ml_switcheroo.compiler.backends.extras
======================================

.. py:module:: ml_switcheroo.compiler.backends.extras

.. autoapi-nested-parse::

   Extra Backends (Standardized implementations for Visual/DSL Targets).

   Provides CompilerBackend implementations for:
   - TikZ (Visualization)
   - HTML (Visualization)
   - LaTeX DSL (MIDL)
   - MLIR (Graph to MLIR Text)
   - StableHLO (Graph to StableHLO-flavored MLIR Text)

   These backends consume the LogicalGraph IR and emit target-specific textual representations.



Classes
-------

.. autoapisummary::

   ml_switcheroo.compiler.backends.extras.HtmlBackend
   ml_switcheroo.compiler.backends.extras.TikzBackend
   ml_switcheroo.compiler.backends.extras.LatexBackend
   ml_switcheroo.compiler.backends.extras.MlirBackend
   ml_switcheroo.compiler.backends.extras.StableHloBackend


Module Contents
---------------

.. py:class:: HtmlBackend(semantics: Optional[Any] = None)

   Bases: :py:obj:`ml_switcheroo.compiler.backend.CompilerBackend`


   Orchestrates the conversion of Logical Graphs to the HTML visual DSL.


   .. py:attribute:: ROW_HEIGHT
      :value: 80



   .. py:attribute:: GAP_HEIGHT
      :value: 0



   .. py:method:: compile(graph: ml_switcheroo.compiler.ir.LogicalGraph) -> str

      Compiles the graph into an HTML string document.

      :param graph: The logical graph.

      :returns: HTML string.



.. py:class:: TikzBackend(semantics: Optional[Any] = None, y_spacing: float = 2.5, x_spacing: float = 3.0)

   Bases: :py:obj:`ml_switcheroo.compiler.backend.CompilerBackend`


   Orchestrates the conversion of a LogicalGraph to TikZ source code.
   Verified to use Rank-Based Layout.


   .. py:attribute:: y_spacing
      :value: 2.5



   .. py:attribute:: x_spacing
      :value: 3.0



   .. py:method:: compile(graph: ml_switcheroo.compiler.ir.LogicalGraph) -> str

      Compile graph to TikZ LaTeX code.



.. py:class:: LatexBackend(semantics: Optional[Any] = None)

   Bases: :py:obj:`ml_switcheroo.compiler.backend.CompilerBackend`


   Transforms Logical Graphs into MIDL LaTeX format.


   .. py:method:: compile(graph: ml_switcheroo.compiler.ir.LogicalGraph) -> str

      Compiles graph to LaTeX.



.. py:class:: MlirBackend(semantics: Optional[Any] = None)

   Bases: :py:obj:`ml_switcheroo.compiler.backend.CompilerBackend`


   Back-end for generating MLIR text from a LogicalGraph.

   This implementation provides a direct Graph-to-MLIR conversion path for
   scenarios bypassing the high-level Python CST Rewriter (e.g. source is RDNA).


   .. py:attribute:: semantics
      :value: None



   .. py:method:: compile(graph: ml_switcheroo.compiler.ir.LogicalGraph) -> str

      Compiles the LogicalGraph into an MLIR string representation.

      It emits a simple `module` structure with a single block, mapping each
      logical node to an `sw.op` operation. Inputs are generated as
      `sw.constant` if metadata values exist, or `sw.op {type="Input"}`.

      :param graph: The logical graph IR.

      :returns: The generated MLIR code.
      :rtype: str



.. py:class:: StableHloBackend(semantics: Optional[Any] = None)

   Bases: :py:obj:`ml_switcheroo.compiler.backend.CompilerBackend`


   Back-end for generating StableHLO text from a LogicalGraph.

   This implementation provides a direct Graph-to-StableHLO conversion path
   used when an ISA is the source format (e.g. SASS -> StableHLO).


   .. py:attribute:: semantics
      :value: None



   .. py:method:: compile(graph: ml_switcheroo.compiler.ir.LogicalGraph) -> str

      Compiles the graph to StableHLO-flavored MLIR.

      :param graph: The logical graph.

      :returns: MLIR code string using stablehlo dialect.
      :rtype: str