GitLab

Changed the pooling values for two structures from strings to specialized enum classes. Many test and operator parsing changes to support this. Introduces one new source file, op_enums.cpp.

* code backup

* clang format

* change corresponding tool files

* clang format
Co-authored-by: mvermeulen <5479696+mvermeulen@users.noreply.github.com>

* Add all_targets cmake target

* Rename target

* Add ref target

* Rename tests

* Refactor compiler target

* Formatting

* Verify for every target

* Formatting

* Add verify test suite

* Formatting

* Add initial test programs

* Formatting

* Add rnn tests

* Formatting

* Validate gpu

* Formatting

* Remove old gpu tests

* Fix gpu tests

* Fix ref error

* Fix tidy issues

* Formatting

* Tidy fixes

* Fix header in python api

* Rename to ref

* Use ref in verify_onnx

* Fix tidy issue

* Build with verbose on

* Fix typo

* Remove verbose

* rename some cpu prefix to ref
Co-authored-by: Shucai Xiao <Shucai.Xiao@amd.com>

* Add save/load functions

* Formatting

* Add loading and saving to the driver

* Formatting

* Add return

* Serialize the context with the program

* Formatting

* Add python API

* Formatting

* Add c/c++ apis

* Formatting

* Add tests

* Formatting

* Fix tidy error

* Fix python doc

* Restore python code

* Add function name to errors

* Formatting

* Use lvalue for writing

* Serialize context

* Fix convolution and pooling operator for miopen

* Formatting

* Add const ref

* Set target name to gpu

* Add target tests

* Formatting

* Move register target to cpp file

* Fix target test

* Use make_target in driver

* Formatting

* Use make_target for the API

* Formatting

* Add cpu include

* Increase timeout

* Add more tests

* Formatting
Co-authored-by: Shucai Xiao <shucai.xiao@amd.com>
Co-authored-by: mvermeulen <5479696+mvermeulen@users.noreply.github.com>

* Use increment instead of division to compute register offset

* Formatting

* Limit layernorm to 1024 elements

* Formatting

* Add verification to driver

* Formatting

* Remove early return

* Use block_size 256

* Vectorize the kernel

* Formatting

* Convert to vector type

* Add layernorm tests

* Formatting

* Formatting

* Refactor layernorm to run both algos

* Formatting

* Fix compile error

* Fix tidy warnings

* Formatting

* Add layernorm function

* Formatting

* Add flags to quantize in driver

* Formatting

* Fix compile error