Commits · e2cbb01eb182c4bbf67fff88078b6aaac8e2d091 · gaoqiong / MIGraphX

11 Sep, 2020 1 commit
- Add support for constructing value from enum (#632) · e2cbb01e
  Paul Fultz II authored Sep 11, 2020
```
* Add support for constructing value from enum

* Formatting
```
  e2cbb01e
10 Sep, 2020 1 commit

Add load/save function for program (#623) · 63c5582a

Paul Fultz II authored Sep 09, 2020



* 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>

63c5582a

31 Aug, 2020 1 commit

Pooling ceil mode (#615) · 9dabe26b

Shucai Xiao authored Aug 31, 2020



* support pooling ceil_mode

* clang format

* add unit test for pooling ceil mode

* clang format

* fix review comments

* clang format

* add more unit tests and fixed a bug in cpu pooling implementation

* clang format

* add one more unit test

* clang format

* fix cppcheck error

* fix cppcheck error

* fix cppcheck error

* fix review comments

* clang format

* remove the padding_mode attribute in pooling

* clang format

* clang format

* fix review comments

* clang format

* fix a cppcheck error

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

9dabe26b

27 Aug, 2020 2 commits

Context serialization (#607) · 6e1f9f20

Shucai Xiao authored Aug 27, 2020



* Add initial serialization

* Formatting

* Add unit tests

* Formatting

* Add tests for serialization

* Formatting

* Use or not and

* Add value test

* Formatting

* Add more tests

* Add shape serialization

* Formatting

* Add serializtion for literal and argument

* Formatting

* Add from and to value to operatation

* Formatting

* Serialize empty types

* Formatting

* Tidy fixes

* Formatting

* Fix tidy issues

* Formatting

* Reformat value type macro

* Formatting

* Handle enum types

* Formatting

* Use const ref

* Update

* Add tests for to_value/from_value

* Formatting

* code backup

* clang format

* code backup

* clang format

* code backup

* clang format

* remove the from/to_value method for the generate context struct

* clang format

* code backup

* Dont print literal data in hip_copy_literal

* clang format

* add unit test to have better coverage

* remove unnecessary code

* remove unnecessary code

* fix review comments

* clang format

* fix review comments
Co-authored-by: Paul <pfultz2@yahoo.com>
Co-authored-by: mvermeulen <5479696+mvermeulen@users.noreply.github.com>

6e1f9f20

Bool type and equal operator (#603) · 59b80d4e

Shucai Xiao authored Aug 27, 2020



* 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>

59b80d4e

26 Aug, 2020 1 commit

Add C++ ability to construct operators by name (#616) · 002eb4e2

Paul Fultz II authored Aug 26, 2020



* Add make_op function

* Formatting

* Add more values

* Formatting

* Remove templates parse_conv functions

* Formatting

* Remove mat_mul template

* Formatting

* Reduce header includes

* Fix compiling for gpu

* Formatting

* Use make_op in lowering

* Formatting

* Sort lines

* Formatting

* Add more tests

* Formatting

* Fix tidy error

* Formatting

* Add const refs

* Add explicit this

* Add more const refs

* Sort the program

* Remove commented out code

* Formatting

* Infer gpu prefix

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

002eb4e2

25 Aug, 2020 1 commit

Improve layernorm performance (#613) · 56b3bf58

Paul Fultz II authored Aug 25, 2020

* 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

56b3bf58

19 Aug, 2020 1 commit

Add to_value/from_value to operation class (#605) · d1caaaa1

Paul Fultz II authored Aug 19, 2020

* Add initial serialization

* Formatting

* Add unit tests

* Formatting

* Add tests for serialization

* Formatting

* Use or not and

* Add value test

* Formatting

* Add more tests

* Add shape serialization

* Formatting

* Add serializtion for literal and argument

* Formatting

* Add from and to value to operatation

* Formatting

* Serialize empty types

* Formatting

* Tidy fixes

* Formatting

* Fix tidy issues

* Formatting

* Reformat value type macro

* Formatting

* Handle enum types

* Formatting

* Use const ref

* Update

* Add tests for to_value/from_value

* Formatting

* Add more tests

* Rewrite test to avoid redundant assignment

d1caaaa1

18 Aug, 2020 1 commit

Paul Fultz II authored Aug 18, 2020

* Register ops for main migraphx

* Formatting

* Register cpu ops

* Formatting

* Show list of operators in the driver

* Formatting

* Simplify regiter

* Try to register gpu ops

* Fix compiler errors

* Register rest of the gpu operators

* Add some tests

* Formatting

* Fix gcc compiler warnings

* Formatting

* Fix tidy warnings

* Fix compile error

* Use correct op name

* Register layer norm

* Use const ref

* Make run const

e8be8548

13 Aug, 2020 2 commits

integrate onnx backend test suit to migraphx (#574) · d612e976

Shucai Xiao authored Aug 13, 2020



* initial progress

* formatting

* add pooling changes

* formatting

* change eliminate_pad

* formatting

* rename var

* fomratting

* update op shape test and compute

* formatting

* revert conv constructor

* formatting

* change initializer

* formatting

* fix tidy

* change quant conv and shape check

* add tests and fixes

* formatting

* fix type

* fix conv test

* formatting

* add pooling and bn tests

* formatting

* add inconsistent attr tests

* fix padding issue

* formatting

* progress on 1d to 2d

* formatting

* change compute and compile functions

* formatting

* fix duplicate

* fix conflict

* fix issue with 1d conv

* formatting

* add check for 3d limit

* rename function

* formatting

* update to MIOPen 2.3

* add support for nd pooling

* formatting

* test miopen 2.4

* change function name

* rename functions

* formatting

* add op_shape test

* add gpu ops tests

* formatting

* initial progress

* formatting

* add pkg-config

* add to support asymmetric padding of averagepool

* clang format

* fix bug for average pooling

* clang format

* fix a bug

* add unit tests for the asymmetric padding of averagepool

* clang format

* change functions

* formatting

* additional code refinement

* clang format

* check existing tests

* formatting

* change to copy_backward

* formatting

* change for loop to transform

* formatting

* add tests

* formatting

* remove comment

* add more tests

* remove an optimization for pooling

* clang format

* add and fix unit tests

* clang format

* update gpu miopen calls

* formatting

* initial progress

* add cpu impl and tests

* formatting

* add NOLINT

* add 3d test

* formatting

* add more op_shape tests

* test diff miopen version

* add submodule onnx

* add pooling shape tests

* fix error msg

* add onnx_test_backend

* reorganize python code

* temp disable test

* fix cppcheck error

* fix cppcheck error

* code backup

* add support device choice

* refine onnx backend test

* revert to miopen 2.4

* fix review comments

* fix review comments

* clang format

* fixed review comments

* clang format

* fix cppcheck error

* copy onnx_backend_test to dest when building

* add testdata folder

* fix bounds

* formatting

* code backup

* code backup

* remove unnecessary file

* fix various bugs

* remove unnecessary changes

* remove unnecessary submodule

* remove unnecessary lines

* fix algorithm

* formatting

* refine onnx backend unit tests

* pin numpy version

* fix build issue

* fixed a filename to be copied

* add the onnx dependency in docker image

* ensure results are copied back correctly

* specify onnx version

* update excluded tests

* remove unnecessary log info

* turn on more unit tests

* restrict onnx backend test to python 3.x

* clang format

* refine retrieving the input parameters

* clang format

* fix program input parameter names

* clang format

* avoid running onnx test in python 2.x

* fix cppcheck error

* fix python2.7 backend unit tests error

* clang format

* resolve the issue of ensure data copy to be completed

* clang format

* fix review comments

* fix onnx backend unit test error

* another change to make onnx backend test pass

* clang format

* fix onnx backend test error

* clang format

* disable onnx backend test to try

* build try

* update Dockerfile to try onnx backend test

* remove unnecessary code

* fix a bug in copying program

* clang format

* update dockerfile to include onnx

* fix review comments

* add the pytest module to the container

* exclude real model to avoid to be downloaded

* resolve the sync device for data copy from gpu to cpu

* clang format

* fix review comments

* clang format

* move sync_device after memory_coloring
Co-authored-by: Khalique <15948690+kahmed10@users.noreply.github.com>
Co-authored-by: mvermeulen <5479696+mvermeulen@users.noreply.github.com>
Co-authored-by: Paul Fultz II <pfultz2@yahoo.com>

d612e976

Add msgpack serialization (#596) · 37fbabf5

Paul Fultz II authored Aug 12, 2020



* Add msgpack serialization

* Formatting

* Fix compiler errors on gcc

* Remove redundant initialization

* Use type to fix compile error with gcc 5

* Formatting

* Add more tests

* Change to migraphx throw

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

37fbabf5

12 Aug, 2020 1 commit

Add dimensionality reduction to device functions (#587) · 63563da2

Paul Fultz II authored Aug 12, 2020



* Add reduce dims

* Formatting

* Reduce dims on the gpu

* Formatting

* Fix tidy issues

* Convert to assert

* Reduce dims for contiguous

* Formatting

* Remove move

* Fix arguments used

* Formatting

* Fix warnings

* Formatting
Co-authored-by: Shucai Xiao <shucai.xiao@amd.com>

63563da2

10 Aug, 2020 1 commit

Convert value to json (#592) · a5648d9c

Shucai Xiao authored Aug 10, 2020



* Add initial serialization

* Formatting

* Add unit tests

* Formatting

* Add tests for serialization

* Formatting

* Use or not and

* Add value test

* Formatting

* Add more tests

* Add shape serialization

* Formatting

* Add serializtion for literal and argument

* Formatting

* Serialize empty types

* Formatting

* Tidy fixes

* Formatting

* Fix tidy issues

* Formatting

* Reformat value type macro

* Formatting

* Handle enum types

* Formatting

* Add float_equal

* Fix tidy issue

* Use declval for better sfinae

* Formatting

* backup code change

* Fix maro name

* Add more test cases to improve coverage

* Formatting

* Add more tests

* Formatting

* Fix assertion

* code backup

* clang format

* Fix bug with keyless assignment

* Formatting

* add implementation of converting json to migraphx::value

* clang format

* code backup

* clang format

* code backup

* clang format

* code backup

* code refactor

* add unit tests

* separate json conversion from serialization

* clang format

* add the missing files

* refine code

* clang format

* fix cppcheck error

* clang format

* fix review comments

* clang format

* code backup

* fix cppcheck error

* refine an implementation

* clang format

* fix review comments

* clang format

* fix review comments and add more unit tests

* clang format

* code backup to try

* fix review comments and add more unit tests

* clang format

* some refinement

* clang format

* fix review comments

* remove unnecessary code

* add assignment of null
Co-authored-by: Paul <pfultz2@yahoo.com>
Co-authored-by: mvermeulen <5479696+mvermeulen@users.noreply.github.com>

a5648d9c

29 Jul, 2020 1 commit

Add serialization framework (#577) · 9c3c3c5f

Paul Fultz II authored Jul 29, 2020



* Add initial serialization

* Formatting

* Add unit tests

* Formatting

* Add tests for serialization

* Formatting

* Use or not and

* Add value test

* Formatting

* Add more tests

* Add shape serialization

* Formatting

* Add serializtion for literal and argument

* Formatting

* Serialize empty types

* Formatting

* Tidy fixes

* Formatting

* Fix tidy issues

* Formatting

* Reformat value type macro

* Formatting

* Handle enum types

* Formatting

* Add float_equal

* Fix tidy issue

* Use declval for better sfinae

* Formatting

* Fix maro name

* Add more test cases to improve coverage

* Formatting

* Add more tests

* Formatting

* Fix assertion

* Fix bug with keyless assignment

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

9c3c3c5f

22 Jul, 2020 1 commit

Gelu matcher fix (#583) · 49a31c65

kahmed10 authored Jul 22, 2020



* fix matcher

* formatting

* change has_value function

* formatting

* check for literal in matcher
Co-authored-by: mvermeulen <5479696+mvermeulen@users.noreply.github.com>

49a31c65

15 Jul, 2020 1 commit

Averagepooling asymetric pading (#553) · dced4d4b

Shucai Xiao authored Jul 15, 2020



* initial progress

* formatting

* add pooling changes

* formatting

* change eliminate_pad

* formatting

* rename var

* fomratting

* update op shape test and compute

* formatting

* revert conv constructor

* formatting

* change initializer

* formatting

* fix tidy

* change quant conv and shape check

* add tests and fixes

* formatting

* fix type

* fix conv test

* formatting

* add pooling and bn tests

* formatting

* add inconsistent attr tests

* fix padding issue

* formatting

* progress on 1d to 2d

* formatting

* change compute and compile functions

* formatting

* fix duplicate

* fix conflict

* fix issue with 1d conv

* formatting

* add check for 3d limit

* rename function

* formatting

* update to MIOPen 2.3

* add support for nd pooling

* formatting

* test miopen 2.4

* change function name

* rename functions

* formatting

* add op_shape test

* add gpu ops tests

* formatting

* add pkg-config

* add to support asymmetric padding of averagepool

* clang format

* fix bug for average pooling

* clang format

* fix a bug

* add unit tests for the asymmetric padding of averagepool

* clang format

* change functions

* formatting

* additional code refinement

* clang format

* change to copy_backward

* formatting

* remove an optimization for pooling

* clang format

* add and fix unit tests

* clang format

* test diff miopen version

* add pooling shape tests

* temp disable test

* fix cppcheck error

* fix cppcheck error

* revert to miopen 2.4

* fix review comments

* fix review comments

* clang format

* fixed review comments

* clang format

* fix cppcheck error
Co-authored-by: Khalique <15948690+kahmed10@users.noreply.github.com>
Co-authored-by: mvermeulen <5479696+mvermeulen@users.noreply.github.com>

dced4d4b

10 Jul, 2020 1 commit

Gpu batchnorm (#564) · 70ba8213

Shucai Xiao authored Jul 10, 2020



* Initial cpu conv-nd

* Formatting

* Make index signed

* Formatting

* Assert the indices are greater than 0

* Use equal instead of lexicographical_compare

* Formatting

* change the batchnorm cpu implementation to support multiple input dimensions

* clang format

* add unit tests for cpu batch_norm nd implementation

* clang format

* support nd batchnormalization

* clang format

* add rewrite batch_norm unit tests

* clang format

* remove a unit test

* Fix tidy errors

* Formatting

* Handle different types

* Formatting

* Fix nested visits

* Formatting

* Add 3d conv test

* Formatting

* revert unnecessary changes

* remove a print line

* Fix ICE

* Formatting

* fix the per_activation mode of 2d

* clang format

* code clean up

* clang format

* add 1d and 3d gpu unit test

* clang format

* add unit test for rewrite_batchnorm

* clang format

* additional refinement

* fix review comments

* added a unit test to have more code coverage
Co-authored-by: Paul <pfultz2@yahoo.com>
Co-authored-by: mvermeulen <5479696+mvermeulen@users.noreply.github.com>

70ba8213

09 Jul, 2020 1 commit

Add conv ND for cpu (#561) · 5cc6e160

Paul Fultz II authored Jul 09, 2020



* Initial cpu conv-nd

* Formatting

* Make index signed

* Formatting

* Assert the indices are greater than 0

* Use equal instead of lexicographical_compare

* Formatting

* Fix tidy errors

* Formatting

* Handle different types

* Formatting

* Fix nested visits

* Formatting

* Add 3d conv test

* Formatting

* revert unnecessary changes

* remove a print line

* Fix ICE

* Formatting

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

5cc6e160

08 Jul, 2020 1 commit

Nd pooling gpu (#551) · d1258e80

kahmed10 authored Jul 08, 2020



* initial progress

* formatting

* add pooling changes

* formatting

* change eliminate_pad

* formatting

* rename var

* fomratting

* update op shape test and compute

* formatting

* revert conv constructor

* formatting

* change initializer

* formatting

* fix tidy

* change quant conv and shape check

* add tests and fixes

* formatting

* fix type

* fix conv test

* formatting

* add pooling and bn tests

* formatting

* add inconsistent attr tests

* fix padding issue

* formatting

* progress on 1d to 2d

* formatting

* change compute and compile functions

* formatting

* fix duplicate

* fix conflict

* fix issue with 1d conv

* formatting

* add check for 3d limit

* rename function

* formatting

* update to MIOPen 2.3

* add support for nd pooling

* formatting

* test miopen 2.4

* change function name

* rename functions

* formatting

* add op_shape test

* add gpu ops tests

* formatting

* add pkg-config

* change functions

* formatting

* change to copy_backward

* formatting

* test diff miopen version

* add pooling shape tests

* temp disable test

* revert to miopen 2.4
Co-authored-by: mvermeulen <5479696+mvermeulen@users.noreply.github.com>

d1258e80

07 Jul, 2020 1 commit

Nd deconv GPU support (#558) · a5fb837d

kahmed10 authored Jul 07, 2020



* initial progress

* formatting

* check existing tests

* formatting

* change for loop to transform

* formatting

* add tests

* formatting

* remove comment

* add more tests

* update gpu miopen calls

* formatting

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

a5fb837d

30 Jun, 2020 1 commit

Cpu batchnorm (#562) · 61cbe923

Shucai Xiao authored Jun 29, 2020



* change the batchnorm cpu implementation to support multiple input dimensions

* clang format

* add unit tests for cpu batch_norm nd implementation

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

61cbe923

29 Jun, 2020 1 commit

Nd deconv read support (#554) · 742b4b82

kahmed10 authored Jun 29, 2020



* initial progress

* formatting

* check existing tests

* formatting

* change for loop to transform

* formatting

* add tests

* formatting

* remove comment

* add more tests

* remove extra slice axes
Co-authored-by: mvermeulen <5479696+mvermeulen@users.noreply.github.com>

742b4b82

22 Jun, 2020 2 commits

Gather elements operator (#549) · dd6523c9

Shucai Xiao authored Jun 22, 2020



* 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

* add parsing the operator GatherElements

* clang format

* add onnx unit tests for the gather_elments operator

* clang format

* clang format

* remove unnecessary files

* remove unnecessary files

* add a verify onnx unit test for the gather element operator

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

dd6523c9

ND convolution GPU support (#550) · 1cc724ee

kahmed10 authored Jun 22, 2020

* initial progress

* formatting

* add pooling changes

* formatting

* change eliminate_pad

* formatting

* rename var

* fomratting

* update op shape test and compute

* formatting

* revert conv constructor

* formatting

* change initializer

* formatting

* fix tidy

* change quant conv and shape check

* add tests and fixes

* formatting

* fix type

* fix conv test

* formatting

* add pooling and bn tests

* formatting

* add inconsistent attr tests

* fix padding issue

* formatting

* progress on 1d to 2d

* formatting

* change compute and compile functions

* formatting

* fix duplicate

* fix conflict

* fix issue with 1d conv

* formatting

* add check for 3d limit

* rename function

* formatting

* rename functions

* formatting

* add op_shape test

* change functions

* formatting

* change to copy_backward

* formatting

1cc724ee

08 Jun, 2020 1 commit

Enable read support for n-dimensional ops (#537) · cb722cf9

kahmed10 authored Jun 08, 2020



* initial progress

* formatting

* add pooling changes

* formatting

* change eliminate_pad

* formatting

* rename var

* fomratting

* update op shape test and compute

* formatting

* revert conv constructor

* formatting

* change initializer

* formatting

* fix tidy

* change quant conv and shape check

* add tests and fixes

* formatting

* fix type

* fix conv test

* formatting

* add pooling and bn tests

* formatting

* add inconsistent attr tests

* fix padding issue

* formatting

* fix review comments, remove duplicate test

* formatting

* fix variable

* fix assert bug

* fix attr check

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

cb722cf9

28 May, 2020 1 commit

Fuse operators that partially match in a concat operator (#539) · 905ebd5e

Paul Fultz II authored May 28, 2020



* Fuse operators that partially match in a concat operator

* Formatting

* Remove unused matcher

* Properly calculate the output_lens

* Formatting

* Formatting

* Formatting

* Fix tidy issue
Co-authored-by: Shucai Xiao <shucai.xiao@amd.com>

905ebd5e

26 May, 2020 1 commit

Add support variable seq lens for the RNN and GRU operators (#535) · d7b8164c

Shucai Xiao authored May 26, 2020



* 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

* add an operator to simplify code

* clang format

* clang format

* fixed a bug and add unit tests

* clang format

* add more unit tests

* clang format

* add more unit tests

* clang format

* add more unit tests

* clang format

* refine a unit test

* clang format

* refine a unit test

* add more unit tests and refine some existing tests for the rnn operator improvements

* clang format

* additional changes to simplify code further

* clang format

* refine a test case to refine cppcheck error

* clang format

* fix cppcheck error

* clang format

* add more unit tests

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

d7b8164c

22 May, 2020 1 commit
- Const propogate dot operator (#534) · c41c3501
  Paul Fultz II authored May 22, 2020
```
Co-authored-by: mvermeulen <5479696+mvermeulen@users.noreply.github.com>
```
  c41c3501
21 May, 2020 1 commit

Skip fusing group convolutions (#531) · bfbf0c27

Paul Fultz II authored May 21, 2020



* Skip fusing group convolutions

* Formatting

* Fix ICE on gcc 5

* Formatting

* Fix gcc check

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

bfbf0c27

20 May, 2020 1 commit

Rnn variable seq lengths (#517) · 90200619

Shucai Xiao authored May 19, 2020



* 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>

90200619

15 May, 2020 1 commit

Add gelu optimization (#521) · 0079028a

kahmed10 authored May 15, 2020



* fix pad calc

* bert tf passes correctness

* formatting

* add test

* formatting

* remove comment

* add inline

* formatting

* fix order for literal

* formatting

* add test for gelu

* formatting

* added add_gelu fusion

* add files

* formatting

* remove layernorm opt

* revert reduce file

* add gelu_fn and tests

* formatting

* fix matcher, remove extra tests

* formatting

* fix matcher

* add used_once

* formatting

* start on new gelu

* formatting

* add matchers in fuse_ops

* formatting

* add dce to fix add_gelu

* add simplify_rsqrt and test

* formatting

* debugging value for matcher

* formatting

* add more to matchers

* formatting

* fix errors

* remove onnx gen

* add any_arg, change matchers to use either_arg

* formatting

* formatting

* add used_once

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

0079028a

11 May, 2020 1 commit

Fix handling of lowest values in pad operator (#514) · 4563b8cd

Paul Fultz II authored May 11, 2020



* Fix handling of lowest values in pad operator

* Formatting

* Formatting

* Formatting

* Add cpu test for lowest padding

* Add test for max
Co-authored-by: mvermeulen <5479696+mvermeulen@users.noreply.github.com>

4563b8cd

08 May, 2020 1 commit

Horizontal fusions of gemms and convolutions (#472) · 1a4ff504

Paul Fultz II authored May 08, 2020



* 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>

1a4ff504

07 May, 2020 1 commit

Usability updates to onnx parsing (#480) · 45bb91ea

Paul Fultz II authored May 07, 2020



* Add skip unknown operators flag

* Formatting

* Add flag to print program on error

* Formatting

* Fix compile error in py

* Formatting

* Workaround cppcheck error

* Initialize with struct

* Formatting

* Disable warning

* Formatting

* Add test for print errors

* Formatting

* Formatting

* Fix compiler error

* Formatting

* Formatting

* Formatting

* Use correct map

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

45bb91ea

30 Apr, 2020 1 commit

Parse onnx using explicit input shape (#474) · 2074d756

Shucai Xiao authored Apr 29, 2020



* refine slice implementation

* clang format

* fix cppcheck error

* clang format

* change parse operator function signature

* clang format

* add parsing the split operator

* clang format

* add parsing split operator

* make squeeze/unsqueeze inputs to standard shape

* fix a bug in parsing slice

* change parsing pad to support opset 11 definition

* clang format

* add unit tests for the split operator

* clang format

* fix cppcheck error

* clang format

* update tests for multiple program outputs

* clang format

* fix cppcheck error

* clang format

* refine an error message

* add unit tests for the pad operator

* clang format

* add unit tests for slice operator

* clang format

* fix review comments

* fix cppcheck error

* add the numpy package in the Dockerfile

* add c api for onnx options

* clang format

* change c/c++ and python apis related to parse_onnx option change

* clang format

* fixed a bug

* fix a bug

* add fix bugs in cpp api

* fix bugs in c api for onnx_options

* clang format

* add unit tests

* clang format

* add missing onnx file

* add more unit test for dynamic input shape support

* clang format

* fix cppcheck error

* fix cppcheck error

* fix cppcheck error

* clang format

* fix cppcheck error

* clang format

* code change to resolve the segmentation problem

* clang format

* change the api

* clang format

* fixed a unit test error

* fix cppcheck error

* clang format

* fixed a cppcheck error

* fix review comments

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

2074d756

29 Apr, 2020 1 commit

Fix bugs in float_equal and add tests (#512) · 1039011a

Paul Fultz II authored Apr 29, 2020



* Fix bugs in float_equal and add tests

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

1039011a

21 Apr, 2020 1 commit

Fix bug in unsqueeze shape and improve test coverage (#495) · f0e530f0

Paul Fultz II authored Apr 21, 2020



* Fix bug in unsqueeze shape and improve test coverage

* Remove else statement

* Revert unsqueeze changes

* Update tests

* Formatting

* Update tests

* Fix handling of scalars

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

f0e530f0

16 Apr, 2020 1 commit

Make contiguous preserve scalar shape (#500) · dfaab007

Paul Fultz II authored Apr 16, 2020



* Make contiguous preserve scalar shape

* Formatting

* Improve standard shape calulation

* Formatting

* Enable some optimizations on debug build

* Up optimization level

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

dfaab007

03 Apr, 2020 1 commit

add improvements to pad calculation (#461) · af073671

kahmed10 authored Apr 03, 2020



* fix pad calc

* add padding calc and test

* formatting

* add parsing auto_pad attribute for convolution

* clang format

* made asym generic function

* formatting

* refine code

* code cleanup

* clang format

* pull changes from other pad branch

* formatting

* revert onnx file

* formatting

* fix a bug in the code

* fix bug in function call

* formatting

* fix bug

* fix review comment

* formatting
Co-authored-by: Shucai Xiao <Shucai.Xiao@amd.com>
Co-authored-by: Shucai Xiao <shucai@gmail.com>
Co-authored-by: Paul Fultz II <pfultz2@yahoo.com>
Co-authored-by: mvermeulen <5479696+mvermeulen@users.noreply.github.com>

af073671

02 Apr, 2020 1 commit

simplify div and sub by constants (#470) · 3c457a3c

kahmed10 authored Apr 02, 2020



* fix pad calc

* progress on div

* formatting

* continue work on pass

* continue testing

* formatting

* add recip and sub matcher

* formatting

* add tests

* formatting

* fix review comments

* remove unnecessary header

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

3c457a3c