GitLab

Changes flatten's compute_shape() to handle dynamic shapes
Calculates the flattened shape with the min, max, and opt

Currently, quantizing a program with rnn layers to fp16 results in segmentation faults due to a "convert" operation being applied to an "undefined" instruction.

The following changes are implemented to fix this issue:

Added is_undefined method to the instruction class that returns true if all inputs to the instruction are from an undefined op.
Updated rewrite_rnn pass to use the new is_undefined method rather than checking ins->name()
Updated the dead_code_elimination pass to also use this new method rather than only checking the instruction name

* Add implicit_conversion

Misc. style changes.  Added a shape test and an onnx test for the case of reduce op. with no axes specified (should reduce all axes).  The new Onnx test case is stll under construction and doesn't pass.

Extends the Argmax operator to handle dynamic input shapes.
Only shape function changes

Need this for when we debug and use MIGRAPHX_TRACE_EVAL() to show tuples
Without this we break when reading our buffer due to the use of visit()
This came up as part of #1283 debugging.

Extends unsqueeze and squeeze to work for dynamic input shapes
Does not handle the steps parameter
Adds some additional negative axes shape tests

Update dialect registration interface
Update 2nd build pipeline call and use full arch name

Onnx test fixes: corrected op name and restored the abs instruction mistakenly removed from reduce_L1 test file

Onnx test fixes: Removed a superfluous "abs" op from reducel1_dyn_test. Changed output of reducemax_dyn_test to be dynamic.  Includes an updated Onnx test file

update an Onnx test.  Original version used optimize_onnx(), which isn't compatible with dynamic shapes

Fix problem with the contiguous operator constructing non-standard shape literals.  A non-standard literal will almost never be used, since a literal is known at compile time.  Added some comments on the intended behavior:

- literal{shape, vector} constructor with a non-standard shape is intended to keep the same ordering as the given vector. The data buffer will be populated such that when the non-standard indexing is used the original order is as given.
- literal{shape, argument} constructor directly copies the data buffer from the argument
- Changed non-standard literal fill() to use tensor_view iterators as it handles non-standard shapes now
- Changed the contiguous ref_ops_test to be more helpful

Extends the pooling operators for dynamic shape inputs

AveragePooling
GlobalAveragePooling
MaxPooling
GlobalMaxPooling
LpNormPooling
GlobalLpNormPooling
y.github.com>

Merge branch 'dyn_unsqueeze' of https://github.com/ROCmSoftwarePlatform/AMDMIGraphX into dynamic_reduce.
Required because squeeze is added in parsing of onnx reduce op.

Bumps [tensorflow](https://github.com/tensorflow/tensorflow) from 2.7.2 to 2.9.3.
- [Release notes](https://github.com/tensorflow/tensorflow/releases)
- [Changelog](https://github.com/tensorflow/tensorflow/blob/master/RELEASE.md)
- [Commits](https://github.com/tensorflow/tensorflow/compare/v2.7.2...v2.9.3

)

---
updated-dependencies:
- dependency-name: tensorflow
  dependency-type: direct:production
...
Signed-off-by: dependabot[bot] <support@github.com>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Chris Austen <causten@users.noreply.github.com>

Merging #1391 caused an extra adjust allocation pass for GPU targets. This removes that merge error.

Extends ref transpose operator for dynamic shapes
Make dynamic tests more consistent naming

* Default ROCm version set to 5.3 and schedule update due to DST for nightly build.

Disabling it untill int8 fix is in mainline from MIOpen and also so that QA tests could run migraphx-driver and unittests from MIGraphX.

Fix to stop types failing for logical_xor during our fusions.