ml_switcheroo.compiler.backends.sass.macros
===========================================

.. py:module:: ml_switcheroo.compiler.backends.sass.macros

.. autoapi-nested-parse::

   SASS Macro Expansion Logic.

   This module defines procedural generators for complex SASS instruction kernels.
   Unlike 1:1 mappings (e.g. ``Add`` -> ``FADD``), these macros generate entire
   control flow blocks (loops, address calculations, memory loads) required to
   implement high-level Neural Network layers like Convolution and Linear layers
   directly in assembly.



Classes
-------

.. autoapisummary::

   ml_switcheroo.compiler.backends.sass.macros.RegisterAllocatorProtocol


Functions
---------

.. autoapisummary::

   ml_switcheroo.compiler.backends.sass.macros.expand_conv2d
   ml_switcheroo.compiler.backends.sass.macros.expand_linear


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

.. py:class:: RegisterAllocatorProtocol

   Bases: :py:obj:`Protocol`


   Protocol for the Register Allocator used during expansion.


   .. py:method:: get_register(var_name: str) -> ml_switcheroo.compiler.frontends.sass.nodes.Register

      Gets or allocates a register for a symbolic variable.

      :param var_name: The logical identifier.
      :type var_name: str

      :returns: The physical register.
      :rtype: Register



   .. py:method:: allocate_temp() -> ml_switcheroo.compiler.frontends.sass.nodes.Register

      Allocates an anonymous temporary register.

      :returns: The physical register.
      :rtype: Register



.. py:function:: expand_conv2d(allocator: RegisterAllocatorProtocol, node_id: str, metadata: Dict[str, Any]) -> List[ml_switcheroo.compiler.frontends.sass.nodes.SassNode]

   Generates the SASS assembly kernel for a 2D Convolution loop.

   Logic flow:
   1.  Initialize Accumulator (R_ACC).
   2.  Setup Loop Counters (Ky, Kx).
   3.  Enter Y Loop -> Enter X Loop.
   4.  Calculate addresses (IMAD) for image and weights.
   5.  Load values (LDG).
   6.  Multiply-Add (FFMA).
   7.  Increment and Branch.
   8.  Store result.

   :param allocator: The register manager.
   :type allocator: RegisterAllocatorProtocol
   :param node_id: The unique ID of the operation node (used for output reg).
   :type node_id: str
   :param metadata: Layer configuration (k, stride, etc).
   :type metadata: Dict[str, Any]

   :returns: Sequence of labels and instructions.
   :rtype: List[SassNode]


.. py:function:: expand_linear(allocator: RegisterAllocatorProtocol, node_id: str, metadata: Dict[str, Any]) -> List[ml_switcheroo.compiler.frontends.sass.nodes.SassNode]

   Generates the SASS assembly kernel for a Linear Layer (Matrix Multiply).

   Structure:
   1. Initialize Accumulator.
   2. Loop over input features (Dot Product).
   3. Load Input element and Weight element.
   4. Fused Multiply-Add.
   5. Increment pointers.
   6. Add Bias (if present).

   :param allocator: The register manager.
   :type allocator: RegisterAllocatorProtocol
   :param node_id: The unique ID of the operation node.
   :type node_id: str
   :param metadata: Attributes (in_features, out_features).
   :type metadata: Dict[str, Any]

   :returns: Sequence of instructions.
   :rtype: List[SassNode]