GitLab

When testing gpu::contiguous instruction replacability recursive calls to try_compute_shape can pick up gpu::contiguous instructions as well.
These instructions always passes the try_compute_shape check because compute_shape of gpu::contiguous always returns a standard shape, thus propagating false `true` values upwards.
For these corner cases we must demand the standard shape of the inputs as well, to avoid ellimination of needed gpu::contiguous instructions.

Extends the ref contiguous operator to handle dynamic shapes
Updates the eliminate_contiguous pass to use the dyn_output struct

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

This reorders the transposes across slice to improve horizontal fusion for contiguous. This also improves eliminate_contiguous to remove contiguous better across splits.

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

Following up on issue #1166 and PR #1220. Using the same approach as in #1220 for parallelizing the eval calls, we can significantly reduce the time spent on eliminate_contiguous pass.

Updated variable names according to #1193

This PR is the resolve two problems in the issue#999, i.e., non_standard_shape input to reshape and reduce_mean.
Three fixes:

Any operator that has a standard shape requirement will add a contiguous input for its input.
Eliminate_contiguous, when computing whether a contiguous can be removed, we should use all the updated args, not just the one that is being checked.
In two optimization in the simplify_reshape, we remove the contiguous in the reshaper name list, since eliminate_contiguous will remove the contiguous if it can be removed.
the solution is add an attribute to the operator that requires standard input shape, then in the auto_contiguous pass, add a contiguous to every input of such operators.

Currently, eliminate_contiguous will never remove contiguous for operators that use module inputs due to the fact that it doesn't pass the module inputs to compute_shape.

- Update to pass the module inputs correctly to compute_shape
- Fix the overloads of compute_shape so that when passed an empty vector of module inputs it will call the overload without module inputs
- Add tests with contiguous and pointwise module function.
- Move add_pointwise function to a seperate header to reuse across different tests

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

* Add flag to enable cpu backend

* Make buffers shared

* Enable optimizations

* Add onednn

* Formatting

* Formatting

* Add dnnl header

* Formatting

* Rewrite rnn first

* Formatting

* Call reference implementation

* Formatting

* Make literal data shared

* Formatting

* Add convolution

* Formatting

* Compensate for dilation

* Formatting

* Use name/make_op instead

* Formatting

* Rename gemm header

* Formatting

* Add dnnl convolution/gemm operators

* Formatting

* Add eliminate_contiguous

* Add faster pointwise operators

* Formatting

* Formatting

* Formatting

* Add dnnl op class

* Formatting

* Add add op

* Formatting

* Add concat operator

* Formatting

* Add more ops

* Create descriptor during finalization

* Formatting

* Dont rewrite pooling

* Enable memory coloring

* Formatting

* Add output aliases

* Formatting

* Fix errors

* Formatting

* Convert literals

* Add missing file

* Remove batch_norm

* Formatting

* Use strides

* Formatting

* Add some debug checks

* Formatting

* Fix big in adjusting shape for gemm

* Formatting

* Fix fallback dot operator

* Zero initialize buffers

* Add suport for group convolutions

* Formatting

* Make adjust allocation target independent

* Formatting

* Enable adjust_allocation for gpu/cpu

* Formatting

* Add copy to allocation model

* Formatting

* Add copy operator

* Formatting

* Better handling of output parameters in adjust_allocation

* Formatting

* Build with dnnl

* Make dnnl required

* Fix compile error

* Tidy fixes

* Formatting

* Tidy fixes

* Formatting

* Fix more tidy issues

* Formatting

* Add mul op

* Add mul op

* Set c compiler to clang as well

* Compensate for normalized compute shape

* Formatting

* Fix cppcheck errors

* Formatting

* Add onednn library to hcc

* Guard clang pragmas

* Disable cpu mode for gcc for now

* Leave it enabled it for gcc 7

* Fix cppcheck suppresion

* Fix compile error on gcc 5

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

* code backup

* clang format

* change corresponding tool files

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

* Add initial api

* Formatting

* Add more api

* Formatting

* Add auto api generation

* Formatting

* Fix some compilation errors

* Change handle struct

* Formatting

* Fix reamining compilation errors

* Formatting

* fixed a bug related to number of outputs

* Simplify using ctype

* Formatting

* Initial c++ generation

* Formatting

* Add C++header

* Formatting

* Add test

* Formatting

* Add initial tests

* Formatting

* Try to fix formatting

* Cleanup formatting

* Formatting

* Fix constructors on the same line

* Fix tests

* Formatting

* Fix tidy issues

* Fix tidy issues

* Fix naming issue

* Add onnx API to parse buffer

* Formatting

* Add arguments api

* Formatting

* Fix verify parameters

* Fix cppcheck issues

* Formatting

* Add method to get output shapes and bytes

* Formatting

* Try formatting

* Formatting

* Improve the test coverage

* Formatting

* Add print method

* Formatting

* Fix cppcheck issue

* Fix package dependency

* code backup for support multiple outputs

* clang format

* change migraphx api to support multiple program outputs

* clang format

* change api implementation

* clang format

* clang format

* fix a build error

* additional changes

* clang format

* change api for correct automatic generation

* clang format

* fix unit test error

* fix unit test error

* fix unit tests error

* support multiple program outputs

* clang format

* remove @ from the add_return name

* Add nolint

* Try fix formatting

* Formatting

* formatting

* formatting

* Fix formatting

* code cleanup

* clang format

* fix cppcheck error

* fix a cppcheck error

* clang format

* fix review comments

* clang format

* fix cppcheck error

* clang format

* record graph output name

* clang format

* refine print the add_return instruction

* clang format

* fix cppcheck error

* clang format

* refine the name of the add_return instruction

* fixed a bug related to workspace

* fixed two small bugs

* clang format

* add more unit tests for multiple program outputs

* clang format

* change an error info

* clang format

* fix cppcheck error

* add unit test for better code coverage

* change to reduce code change

* clang format

* remove storing program output

* fix cppcheck error

* fix review comments

* clang format

* clang format

* remove unnecessary change

* resolve an assert error

* clang format

* change the output name with prefix '#'

* changes in quantization function to support the returns instructin

* clang format

* refine unit tests

* clang format

* refine profiling print out report
Co-authored-by: Paul <pfultz2@yahoo.com>
Co-authored-by: Khalique <15948690+kahmed10@users.noreply.github.com>
Co-authored-by: mvermeulen <5479696+mvermeulen@users.noreply.github.com>

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