[TVMC] Allow output module name to be passed as a command line argument #10962
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
reviewed
Apr 11, 2022
There was a problem hiding this comment.
@grant-arm thanks for this PR, looks great! a few minor comments, could be swayed either way on them (don't take my review as blocking)
| @@ -202,6 +208,7 @@ def compile_model( | |||
| pass_context_configs: Optional[List[str]] = None, | |||
| additional_target_options: Optional[Dict[str, Dict[str, Any]]] = None, | |||
| use_vm: bool = False, | |||
| mod_name: Optional[str] = "default", | |||
There was a problem hiding this comment.
perhaps "default" should be a constant somewhere?
There was a problem hiding this comment.
Thanks @areusch , I agree it would be good to have "default" as a constant.
It feels like this should be a separate PR though.
gromero
approved these changes
Apr 11, 2022
There was a problem hiding this comment.
@grant-arm LGTM! Thanks for cc:ing me, I just learned about the different ACCEL_TYPES :)
leandron
reviewed
Apr 12, 2022
grant-arm
force-pushed
the
tvmc_module_name_arg
branch
from
681770c to
b6435f1
Compare
ekalda
reviewed
Apr 12, 2022
* Allows module-name as a command line argument to tvmc * Updates microNPU graph partitioner to pass module name to PartitionGraph() * Updates CMSIS-NN graph partitioner to pass module name to PartitionGraph() Change-Id: I12a4a2eef2ddc7e3c4a6c0dd8fdcab009c975bac
grant-arm
force-pushed
the
tvmc_module_name_arg
branch
from
b6435f1 to
061f1ea
Compare
AndrewZhaoLuo
added a commit
to AndrewZhaoLuo/tvm
that referenced
this pull request
Apr 15, 2022
* main: (527 commits) [hexagon] 'add_hvx' test to explore HVX usage. (apache#10604) [COMMUNITY] @yzh119 -> Reviewer (apache#10993) [Metaschedule] Make custom schedule_rule registration optional (apache#10975) [ONNX] Add imports for BERT contrib operators (apache#10949) sort axes (apache#10985) [Hexagon] Remove HexagonBuffer external constructor and support (apache#10978) [CI] Update GPU image (apache#10992) [Runtime][Vulkan] Add RGP support to TVM for vulkan device (apache#10953) [FIX] resolve int64/32 for AttrStmtNode (apache#10983) [TVMC] Allow output module name to be passed as a command line argument (apache#10962) [ONNX] Add MatMulInteger importer (apache#10450) [COMMUNITY] @guberti -> Reviewer (apache#10976) Support `qnn.conv2d` in FoldExplicitPading (apache#10982) change Hexagon docker version (apache#10981) remove exception handling of autotvm xgboost extract functions (apache#10948) [CUDNN] Add partitioning support for conv2d and log_softmax (apache#10961) [Hexagon][LLVM] Enable/test tensorized Hexagon DMA on 2d transformed layout (apache#10905) [Hexagon] Move aot/graph_executor interactions into launcher (apache#10907) [HEXAGON] Split huge 1D DMA Transfers into smaller transfers with legal sizes. (apache#10971) [CI][DOCKER] Add pytest-lazy-fixture to images (apache#10970) ...
Lucien0
pushed a commit
to Lucien0/tvm
that referenced
this pull request
Apr 19, 2022
…nt (apache#10962) * Allows module-name as a command line argument to tvmc * Updates microNPU graph partitioner to pass module name to PartitionGraph() * Updates CMSIS-NN graph partitioner to pass module name to PartitionGraph() Change-Id: I12a4a2eef2ddc7e3c4a6c0dd8fdcab009c975bac
altanh
pushed a commit
to altanh/tvm
that referenced
this pull request
Apr 28, 2022
…nt (apache#10962) * Allows module-name as a command line argument to tvmc * Updates microNPU graph partitioner to pass module name to PartitionGraph() * Updates CMSIS-NN graph partitioner to pass module name to PartitionGraph() Change-Id: I12a4a2eef2ddc7e3c4a6c0dd8fdcab009c975bac
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.
Currently there is no way to pass an output module name to tvmc on the command line when compiling a model.
This means that (for the use cases we are interested in) generated C code is always placed in files named
default_lib*.cand that functions are namedtvmgen_default*().If we want to compile multiple models for use with a single application, the C source file names and function names are not unique, resulting in failure when building the generated C code.
This PR allows module-name to be passed to tvmc on the command line, for example:
In this case, the generated C code is placed in files named
classify_lib*.cand functions are namedtvmgen_classify*().Additionally, this PR updates the microNPU and CMSIS-NN graph partitioners to pass the module name to PartitionGraph().
This is necessary to ensure that the C code function names generated for microNPU and CMSIS-NN include the module name and not
default.@leandron @Mousius @manupa-arm @areusch
cc @gromero