GitLab

Allows migraphx to inline the IF operator when we run into an IF that can be evaluated at compile time, thus avoiding us injecting IF and just inserting the instructions directly.

The satakey proiject has been abandoned satackey/action-docker-layer-caching#347. Another repo has taken over this work. It is active and has resolved recent github action deprecation issues.

upgrade to ROCm 5.4.2 in CI

Added CMakeFlag for hipRTC. MIGRAPHX_USE_HIPRTC.
Added stages in Jenkins for hipRTC.
Fixes for some of the pending issues from hipRTC.

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

Declare OS type in action

Dynamic shape support for gather op.

Fix to use the contents of the .onnxrt-commit file. Docker was not assigning the contents to the dockerfile argument. Changed the technique to be used as part of the git clone download.

Enable cron based action

* Create the shape correctly in python printout

Adding action to setup CI for weekly commits for Friday 9AM

* Update MIGraphx Docker to point to latest working onnxrt branch.
* Add output for ONNXRUNTIME_COMMIT in CI and add env var in brackets

supports upper and lower trilu
not able to support dynamic k values
not able to support negative k values

Adds support for parsing dynamic ONNX gemm bias input C

This prevents multiple adds.

Extends ONNX Gemm parser to handle dynamic input shapes
Limits ONNX Gemm parsing to 2D input tensors for A and B inputs
As per the ONNX specifications
Changed Gemm ONNX tests to 2D input versions
Add onnx_verify tests for Gemm
Parsing ONNX Gemm links to more than one operator, checking that it produces the correct result

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

Create a workflows to allow issues to be assigned to a project in github

This PR resolves the bug addressed in #1496. 

Extends parse_matmul.hpp to handle dynamic input shapes
Does not support broadcasting of the outer dimensions for dynamic shapes at this time

* Use cosine to compute half sin

Fixes ONNX parsing of convolution to handle dynamic broadcasting of bias input

Change to python ONNX package 1.10.0 to handle new ONNX test generation.

* Getting incorrect token error on workflow
* Try using the other token from ci.yaml
* Rename workflow
Co-authored-by: Chris Austen <causten@users.noreply.github.com>

JIT implementation of the gather operator
Added a few more unit tests to this one as well since I saw some odd behavior during bring up.

* Create workflow to add to Github project

Run a stage using MIGRAPHX_GPU_DEBUG=1.

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

HIP had change in previous rocm releases to use --offload-arch instead of --cuda-gpu-arch.

This should be backwards compatbile. hipRTC also supports --offload-arch.

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

* Add implicit_conversion