Age | Commit message (Collapse) | Author |
|
A version has been added to the driver library so users can check if
they are compatible with the driver library in use.
The Python wrapper has been updated accordingly to make the version
information available.
Change-Id: I8affbf7068c057f7103adf14c9e4a331d547fbcc
Signed-off-by: Mikael Olsson <mikael.olsson@arm.com>
|
|
The driver library will now check that it's compatible with the kernel
driver in use by checking the kernel driver's version.
The kernel driver version has also been made available to the library
users and the Python wrapper has been updated accordingly.
Change-Id: Ieae8c0bfc323f945038e7264eceeab90c833f76d
Signed-off-by: Mikael Olsson <mikael.olsson@arm.com>
|
|
The current implementation of the protocol version request IOCTL call
doesn't return any version information and the protocol version is not
needed by any userspace program as it's for the communication between
the Linux kernel NPU driver and firmware. The IOCTL call has therefore
been removed from the UAPI and the inference runner has been updated
accordingly.
Change-Id: I9ed09e55d9522996a182f237c8a6db2f45bc40a9
Signed-off-by: Mikael Olsson <mikael.olsson@arm.com>
|
|
Send cancel inference messages to the ethosu subsystem to abort
inference execution there. Also mark inference as aborted in the
linux driver stack itself, so pending inference messages are not
resent when resetting the firmware.
Change-Id: I244c2b119fd7995d14e3859815abf2a00c7f0583
|
|
Change-Id: I62e13df69c712ed4cf70766429b4cb13fc9c9dcb
|
|
Add UAPI and core message that allows user space space to fetch
information about network models built into the firmware.
Change-Id: Ic92529bce3edd0a5499e691a566bd065da2a72ad
|
|
Support referencing a network model by index that has been built into
the firmware binary.
Change-Id: Idd5294376ea82503dfeafe1203dcc0694d296dfe
|
|
By default the logd will try to fetch the address of the print buffer
from the device tree entry, assuming there is a device tree entry
named 'print_queue'.
Change-Id: Ic4750fe793f450152ba537820adc794731aaacaf
|
|
It now accepts a timeout expressed in nanoseconds.
Change-Id: I77fb89c33dc117f846b86494883548ef3241f0ab
|
|
Change-Id: Ia90e2d74c3e071c6e3de381cfada9a5a155d7529
|
|
Also add a call to send a ping message in the inference_runner example
app.
Change-Id: Ia2b4abf5fec8285c320ec0f28df167ff2ea13d82
|
|
Change-Id: Id5aa197312c88b0c448dc085d8477ed67da24724
|
|
Update all license headers to the correct years.
Change-Id: Ie1aee82af91c744a3cdb949044334ade0d834c16
|
|
Introduce a 32b magic for each message. Verify the magic for
all incoming messages.
Add reset function - in case of protocol error, effectively
reset/empty the incoming queue.
Add an error message type and message
Add version request/response
Verify payload length of responses (when applicable)
Change-Id: I8aadd4012024492533d52e2cdb38630fce5c36e2
|
|
Change-Id: I3291de22a5461e285b8750094aa1c65716374bd7
|
|
Change-Id: I2ebac7df9c4716be7fee10ce4cba350e40860ca2
|
|
Build flatbuffers library.
Update network class to extract IFM and OFM dimensions from the tflite
file.
Update the uapi and core apis to support up to 16 IFM and OFM buffers
per inference.
Change-Id: I2f2f177aa4c2d5f9f50f23eb33c44e01ec2cbe09
|
|
Change-Id: I14b6becc908a0ac215769c32ee9c43db192ae6c8
|