* address klocwork issue

* move class init

* more klocwork

* more klocwork

* more klocwork

* comment on where the magic number is from

* address review comments

* address review comments

* Add op::Sigmoid to nvgpu.

* Bring rnn fusion and concat passes over into GPU from IA. This is a temporary move until generalization and gpu specification can occur.

* Add LSTM fusion and cudnn inference kernel. Next need recurrent fusion and layer fusion.

* Formatting

* Removed unecessary extra output from LSTM op (rnn with seq. length = 1, so y = hy).

* Add RNN fusion of LSTM cells within a recurrent layer.

* Formatting.

* Add fusion across RNN layers.

* Formatting.

* Add algebraic simplification.

* Added rnn fusion tests.

* Updated conditional on LSTM fusion to better distinguish bound nodes as ht vs xt.

* Formatting.

* Removed print statements.

* Formatting.

* Committing missing file.

* Remove concat inputs pass and mkldnn references.

* fix cmake paths

* conflict resolution with merge from master.

* remove explicit lstm op support. bare LSTM ops are converted to RNN ops for emission.

* Formatting.

* Use NGRAPH_ASSERT. Formatting of intel copyright.

* Add check on the feature size (shape) of the recurrent (hidden) input and cell state, to ensure they are the same size.

* fix wrong rnn header

* Formatting.

* Add back lstm op to dispatch table.

* Added RNN test which shows cudnn rnn kernel is not producing correct results.

* With update to AlgSimpl. to simplify concat-reshape-slice, the check modifed in this commit needed to be relaxed.

* Bug fix in parameter tensor packing.

* Alias third output element of RNN for cell state (bug fix).

* Resolve numerical correctness issue with negative values in RNN (bug fix).
Add minimal test to evaluate LSTM and compare with values calculated by hand.

* Add tensor parameter sizes to kernel hash as
they are kernel-specific.

* Add 2 layer lstm fusion test against by-hand solution.

* Export param concatenation to graph for cudnn kernel at both the single rnn layer and multi-layer.

* Formatting.

* Finishing touches after merge: add support for macro expansed dispatch via op_tbl.

* Simplify macro support for gpu ops.

* Add CUDNN_VERSION >= 7200 defguards for RNN fusion.
Need to decide how to notify user of increased performance with >= 7200.

* Revert lstm_analytic test to explicitly copy data to tensor params.

* Removed namespace arg from NGRAPH_GPU_OP.

* Refactored macros to different header so op_tbl only contains op list.

* Defguard on cudnn_descriptor<cudnnRNNDataDescriptor_t>.

* doubles -> floats

* Reorg. pass asserts, prepare to replace with non-throwing pass failures.

* Remove Lstm op and replace it with Rnn.

* Format

* Utilize RETURN_IF_FALSE in rnn pass to avoid any RT asserts.
Note that falling back to raw (no passes) graph for 2rnn_3lstm json from mxnet models
results in a double free inside of the memory layout pass. Appears to be a bug
in Reshape pass through.

* Removed print statements. Add check on input data and recurrent data.

* Don't reuse memory for non-destructive ops.

* Add back Rnn test.

* Formatting.

* Clean up comments.

* Update test per review comments.

* Add some asserts to make sure we don't overshoot certain iterators in the reference kernels

* Add missing assertion.hpp include

IntelGPU backend: Broadcast bug fix: (output_shape.at(0) == 1) doesn't mean that it is scalar (#1754)

* global stats fix

* Formatting.

* address klocwork number overflow issue

* one more issue

* Adapt Tensor class to have partial shapes

* Add PartialShapes to Input, Output, Function, Node classes

* Terminological cleanup

* Add conv+bias

* Add test case for QuantizedConv2DWithBiasAndRelu and address feedback

* add a test failed on gpu, pass on cpu

* fixed bug

* get datatype size

* add descript for test

* update comment

* update comments and name

* show types in visualize_tree

* fix a warning

* address Bob's feedback

* add doctools js from basic theme sphinx repo

* fixes from PR 672 RTD theme regarding sphinx build

* IntelGPU backend: Operation Reduce implemented

* PR1736. Style fixed

* cublas emitter

* clang format fixes

* Initial comment incorporation from Chris

* Chris's If-else change comment incorporation

* incorporating Bob's comments phase 1

*  Remove unnecessary headers in cublas emitter hpp & cpp (as per Bob's comments)

* clang format on previous commit

* incorporate fenglei's refactoring comment

* incorporating comments

* Incorporate Chris's final comment

* All comments resolved

* Resolve Geoff's comments

* Change cache_primitive to register_primitive

Partial Shapes, Part 1: Classes for partially known shapes, possibly unknown dimensions

Pretty sure at this point that I was reading the docs correctly.

* WIP input * weights rnn optimization

* concat + slcing + replacing new node works

* WIP unit test case of fusing rnn inputs

* - Added unit test case for fusing rnn input weights
- registered CPURnnMatFusion_v1/v2 in codegen and DEX

* fixed redeclaration of a variable

* Refactored rnn input traformation passes into a single pass

* Refactored CPURnnMatFusion call back functions

* change random generator range to include -ve values in unit test

* address PR comments

* dont fuse if the shape of the data slices dont match

* rename GPU_TensorView to GPUTensor and GPUTensorViewWrapper to GPUTensorWrapper

* undo bad search/replace

* revert change

* cleanup

* cleanup header includes

* cleanup

* cleanup TensorMemoryReservation pass

* include cleanup

* more cleanup

* more header cleanup

* style

* Remove obsolete comments

* Sigmoid and tanh  doc, edit for abs

* Add equation for sigmoid.

* Add CODEOWNERS file (will have no effect until enabled in GitHub settings)

* Review comments, and fix a username

* Tabs -> spaces

* Review comments

* /maint/ to @cconvey

* /maint/ back to @diyessi by default

* rename files

* rename runtime TensorView to Tensor

* rename HostTensorView to HostTensor

* Address deferred comments from PR 1676

* use dynamic pointer cast for added error checking

* set_output_size fix

* add assert

* dont run get_loop_kernels twice