GitLab

Upgraded Dockerfiles and fixed tidy issues to make Ubuntu 20.04 and ROCm 5.3.0 the default 

- Added cases to handle error cases of invalid splits for split-11 and split-13
- should solve issue with code coverage.

updated GPU pad to now use JIT version.
added range functions for JIT kernels.

Newer split moves the split attribute to an input. In this case we check the
number of input args then.

This changes allows us to move the accumulte check to outside each conditional branch
Added more debug on this as well to show more details on this failure mode.

Adds an additional test case using a generated split-13 operator styled
test.

Fixes an observed regression error on certain Frozen Protobuf models due to PR 1280

- Initial fix to handle scalars on input for empty constant values
- Using scalar, multibroadcast, contiguous
- Fixed appropriate unit tests for simple single output constants
- Added unit tests for multi if outputs.

- TODO - multibroadcast to handle scalar so we don't use scalar

Adding test to validate what a "valid" multi input should look like and
that we correctly handle trailing 1s and correctly sized outputs.

Generated and added the two tests from gen_onnx.py with matching test
in onnx_test.cpp

-if_then_else_multi_output_shapes_test.onnx
-if_then_else_multi_output_shapes_test2.onnx

Refactor dynamic compute
- add a compute_output_shape object that implicitly converts to a new dyn_output or shape object
- dyn_output object can handle computing the static output shape of an operator given the input arguments shapes
  change an operator's compute function to argument compute(const dyn_output& dyn_out, std::vector<argument> args) to 
  use dyn_output object

Dynamic ref unary functions
-  Included these changes to have an example of the refactored dynamic compute being used
-  Changes to unary base class to handle dynamic shapes
-  Changed elu and leaky_relu to use unary base class and pointwise JIT

* use find2.0 for the convolution
Co-authored-by: Vasilii Filippov <DrizztDoUrden@users.noreply.github.com>
Co-authored-by: Chris Austen <causten@users.noreply.github.com>

* Enable non-standard shape
* Use perfdb for non xdlops
* Fix transpose+broadcast strides
Co-authored-by: jungpark-mlir <jungwook.park@amd.com>

outline seems to be bugged, and going to be depreciated, thus switching to
creating a new literal with the proper shape for the empty output branch.

This test should error out as, having different output shapes for each
branch with one non empty is invalid.

Changes to gen_onnx.py as well as generated onnx file provided

Add the testcase and onnx file generated to handle the case of two output
shapes that vary in rank by one, with a trailing 1 but sub lengths are not equivalent

This should be flagged as an error always for static inputs

- added changes to gen_onnx.py for different type, shape, and incompatible lens
- added test cases that should except in onnx_test.cpp

- gen_onnx.py changes for onnx output of empty const input branches (seen in resnext50)
- updated onnx_test.cpp to validate parsing of input.
- new onnx files generated from onnx tests

hipMemset is causing random failure.
hipMemsetAsync is doing the correct synchronization.

- Handle checks for each IF output
- add const to inputs of all_but_last_dims_equal
- add std::equal instead of using equal
- Use .back() for vectors in getting last value
- Use input().front() instead of prev(prev()) when replacing the last value.

Allows for rank 2 tensors into batchnorm.  Specifically when spatial dimensions are all 1 and removed

Removes use_dynamic_same_auto_pad
Change padding_mode to be used for dynamic padding
Move compute_padded_shape to pad_calc.cpp as it will be used in other dynamic padding cases
Fix same_lower compute_padded_shape bug and add a test.

Rewrites the TF batch norm like operators to other MIGX operators
Removes the code related to batch_norm_inference

Hand verified results before running test using random data generated from
the new protobuf files for this.

Everything is correctly functionally within tolerances.

Had to readjust input sizes to that of the .onnx file as one input is deliberately
made smaller (without the trailing 1) for theses tests to test the case correctly

Fixes test which verifies how we interpret vectors with trailing ones, between input branches to
an IF module block.

Update test for new generated onnx file, as well as using unsqueeze output
for when we parse in a network with mismatched shapes with a trailing 1

Inverted logic when I wrote generated statements for these. Regenerated files

- Gets past to the split section of the resnext model
- adding outline seems to solve if issues but verify calls broken
- Referencing wrong element now instead of output of correct if block?
- Need to determine proper output through verify tests.
- Modified protobuf to handle case of extra 1 to "vectorize" scalar
- Modified verify/tests to get things to "work", may need to be revised further.

Simplified algebraic operations (x*1), x*(-1), x/1, 0+x & x+0,  x-0, 0-x, 0*x, x*0, and 0/x operations

- Update if_then/else_empty test protobuff and cases
- Need to update rand() vector used
- Make y empty instead of x for if_else_empty_test.onnx
- Regenerate protobufs with updates
- Add changes to handle empty/scalar input branch size to if operator.
- Add case where if both branches empty throw an error.
- Update verify tests with gold vectors and new shapes for empty input vec
  which we handle like a scalar before broadcasting

- Verification tests that test each then/else branches for parsed IF operator
- Testing empty shape tensors for one branch -> output must be the other branch's shape
- Testing trailing 1 shape for one branch -> output must be union of both inputs

Current issue with IF operator is that we can't handle training vectors that match
in size correclty while also running into issues with empty inputs for one of the
branches for size/type checks.

This seemed to be missing, just leveraging the existing protobuf made
to test parsing of if_then_test.onnx for this and using the tensor of all
ones to default to an ADD operation to ensure cond =1 is being handled and parsed
in correctly.

Stream sync changes and associated API level changes

optimize the softmax operator

Adds two methods for the custom_ops virtual class.

bool runs_on_offload_target(), if the custom op runs directly on the gpu then it should be set to true. in this case, custom op expects its parameters to reside in GPU memory and writes output to the GPU memory. If it is set to false then, custom op expects it's parameter to reside on the host and puts back the result into the host memory.

output_alias, if output of the custom op is aliasing the input buffer. i.e. interpreting the same input buffer with differnet shape and strides.

Update as_vector() in C++ API to handle non-standard shapes. It required exposing element_index to space_index conversion method for the shape class.

Improvements/Additions to be made:

changes for the quant_convolution,
changes for the deconvolution,
Macros for MIOpen status checks

test_gpu_pack_int8_args fails on gfx908 machine, because it doesn't set compute_fp32 flag correctly. This PR fixes the test such that it checks for the device-name, and rocblas-versions and sets this flag accordingly.

Implement operator for CPU and GPU implementations

Rewrites the BatchNormalization ONNX operator into other MIGX operators
- Added handling of 1D input tensor case (edge case in ONNX spec)
Removes the spatial and per_activation functionality (not in the ONNX spec)
- Did not remove the batch_norm_inference related code as the TensorFlow parser still uses it
- Can remove that code when the TF version is updated