Age | Commit message (Collapse) | Author |
|
Rationale for making this change:
- In the original design, for control flow operators like WhileOp,
child blocks couldn't read the tensor variables (global consts) in the root level block,
this patch added the machanism for child blocks to access their parent
level block's tensors.
- This change also relies on another serialization change on adding
another layer of abtraction called Region:
- Serialization patch: [region] Add TosaSerializationRegion to serialization_lib
- Updated the corresponding python version of the serialization code: TosaSerializerRegion to python version of serialization_lib
- This change also relies on the TOSA MLIR Translator change: Add RegionBuilder to TOSA MLIR Translator
- Added the WhileOp related test cases: While, LSTM, GRU, RNN
- Other related fixes
Signed-off-by: Jerry Ge <jerry.ge@arm.com>
Change-Id: I13ae33628ad07e41d248e88652ce1328654694ab
|
|
- Adds a script to generate operators.h and operators.cc
- Adds jinja2 templates for generating operators.h and operators.cc
- Adds unit tests for a subset of the operators generated
- Includes the TOSA specification as a submodule
- Adds supporting C++ and header files
Signed-off-by: Grant Watson <grant.watson@arm.com>
Change-Id: I5b60db4c56113110d8e75fe1152525d258233f9c
|
|
* Upgrade Eigen to 3.4.0 (for bfloat16 support) and add work-
arounds for reduce.any() and reduce.all() bugs (introduced
between 3.3.7 and 3.4.0)
* Truncation to bfloat16 now performed in eval() methods
Signed-off-by: James Ward <james.ward@arm.com>
Signed-off-by: Jeremy Johnson <jeremy.johnson@arm.com>
Change-Id: If5f5c988d76d3d30790acf3b97081726b89205fe
|
|
* Added specific FP16 readfromVector and writeToVector methods.
* Added FP16 support to float readfromVector and writeToVector methods.
* Added missing reference to IModelRunner::setInput.
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: I6b66468737e672afc925ccad4fb710fbb9427c14
|
|
Update tensor operations naming to state input type as TxT in
all cases. Effects CONV2D, CONV3D, DEPTHWISE_CONV2D,
FULLY_CONNECTED, TRANSPOSE_CONV2D.
Signed-off-by: Jeremy Johnson <jeremy.johnson@arm.com>
Change-Id: Ic959acfcb3aa0a910b33b774a5a85fac08219205
|
|
Change-Id: I72f21fcfa153046274969d327313e3349981dbe6
Signed-off-by: James Ward <james.ward@arm.com>
|
|
* Added IModelRunner interface using pimpl idiom, which allows a user to
initialize, configure and run the model.
* Added unit tests for IModelRunner.
* Added doctest as third-party submodule.
* Added user options to specify paths for dependencies.
* Moved general func_config functions to separate utility, which removes
cxxopts dependency.
Signed-off-by: Matthew Sloyan <matthew.sloyan@arm.com>
Change-Id: If42f1f82cd6dadf18911a48dcd5fa579b719aff2
|
|
Update ref-model RESCALE op to support UINT16 conversions
Add testing for RESCALE UINT16 and ERROR_IFs
Signed-off-by: Jeremy Johnson <jeremy.johnson@arm.com>
Change-Id: Ic6e6e53de1f0b054bedb9e6ba3856e7475498aba
|
|
- test like [1] + [2] = [1] should be treated as invalid test
- modify matchRankShape() function so it allows size 1 only on the source tensor but not target tensor
Signed-off-by: Kevin Cheng <kevin.cheng@arm.com>
Change-Id: I6bbb6a63dc1143712e7eef736a991cac419b009e
|
|
Signed-off-by: Kevin Cheng <kevin.cheng@arm.com>
Change-Id: I9ed3d8971a133b4cbb2cf7d827f4e69d55dee246
|
|
- Also replace SIMPLE_FATAL_ERROR() with FATAL_ERROR() since they're duplicate
- Replace FATAL_ERROR()/ASSERT_MSG() with ERROR_IF_SUBGRAPH() if the condition is a graph error
FATAL_ERROR()/ASSERT() should only be used by model internal/runtime error like file reading.
Signed-off-by: Kevin Cheng <kevin.cheng@arm.com>
Change-Id: If1e1e2488054a0ecd800fb0f2ea6487019282500
|
|
or ERROR_IF()
- Adding return code enum class: {VALID, UNPREDICTABLE, ERROR}
- Runtime errors (e.g. memory allocation failure) will abort immediately, or will return one of the three return codes
Part of the codes are re-written to pass REQUIRE() to the top-level (e.g. apply_scale_32/16())
- Update setExpectedFailure() to setExpectedReturnCode() on test generation script
- Update test regression script to interface with reference model change
Signed-off-by: Kevin Cheng <kevin.cheng@arm.com>
Change-Id: Ia063c936bcb2a54d6e379a5bb6801aa72d1186f1
|
|
Bring CONV2D/DEPTHWISE_CONV2D/TRANSPOSE_CONV2D/FULLY_CONNECTED up running.
Other minor fixes:
- reference model should bail out if shape is invalid, along with "goto done" cleanup.
- cleanup typos/duplicate in tosa_test_gen.py/tosa_serializer.py.
- wrong input_zp/output_zp being generated for RESCALE.
Signed-off-by: Kevin Cheng <kevin.cheng@arm.com>
Change-Id: Ic1f3fe0090482bdee8a61508be7c738714191e19
|
|
- Remove Usage and Format
- Run black on verif/*.py scripts
Signed-off-by: Kevin Cheng <kevin.cheng@arm.com>
Change-Id: Ie81515891eb0039540f614894f4b6b0e0e78ba74
|
|
- Updated C and Py serialization libraries, updated licence files
- Removed AINT8 from TOSA reference tests
Signed-off-by: Kevin Cheng <kevin.cheng@arm.com>
Signed-off-by: Jared Smolens <jared.smolens@arm.com>
Change-Id: I860bfeaad5a075e50f569c8f6861927ebacf1378
|
|
Change-Id: I2f8e7fa63e2ae40203e57d2cc8814bde3b312cb6
Signed-off-by: Eric Kunze <eric.kunze@arm.com>
|