Age | Commit message (Collapse) | Author |
|
* Use UART component from Ethos-U core-platform
* Components as cmake project
Change-Id: I053f3a59800abc20216e6a4df8555db357e3f21d
Signed-off-by: Isabella Gottardi <isabella.gottardi@arm.com>
|
|
* Core-platform now a depdenency for timing adapter
Signed-off-by: Richard Burton <richard.burton@arm.com>
Change-Id: I54f3773bdf91083fa1513be15372fcf2231bea2c
|
|
Removing git as a requirement for the checks performed for downloaded
resources. Another minor change is renaming of RTE_components.h to
RTE_Components.h as per the convention.
Change-Id: If93f80f2f5dfa6a3f143259904c33b3b6d3a6e7c
Signed-off-by: Kshitij Sisodia <kshitij.sisodia@arm.com>
|
|
Check could have been bypassed if the script path provided as
an argument was incorrect. Also, a minor update in the CMake
function to fix the path.
Signed-off-by: Kshitij Sisodia <kshitij.sisodia@arm.com>
Change-Id: Id3cd4027843783e3ed8700eac503e7ba3f09ad04
|
|
Adding basic support to allow applications to build with semihosting
support. Default state is always disabled.
Signed-off-by: Kshitij Sisodia <kshitij.sisodia@arm.com>
Change-Id: I1d34c3a246560aaffcb34eee801e1a87d887d559
|
|
MLECO-2949: Platform drivers should own NPU and TA init
Change-Id: I13606a0197f137816bae803eb9d7d46c358b5fb8
Signed-off-by: Isabella Gottardi <isabella.gottardi@arm.com>
|
|
Change-Id: I12777c3818463c11d6351db0b4961a2bc0b00b18
Signed-off-by: Isabella Gottardi <isabella.gottardi@arm.com>
|
|
Reducing dependency on cmsis-device sources as these will
be removed under MLECO-2944. Also, starting to refactor
to allow HAL to drop NPU and TA init routines - this will
happen in future CRs.
Added platform driver for native, and subsequent patches
will attempt to get rid of the HAL "profile" specific
sources and allow platform stub implementations at a level
below HAL. This will allow platforms drivers to only
override the range of functions that they actually want to
implement and will fall back on stubs for the rest. In this
CR only "utils" have been removed.
Change-Id: I09b4a28e20847a07a956c818c6f47c74aab89063
|
|
* TensorFlow CMake uses Arm Ethos-U NPU driver lib path
* armclang DWARF level config flag removed
* uses and mentions of DWARF level removed
* TensorFlow uses Arm Cortex-M generic target
* removed Arm Cortex-M custom target makefile and dir
Change-Id: Ie0d3edb5473462ef8552f8b9f832190de5e99a7c
|
|
Profiler is a stand alone static lib that will depend on
log and hal targets.
Change-Id: Ibbff289c6760982f54ae278d95a054e73db018c8
|
|
And further optimisations of extendability for platform build
steps. Added a list for excluded use-cases.
Change-Id: I5a9398bbeb595a5bf2ea39b81623e4f20238f948
Signed-off-by: alexander <alexander.efremov@arm.com>
|
|
MLECO-2930: logging macros were extracted from hal.h and used separately around the code.
MLECO-2931: arm_math lib introduced, cmsis-dsp removed from top level linkage.
MLECO-2915: platform related post-build steps.
Change-Id: Id718884e22f262a5c070ded3f3f5d4b048820147
Signed-off-by: alexander <alexander.efremov@arm.com>
|
|
Added QSPI_SRAM_BASE for Secure region.
Updated UART and other peripherals affected by change in reserved region
Updated names of some base addresses in cmake and template files
Error in TRM swapping individual for combined GPIO IRQs reported
Follow-up - Marked region in TRM not covered in CMake
Change-Id: I046e740053477fe3a51bc171a2b7e28f4a9f0523
Signed-off-by: Liam Barry <liam.barry@arm.com>
|
|
Change-Id: I182bfa55b5ae743d6f0b9f5c766b746202a7968d
Signed-off-by: Isabella Gottardi <isabella.gottardi@arm.com>
|
|
Issues identified with Armclang 6.15; bumping up the minimum
version required to Armclang 6.16.
Change-Id: I33ec21f04e0c954919cacaf6f3c4d99ef8f517cc
Signed-off-by: Kshitij Sisodia <kshitij.sisodia@arm.com>
|
|
Added tests for recently added Softmax function in
PlatformMath module.
Change-Id: Iacf1f4eaf33a92e1d42275000765e7152d17176b
|
|
builds
-Added conditonals to ethos-u-driver and cmsis path for making tflite micro library native build
Change-Id: I89ce87ef368392b087cfca1898531bd2c5a2ba1c
|
|
* Currently using 21.11 release candidates
Signed-off-by: Richard Burton <richard.burton@arm.com>
Change-Id: I696b48c3a4c87c5dca3bbee957049790d900b48e
|
|
These changes will limit the use of FPGA internal SRAM from a max
of 4MiB to 2MiB and the BRAM from 2MiB to 1MiB.
Change-Id: I69c8e695aee26ff4f235bfe83ffd26efbd66f547
|
|
For easier look up and maintenance, all common CMake user options
have been consolidated in one CMake file.
NOTE: the individual use case specific options are still within
the correspoinding use case CMake files.
Change-Id: Id887f7b2c763f4d3eb997d997cf466684d0089b6
|
|
-Updated CMake to use C++ 14
-Removed cmsis makefile include from tensorflow.cmake
-Documentation update
-Added more flags for processor in CMake
Change-Id: I1c2b72141e98a5cf8bb09176d7c331da3b05b4c5
|
|
Signed-off-by: Liam Barry <liam.barry@arm.com>
Change-Id: Ibf712cb9359b9bc9977d4f77aec1d7c7f4245825
|
|
* Use RNNoise model from PMZ
* Add Noise reduction use-case
Signed-off-by: Richard burton <richard.burton@arm.com>
Change-Id: Ia8cc7ef102e22a5ff8bfbd3833594a4905a66057
|
|
Python scripts 'build_default.py' and 'set_up_default_resources.py'
now allow building for non-default Ethos-U configurations: H32, H64,
H256 and Y512.
Change-Id: Iefdbf135410396c4dc0be73462644725d4b47910
|
|
* Changed image->cc conversion to be similar with preprocessing
of img_class and vww models: images are scaled maintaing the
aspect ration and then the centre crop of the correct size
is taken.
* VWW applies input quantization info to the int8 image
(prior converted to [0,1] float range).
* Changed adult_blur to a image without person.
* Fix menu print when selecting a specific ifm to run
(Select message was displayed after typing something)
Change-Id: Ie6cde7ab4835ea842667b87397458a5d32131df3
|
|
* Fixed vww usage warnings (imageData in RunInferene and _GetImageIdx function)
Change-Id: I2c37e4e4cc8c8eca841690f2df8d525ed516ecc8
|
|
Change-Id: Icf09410f12072e8d7850dd1e540c3243af24ed09
|
|
Change-Id: Ifd6d3d72abb1e8ce058e612295d01a148962627e
|
|
Documenting how the target platform's SRAM size impacts configuration files,
sources and linker scripts.
Change-Id: I8647ab67b73bafd0c44e6c586a1b5f2602bf03f5
|
|
* Update all dependancies to 21.08
* Refactoring to fit the new changes
Change-Id: Icc2ae3628ee6e8fbc0af2cd8f91e368c9ccae053
|
|
With this patch, the generic inference runner use-case can be
configured to accept the model tflite file at run-time via
the FVP's command line parameters. Same is true for the IFM
and the inference results can be dumped out too.
NOTE: this change is only for supporting the FVP, the FPGA
implementation will not allow additional loading for the
changes in this patch to be useful.
Change-Id: I1318bd5b0cfb7bb635ced6fe58d22c3e401d2547
|
|
Change-Id: I744a4eb2553207004c9403b956e5bd9e9b352bfb
Signed-off-by: Isabella Gottardi <isabella.gottardi@arm.com>
|
|
* Now uses seperate TFLu github repo
* Fixes to align with API changes
* Update ASR model ops and re-enable ASR inference tests
* Set default release level to release_with_logs
Signed-off-by: Richard Burton <richard.burton@arm.com>
Change-Id: I57612088985dece1413c5c00a6e442381e07dd91
|
|
Change-Id: I64ab930a1de5210f435f91bed7600a700581946f
Signed-off-by: Isabella Gottardi <isabella.gottardi@arm.com>
Reviewed-on: https://eu-gerrit-2.euhpc.arm.com/c/ml/ecosystem/ml-embedded-evaluation-kit/+/459126
Tested-by: mlecosys <mlecosys@arm.com>
Tested-by: George Gekov <george.gekov@arm.com>
Reviewed-by: George Gekov <george.gekov@arm.com>
Reviewed-by: Kshitij Sisodia <kshitij.sisodia@arm.com>
|
|
Breaking down the elf(axf) file into bin blobs for the
simple_platform target too.
Change-Id: Ie909508433ef03f8b4a32e04bc69353aed0d0849
|
|
Signed-off-by: George Gekov <george.gekov@arm.com>
Change-Id: I92b9ab60974ad266246994deae5833f7f374633d
|
|
ASRSlidingWindow can be used in other use-cases,
thus it was renamed to decouple from ASR.
Signed-off-by: alexander <alexander.efremov@arm.com>
Change-Id: I2df977e4f18f490a532e0f27e3625b153ca464d7
|
|
Changes:
* minor speed up for tflite to C++ file generation
* virtual env's pip upgrade before installation of packages
Change-Id: If8cef85779b7381f444f608b565da0b8f994d364
|
|
Core driver and sofware dependencies updated to latest release
candidate revisions. Note: TensorFlow Lite Micro has not been
updated.
Also, gcc warnings for simple_platform target and ad use case have
been fixed.
Change-Id: I455b421f34375a719a941e6e220fe292a57613f5
|
|
Signed-off-by: alexander <alexander.efremov@arm.com>
Change-Id: Ic3e940a9d289d649976c4e951ced1473fc31ff3f
|
|
This patch enables compilation of ML use cases bare-metal applications
using Arm GNU Embedded Toolchain. The GNU toolchain can be used instead
of the Arm Compiler that was already supported.
The GNU toolchain is also set as the default toolchain when building
applications for the MPS3 target.
Note: The version of GNU toolchain must be 10.2.1 or higher.
Change-Id: I5fff242f0f52d2db6c75d292f9fa990df1aec978
Signed-off-by: Kshitij Sisodia <kshitij.sisodia@arm.com>
|
|
MLECO-1882: Anomaly Detection use-case default model download added
and tests updated to run with it.
Test data generation cmake logic moved from use-case cmakes to top-level cmake script.
Signed-off-by: Isabella Gottardi <isabella.gottardi@arm.com>
Change-Id: Ifde469e3585c37b9a53810236a92ce52d4fbb407
|
|
Signed-off-by: alexander <alexander.efremov@arm.com>
Change-Id: Ie462e786af1d429bcb815f2c10656ed82862715a
|
|
Signed-off-by: Isabella Gottardi <isabella.gottardi@arm.com>
Change-Id: Ic7bcb0cbf334049ff89e9973e58fd0b3bf463892
|
|
Change-Id: I12e807f19f5cacad7cef82572b6dd48252fd61fd
|