Age | Commit message (Collapse) | Author |
|
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>
|
|
Change-Id: I2036332cffee94f1a3b69b391586d0a2f6c9db55
|
|
* RTE_components header to include corresponding Arm Cortex-M system header
* remove custom CMSIS implementation from repo
* use templates within CMSIS repo instead
* update cmake to use header and source files within CMSIS repo
Change-Id: I3534dae97b93c07a5056471b1d1dedbc78f00aa7
|
|
guidance to add custom platform.
Signed-off-by: alexander <alexander.efremov@arm.com>
Change-Id: Ib2eb2b7460c0ee8161403e5b135cd8b5cd854334
|
|
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
|
|
Change-Id: I013cb638483d4b774f2729ba02b6863c5ff7a99a
|
|
CPU_PROFILE_ENABLED was moved to profiler sub-project build.
Signed-off-by: alexander <alexander.efremov@arm.com>
Change-Id: I8191c83c7ae0f618769449d7d25fe58876cbcf05
|
|
* 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
|
|
Signed-off-by: Michael Levit michaell@emza-vs.com
Change-Id: If59b6bc63375c3f1172505684d75097ff526e32e
(cherry picked from commit fba4e3a12b50d0ebb3804c6bf22cf688fcdaeee8)
|
|
Signed-off-by: Isabella Gottardi <isabella.gottardi@arm.com>
Change-Id: I076c3431e8106ff9430e66727607438c36d1acbc
|
|
* No longer copy the source image
* Boxes are drawn directly to LCD rather than on source image
* Change c style casts to static casts
Signed-off-by: Richard Burton <richard.burton@arm.com>
Change-Id: Ib8e926cb1a87bc2c40424eb5aace40170c526f1d
|
|
* Adding troubleshooting for cloning errors
Change-Id: Ib57353900064c68c30ecb2141602081180c50c99
Signed-off-by: Isabella Gottardi <isabella.gottardi@arm.com>
|
|
* set CMP0123 policy to remove warning
* remove parentheses to avoid assert is always true warning
Change-Id: Ifcdf089183d750d7b00b345f5c4115c82d897def
|
|
* Add ImageUtils
* Move image related code from UseCaseCommonUtils to ImageUtils
* Move NMS related code to ImageUtils
* Delete test specific ImageUtils and use new ImageUtils
Signed-off-by: Richard Burton <richard.burton@arm.com>
Change-Id: Icbf5dd9c6a941b0126ecdf69a0c9d9969f22729f
|
|
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>
|
|
Change-Id: Ic14e93a50fb7b3f3cfd9497bac1280794cc0fc15
Signed-off-by: Isabella Gottardi <isabella.gottardi@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>
|
|
Signed-off-by: Michael Levit michaell@emza-vs.com
Change-Id: I7958b05b5dbe9a785e0f8a241b716c17a9ca976f
|
|
Replaced overloaded PresentInferenceresults with single function and removed
logic to handle arguments which are no longer passed.
Change-Id: I745271638fcf78b7121c2a4b95844b752643bac2
Signed-off-by: Liam Barry <liam.barry@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
|
|
Replaced ctx.set/get<uint32>(keywordindex) with
keyword itself as const std::string&
Change-Id: I1811d93548105d6db58e57b88675f9b41e66d914
Signed-off-by: Liam Barry <liam.barry@arm.com>
|
|
Aligning with output from other use cases, inference runner
output now prints the number of inferences as one.
Change-Id: Ifc03385a5de86477508fe8c377d481b7140a8429
Signed-off-by: Kshitij Sisodia <kshitij.sisodia@arm.com>
|
|
Added SoftMax function to Mathutils to allow MicroNet
to output probability as it does not nativelu have this layer.
Minor refactoring to accommodate Softmax Calculations
Extensive renaming and updating of documentation and resource download script.
Added SoftMax function to Mathutils to allow MicroNet
to output probability.
Change-Id: I7cbbda1024d14b85c9ac1beea7ca8fbffd0b6eb5
Signed-off-by: Liam Barry <liam.barry@arm.com>
|
|
Change-Id: I2b2685dd65e08e3d8b52d223cfad53e90a73d2ba
|
|
builds
-Added conditonals to ethos-u-driver and cmsis path for making tflite micro library native build
Change-Id: I89ce87ef368392b087cfca1898531bd2c5a2ba1c
|
|
* LCD display behavior for Run All now matches Run Next
* Remove repeated code
Signed-off-by: Richard Burton <richard.burton@arm.com>
Change-Id: I16706187fd4e7a59dd935783f5bfb8731435f381
|
|
-Fixed noise_reduction CMake bug cause inference to fail when non-default mac_units passed to build script
-Inference complete message added to noise_reduction LCD
-Doc update clarfiy vela.ini config file for compiling to non-default memory modes
-QOL improvement by adding a note on how to make path variables permenant when configuring Arm compilers
Change-Id: Id798b25638260721d8e48468b7a5942bd802d63b
|
|
Change-Id: I81fc96b412959d2a6dd61b6fbd671345b2f39b8d
|
|
* CMSIS-DSP acceleration will now be used for FFT in RNNoise pre-processing
* PESQ scores tested and similar
Signed-off-by: Richard Burton <richard.burton@arm.com>
Change-Id: Ifeebc041f58867909b27c948950e08f8f39ef276
|
|
Arena-cache-size is different from default when using
Dedicated_Sram memory mode.
Change-Id: Ie112146218e1ec456e17babd4ed3e7c7bc2009a8
|
|
Signed-off-by: Richard Burton <richard.burton@arm.com>
Change-Id: I47879089734cd3ab70ef8068277e677742e1b2b3
|
|
* Documentation added with missing prerequisite
* build_default.py can now be tuned for constraint build systems
Change-Id: I74c061359ff663335e664528c4f0616f55cff0f7
|
|
* 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
|
|
Change-Id: I0ea57b69bdb095f2580d80001d145fefed5cd72c
Signed-off-by: George Gekov <george.gekov@arm.com>
|
|
-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
|
|
Change-Id: I3ec18583c321eb2815a670d56f4958e610331d6d
|
|
Signed-off-by: Liam Barry <liam.barry@arm.com>
Change-Id: Ibf712cb9359b9bc9977d4f77aec1d7c7f4245825
|
|
Change-Id: I15dceeafec554e58257e8e6d6e8896cc9b397106
|
|
Change-Id: I90fca833d501bbd4db4fd99903b9ffef161a9a6b
Signed-off-by: George Gekov <george.gekov@arm.com>
|
|
* Use RNNoise model from PMZ
* Add Noise reduction use-case
Signed-off-by: Richard burton <richard.burton@arm.com>
Change-Id: Ia8cc7ef102e22a5ff8bfbd3833594a4905a66057
|
|
Change-Id: I5170aafa6d159d537906da17b194534fd7d44bea
Signed-off-by: Liam Barry <liam.barry@arm.com>
|
|
Change-Id: If34a22cdc1313bd8cce4d1cd30e845eb361b93e4
Signed-off-by: George Gekov <george.gekov@arm.com>
|
|
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
|