diff options
| author | Nina Drozd <nina.drozd@arm.com> | 2022-02-15 14:32:57 +0000 |
|---|---|---|
| committer | Isabella Gottardi <isabella.gottardi@arm.com> | 2022-02-21 17:42:29 +0000 |
| commit | 68549b4afbe5098e46bda12be3769c7bf70b6e8b (patch) | |
| tree | 053f1aa8c629cf42a0dede59abccb2a1471afda9 /docs | |
| parent | 52dbd947e710cc91d3309bc96de3802bd922154c (diff) | |
| download | ml-embedded-evaluation-kit-68549b4afbe5098e46bda12be3769c7bf70b6e8b.tar.gz | |
MLECO-2927: Build Arm Ethos-U NPU driver outside TFLu
* 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
Diffstat (limited to 'docs')
| -rw-r--r-- | docs/sections/building.md | 24 |
1 files changed, 0 insertions, 24 deletions
diff --git a/docs/sections/building.md b/docs/sections/building.md index c39cabc..5fdadb0 100644 --- a/docs/sections/building.md +++ b/docs/sections/building.md @@ -234,16 +234,6 @@ chosen configuration. - `TENSORFLOW_LITE_MICRO_CLEAN_DOWNLOADS`: Optional parameter to enable wiping out `TPIP` downloads from TensorFlow source tree prior to each build. Disabled by default. -- `ARMCLANG_DEBUG_DWARF_LEVEL`: When the CMake build type is specified as `Debug` and when the `armclang` toolchain is - being used to build for a *Cortex-M* CPU target, this optional argument can be set to specify the `DWARF` format. - - By default, this is set to 4 and is synonymous with passing `-g` flag to the compiler. This is compatible with Arm - DS and other tools which can interpret the latest DWARF format. To allow debugging using the Model Debugger from Arm - Fast Model Tools Suite, this argument can be used to pass DWARF format version as "3". - - > **Note:** This option is only available when the CMake project is configured with the `-DCMAKE_BUILD_TYPE=Debug` - > argument. Also, the same dwarf format is used for building TensorFlow Lite Micro library. - For details on the specific use-case build options, follow the instructions in the use-case specific documentation. Also, when setting any of the CMake configuration parameters that expect a directory, or file, path, **use absolute @@ -452,20 +442,6 @@ cmake \ ml-embedded-evaluation-kit ``` -#### Working with model debugger from Arm Fast Model Tools - -To configure a build that can be debugged using a tool that only supports the `DWARF format 3`, such as *Modeldebugger*, -you can use: - -```commandline -cmake .. \ - -DTARGET_PLATFORM=mps3 \ - -DTARGET_SUBSYSTEM=sse-300 \ - -DCMAKE_TOOLCHAIN_FILE=scripts/cmake/toolchains/bare-metal-armclang.cmake \ - -DCMAKE_BUILD_TYPE=Debug \ - -DARMCLANG_DEBUG_DWARF_LEVEL=3 -``` - #### Configuring with custom TPIP dependencies If the TensorFlow source tree is not in its default expected location, set the path using `TENSORFLOW_SRC_PATH`. |