Add command line option to select -stdlib=libc++ with Xtensa.
#47681
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Confirmed that the following two commands build and we see different sizes with and without `-stdlib=libc++`. ``` make -f tensorflow/lite/micro/tools/make/Makefile TARGET=xtensa OPTIMIZED_KERNEL_DIR=xtensa TARGET_ARCH=fusion_f1 XTENSA_CORE=F1_190305_swupgrade keyword_benchmark -j8 BUILD_TYPE=release XTENSA_USE_LIBC=true xt-size tensorflow/lite/micro/tools/make/gen/xtensa_fusion_f1_release/bin/keyword_benchmark ``` gives: ``` text data bss dec hex filename 84496 384 22704 107584 1a440 tensorflow/lite/micro/tools/make/gen/xtensa_fusion_f1_release/bin/keyword_benchmark ``` And ``` make -f tensorflow/lite/micro/tools/make/Makefile TARGET=xtensa OPTIMIZED_KERNEL_DIR=xtensa TARGET_ARCH=fusion_f1 XTENSA_CORE=F1_190305_swupgrade keyword_benchmark -j8 BUILD_TYPE=release xt-size tensorflow/lite/micro/tools/make/gen/xtensa_fusion_f1_release/bin/keyword_benchmark ``` gives: ``` text data bss dec hex filename 66696 40212 24856 131764 202b4 tensorflow/lite/micro/tools/make/gen/xtensa_fusion_f1_release/bin/keyword_benchmark ``` Progress towards tensorflow#47575 and http://b/182209217
|
Thanks for contributing to TensorFlow Lite Micro. To keep this process moving along, we'd like to make sure that you have completed the items on this list:
We would like to have a discussion on the Github issue first to determine the best path forward, and then proceed to the PR review. |
njeffrie
approved these changes
Mar 9, 2021
advaitjain
added a commit
to advaitjain/tensorflow
that referenced
this pull request
Mar 18, 2021
tensorflow#47681 changed the default back to not using -stdlib=libc++ which meant an expected size increase. This increase can be avoided at the application level by adding stubs for the exception code prior to linking the final binary. We had an (unexpected but completely insignificant) increase in cycles 3 ticks for hifimini and 4 ticks for fusion_f1 from tensorflow#47830
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Confirmed that the following two commands build and we see different sizes with and without
XTENSA_USE_LIBC=true.gives:
And
gives:
Progress towards #47575 and http://b/182209217