* swim a special case of broadcast

* general case broadcast swimming for reshape sinking

* fix in_order=false case

* fix reshape redef warning

* add broadcast swimming test

* cleanup test case

* fix warnings

* fix test case

* editing docs

* more doc updates

* Cleanup theme, update backends for PlaidML, remove stale font

* Add PlaidML description and doc update that should have been added with PR 1888

* Add PlaidML description and doc update that should have been added with PR 1888

* Latest release doc updates

* Add PlaidML description and doc update for PR 1888
* Update glossary with tensor description and quantization def
* Refactor landpage with QuickStart guides
* Add better details about nGraph features and roadmap

* Placeholder detail for comparison section

* Add section link

* order sections alphabetically for now

* update compiler illustration

* Address feedback from doc review

* Update illustration wording

* Formatting and final edits

* keep tables consistent

* Clarify doc on bridge and compiler docs

* Clarify doc on bridge and compiler docs

* yay for more feedback and improvements

* edit with built doc

* Fix typo

* Another phase of PR review editing

* Final review comment resolved

* Update README with different sort of navigation options

* Remove unnecessary repetition

* Add links to announcement blogs for previous contributions to ONNX and PyTorch projects

* Better link

* Add syllabus for perf criterion

* Editing and readability on README and add page for performance-validated workloads

* Editing and readability on README and add page for performance-validated workloads

* Editing and readability on README and add page for performance-validated workloads

* Update README

* Update illustrations with detail pertinent to br

* Documenting diagram and updating about features faqs doc

* Latest Beta doc updates

* clarify wording on arch doc

* Update deprecated INSTALL.md file and CONTRIB.md

* Legacy framework support for neon removed; instead show how nGraph enables custom or customizable frameworks

* nGraph Compiler stack beta

* Add markdown version of some docs as requested

* update full ng stack diagram

* Make sure diagrams work after moving them to tld

* Update ABOUT tld info doc with PR review feedback

* unit test for sigmoid layout.

* fixed layout bug and added unit test.

* same fix for cpu emitter.

* removed unused vars.

* Support dynamic scales for quantization

* Avoid static object inside functors

* Added missing capture and removed mkldnn_submit

* fix merge error

* fix klocwork issues

* more klocwork issues addressed

* Support to selectively enable/disable passes through env variable

* Address compiler warning about zero arg macros

* Move pass selection options to PassConfig object

* remove unnecessary header include

* use default copy constructor

* Address PR feedback

* switch to map to keep xcode clang happy. doesn't seem to have a hashing function for string

* Move ParameterVector and ResultVector to the ngraph namespace where they belong

* update python wrapper

* more python fixes

* style

* Update setup.py

* fix some new code

* [ONNX] Enable transposed convolution

* Review fix pt. 1

* Review fix pt. 2

* Remove unused new_shape

Replaced the git command 'ls-repote --tags' with  which produces the same output but works for clones without branches (#2066)

* Add test revealing issue in current cudnn pooling operation. To fix we need op::MaxPoolBackprop to take the fprop output as an input argument.

* Formatting.

* Add comments and test description. Increase tensor size well past most cache sizes.

* exclude intelgpu

* adding i32 as quantized type

* code format

* mask gpu unit tests

* unused variable

* intel gpu unit test manifest

* fix typo in unit test manifest

Signed-off-by: Artur Wojcik <artur.wojcik@intel.com>

Signed-off-by: Artur Wojcik <artur.wojcik@intel.com>

* Unit tests for conv2d causing errors.

* UT for conv3D_bias

* Fix padding order.

`padding below` in nGraph terminology means padding added at the beginning
of the axis. Whereas `padding above` means padding added at the end of
the axis.

* Rename test to sth more descriptive.

* Apply clang-format.

* Fix handling of `SAME_UPPER/LOWER` auto_pads mode for convolution/pooling ops.

* Fix order of padding_below/above.
Signed-off-by: Adam Rogowiec <adam.rogowiec@intel.com>

* Fix error in calculating output data shape.

* remove exit call

* disable some failing unit tests

* Add cudnn sum and test that exposes failure

* Add test to interpreter manifest and move test to sum file

* change test name

* Fails INTELGPU and no need to run on CPU

* Comment incorporation + kahan summation for interpreter

* small oversight correction

* resolve conflict

* minor variable name edit

* Add static keyword for helper function.

* Fix MatMul for cases where left hand side is 1D vector.

- Add unit-test for this case.

* Add new line at the end of file.

* Log warning when dealing with scalars

* Apply clang-format

* Review: fix spelling, rename test model.

* Add cacheablility propagation pass.

* Use a functor to create op annotations.

* Address PR feedback.

* Address PR feedback.

* Address PR feedback.

* Kill previous builds on PR update

* Remove Jenkinsfile.groovy

* Lower case method names

* Fix method notify()

* Added comment

Previous build deletion workaround to be removed as soon as better, less security vulnerable solution is found.

* Fix inconsistent stage names

* Moved mkldnn conv availability checks to utils and use it across passes

* Style fix

* cse for convert layout

* addressed PR comments

* Addressed PR comments

* Quantize the bias to int32

* Bias scale fix

* mnist works

* Quantize Bias

* Introduce Quantize op in the graph to quantize bias & feedback

* Comments and some refactoring

* Add test case with float bias and enable int32 as quantized type in ngraph

* Change shape of scale from Shape{} to Shape{1} in the backend

* tracing

* count tracepoint

* address scotts feedback

* merge

* fix an ununsed var warning

* Faster argmax/argmin kernels

* Use switch statement for macro

* add softmax cuda support

* optimize block size

* remove debug info

* remove debug

* style

* remove unused

* remove cudnn softmax

* format

* using nullptr

* move helper, add test

* fix style

* using all_close_f

* using kahansum

* style

* remove commentted out code

* add isfinite check

* style

* output 5 diff and total diff

* output limit of diff for all_close_f

* dix bug

* disable tests

* remove failing unit test that does not make sense.

* Heterogenous sub-graph comparison testing

* Print index for float differences

* Disabled compare_backends_with_graphs on most backends for now. Moved to new file. Added testing of unsigned values.

* Fixed element::boolean range. Added missing include.

* Switched use of shared_ptr as parm to raw *. Moved to using namespace std in cpp. Fixed comment marker in unit_test.manifest files. Switched some EXPECT_EQ TO ASSERT_EQ. Fixed parameterized test disabling.

* Frozen naming -> serialized. Removed extraneous comments.

* Graph comparison unit test relies on CPU for reference, so only build when CPU is built.

* Reworked per backend disabling of compare_backends_with_graphs

* Update l2_norm and std_dev builders to use op::Sqrt instead of op::Power(...,0.5)

* Removed unneeded power.hpp include

* optimization for about 2x speedup

* more optimizations