Add Module-Based Model Runtime Interface for AOT (support C++ runtime) #9697
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
areusch
force-pushed
the
aot-executor-no-codegen
branch
2 times, most recently
from
66cc5a8 to
e879841
Compare
mehrdadh
reviewed
Dec 14, 2021
| @@ -390,6 +391,13 @@ if(USE_PROFILER) | |||
| list(APPEND RUNTIME_SRCS ${RUNTIME_VM_PROFILER_SRCS}) | |||
| endif(USE_PROFILER) | |||
|
|
|||
| if(USE_AOT_EXECUTOR) | |||
There was a problem hiding this comment.
I suggest to add USE_AOT_EXECUTOR to cmake/config.cmake with default value ON
|
|
||
|
|
||
| def test_conv2d(): | ||
| RELAY_MODEL = textwrap.dedent( |
There was a problem hiding this comment.
I suggest to use relay directly to build the relay model. Here is an example:
tvm/tests/micro/zephyr/test_zephyr.py
Line 394 in 01599d1
| output_list = generate_ref_data(ir_mod, inputs, params) | ||
|
|
||
| with tvm.transform.PassContext(opt_level=3, config={"tir.disable_vectorize": True}): | ||
| mod = tvm.relay.build(ir_mod, params=params, target="c -executor=aot -link-params") |
There was a problem hiding this comment.
change this to use executor and runtime args?
* These were autogenerated in the original PR, but checking them in as plain code until we can revisit the auto-generator approach.
multiple-models case.
areusch
force-pushed
the
aot-executor-no-codegen
branch
from
94a72c3 to
94bcb1c
Compare
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Outdated suggestions cannot be applied.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 implements Module-based Model Runtime for AOT RFC. It adds support for targeting the C++ runtime with the Ahead-of-Time Executor for workloads which are purely CPU-based (e.g. the Device API cannot be used).
cc @manupa-arm @kparzysz-quic @csullivan @mehrdadh @adstraw for early feedback while I iterate to prepare to merge this.