GitLab

* init reverseOp branch: ref op + ref test. WIP

* first passing basic test

* cleanup

* additional axis implementation

* additional test

* ref op implementation vec to int for axis

* ref op test change for axis

* initial gpu files and test

* updates to implementation and test

* fixed some issues

* clang format

* cleanup

* formatting

* removing comments

* changes to parse_slice.cpp debug copy

* cleanup + additional axis  for reverse instruction

* formatting

* remove local size, back to default

* update tests: replace with std functions

* multiple axis for reverse op

* fix a build error

* clang format

* changes to parse_slice.cpp debug copy

* cleanup + additional axis  for reverse instruction

* formatting

* axes update to parse slice

* typo

* more tests

* fix a bug for the reverse device function

* clang format

* fix a bug

* clang format

* ref test updates, multiaxis

* formatting

* formatting, cleanup bool op

* casting for tidy warning

* tidy fix

* remove bool, add steps, check only negative axis

* clang-format

* step op for parse slice

* cleanup & format

* missing axis for logsoftmax_nonstd_input_test

* updated onnx file for logsoftmax_nonstd_input_test

* updates to parse slice. tests for slice+reverse, slice+step+reverse

* removing tests for slice+step+reverse as step requires normalization, will move it to other branch. removed related lines and tests

* duplicate test removal

* some refinement of the code

* clang format

* undefined behavior fix

* undef behavior v2

* formatting

* formatting & updates

* change to parse slice

* update to parse_slice for undef/asan + test update

* formatting

* remove header, no if

* assertions + change the loop from axis to steps for logsoftmax test segfault
Co-authored-by: Shucai Xiao <Shucai.Xiao@amd.com>
Co-authored-by: mvermeulen <5479696+mvermeulen@users.noreply.github.com>

* Add optional header

* Formatting

* Use optional in the matcher

* Foramtting

* Remove program from tests

* Formatting

* Dont bind or match non-local variables

* Formatting

* Fix gcc 5 error

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

* alternative impl

* formatting

* add gpu pass to insert pad

* formatting

* update onnx test, still need cleanup

* formatting

* update tf_test

* modify existing tests

* formatting

* remove print

* code cleanup

* formatting

* code cleanup

* formatting

* fix tidy and cppcheck

* remove variable

* add test

* formatting

* add test and address comments

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

* Enable libstdc++ debug mode

* Add is_end function

* Compare addresses in a map or set

* Formatting

* Check end

* Fix comparision of instruction_ref

* Formatting

* Some more iterator fixes

* Formatting

* Fix assert

* Fix invalid iterators

* Fix debug print in program

* Remove debug flag for now

* Set correct bool type
Co-authored-by: mvermeulen <5479696+mvermeulen@users.noreply.github.com>

* init reverseOp branch: ref op + ref test. WIP

* first passing basic test

* cleanup

* additional axis implementation

* additional test

* ref op implementation vec to int for axis

* ref op test change for axis

* initial gpu files and test

* updates to implementation and test

* fixed some issues

* clang format

* cleanup

* formatting

* removing comments

* remove local size, back to default

* update tests: replace with std functions

* multiple axis for reverse op

* fix a build error

* clang format

* more tests

* fix a bug for the reverse device function

* clang format

* fix a bug

* clang format

* ref test updates, multiaxis

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

* changes for CPP mnist example for cpu bug

* formatting

* one liner for input parameter

* generalizing input name

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

* Skip extensions on python 2.7

* Make macro instead of function

* Fix prefix and suffix for 2.7 lib

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

Bumps [tensorflow](https://github.com/tensorflow/tensorflow) from 2.4.0 to 2.5.0.
- [Release notes](https://github.com/tensorflow/tensorflow/releases)
- [Changelog](https://github.com/tensorflow/tensorflow/blob/master/RELEASE.md)
- [Commits](https://github.com/tensorflow/tensorflow/compare/v2.4.0...v2.5.0

)
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Cagri Eryilmaz <63118943+cagery@users.noreply.github.com>
Co-authored-by: mvermeulen <5479696+mvermeulen@users.noreply.github.com>

* add the operator step

* clang formatJ

* add unit tests

* clang format

* add more unit test for step op

* clang format

* add more unit tests

* clang format

* fix review comments

* clang format

* rename two unit tests
Co-authored-by: Paul Fultz II <pfultz2@yahoo.com>

* Add rbuild.ini file

* Skip rbuild step

* Use rbuild for gh runners

* Update ini file

* Invalidate cache

* Use full path for ccache

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

* Add timing to trace eval

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

* backup implementation of resize enhancement

* clang format

* code backup for the resize

* clang format

* fix build error for resize operator

* clang format

* tmp code backup

* clang format

* remove changes in parse_resize

* remove unnecessary changes

* clang format

* add unit test for the bug

* clang format

* remove print code

* remove a semi-colon

* clang format

* fix a tidy error

* fix review comments

* clang format
Co-authored-by: Paul Fultz II <pfultz2@yahoo.com>
Co-authored-by: mvermeulen <5479696+mvermeulen@users.noreply.github.com>

* rename merge_from to merge_to

* refine comments

* code backup

* clang format

* The first version that can reduce scratch memory usage

* code backup

* clang format

* code backup

* clang format

* fixed a bug related to removing gemm copy

* clang format

* code backup

* clang format

* fix review comments

* clang format

* fix unit test failure

* code backup

* clang format

* code base for further investigation

* code with both the forward and backward approach to compute the conflict table

* clang format

* clang format

* backup changes

* remove unnecessary file

* remove unnecessary code

* code backup

* clang format

* code backup

* clang format'

* fix a bug in the code

* clang format

* code backup

* clang format

* remove unused code

* remove unused code

* rename some functions

* remove print code

* code backup

* add dominator to scheduling

* add dominator algorithm to remove unnecessary conflicts

* Remove comment

* Use erase_if instead

* Formatting

* Code clean up:

* Formatting

* Add dominator info class

* Formatting

* Add dom_info

* Formatting

* Add test case and fix some bugs

* Formatting

* Add unit test for scheduler

* Formatting

* Use index map instead of distance

* Formatting

* Add memory coloring test

* Check for conflict in memory coloring

* Formatting

* Use 1 stream by default

* Update to use modules

* Formatting

* Skip live on entry check

* Formatting

* Formatting

* Fix tidy warning

* Fix tidy warning

* Formatting

* Add nolint

* Use C++17 to build everything when using clang

* Remove input names

* Formatting

* Remove input names

* Keep order of params

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

* Create lazy range

* Formatting

* Use lazy iota

* upgrade protobuf to 3.16.0 to be compatible with onnxruntime

* change the link flag to fix a protobuf version conflict with ort

* Update pass manager to get modules after every pass

* Add program overload for module

* Formatting

* Hash modules for quicker lookup of modules

* Bump file version

* Add methods to remove modules

* Formatting

* Eliminate unused modules

* Formatting

* Fix test errors

* Foramtting

* Fix tidy issues

* Use hipStreamSynchronize instead of device sync

* Formatting

* Suppress FPs

* Use sync_stream instead of device

* Formatting

* Fix python bindings

* Formatting

* update to readme for pip3 upgrade, needed for tf2.4. requirement file change. initial commit for bert example update

* remove tokenization.py file

* added tokenizers and bertwordpiecetokenizer to main file

* added tokenizers to requirements file

* changes to run_onnx_squad after importing tokenizers module, to replace py file

* additional post processing tokenizer change in run_onnx_squad.py

* changes to notebook after tokenizers

* cleanup notebook output cells

* typo in readme

* formatting on py file
Co-authored-by: mvermeulen <5479696+mvermeulen@users.noreply.github.com>

* Hash instruction in module for faster checking if instruction is in module

* Formatting

* Fix cppcheck error
Co-authored-by: Shucai Xiao <shucai@gmail.com>
Co-authored-by: mvermeulen <5479696+mvermeulen@users.noreply.github.com>

* Remove unused data types

* Formatting

* Reduce types generated for hip kernels

* Formatting

* Fix onnx tests

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

* MLIR MIOpen Dialect integration (phase 1) (#768)

* Added Findmlir.cmake (using environment variables to import)

* Added mlir_conv pass to GPU target

  * Apply to any gpu::convolution if supported by MLIR

  * Call MLIR C-API to generate iGEMM kernel with configuration from gpu::convolution

  * Capture binary in dictionary for matching convolutions

  * Build a code_object_op with the binary and execution dimensions

  * Substitute for the gpu::convolution

* Changed the parameters for the code_object to reflect the generated MLIR kernel

* Expanded out MemRefDescriptor fields in param list

* Also updated for MLIR C-API changes

* * fixed global_size calculation

* MLIR MIOpen Dialect integration (phase 1) (#768)

* Added Findmlir.cmake (using environment variables to import)

* Added mlir_conv pass to GPU target

  * Apply to any gpu::convolution if supported by MLIR

  * Call MLIR C-API to generate iGEMM kernel with configuration from gpu::convolution

  * Capture binary in dictionary for matching convolutions

  * Build a code_object_op with the binary and execution dimensions

  * Substitute for the gpu::convolution

* Changed the parameters for the code_object to reflect the generated MLIR kernel

* Expanded out MemRefDescriptor fields in param list

* Also updated for MLIR C-API changes

* * Added command line option: --enable_mlir

* * fixed command line switch

* updated for new MLIR API changes

* * Added cget llvm-project-mlir to import MIIR API libraries into Dockerfile
  * removed cmake Findmlir

* updated for changes in MIIR C-API

* * updated CMakeLists.txt to allow disable of MLIR import

* fixed memory leaks and removed copies

* updated for 5D memrefs

* * formatting

* * fixed review comments

* * fixed merge issues

* hip gcnDeviceName now includes specifiers at the end
  * use major/minor values instead

* * disable MLIR by default

* * removed command-line switch --enable-mlir

* * fix unused when MLIR disabled

* * enable jenkins enable/test MLIR

* * format

* * fixed clang-tidy

* * added new type
Co-authored-by: Paul Fultz II <pfultz2@yahoo.com>
Co-authored-by: mvermeulen <5479696+mvermeulen@users.noreply.github.com>

One line change in the readme file for the wrong file name.
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>

* Add scan struct; add initial tests; initial algorithm by cases; refactor into one algorithm; clean up code

* Rename; restructure; begin adding additional attributes

* refactor to use shape_for_each; temporarily drop reverse mode

* Add back reverse mode with shape_for_each_reverse; update tests; add axis bounds check

* Begin adding to onnx parser

* Add to onnx parser

* Fix onnx test

* Fix CI warnings

* Update algorithm to use slice+par_for; update gen_onnx; remove .o files; remove redundant axis normalizing

* Add exclusive mode

* Add reverse mode

* Remove .pyc file

* Fix warning

* Remove shape_for_each_reverse; clean up pointer usage for exclusive cases

* Remove unused variable

* Fix onnx test

* Add test case to op_shape_test

* Formatting

* Formatting

* Fix tidy warning

* Formatting

* Formatting

* Formatting

* Increase code coverage

* Formatting

* refine the script for creating the cumsum onnx file

* Alphabetize includes for operators.hpp

* Revise onnx test

* Remove redundant bounds check

* Formatting and style

* Alphabetize tests

* Remove duplicate tests from merge

* Fix tidy warning for sub_test
Co-authored-by: Shucai Xiao <Shucai.Xiao@amd.com>
Co-authored-by: mvermeulen <5479696+mvermeulen@users.noreply.github.com>

* add support for axes inputs for sequeeze/unsqueeze/reduce_sum

* clang format

* fix build problems

* backup code changes

* clang format

* fix a bug in parsing quantizelinear operator

* clang format

* fix a cppcheck error

* disable different versions of unit tests for different onnx version

* clang format

* upgrade onnx to 1.8

* update onnx to 1.8.1

* disable two more real models

* clang format

* fix review comments

* fix the function of assign axes in parsing the squeeze operator

* add unit tests and fix a bug

* clang format

* fix review comments

* clang format

* fix a build error

* backup code changes

* clang format

* add more unit tests and add parsing opset version

* clang format

* fix cppcheck error

* adding installing the onnx package

* resolve no protobuf compiler

* fix cppcheck error

* add unit tests for more code coverage

* clang format

* try a comment in jenkins build

* include the install onnnx line

* code backup

* reorder the dependenciesd installed

* refine dockerfile

* fix review comments

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

* code backup

* clang format

* add a matcher related to the special resize case for optimization

* clang format

* code backup

* clang format

* code backup

* remove unnecessary code

* add optimization for the where op

* clang format

* fix cppcheck error

* add a unit test for optimize resize

* clang format

* remove unnecessary header include

* code backup

* clang format

* add unit tests for optimizing resize

* clang format

* add more unit test for optimizing where op

* clang format

* remove unnecessary code

* add one more optimzation to remove contiguous

* clang format

* add a pointwise requirement

* clang format

* fix cppcheck error

* add one more unit test

* fixed a bug

* clang format

* remove unnecessary code

* clang format

* fix a build error

* fix review comments

* clang format

* fix a review comments

* clang format

* code refinement

* clang format

* refine more code

* refine more code

* fix a bug related to reshape_cont optimization

* clang format

* fix a review comment

* removed an unnecessary comment

* refine code according to comments

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

* Add eliminate_data_type pass

* Formatting

* Auto convert quant ops

* Formatting

* Flip the order of decompose

* Compute max size differently

* Formatting

* Clamp values in convert

* Formatting

* Fix loss of precision in reduce

* Formatting

* Fix bugs in reduction

* Fix accumulator type in reference softmax implementation

* Formatting

* Update convert test

* Remove unused variables

* Remove unnecessary quant_dot check

* Formatting

* Add tests

* Formatting

* Remove unused code

* Remove duplicate ops

* Remove blaze dependency

* Use set since shape::type_t is no hashable on gcc 5

* Formatting

* Add dnnl binary op

* Formatting

* Add binary and eltwise

* Formatting

* Add softmax

* Formatting

* Remove unused operators

* Add missing files

* Formatting

* Add lrn

* Formatting

* Add deconvolution

* Formatting

* Change allocate default

* Add reorder

* Formatting

* Add reductions

* Formatting

* Sort lines

* Change literals in another loop

* Add pow operator

* Formatting

* Add pow operator

* Formatting

* Make sure shapes are packed

* Allow broadcasted inputs

* Remove unused operators

* Simplify functions

* Remove softmax

* Add sub and erf functions

* Formatting

* Fix bug

* Formatting

* Improve parallism

* Formatting

* Allow multiple batch dimensions

* Formatting

* Move literal transforms out of lowering

* Formatting

* Add gather operator

* Sort lines

* Add early exit for carry

* Formatting

* Add missing concat

* Rename macro

* Fix deep nesting

* Formatting

* Fix cppcheck issues

* Remov else

* Move attribute to typedef

* Formatting

* Disable maybe-uninitialized warning since its broken on gcc

* Add constexpr default constructor

* Formatting

* Fix compiler warnings

* Fix adjust_allocation test

* Add layernorm matcher

* Add gelu_erf matcher

* Formatting

* Add gelu_tanh matcher

* Formatting

* Remove match namespace

* Formatting

* Use matcher instead of string

* Formatting

* Add fusions

* Formatting

* Add post op field

* Formatting

* Make post_ops serializable

* Formatting

* Add eltwise fusions

* Formatting

* Fix null conversions

* Formatting

* Add fuse_ops source files

* Formatting

* Set binary post op index correctly

* Formatting

* Fix serialization bugs

* Check if used once

* Formatting

* Fix error in get_primitive_attr

* Formatting

* Add compile function

* Formatting

* Limit fusions

* Formatting

* Disable with env variable instead of using compile arg

* Formatting

* Fix implicit conversion to bool

* Declar on seperate lines

* Formatting

* Fix cppcheck issues

* Fix ICE in pack_join

* Formatting

* Use const ref

* Make enum hashable

* Formatting

* Add explicit this

* Fix merge issues

* Fix dangling ref

* Formatting

* Add test for compile

* Formatting

* Add more value tests

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

* initial push for super resolution: notebook + image + requirements

* first version of working notebook

* cleaning up notebook

* added super resolution to main examples readme file

* readme file for super resolution example

* torch is not needed, removed from requirements

* removed not-needed imports and code from notebook

* update to super resolution readme

* New input image. Added PSNR. Related code changes in notebook

* readme file update for step-by-step instructions

* opencv requirement moved to requirements file. updated notebook accordingly

* update to main examples readme file

* typo in readme
Co-authored-by: kahmed10 <15948690+kahmed10@users.noreply.github.com>
Co-authored-by: mvermeulen <5479696+mvermeulen@users.noreply.github.com>

* initial push for bert-squad example

* migraphx and ort implementation + json input sample

* notebook draft

* first working example for bert-squad with migraphx

* cleaning up ORT example

* updated inputs file, 3 questions

* Simple and rather ugly readme. Requirements file

* formatting

* updates to readme file

* Update README.md

* Update README.md

* cleanup

* no need timer function for now

* jupyter notebook example

* updates to notebook file

* readme flow change

* typo in notebook

* another example input file

* cleanup

* benchmark file

* formatting

* bert update to examples readme file

* formatting

* missed another formatting

* removed path workaround from .py and notebook

* renaming requirements file to requirements_bertsquad.txt

* no need for bench and ort files

* reflecting requirement file name change in notebook

* removing duplicates of import json

* formatting
Co-authored-by: root <root@rocm-framework-1.amd.com>
Co-authored-by: kahmed10 <15948690+kahmed10@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

* Remove .o files

* change to readme for python import

* added PYTHONPATH choice for using python module

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

* Add version command and option to driver to print migraphx version being used

* Address review comments

* Address review comments

* Fix leftover mistake

* Add newline to version.h.in

* Address review comments

* Fix tidy warning

* Remove unneccesary line from cmake file

* Formatting; remove .o files
Co-authored-by: mvermeulen <5479696+mvermeulen@users.noreply.github.com>

* Fix tidy warnings for 4.1

* Formatting

* Upgrade to 4.1 in docker

* Remove hcc build and enable ubsan on clang debug

* Add missing openmp package

* Construct directly

* Construct directly

* Upgrade rocm-cmake version