-
Notifications
You must be signed in to change notification settings - Fork 3.4k
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.
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
[microTVM] Autotuning performance tests #11782
Merged
Merged
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
mehrdadh
reviewed
Jun 21, 2022
guberti
force-pushed
the
autotuning-perf-tests
branch
from
June 22, 2022 01:04
aeab97c
to
19d3e53
Compare
areusch
reviewed
Jun 22, 2022
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
thanks @guberti just a couple comments here
guberti
force-pushed
the
autotuning-perf-tests
branch
2 times, most recently
from
June 27, 2022 18:40
c853eb3
to
80d7c76
Compare
mehrdadh
reviewed
Jun 27, 2022
alanmacd
reviewed
Jul 2, 2022
Bugfixes to get tests passing Refactor to remove tflite model for consistency Black formatting Linting and bugfixes Add Apache license header Use larger chunk size to read files Explicitly specify LRU cache size for compatibility with Python 3.7 Pass platform to microTVM common tests Better comment for runtime bound Stop directory from being removed after session creation
guberti
force-pushed
the
autotuning-perf-tests
branch
from
July 2, 2022 01:45
1e0f4ba
to
acd0b48
Compare
Use unsigned integer Additional logging Try negation Try 64 bit timer Use Zephyr's timing library Fix linting Enable timing utilities
guberti
force-pushed
the
autotuning-perf-tests
branch
from
July 2, 2022 01:45
acd0b48
to
aed52f7
Compare
@areusch @alanmacd I've gotten the tests passing - mind taking a final look so I can merge? |
areusch
approved these changes
Jul 5, 2022
@@ -1661,6 +1663,47 @@ def install_request_hook(depth: int) -> None: | |||
request_hook.init() | |||
|
|||
|
|||
def fetch_model_from_url( |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
blackkker
pushed a commit
to blackkker/tvm
that referenced
this pull request
Jul 7, 2022
* Common autotuning test * Autotuned model evaluation utilities * Bugfixes and more enablement * Working autotune profiling test * Refactoring based on PR comments Bugfixes to get tests passing Refactor to remove tflite model for consistency Black formatting Linting and bugfixes Add Apache license header Use larger chunk size to read files Explicitly specify LRU cache size for compatibility with Python 3.7 Pass platform to microTVM common tests Better comment for runtime bound Stop directory from being removed after session creation * Use the actual Zephyr timing library Use unsigned integer Additional logging Try negation Try 64 bit timer Use Zephyr's timing library Fix linting Enable timing utilities
masahi
pushed a commit
to masahi/tvm
that referenced
this pull request
Jul 15, 2022
* Common autotuning test * Autotuned model evaluation utilities * Bugfixes and more enablement * Working autotune profiling test * Refactoring based on PR comments Bugfixes to get tests passing Refactor to remove tflite model for consistency Black formatting Linting and bugfixes Add Apache license header Use larger chunk size to read files Explicitly specify LRU cache size for compatibility with Python 3.7 Pass platform to microTVM common tests Better comment for runtime bound Stop directory from being removed after session creation * Use the actual Zephyr timing library Use unsigned integer Additional logging Try negation Try 64 bit timer Use Zephyr's timing library Fix linting Enable timing utilities
mikeseven
pushed a commit
to mikeseven/tvm
that referenced
this pull request
Sep 27, 2023
* Common autotuning test * Autotuned model evaluation utilities * Bugfixes and more enablement * Working autotune profiling test * Refactoring based on PR comments Bugfixes to get tests passing Refactor to remove tflite model for consistency Black formatting Linting and bugfixes Add Apache license header Use larger chunk size to read files Explicitly specify LRU cache size for compatibility with Python 3.7 Pass platform to microTVM common tests Better comment for runtime bound Stop directory from being removed after session creation * Use the actual Zephyr timing library Use unsigned integer Additional logging Try negation Try 64 bit timer Use Zephyr's timing library Fix linting Enable timing utilities
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.
This PR adds utilities for autotuning with microTVM and evaluating the subsequently generated AOT-compiled model to
tvm.micro.testing
. A example end-to-end autotuning test is also added totests/micro/common/test_autotune.py
, which works for Arduino and Zephyr. This will be the only working autotuning test for microTVM, but it will not be run on the CI, as@tvm.testing.requires_micro
is set (it requires physical hardware). The test takes about three minutes to run on the Sony Spresense.A few other changes in this PR:
fetch_model_from_url
function is added to reduce redundant logic for importing modelstests/micro/common
are changed to be parameterized with the platform as well as the board. This eliminates the need for tests to decide whether a board is an Arduino or Zephyr board, and allows us to support boards that are compatible with both.yes_no.tflite
model has been removed, and been replaced by usingfetch_model_from_url
to download it. This is the same model downloaded bytest_tvmc.py
.timing/timing.h
, as our previous implementation was complicated and had bugs.cc @alanmacd @gromero @mehrdadh