GitLab

* Add initial optimization when using a mul over a sliced convolution

* Formatting

* Add more tests

* Formatting

* Convert to an assert

* Check if used once

* Formatting

* Add test with horiz fusion

* Formatting

* Optimize nested slice

* Formatting

* Fix test

* Add const refs

* Remove unnecessary assert
Co-authored-by: mvermeulen <5479696+mvermeulen@users.noreply.github.com>

* code backup

* clang format

* fix compiling errors

* clang format

* rename a few files

* rename a few files

* fix variable bugs

* clang format

* add an operator to shift input sequences

* clang format

* fixed a bug

* clang format

* fixed a bug

* clang format

* code backup

* clang format

* code backup

* clang format

* code backup

* clang format

* refine code related lstm operator optimization

* clang format

* fix various bugs

* clang format

* fixed a bug in rewrite_lstm

* clang format

* fixed another bug

* refine two operator names

* clang format

* refine file names

* fix cppcheck error

* clang format

* fix cppcheck error

* clang format

* fix cppcheck error

* fixed review comments

* clang format

* add unit tests

* clang format

* add unit tests

* clang format

* refine unit tests for better coverage

* clang format

* fixed a bug

* fix cppcheck error

* fix review comments

* clang format

* rename two operators according to review comments

* clang format

* fix review comments

* clang format

* fix review comments

* clang format

* fix review comments

* fix a cppcheck error

* clang format

* fix review comments

* clang format
Co-authored-by: Shucai Xiao <scxiao@prj47-rack-99.local.lan>
Co-authored-by: mvermeulen <5479696+mvermeulen@users.noreply.github.com>

* Add decompose pass

* Add decompose test

* Formatting

* Add remap

* Formatting

* Add compute method for dot

* Formatting

* Add finder for horizontal fusion

* Formatting

* Formatting

* Reuse predicate

* Add gemm fusions

* Formatting

* Add some fixes for convolution

* Formatting

* Fix shape tests

* Formatting

* Reuse axis equal

* Add initial split fusion

* Formatting

* Update offset

* Workaround outputs that cant accept nonstandard shapes

* Formatting

* Add check for split concat

* Formatting

* Add missing headers

* Formatting

* Add tests

* Formatting

* Add more testing

* Formatting

* Fix when there is duplicate splits in inputs

* Formatting

* Fix mismatch iterators

* Add tests for dot fusions

* Formatting

* Add test for convolution

* Formatting

* Fix tidy issues

* Add more tests

* Formatting

* Ignore build directory for codecov

* Add test for groups

* Formatting

* Add more tests for groups

* Formatting

* Add test for missing end slice

* Add newline

* Remove unused function

* Add support for when beta is not 1

* Formatting

* Add test for scalar

* Add one more scalar test
Co-authored-by: mvermeulen <5479696+mvermeulen@users.noreply.github.com>

* Add compiler options

* Add copy operators

* Formatting

* Use run_passes in tests

* Formatting

* Use run_pass in schedule test

* Formatting

* Add compile_options to get_passes in target

* Formatting

* Offload copy option

* Formatting

* Copy using pinned memory

* Formatting

* Improve performance of gpu copying

* Formatting

* Dont copy

* Formatting

* Always make an extra copy

* Formatting

* Remove unused write op

* Add missing include

* Remove copy_to_gpu function in python api

* Make offload copy disabled by default on C++

* Formatting

* Fix tidy issues

* Formatting

* Fix namespace

* Fix python tests

* Turn clang format off since its broken

* Fix compile error on gcc 5

* Remove commented code

* Fix bug in eliminate_concat

* Formatting

* Skip context_free operators

* Formatting

* Fix unit test

* Formatting

* Enable scheduler for 1 stream

* Formatting

* Improve performance of sorting

* Formatting

* Adjust the weight calculation

* Formatting

* Simplify formula

* Formatting

* Avoid division by zero

* Fix scheduler test

* Check for either 1 or 2

* Check for waits when order may change

* Formatting

add a pass to resolve the problem that hip_allocation shape is different from instruction output shape.

changed the eliminate_contiguous pass to skip the reshape operator, so onnx file exported from lstm operator can work correctly in the bidirectional case.