* [MLIR] Fix naming convention in MLIR files

Add naming convention note per file to state which files should use
nGraph naming convention and which MLIR naming convention and align
naming convention in those files with such a note.

* Remove m-prefix

* Initial sub-graph extraction

* Works without detaching input edges from sub-graph

* Added removing input edges to graph

* Works with whole func sub-graphs. Inputs edges to sub-graph are still there

* Works on 2 exclusive sub-graphs. Still not on merged sub-graphs

* Revert removing inputs to sub-graph. nGraph validation crashes

* Added 3 sub-graph test. Remove compiled_kernel fusion pass. Comments

* Revert some changes

* Added cycle detection. Removed unit-tests to backend_mlir.in.cpp. Still not fully functional

* Construct CK nodes after finding outputs to preserve the graph.

* Fix topological sort. UTs pass.

* Minor fixes

* PR fixes

* Enable mlir tests only when building with MLIR on

MLIR Compile only supported ops

This patch leverages CompiledKernel to delimit sub-graphs to be compiled
with MLIR. It introduces a pass that creates a CompiledKernel for the
whole function (for now) and changes MLIRCompiler to align with this new
approach.

* - Moves some fused convolution ops to core FusedOps
- Adds support for decomposing and replacing multi-output FusedOps
- Adds query callbacks to FusedOpDecomposition to check if a FusedOp is
  supported by a backend
- Adds core fusion patterns for FusedOps
-

* style fix

* Added comments on FOP_FUSIONS

* gpu convolution 1d bug fix (#2741)

* Fix bug with dex-only compilation and addressed PR comments

* Initial support for specification of fused ops and type inference

* Added FusedOpDecomposition pass and execution test cases

* Serializer support

* style fix

* Add FusedOpDecomposition to GPU and IGPU backends

* Addressed PR feedback

* Fix comment

* Addressed PR feedback

* update licenses for 2019

* style

* use line comments instead of multiline comments for license header

* update more

* update new files

* more header updates

* style

* move nop elimination pass to nGraph and add broadcast elimination

* fix pad test bug

* remove graph visualizer and clean up includes in nop eliminate test

* code format

* rough draft but needs to use get_n to get the right input

* v2 fully working but hacky

* remove hacks ; switch back build_users() to users()

* rollback hacks to node.cpp

* perms, remove prints, format

* removing extra copies due to op::Result

* remove comment

* fix comment

* switch to a flag version

* add copyright header #pragma once

* add impl file, rename result_elimination.hpp to result_copy_elimination.hpp to match the opt name

* add cpp suffix to result_copy_elimination

* use member in-class member init

* cleanup

* fix node includes

* port functions from funky passman branch

* update pass tests

* wip

* fixed

* remove obsolete test

* remove debug prints

* Done to achieve goal of having our #include directives all start
  with `"ngraph/`, like LLVM does.

add naming of tensors and tensor views
add visualization pass
add graph dump pass

Add memory layout and liveness passes.

add test framework

stuff wired up

benchmark segfault for 5M nodes. fun

make traverse_nodes not recursive

print timings on benchmark

unit test for pass manager

All tuples are expanded out to their component tensors.

Output: Describes one tensor output of an node
Input: Described one tensor input to a node, including the output supplying the value.