Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Enforce single optimized kernel implementation #44566

Closed
advaitjain opened this issue Nov 3, 2020 · 4 comments
Closed

Enforce single optimized kernel implementation #44566

advaitjain opened this issue Nov 3, 2020 · 4 comments
Assignees
@advaitjain @mohantym
Labels
comp:lite TF Lite related issues comp:micro Related to TensorFlow Lite Microcontrollers stale This label marks the issue/pr stale - to be closed automatically if no activity stat:awaiting response Status - Awaiting response from author type:bug Bug

Comments

@advaitjain
Copy link
Member

Currently we can provide potentially multiple optimized kernel implementations via the TAGS parameter to the TFLM Makefile.

While this was originally supported, we don't have any use-case for it and are moving towards enforcing a single optimized kernel implementation. This will also reduce some complexity in the makefile and allow for improved debugging.

Corresponding internal issue: http://b/170501366
@advaitjain advaitjain added the comp:micro Related to TensorFlow Lite Microcontrollers label Nov 3, 2020
@advaitjain advaitjain assigned advaitjain and unassigned ravikyram Nov 3, 2020
advaitjain added a commit to advaitjain/tensorflow that referenced this issue Nov 4, 2020
@advaitjain
Specialize sources for target and optimized kernels independently.
2610320 
This change:
 * adds a new command line option to the makefile called
   OPTIMIZED_KERNEL_DIR which should be used instead of TAGS

 * TAGS is currently supported for backwards compatibility and a gradual
  rollout but will be dropped (for optimized kernels) in follow-up
  changes.

 * Makes the necessary change to use OPTIMIZED_KERNEL_DIR for
   xtensa_hifimini.

First step towards tensorflow#44566

Fixes internal bug: http://b/160795217
Addresses internal bug: http://b/170501366
@advaitjain advaitjain mentioned this issue Nov 4, 2020
Merged
advaitjain added a commit to advaitjain/tensorflow that referenced this issue Nov 4, 2020
@advaitjain
Specialize sources for target and optimized kernels independently.
6d9bf3d 
This change:
 * adds a new command line option to the makefile called
   OPTIMIZED_KERNEL_DIR which should be used instead of TAGS

 * TAGS is currently supported for backwards compatibility and a gradual
  rollout but will be dropped (for optimized kernels) in follow-up
  changes.

 * Makes the necessary change to use OPTIMIZED_KERNEL_DIR for
   xtensa_hifimini.

First step towards tensorflow#44566

Fixes internal bug: http://b/160795217
Addresses internal bug: http://b/170501366
advaitjain added a commit to advaitjain/tensorflow that referenced this issue Nov 4, 2020
@advaitjain
Specialize sources for target and optimized kernels independently.
d17d07a 
This change:
 * adds a new command line option to the makefile called
   OPTIMIZED_KERNEL_DIR which should be used instead of TAGS

 * TAGS is currently supported for backwards compatibility and a gradual
  rollout but will be dropped (for optimized kernels) in follow-up
  changes.

 * Makes the necessary change to use OPTIMIZED_KERNEL_DIR for
   xtensa_hifimini.

First step towards tensorflow#44566

Fixes internal bug: http://b/160795217
Addresses internal bug: http://b/170501366
advaitjain added a commit to advaitjain/tensorflow that referenced this issue Nov 4, 2020
@advaitjain
Specialize sources for target and optimized kernels independently.
9f27888 
This change:
 * adds a new command line option to the makefile called
   OPTIMIZED_KERNEL_DIR which should be used instead of TAGS

 * TAGS is currently supported for backwards compatibility and a gradual
  rollout but will be dropped (for optimized kernels) in follow-up
  changes.

 * Makes the necessary change to use OPTIMIZED_KERNEL_DIR for
   xtensa_hifimini.

First step towards tensorflow#44566

Fixes internal bug: http://b/160795217
Addresses internal bug: http://b/170501366
@ravikyram ravikyram added comp:lite TF Lite related issues type:bug Bug labels Nov 5, 2020
@mohantym mohantym self-assigned this Oct 7, 2022
@mohantym
Copy link
Contributor

mohantym commented Oct 7, 2022

Hi @advaitjain !
It seems that it has been updated to fixed status in the above buganizer ticket. Can it be considered as resolved then.
Thank you!

@mohantym mohantym added the stat:awaiting response Status - Awaiting response from author label Oct 18, 2022
@google-ml-butler
Copy link

This issue has been automatically marked as stale because it has no recent activity. It will be closed if no further activity occurs. Thank you.

@google-ml-butler google-ml-butler bot added the stale This label marks the issue/pr stale - to be closed automatically if no activity label Oct 25, 2022
@google-ml-butler
Copy link

Closing as stale. Please reopen if you'd like to work on this further.

@google-ml-butler
Copy link

Are you satisfied with the resolution of your issue?
Yes
No

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@advaitjain advaitjain

@mohantym mohantym

Labels
comp:lite TF Lite related issues comp:micro Related to TensorFlow Lite Microcontrollers stale This label marks the issue/pr stale - to be closed automatically if no activity stat:awaiting response Status - Awaiting response from author type:bug Bug
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@advaitjain @ravikyram @mohantym