- 09 Jan, 2020 1 commit
-
-
Katarzyna Mitrus authored
* Checking if provenance_tags key exists * Add provenance tag prototype * Format provenance tag * Display provenance tag * Clean debug printing * Add const to variables * Separate method for add provenance tags * Return NodeVector reference * Return const NodeVector * Moved add_provenance_tags function to commons * Style apply * Simple model for tests * Provenance tag test * Expect substring instead of equal * Add provenance tags to intermediate nodes recursively * One tag per node * Add traverse node args instead of recursion * Return NodeVector instead of set of pointers * Use treverse_nodes and lambda function * Remove unused helper functions * Remove is_constant() condition * Update test model prototxt * Update test substring * Make code slightly more readable Co-authored-by: Tomasz Dołbniak <tomasz.dolbniak@intel.com> Co-authored-by: Michał Karzyński <postrational@users.noreply.github.com> Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com> Co-authored-by: Sang Ik Lee <sang.ik.lee@intel.com>
-
- 08 Jan, 2020 1 commit
-
-
Robert Kimball authored
* wip * Add unit test to check that every v0 op properly implements the is_* methods in Node Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com>
-
- 07 Jan, 2020 2 commits
-
-
Adam Rogowiec authored
* Fix spelling, and comment formatting. * Update Reduction operation to use v1 operators. * Upgrade/downgrade passess for ReduceMin/Max ops. * Address review comments: - Remove unnecessary AutoBroadcast arg. - Use default_opset namespace. Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com>
-
Nishant Patel authored
* Fix maxpoolbprop layout pass * Use default format for max pooling bprop. * Fix MaxPoolWithIndicesBackprop unit test. * Fix CODEGEN. * Modify MaxPoolWithIndicesBackprop unit test. Co-authored-by: Amy Zhuang <amyzhuang97@gmail.com> Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com>
-
- 06 Jan, 2020 2 commits
-
-
Robert Kimball authored
* Remove conditional compile * style Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com>
-
Chris Sullivan authored
* Enable self-concat to broadcast replacement for a single concat. * Update tests. Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com> Co-authored-by: Robert Kimball <robert.kimball@intel.com>
-
- 03 Jan, 2020 1 commit
-
-
Pruthvi authored
* Affine lowering support for 1) GreaterEq 2) LessEq 3) Equal 4) NotEqual * - cast result op from i1 to i8 for comparision operators * Addressed PR comments * Style fix * - style check - use select instead of zero_extendi durinng CompOp lowering * - fix style - use createOneConstant and createZeroConstant helpers in select intrinsic * Use NG_U8_TYPE_ID for BooleanType in ngraph dialect * Diable CE and Softmax unit test in MLIR * - LIT parser test for comparision ops * - Affine dailect LIT tests for Comparision Ops * Address PR feedback * fix typo * - use `cast` to deduce element Type - add more strict type checking to LIT Test * fix CHECK label's for comparision ops * Use UInt8 in verification logic for CMP op's * - use UInt8 for the resultOp verification Logic in CMP op - fix unit test failures
-
- 01 Jan, 2020 1 commit
-
-
Robert Kimball authored
* Update license to new year * Pick up some strays
-
- 19 Dec, 2019 2 commits
-
-
Amy Zhuang authored
-
Mateusz Bencer authored
* first version * Added constant cast * Updated ref implementation * Fixed out element type * Added UT * Code refactor
-
- 18 Dec, 2019 1 commit
-
-
Jayaram Bobba authored
-
- 17 Dec, 2019 4 commits
-
-
mozga-intel authored
* The stack operator support for a engine: 1) Added the package of stack tests 2) Added stack fused operator 3) Modified cmake file to support stack operator * 1) Support for a v0 version * Stack.cpp file is modified 1) Removed unused function * The stack.cpp file is modified: 1) Empty line was removed: [line: 72] * Modification of test/backend/fused_op.in.cpp file 1) [line 1340], fall back to the previous version of comment * Code refactoring: 1) Comment message is different, adjusted to get much more details about stack operator 2) Seralize.cpp file is adjusted to work with stack operator * Added: 1)generated_adjoints has not implemented yet. 2)int64_t -> size_t * The variable stored negative value was removed from the code * Source files: code-format check * Added included * fix error * set output type
-
Ewa Tusień authored
* Added scatterND op to ONNX importer. * Added ScatterND FusedOp. * Removed unnecessary files. * Added op to config files. * Changed input order. * Fixed validation checking. * Added suport for int64 in ScatterNDAdd op. * Changed test. * Disabled test for plaidML. * Code refactoring * Added tests.
-
Diego Caballero authored
This PR fixes some of the inconveniences that we had with lit in nGraph and aligns configuration files with MLIR/LLVM. In particular: - `make install` is not needed to run lit test with the latest compiled version of testing tools (ngraph-opt). - LD_LIBRARY_PATH doesn't need to be modified.
-
Mateusz Bencer authored
* POC of Split ConstantFolding * Removed unused code * code styles * Added constant folding variadic split file * Added variadic split + UT * Update VariadicSplit tests
-
- 16 Dec, 2019 2 commits
-
-
Amy Zhuang authored
* [MLIR]Add clang flag and skip bf16 tests for MLIR. * Address PR feedback.
-
Mateusz Bencer authored
* First debug version of support ND input * Added type_prop tests * Implemented ND support for SpaceToDepth * Added type_prop tests for SpaceToDepth * Added fused op tests * code refactor * Fixed DepthToSpaceMode::BLOCKS_FIRST * Code review remarks introduced * Code review ramarks. Part.2 * Using NODE_VALIDATION_CHECK introduced
-
- 13 Dec, 2019 1 commit
-
-
Tomasz Dołbniak authored
-
- 12 Dec, 2019 3 commits
-
-
Ilya Churaev authored
* Fixed bin constant ops * Added export * Fixed buffer size * Fixed code style
-
Tomasz Socha authored
* Add upgrade and downgrade pass for GroupConvolutionBackpropData ops - Add up/downgrade passes for GroupConvolutionBackpropData operators - Improve decompose operatorion of v0::GroupConvolutionBackpropData to support N-dimensional data - Add UT for up/downgrade passes. * Remove unused variable
-
Robert Kimball authored
* Fix tolerance for all_close_f * Lower tolerance * use all_close
-
- 11 Dec, 2019 3 commits
-
-
Amy Zhuang authored
* Update MKLDNN to v1.0.4. Build MKLDNN-v1 by default. * Add bf16 support check. * Modify visibility.
-
Robert Kimball authored
* Change generate_adjoints to take an OutputVector instead of a NodeVector for deltas. * Cleanup * Adjoints class convert to use Output<Node> * More cleanup * More cleanup * Post-merge build issues * Don't push initial bprops multiple times * Eliminate GOE correctly * back-compatibility, unit test
-
Diego Caballero authored
* [MLIR] Update MLIR/LLVM repos * Move MLIR/LLVM repos forward This includes fix to affine fusion algorithm. * Fix issues after merge * Fix lit test * [MKLDNN] Emit dgemm for 2D DP FP Dot op Add support for emitting MKLDNN's double precision FP gemm from a 2D double precision floating point Dot operation. * Removed unnecessarily duplicated pattern * Add f64 matmul support to CPU Emitter + unit test * Add check for DP unsupported bias in cpu_fusion.cpp
-
- 10 Dec, 2019 1 commit
-
-
baojun authored
* fix layernorm flatten issue * update ut * checkout output val * fix style * apply tolerance
-
- 09 Dec, 2019 1 commit
-
-
Scott Cyphers authored
* Make sure examples compile * Resolve doc build error due to opset versioning and align dynamic tensor doc to cpp example * Add latest rc * Remove deprecated API * Update brief link summary * Dist example * update doc for cpp code examples folder * Fix typo and toc index * Build config for example, deprecation in dist test * style
-
- 07 Dec, 2019 1 commit
-
-
Ewa Tusień authored
* [ONNX] Added gatherND op to ONNX importer. * Added tests. * Removed new line. * Update onnx_import.in.cpp * Changed tests.
-
- 06 Dec, 2019 6 commits
-
-
Geoffrey Wenger authored
-
baojun authored
* add ut to reproduce issue from PR#3931 * disable ut for plaidml
-
Tomasz Socha authored
-
Mateusz Bencer authored
-
Diego Caballero authored
* [MLIR] Update MLIR/LLVM repos * Move MLIR/LLVM repos forward This includes fix to affine fusion algorithm. * Fix issues after merge * Fix lit test
-
Diego Caballero authored
-
- 05 Dec, 2019 3 commits
-
-
Tomasz Dołbniak authored
* fused::v1::Split op skeleton & serialization * Shape inference for Split and upgrade/downgrade passes * Upgrade pass for the Split op * Disable the failing onnx_importer Split op tests on interpreter * Opset1 test correction for v1::Split * Disable the failing Split op unit tests on PlaidML * Fix of the upgrade pass for Split * Remove one of the obsolete v0::Split constructors
-
Jayaram Bobba authored
* Added v1::Select op with support for implicit broadcasting * Addressed PR feedback * Constant folding support for v1::Select op * Remove commented-out code * More shape inference tests
-
- 04 Dec, 2019 2 commits
-
-
Scott Cyphers authored
* Fix some opset bugs Typo in opset0 Include ops.hpp rather than ngraph.hpp * Opset op insertion * Make opsets extendable, able to create instances * Update like replacement * Review comments
-
Ilya Churaev authored
* Added reproducer for specialize_function * Remove GOEs that might have been introduced while cloning nodes in function specialization * Address PR feedback * Fix incorrect merge
-
- 03 Dec, 2019 2 commits
-
-
Tomasz Dołbniak authored
* NonMaxSuppression op skeleton * Validation of the NonMaxSuppresion op * Correct last 'boxes' dimention check * onnx_importer support for NonMaxSuppression * Code formatting * Type and shape inference for NonMaxSuppression * Different initialization of NMS inputs in onnx_importer * Code formatting * Basic type_prop tests for NonMaxSuppression * More type_prop validation for NMS
-
Tomasz Socha authored
* [SPEC] Add new v1::GroupConvolution and v1::GroupConvolutionBackpropData ops. * Sort downgrade passes * Add downgrade pass fro GroupConvolution * WIP I * Fix GroupConvolution validate and infer types * Add upgrade pass for GroupConvolution * Remove unnecesary get_static_groups() method * Disable pass for cases when groups are in filters * Review Fix I * Move ops to fused/group_conv.hpp * Use Op instead of FusedOp again * Move v1::GroupConvolution and v1::GroupConvolutionBackpropData to FusedOp but temporarily disable decomposition
-