- 17 Sep, 2021 3 commits
-
-
Paul Fultz II authored
This reverts commit 9e43cb8b.
-
Umang Yadav authored
This PR aims to remove alpha and beta attributes from dot operator completely. Previously dot operator was defined as C = alpha * A . B + beta * C where * is scalar multiplication and . is dot product or matrix multiplication depending on dimension of the inputs. Aim is to have the definition of dot operator as C = A . B without having alpha or beta. In order to achieve the same effect as alpha and beta (1) it multiplies the one of the inputs to the dot operator with alpha value. (2) if beta is present then, multiplies the C with beta and then adds into the output from step 1.
-
Umang Yadav authored
make file_options struct an opaque object for ABI compatibility, uses make generate to auto-generate and includes modified tests. Co-authored-by:Paul Fultz II <pfultz2@yahoo.com>
-
- 16 Sep, 2021 1 commit
-
-
Shucai Xiao authored
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:
mvermeulen <5479696+mvermeulen@users.noreply.github.com>
-
- 10 Sep, 2021 2 commits
-
-
Paul Fultz II authored
Assert shapes dont change Co-authored-by:Shucai Xiao <Shucai.Xiao@amd.com>
-
turneram authored
Add ability to parse ThresholdedRelu ONNX operator. Resolves #888 Co-authored-by:Shucai Xiao <shucai@gmail.com>
-
- 07 Sep, 2021 3 commits
-
-
Shucai Xiao authored
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>
-
Paul Fultz II authored
Improve check_context to handle submodules better Co-authored-by: -
Paul Fultz II authored
* Add module pass manage
-
- 02 Sep, 2021 2 commits
-
-
turneram authored
Implement the Where operator for the CPU and GPU. This is for better performance.
-
Shucai Xiao authored
* add topk operator doe ref, cpu and gpu * Hash modules for quicker lookup of modules * add onnx unit test * add unit tests for the topk operator Co-authored-by:
-
- 01 Sep, 2021 2 commits
-
-
Paul Fultz II authored
* Add a command to list supported onnx operators
-
Chris Austen authored
In ROCm 4.5.0 hip compile flags are coming in differently. This has caused some parsing issues for the HIP_COMPILER_FLAGS variable. As an example ROCm 4.3.0: --offload-arch=gfx900 ROCm 4.5.0: <$<COMPILE_LANGUAGE:CXX>:SHELL:--offload-arch=gfx900> Using existing code... $<$<COMPILE_LANGUAGE:CXX>:SHELL:--offload-arch=gfx900> Becomes... $<$<COMPILE_LANGUAGE:CXX>:SHELL: There are two problems with that. 1) The "<" is not balanced with a "> due to the regex consuming the ">" 2) There is still a `SHELL:` label. This commit repairs both. I took the regex parsing code from ROCmSoftwarePlatform/MIOpen/blame/develop/CMakeLists.txt but improved it to support handling of target features like <$<COMPILE_LANGUAGE:CXX>:SHELL:--offload-arch=gfx900:xxx+> Co-authored-by:
-
- 31 Aug, 2021 3 commits
-
-
Paul Fultz II authored
* Improve handling of constructing a tuple from a buffer * Add unit test * Remove unused function Co-authored-by: -
kahmed10 authored
* Add preallocate method * Add preallocate_param pass * Preallocate buffers on the cpu * Formatting * Preallocate on the gpu * Add missing cpp file * Formatting * Add lifetime function * Formatting * Improve handling of exceptions in test driver * Formatting * Auto print exception * Formatting * Fork each test case * Formatting * Exclude gcc 5 debug build * Fix tidy issues * Add color * Formatting * Create driver class * Formatting * Customize test_case names * Formatting * Report status from forked processes * Formatting * Update the verify driver * Formatting * Print out failed tests * Formatting * Fix tidy issues * Formatting * Expect passing * Improve failure reporting on non-linux systems * Fix ifdef * Always allocate * Fix tidy warning * Flush code code cov * Formatting * Fix tidy * Add const * Check if weak symbols is linked * Formatting * initial progress * formatting * Add continue flag * Formatting * Set exe name * Use stringstream and use quotes * rename vars * formatting * more testing * formatting * Fix bug when using --continue in the tests * Formatting * revert gemm * revert dot file * rename var * update cmakelists and deconv compute Co-authored-by:
-
Shucai Xiao authored
* fix two asserts for debug build * add unit test for copy parameters * clang format * add a unit test for reorder_dims * change tranpose to always require perm not be empty * clang format * remove an unnecessary line * fix tidy error * fix review comments
-
- 25 Aug, 2021 1 commit
-
-
Shucai Xiao authored
* always keep parameters * clang format * fix tidy error * clang format * add more unit tests to have more code coverage * fixed a bug to ensure get_parameter_names to return ordered parameter names * clang format * remove unnecessary print out * refine a code change * clang format * add a unit test to check parameter is not removed by dead code elimination * clang format * rename a function name Co-authored-by:Chris Austen <causten@users.noreply.github.com>
-
- 24 Aug, 2021 1 commit
-
-
Umang Yadav authored
* rename broadcast and multibroadcast output_lens attribute to out_lens attribute, and change tests and source code to reflect the same * change the reshape attribute from dims to out_lens * change transpose attribute's name from dims to perm to reflect better meaning * use permutation instead of perm for transpose clang formaating * use dims instead of out_lens for reshape clang formatting
-
- 20 Aug, 2021 1 commit
-
-
Shucai Xiao authored
* unary scalar input processing * remove an unnecessary change * remove unnecessary blank line
-
- 19 Aug, 2021 1 commit
-
-
Paul Fultz II authored
* Enable warnings when jit compiling * Formatting
-
- 18 Aug, 2021 2 commits
-
-
turneram authored
* 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 * Switch certain variables to int64_t * Fix overflow in implicit constant conversion * Remove operators.hpp from includes in tf_test.cpp * Add conversion for int32 input to quantizelinear and add test case; remove operators.hpp from onnx_test.cpp includes * Switch dequantizelinear math from int32 to float * Remove changes to operators.hpp * Simplify apply_quantizelinear * Add verify test for int32 data * Add rewrite_quantization back to CMakeLists * Add passes to insert qdq after add_bias is applied, replace quant_ops, and remove remaining qdq pairs * Renaming, refactoring, cleaning up code, adding formal test, and adding passes to targets * Renaming, review comments, begin adding more specific tests * Add more specific unit tests * Fix failing test on CI * Correct matcher and update qop rewriting, update tests and add more tests * Update matcher, clean up simplify_qdq, tweak tests * Add tests, remove pass from CPU target, update dot parameters, clean up simplify_qdq * Fix correctness bug in ref q/dq implementations; edit gemm parser to make beta always 0.0 * Remove unused variables in onnx gemm tests
-
turneram authored
Co-authored-by:
-
- 10 Aug, 2021 1 commit
-
-
Paul Fultz II authored
* Add hiprtc compile option * Add cross compile test * Update error reporting * Add tests for errors and warnings * Fix tidy warning * Add comment to ifdefs * Skip null character at end of log * Assert there is null at the end
-
- 09 Aug, 2021 1 commit
-
-
Cagri Eryilmaz authored
* check for divisor encodable or not, fallback if needed * verify test for retinaface case
-
- 05 Aug, 2021 1 commit
-
-
Paul Fultz II authored
* Add method to compile pointwise * Formatting * Add lambda * Add semicolon * Rename variable * Add driver to run jit kernels * Formatting * Add context * Formatting * Make seperate driver folder * Add more general gpu driver * Formatting * Print out wll time * Formatting * Run multiple times and skip first run * Formatting * Seperate time_op * Run an op for comparison * Formatting * Add debug asserts * Formatting * Change parameer name * Formatting * Fix argument order * Formatting * Add preloading * Formatting * Allow a different data type * Formatting * Pipeline transformations * Formatting * Add vectorization * Formatting * Reduce dims * Formatting * Compile with launch params as constant * Formatting * Make sure buffer can be vecotrized * Formatting * Enable vectorization and preloading * Formatting * Add print header * Formatting * Avoid allocating to large of LDS * Formatting * Add some vec functions to a seperate header * Formatting * Add stride loops * Formatting * Improve the transform pipeline * Formatting * Add const * Fix shape check * Formatting * Just check stride axis is zero * Remove extra finc_vector_axis overload * Simplify some mroe functions * Formatting * Remove some more extra functions * Formatting * Simplify more decltypes * Add another const * Fix test * Get buffer pointer different for older compilers Co-authored-by:
-
- 03 Aug, 2021 1 commit
-
-
Shucai Xiao authored
Co-authored-by:
-
- 28 Jul, 2021 1 commit
-
-
Shucai Xiao authored
* fix an issue for type mismatch in parsing gemm * clang format * add unit tests * clang format * add missing onnx file Co-authored-by:
-
- 21 Jul, 2021 1 commit
-
-
Khalique authored
-
- 17 Jul, 2021 1 commit
-
-
Umang Yadav authored
* gemm_test_workign clang_formatting tests passing clang formatting look for beta not equal to one * make_use of broadcastable_binary_op clang formatting * make use of common_op clang formatting * move transposes after multiplication clang formatting fix transpose formatting fix cpp check foramtting * fix parsing conditions and ci fails
-
- 15 Jul, 2021 1 commit
-
-
turneram authored
* Add operators, refactor parsers, add rewrite passes, add tests * Formatting * Fix cppcheck * Review comments * Formatting * Combine rewrite passes * Formatting * Add ref implementations * Formatting * Review comments * Formatting * Tidy warnings * Apply review comments * Formatting * Fix CI error * Formatting * Increase code coverage * Formatting * Move broadcasting of scales and zero points to onnx parser * Formatting * Allow for x and zero_point to have different types in quantizelinear; fix zero_point default type * Formatting * Increase code coverage * Formatting * Switch certain variables to int64_t * Formatting * Fix overflow in implicit constant conversion * Formatting * Increase code coverage * Formatting * Remove operators.hpp from includes in tf_test.cpp * Formatting * Add conversion for int32 input to quantizelinear and add test case; remove operators.hpp from onnx_test.cpp includes * Formatting * Switch dequantizelinear math from int32 to float * Formatting * Remove changes to operators.hpp * Simplify apply_quantizelinear * Formatting * Add verify test for int32 data * Add rewrite_quantization back to CMakeLists
-
- 14 Jul, 2021 1 commit
-
-
Paul Fultz II authored
* Unify device_name function * Formatting Co-authored-by:
-
- 13 Jul, 2021 1 commit
-
-
Paul Fultz II authored
* Add build for ubuntu 20.04 * Fix ambiguous overload resolution with stream * Fix warning * Capture by value * Format
-
- 12 Jul, 2021 1 commit
-
-
Shucai Xiao authored
Co-authored-by:
-
- 09 Jul, 2021 2 commits
-
-
Paul Fultz II authored
* Add implicit type conversion for broadcastable operators * Formatting * Fix warnings
-
Shucai Xiao authored
-
- 08 Jul, 2021 4 commits
-
-
Paul Fultz II authored
* Add initial scan operator * Formatting * Fix with a working test * Fix bugs * Formatting * Formatting * Simplify * Formatting * Use non-power of 2 for test * Make pointer Co-authored-by: -
Paul Fultz II authored
* Add preallocate method * Add preallocate_param pass * Preallocate buffers on the cpu * Formatting * Preallocate on the gpu * Add missing cpp file * Formatting * Add lifetime function * Formatting * Always allocate * Fix tidy warning * Add const * Add missing lifetime annotations Co-authored-by: -
Shucai Xiao authored
-
Shucai Xiao authored
-
- 06 Jul, 2021 1 commit
-
-
Paul Fultz II authored
* Improve handling of exceptions in test driver * Formatting * Auto print exception * Formatting * Fork each test case * Formatting * Exclude gcc 5 debug build * Fix tidy issues * Add color * Formatting * Create driver class * Formatting * Customize test_case names * Formatting * Report status from forked processes * Formatting * Update the verify driver * Formatting * Print out failed tests * Formatting * Fix tidy issues * Formatting * Expect passing * Improve failure reporting on non-linux systems * Fix ifdef * Flush code code cov * Formatting * Fix tidy * Check if weak symbols is linked * Formatting * Add continue flag * Formatting * Set exe name * Use stringstream and use quotes Co-authored-by:
-
