| Age | Commit message (Collapse) | Author |
|---|
|
To avoid copying strings unnecessarily in the inference runner the
functions have been changed to take the strings as const reference
rather than copying them.
Change-Id: I173e37c7f7b08ada5d421bb9008a4bf36284f6c5
Signed-off-by: Mikael Olsson <mikael.olsson@arm.com>
|
|
In preparation to support the Linux kernel driver directly managing the
NPU without a subsystem. A NPU device type has been added to the
capabilities to be able to specify what kind of NPU is used.
Change-Id: I45345b7d75d234f821d70b858453d3af2a99194e
Signed-off-by: Mikael Olsson <mikael.olsson@arm.com>
|
|
The PMU event counter value is an accumulation of 32-bit values during
the inference and to ensure the total value fits in the rpmsg message
and UAPI, the variable holding the value has been changed to 64-bit.
The driver library, Python wrapper and inference runner have been
changed accordingly to support the 64-bit values.
Change-Id: I09a8e45eb75800c8a787f83abff5a3693148cc15
Signed-off-by: Mikael Olsson <mikael.olsson@arm.com>
|
|
To not allow the buffer for a network instance to be changed after
creation, the create network UAPI will now take the network model data
as a user buffer. The content of the user buffer is copied into an
internally allocated DMA buffer that cannot be accessed by the user.
This breaks the current API so the Linux kernel NPU driver version and
the driver library version have been given major version bumps. All the
tests, documentation and other applications affected by the changes have
been updated accordingly.
Change-Id: I25c785d75a24794c3db632e4abe5cfbb1c7ac190
Signed-off-by: Mikael Olsson <mikael.olsson@arm.com>
|
|
The UAPI no longer supports the buffer capacity, offset and resize
functionality. Instead, the UAPI now only accepts a fixed size given at
the creation of the buffer. This change was made because the features
were not used and made the buffer handling more complicated. The user
knows how big buffers they need for their networks so they don't need
resize support or partial buffer usage support by having separate size
and capacity with an offset.
Without these features, the buffer instance no longer needs any IOCTL
call support so it has been removed. However, to still be able to check
the size of a buffer from its file descriptor, seek support has been
implemented so lseek and similar functions can be used to get the size.
The driver library's clear function that previously only reset the size
and offset values of the buffer will now clear the buffer content
instead.
These are breaking changes so the Linux kernel NPU driver version and
the driver library version have been given major version bumps. All the
tests and other applications affected by these changes have been updated
accordingly.
Change-Id: Ifc34cf04724a95853ad23fd7398dd286f73bcdab
Signed-off-by: Mikael Olsson <mikael.olsson@arm.com>
|
|
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
|
|
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
|
