GitLab

First try to compile a call to rocblas-beta API; doesn't compile.  Note the update to rocm version in Dockerfile.  May require a new Docker image build.

Improves performance for 4/6 GEMMs used by huggingface BERT models with batch_size>1 by using a non-batched rocBLAS call for GEMMs where the B input has a broadcasted batch dimension.
The four verify tests added reflect the actual configurations used by bert-base-cased, with varied batch sizes.

Also adds a matcher to simplify_reshapes to move multibroadcasts after concats.

Using not and or improves readability. The cppcheck rule will help ensure we are doing it consistently.

This will rewrite dot operators like X(Y + b) to XY + Xb when b is constant as we can fold the add away.
This improves handling pointwise with broadcasted operators, this helps improves const propagation.
Improve gemm fusion with a mul_add
Improve support for broadcast shapes in gemm

Updated each source file in the repo with the existing license.

* Improve applicable batched gemms for bert

better performance doing it this way

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

* add a flag to indicate int8x4 input format

* clang format

* code backup

* clang format

* code backup

* clang format

* code backup

* clang format

* code backup

* clang format

* code backup

* clang format

* remove log info

* remove unnecessary changes

* fix cppcheck error

* add unit tests to have more code coverage

* clang format

* add debug info

* remove log info

* fix cppcheck error

* clang format

* clang format

* add one more unit tests for more scenarios

* fix cppcheck error

* clang format

* fix review comments

* clang format

* rename p to m

* fix review comments

* refine unit tests

* clang format

* refine unit tests and fixed a bug

* clang format

* fix build error related to rocm4.2

* fix a bug related to alpha and beta

* refine two unit tests related to int8_gemm

* fix cppcheck error

* refine unit test to pass on mi100

* add unit test for packing int8 args

* clang format

* change unit tests back

* disable some unit tests for gpu

* clang format

* refine unit tests to run on mi100

* clang format

* refine unit tests

* refine unit tests

* clang format

* change back a unit test
Co-authored-by: mvermeulen <5479696+mvermeulen@users.noreply.github.com>

* Add definitions for all pointwise operators

* Formatting

* Add cpp generator class

* Formatting

* Move compilation to core

* Formatting

* Add clock to tmp name

* Add dynamic loader

* Formatting

* Add tests for code gen

* Formatting

* Add test for literals

* Formatting

* Use with_char

* Add missing header

* Fix mismerge

* Ignore tidy warning

* Fxx gcc 5 errors

* Apply fixits

* Skip signed bitwise of status

* Remove unused parameters

* Explicitly add c++14 flag

* Fix tidy warning

* Add tuple type to shape class

* Formatting

* Make data member private

* Formatting

* Add sub arguments

* Formatting

* Trun clang format off

* Disable clang-format

* Improve visiting tuples

* Formatting

* Add more argument tests

* Formatting

* Handle tuple in load

* Formatting

* Remove .o files

* Add tuple type to api

* Formatting

* Fix tidy warnings

* Fix tidy warnings

* Add a test for share method

* Formatting

* Add a test cpp_type

* Suppress tidy warning
Co-authored-by: Shucai Xiao <Shucai.Xiao@amd.com>

* fix the flag in rocblas api for int8 data type

* used different flag for different rocblas versions

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

* Make global variables const

* Tidy fixes

* Disable some lints

* Formatting

* Fix tidy const

* Formatting

* Add missing const keywords

* Formatting

* More fixes

* Fix remaining tidy issues

* Formatting

* Fix rocblas function call

* Formatting

* Fix nodiscard warnings

* Formatting

* Use named parameters

* Remove overload

* Add overload

* Remove noncps

* Use named param for node

* Add auto register header

* Use named parameters

* Refactor jenkinsfile

* Fix shadow

* Add missing body variable

* Add more const methods

* Add hip-clang docker builds

* Remove comments

* Add clang-format

* Add more const

* Formatting

* Rename stage

* Disable check

* Add another const

* Add python 2 dev packages

* Add sphinx to dockerfile

* add bool type

* code backup

* code backup

* clang format

* fix build warnings

* clang format

* add the equal operator

* add the equal operator

* clang format

* remove unnecessary code

* refine unit tests

* clang format

* fix review comments and a bug

* clang format

* additional changes

* clang format

* fix cppcheck error

* add bool type in c api

* fix cppcheck error

* fix review comments

* fix cppcheck error

* fix a build error related to gcc

* fix cppcheck error

* fix cppcheck error

* added the equal operator to register list

* add parsing boolean type

* clang format

* fix bool type issue for python output

* clang format

* add support for automatic multibroadcast of the equal operator

* additional unit tests for more code coverage

* clang format

* missing an onnx file
Co-authored-by: Paul Fultz II <pfultz2@yahoo.com>

* Remove extra copy in gemm

* combine rocblas gemm call

* clang format

* fix a bug in calling rocblas function

* clang format'

* backup of temporary changes

* clang format

* unify the gemm call to avoid multiple gpu implemantation

* clang format

* remove unnecessary code

* backup temp changes

* clang format

* fix cppcheck error

* code backup

* clang format

* remove unnecessary synchronization function

* clang format

* fix bugs

* clang format

* more optimization related to gemm

* clang format

* code cleanup

* implementation that can achieves better performance

* clang format

* temp changes to try performance

* clang format

* revert to previous commits

* fixed review comments

* clang format

* fix review comments