GitLab

* use implicit deps for the sorting
* use BFS for sorting program

This is to help enable multi-target execution. We store a vector of targets and contexts. Currently this will only compile a single target, the PR #1672 is needed to enable multiple targets.

This will also serialize the targets and contexts.

When using the execution_environment or prog.get_context() it will always use the context from the first target assuming this is the "primary" target. Although, its unlikely a user would use execution_environment with a multi-target environment.

* add fix for the trace_eval

* Add throw for the debug builds

* Formatting

---------
Co-authored-by: Chris Austen <causten@users.noreply.github.com>

partially solves #1656
This PR only handles compilation part of multitarget.

Use generate_argument instead of generate_literal for python output as generate_literal doesnt exists
Shorten the names for variables from the main module
Use prefix p_ for parameters
Use shorter variable m for main module in python

Examples..

bin/driver verify /codes/onnx_models/resnet50-v1-7/resnet50-v1-7.onnx --split-single-dyn-dim --batch 3 --dyn-input-dim @data "[{min:1, max:4}, 3, 224, 224]"

bin/driver compile /codes/onnx_models/resnet50-v1-7/resnet50-v1-7.onnx --split-single-dyn-dim --default-dyn-dim "{min:1, max:10}" --output resnet50_batch1-10.mxr

bin/driver perf resnet50_batch1-10.mxr --batch 4

Creates the select_module operator that selects one of the submodules passed to it to run based on the submodule parameters.  The submodule is selected by having the exact same static shapes for the arguments to select_module as the parameters in the submodule

* Add driver flag "--exhaustive-tune" to enable tuning, add support for the same in C/C++ and python API

Dynamic shape support for gathernd op.

* Print python code

Stream sync changes and associated API level changes

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

* Update is_supported
* Return object from is_supported
* Return by reference in interator

* Dynamic shape handling in shape object

* rewrite empty lens multibroadcast test

* Shape class changes to handle dynamic
* More throw errors for functions that don't make sense for dynamic shape
* Print output changes
* Serialization changes

* Fixing serialization errors

* Remove const on dyn_dim copy getters

* Dynamic shape tests

* Fix serialize errors

* Add dyn_data struct to avoid ambiguous constructor

* Tidy fix: emplace_back() over for loop

* Tidy fix: use move

* Use std::initializer_list in constructor
Reverts the dyn_data struct change
Should get around the ambiguous braced initialization list error

* avoid typedef

* element_space, min,max,opt _lens change

* formatting

* Comments fix

* dynamic bytes() test

* Seralize and reflect changes

* formatting

* Test the dynamic lens functions

* progress

* Formatting

* Dynamic conv draft progress

* Add operator<< tests for coverage

* Coverage update

* Add to conv dynamic batch test

* Dynamic image size test

* Dynamic weight handling

* Dyn image shape test change, fix dyn weight cond

* Comment update

* Dynamic weights shape test and fix

* Use ternary operator

* Tidy fixes

* Handle dynamic graph input shapes in ONNX parser

* Formatting

* Handle dynamic shape for convolution

* formatting

* cppcheck fixes

* Add onnx test files

* Fix typo

* Disable auto_pad for dynamic input shape

* check_shapes object checks for allowing dynamic shapes

* Fix any_of

* Change to maintain const objectness

* Formatting

* Check shapes allow dynamic

* Refactor compute_shape() call into op.compute()
Allows for per operator differences with handling dynamic shape
Fix operation.hpp change to use the generator

* Comment fix

* Refactor normalize_attributes() calls to use max_lens()

* Comment addition

* Update other normalize_attributes() calls

* Change to using constructor and add tests

* Use const member function

* Add more dynamic shape support

* Add tests for error code coverage

* Fix opt shape bug and add shape tests

* capture all by ref

* Fix typo with img shape calculation

* Add more tests

* dynamic auto pad attempt
Linker error with pad_calc.cpp

* Fix parse dyn auto_pad
Should only need to use dynamic auto pad when the image shape or kernel
shape are dynamic. For a dynamic batch size, the auto pad calculation is
the same.

* Fix linking error

* Fix auto_pad bug
Fixed input tensor with auto_pad setting on

* auto_pad onnx tests

* Fix auto_pad calculation, evaluate in ref_conv
add ref_ops tests

* Add shape tests, fix bugs

* Refactor first two output dynamic len calculation

* Conv MLIR test update

* i64 MLIR test fix

* Fix MLIR test typo
Co-authored-by: Chris Austen <causten@users.noreply.github.com>

Show the number of operators and per operator avg time in summary...

Summary:
gpu::gemm: 8.738ms / 73 = 0.119699ms, 64%
gpu::triadd_layernorm: 0.831381ms / 24 = 0.0346409ms, 7%

Added is_supported and get_target_assignments methods to the target and program, respectively, to eventually support multi-target compilation and execution.

*In the verification tests, check that saving and reloading the program is the same program. This also fixes serialization to always load instructions in the same order. There is also fixes for deconv and quant_conv which didn't save the solution id, and was broken for serialization.

 Compiles significantly faster than constructing all the objects. It also reduces recompiles as well.

* Add function to get a module tree
* Get parent module in the pass manager

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

The module::debug_print(ins) is very slow, which makes the trave_eval==1/2 very slow. The reason is printing an ins involves search the whole module to get the instruction, the print it.  This change is to fix that by calling module::print() to get names of all instructions of a program, then print the instruction by getting its name from a hash map.

Update the base version of clang-format from 5.0 to 10.0

Currently, MIGRAPHX_TRACE_EVAL=2 prints out the entire output buffer, but this can produce a lot of output. To make it easier to inspect and debug, using MIGRAPHX_TRACE_EVAL=2 now only prints 10 elements from the buffer(the first 5 and last 5) and shows any fp classifications found in the buffer(ie nans, infinity, etc). The previous behavior can still be enabled with MIGRAPHX_TRACE_EVAL=3.

Currently we have the option of passing in --batch to the driver to change the batch size when the model has a dynamic dim value. We can use this flag to adjust the perf report's rate.

Added features:
This enables wrapping each migraphx operator with rocTX markers.
It adds new knob trace to migraphx-driver binary.

Limitation:

rocTX standalone does not output a file, it needs to be used with rocprof. Example command line:

/opt/rocm/bin/rocprof -i ./in.txt --hip-trace --roctx-trace --flush-rate 10ms --timestamp on -d cagri_out --obj-tracking on /opt/rocm/bin/migraphx-driver trace ./resnet50-v2-7.onnx --onnx --gpu
Co-authored-by: Shucai Xiao <shucai@gmail.com>

 when running a model on GPU, migraphx tries to print out content from gpu memory, which causes a segfault. The solution is to copy the gpu memory content back to CPU before the print.

Add Loop operator for opset version 13.
Notes: 1) Default max iteration number is 10 if no max iteration number is provided
2) To change the max iter number, a user can set the max_loop_iterations in the onnx_option struct when parsing a model.
3) The returned shape of the scan output is from the max_loop_iterations even the actual loop num is less than that. This issue also applies to other operators like NonZero and NonMaxSuppression. A issue #948 is created to track this and to be resolved later.
Co-authored-by: Paul <pfultz2@yahoo.com>
Co-authored-by: mvermeulen <5479696+mvermeulen@users.noreply.github.com>

Assert shapes dont change
Co-authored-by: Shucai Xiao <Shucai.Xiao@amd.com>

Add operators, refactor parsers, add rewrite passes, add tests
Add ref implementations
Move broadcasting of scales and zero points to onnx parser
Allow for x and zero_point to have different types in quantizelinear; fix zero_point default type
fp16 and fp8 quantization to include subgraph and parameters
fix unit test to use qdq operators for int8 quantization
Co-authored-by: turneram <alturner@amd.com>

Improve check_context to handle submodules better
Co-authored-by: Shucai Xiao <shucai@gmail.com>