- 07 Jan, 2020 6 commits
-
-
Tomasz Dołbniak authored
* Use v1::Broadcast in ONNX LpNorm * Missing include * Missing include * Include the default opset in lp_norm.cpp * Reference Constant from default_opset * Some extra comments Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com>
-
Tomasz Dołbniak authored
Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com>
-
Amy Zhuang authored
* Update MKLDNN to v1.1.1. * Modify mkldnn_v1 patch. * Modify bf16 check for mkldnn-v1. Co-authored-by: baojun <32073718+baojun-nervana@users.noreply.github.com> Co-authored-by: Sang Ik Lee <sang.ik.lee@intel.com>
-
Robert Kimball authored
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>
-
Robert Kimball authored
* Fix using statements * Add missing line ending * Add license Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com>
-
- 06 Jan, 2020 6 commits
-
-
Robert Kimball authored
* Remove conditional compile * style Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com>
-
Tomasz Dołbniak authored
Co-authored-by: Sang Ik Lee <sang.ik.lee@intel.com>
-
Tomasz Dołbniak authored
Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com>
-
Robert Kimball authored
Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com>
-
Tomasz Dołbniak authored
* Use v1::Minimum and v1::Maximum in ONNX Clip implementation * Use v1::Maximum in ONNX LeakyRelu 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
-
- 23 Dec, 2019 1 commit
-
-
Diego Caballero authored
* [MLIR] Update MLIR/LLVM repo I need it to get MemRef lowering override mechanism (291a309d). * Fix style Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com>
-
- 21 Dec, 2019 1 commit
-
-
Robert Kimball authored
* wip * Use AlignedBuffer instead of vector for performance * cleanup * More cleanup * Revert Constant change Co-authored-by: Scott Cyphers <diyessi@users.noreply.github.com>
-
- 20 Dec, 2019 3 commits
-
-
baojun authored
* update matmul fprop * clean up
-
baojun authored
-
Pruthvi authored
* - emit mlkddn for LRN only for normalizing acorss/within channel * - remove explicit checking of axes in lrn builder Co-authored-by: Jayaram Bobba <jayaram.bobba@intel.com>
-
- 19 Dec, 2019 5 commits
-
-
pawelpiotrowicz authored
* Backprop matmul maybe works - due to internal error with /usr/bin/ar issue file truncated, I could`t check it * fix error * clean up * update * fix style Co-authored-by: baojun <32073718+baojun-nervana@users.noreply.github.com>
-
dkalinowski authored
* Pass _GLIBCXX_USE_CXX11_ABI to protobuf - this change allows building nGraph with newer GLIBC: v5.1+ * Specify _GLIBCXX_USE_CXX11_ABI only when NGRAPH_USE_CXX_ABI is defined
-
Amy Zhuang authored
-
Mateusz Bencer authored
* first version * Added constant cast * Updated ref implementation * Fixed out element type * Added UT * Code refactor
-
Pruthvi authored
* - update external_mlir_prebuilt.cmake to support pre built MLIR * fix typo * - unify prebuilt and external pull, build "mlir" cmake logic - throw cmake error if MLIR_LLVM_PREBUILT_PATH is not specified when -DNGRAPH_USE_PREBUILT_MLIR=True
-
- 18 Dec, 2019 4 commits
-
-
Robert Kimball authored
-
Jayaram Bobba authored
-
baojun authored
* use pre_validate function * use pre_validate
-
baojun authored
-
- 17 Dec, 2019 8 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
-
Scott Cyphers authored
* Some type info cleanups/improvements * Missed change
-
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.
-
Diego Caballero authored
* [MLIR] Update MLIR/LLVM repos To have access to unranked memrefs. * Fix MLIR forward again to fix lit test in MLIR repo
-
Evgenya Stepyreva authored
* [ TI ] TensorIterator m_num_iterations fix * style
-
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
-
baojun authored
-
- 16 Dec, 2019 4 commits
-
-
baojun authored
* set output type * set output type
-
Robert Kimball authored
-
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
-