GitLab

Add dynamic shape support to slice operator.

First draft of this feature doesn't support ops slicing non-fixed, dynamic axes. Resulting shape in such cases is not guaranteed.* Also, onnx parsing doesn't support any arguments other than "axes".

Expands on the documentation and corrects default option documentation error.

* Add serialization of tuples and optional types

* add dynamic shape support to concat operator.  Includes new op_shape_test and ref_ops_test cases

dyn shape support for Where operator.  Includes shape test, ref_ops test, onx_test. 

* Fuse layernorm with different patterns
* Only match when using the last axis
Co-authored-by: kahmed10 <15948690+kahmed10@users.noreply.github.com>
Co-authored-by: kahmed10 <15948690+kahmed10@users.noreply.github.com>

Refactors memory coloring to only handle allocation instructions. It also handles allocations for tuple shapes.

* Implement dynamic shapes for scatterND operators.

Dynamic shape support for gathernd op.

upgrade to ROCm 5.4.2 in CI

* Add general optimize pass
* Fuse gemm multiplies by scalar
* Handle zero epsilon

Dynamic shape support for gather op.

Extends reshape to handle the case of a single non-fixed dynamic_dimension

Extends pad operator to handle dynamic input shapes
Only handles computing the shape for adding constant padding to a dynamic shape
- adds the padding to the min, max, and opt values (unless opt is 0, where it keeps it 0)
- does not handle reflect padding with dynamic shapes

Implements dynamic shapes in reduce_op and all its child operator classes (reduce_max etc.)

* Print python code

Implements the operator==(dynamic_dimension, size_t) functions

Extends dot MIGX operator to handle dynamic input shapes
Only allow dot between two dynamic shapes that have exactly matching outer dimensions
Inner dimensions must also match correspondingly
Updates dot related tests
Change check_shapes to use shape.ndim()
ONNX parsers for GEMM and MatMult will be updated in a separate PR

No major changes required, use dyn_output and pass dynamic shape when calling compute_shape()
Adds dynamic shape tests

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

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

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

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>

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

Extends the ref contiguous operator to handle dynamic shapes
Updates the eliminate_contiguous pass to use the dyn_output struct

Updated Multibroadcast op to have a two input version for dynamic shapes
Current dynamic shape broadcasting logic
dynamic_dimensions must be the same or one of them is {1, 1, 0} or {1, 1, 1}
Works for dyn-dyn, dyn-static, and static-static shape combinations
Changed common.cpp for multibroadcasting for binary ops with dynamic shapes
Extended binary.hpp for dynamic shapes to test the new common.cpp stuff

Can be enabled via environment variable MIGRAPHX_ENABLE_NHWC

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

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>

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

Stream sync changes and associated API level changes

Improvements/Additions to be made:

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

Implement operator for CPU and GPU implementations

This PR allows for other values of epsilon to be matched when finding layernorm. Similarly, the calculation now uses the variable for epsilon.

* Remove unused headers