users, mpremote releases will now be the same as MicroPython releases and
use the same tag. The version strings for mpremote will look like:
- X.Y.Z -- clean build at the tag
- X.Y.Z.postN+gHASH -- clean build, N revisions from the most recent tag
- X.Y.Z.postN+gHASH.dYYYYMMDD -- dirty build, N revisions from out
This commit extends on the idea from #8404.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
Makefile's support "else ifdef", so use it to make the logic clearer.
Also dedent some associated lines for consistency.
Signed-off-by: Damien George <damien@micropython.org>
This matches the behavior of the makefile ports but implemented for CMake,
making it easy to specify custom board definitions.
This work was funded through GitHub Sponsors.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
This matches the behavior of the makefile ports but implemented for CMake,
making it easy to specify custom board definitions.
This work was funded through GitHub Sponsors.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
This allows:
$ make BOARD_DIR=path/to/board
to infer BOARD=board, rather than the previous behavior that required
additionally setting BOARD explicitly.
Also makes the same change for VARIANT_DIR -> VARIANT on Unix.
This work was funded through GitHub Sponsors.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
Signed-off-by: Damien George <damien@micropython.org>
This RNG passes many of the Diehard tests and also the AIS31 test suite.
The RNG is quite slow, delivering 200bytes/s.
Tested on boards with and without a crystal.
It turned out that the result of calling ticks_us() was always either odd
or even, depending on some internal state during boot. So the us-counter
was set to a 2 MHz input and the result shifted by 1. The counting period
is still long enough, since internally a (now) 63 bit value is used for us.
By using the phase jitter between the DFLL48M clock and the FDPLL96M clock.
Even if both use the same reference source, they have a different jitter.
SysTick is driven by FDPLL96M, the us counter by DFLL48M. As a random
source, the us counter is read out on every SysTick and the value is used
to accumulate a simple multiply, add and xor register. According to tests
it creates about 30 bit random bit-flips per second. That mechanism will
pass quite a few RNG tests, has a suitable frequency distribution and
serves better than just the time after boot to seed the PRNG.
Allowing to increase the clock a little bit to 54Mhz. Not much of a gain,
but useful for generating a RNG entropy source from the jitter between
DFLL48M and FDPLL96M.
Remove two SPARKFUN_SAMD51_THINGS_PLUS pin definitions. There were
definitions of TXD and RXD, but these pins do not exist on the board. They
were only shown in the schematics.
Also remove any reference to LED_. This is just a text change, no
functional change.
Since commit d6d8722558, modbtree.c is
included unconditionally in the build (if SRC_EXTMOD_C is used). So guard
the includes of system headers files in case a target doesn't have them.
Signed-off-by: Damien George <damien@micropython.org>
Now that the code-size-check CI action gives a nice report (as a comment)
on the code size difference, it's possible to have a few more ports
reported there. In this commit, unix, stm32 and rp2 are added. Unix
represents non-MCU builds, and stm32 and rp2 represent ARM-based builds,
for ports that have lots of features enabled.
Signed-off-by: Damien George <damien@micropython.org>
For compatibility with other ports. Code increase up to ~1250 bytes for
SAMD21. The feature is configurable via MICROPY_PY_MACHINE_PIN_BOARD_CPU
in case flash memory is tight.
Changes since the previous version:
- add an API to get the BSSID
- support auto channel selection when using BSSID for join
- improve performance for the Murata 1DX module and SDIO
- return EINVAL for invalid auth type
- add support for Bluetooth over SPI
- convert 4343WA1-7.45.98.50.combined to C header files
This further aligns the features available on Pico and Pico W boards.
os.dupterm is generally useful, but can still be disabled by a board if
needed. hashlib.sha1 requires mbedtls for the implementation, but that's
always available (due to ucryptolib's requirements). The entire hashlib
module can still be disabled by an individual board if needed.
Fixes issue #7881.
Signed-off-by: Damien George <damien@micropython.org>
The previous computation incorrectly assumed that the uint32_t ticks
counter MICROPY_SOFT_TIMER_TICKS_MS was in the range [0,0x80000000) where
its actually [0,0xffffffff]. This means the diff calculation can be
simplified compared to the original implementation copied from
utime_mphal.c, which has to deal with a ticks range constrained by the
small int range.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
Before, both uwTick and mp_hal_ticks_ms() were used as clock source. That
assumes, that these two are synchronous and start with the same value,
which may be not the case for all ports. If the lag between uwTick and
mp_hal_ticks_ms() is larger than the timer interval, the timer would either
rush up until the times are synchronous, or not start until uwTick wraps
over.
As suggested by @dpgeorge, MICROPY_SOFT_TIMER_TICKS_MS is now used in
softtimer.c, which has to be defined in a port's mpconfigport.h with
the variable that holds the SysTick counter.
Note that it's not possible to switch everything in softtimer.c to use
mp_hal_ticks_ms() because the logic in SysTick_Handler that schedules
soft_timer_handler() uses (eg on mimxrt) the uwTick variable directly
(named systick_ms there), and mp_hal_ticks_ms() uses a different source
timer. Thus it is made fully configurable.
The default now includes all sub-components (security, l2cap, etc)
and using the kwarg options is no longer supported.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
The default now includes all sub-components (security, l2cap, etc)
and using the kwarg options is no longer supported.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
So it can run on targets with low memory, eg esp8266.
Also enable the viper_4args() sub-test, which is now supported.
Signed-off-by: Damien George <damien@micropython.org>
This ensures that all builds unconditionally run makeversionhdr.py and
makemanifest.py to generate mpversion.h and frozen_content.c respectively.
This now matches the Makefile behavior, and in particular this fixes the
issue on ESP32 builds that changes in code-to-be-frozen will cause the
build to update. Both these already tools know not to touch their output
if there is no change.
This work was funded through GitHub Sponsors.
Signed-off-by: Jim Mussared <jim.mussared@gmail.com>
Prior to this commit, on Pico W (where the CYW43 driver is enabled) the PIO
instruction memory was not released on soft reset, so using PIO after a
soft reset would eventually (after a few soft resets) lead to ENOMEM when
allocating a PIO program.
This commit fixes that by tracking the use of PIO memory by this module and
freeing it on soft reset.
Similarly, use of the state machines themselves are tracked and released on
soft reset.
Fixes issue #9003.
Signed-off-by: Damien George <damien@micropython.org>
Make this more generally useful and in line with what the mingw
and unix ports do: 16bit dig size to work on 32bit ports, a
self-contained qstrdefs.preprocessed.h because makemanifest.py
uses that, and a dev variant which effectively puts this to use:
previously the uasyncio module wasn't frozen but instead tests
ran by importing it from the extmod/ directory.
Code in tools/mpy-tool.py and py/frozenmod.c relies on the source file
path encoded in a .mpy file to have forward slashes (e.g. by searching
for '/__init__.py'). Enforce that when creating these files, thereby
fixing import of .mpy files and frozen modules not working before
because they could have backslashes when built with the windows port.
