Datasheet

'D','E' _debug_trampoline_end
This is the address of the final BKPT #0 instruction of debug_trampoline. This can be compared with the
program counter to detect completion of the debug_trampoline call.
2.7.3.1.5. Miscellaneous Functions
These remaining functions don’t fit in other categories and are exposed in the Pico SDK via the pico_bootrom library (see
pico_bootrom).
Table 162.
Miscellaneous
Functions
CODE Description
'U','B' void _reset_to_usb_boot(uint32_t gpio_activity_pin_mask, uint32_t disable_interface_mask)
Resets the RP2040 and uses the watchdog facility to re-start in USB boot mode:
•
gpio_activity_pin_mask is provided to enable an "activity light" via GPIO attached LED for the USB Mass
Storage Device:
◦
0 No pins are used as per a cold boot.
◦
Otherwise one bit per GPIO pin indicating which GPIO pins should be set to output and raised
whenever there is mass storage activity from the host.
•
disable_interface_mask may be used to control the exposed USB interfaces:
◦
0 To enable both interfaces (as per a cold boot)
◦
1 To disable the USB Mass Storage Interface (see Section 2.7.4)
◦
2 To disable the USB PICOBOOT Interface (see Section 2.7.5)
'W','V' _wait_for_vector
This is the method that is entered by core 1 on reset to wait to be launched by core 0. There are few cases
where you should call this method (resetting core 1 is much better). This method does not return and
should only ever be called on core 1.
'E','C' deprecated
Do not use this function
2.7.3.2. Fast Floating Point Library
The Bootrom contains an optimized single-precision floating point implementation. The function pointers for these are
kept in a single structure found via the rom_data_lookup table (see Section 2.7.3.3).
2.7.3.2.1. Implementation Details
There is always a trade-off between speed and size. Whilst the overall goal for the floating-point routines is to achieve
good performance within a small footprint, the emphasis is more on improved performance for the basic operations (add,
subtract, multiply, divide and square root) and more on reduced footprint for the scientific functions (trigonometric
functions, logarithms and exponentials).
The IEEE single- and double-precision data formats are used throughout, but in the interests of reducing code size, input
denormals are treated as zero, input NaNs are treated as infinities, output denormals are flushed to zero, and output NaNs
are rendered as infinities. Only the round-to-nearest, even-on-tie rounding mode is supported. Traps are not supported.
The five basic operations return results that are always correctly rounded.
The scientific functions always return results within 1 ULP (unit in last place) of the exact result. In many cases results are
RP2040 Datasheet
2.7. Bootrom 120