tilelang.ascend.language.reduce_op
==================================

.. py:module:: tilelang.ascend.language.reduce_op

.. autoapi-nested-parse::

   Ascend dialect of the reduce operators.

   Same surface as :mod:`tilelang.language.reduce_op`, plus the SimdVF direct
   path: a SimdVF region has no thread domain, so the common implementation's
   fragment round-trip (alloc_fragment + copy in + reduce + copy out) for
   shared-to-shared reductions cannot lower there. Inside SimdVF the reduce is
   emitted directly on the UB regions and AscendSimdVFLowerParallel lowers it to
   the SIMD reduction intrinsics.

   The thin ``reduce_*`` wrappers are redeclared because the common ones call
   the common ``reduce`` by module-level binding and would bypass this dialect's
   dispatch.



Functions
---------

.. autoapisummary::

   tilelang.ascend.language.reduce_op.reduce
   tilelang.ascend.language.reduce_op.reduce_max
   tilelang.ascend.language.reduce_op.reduce_min
   tilelang.ascend.language.reduce_op.reduce_sum
   tilelang.ascend.language.reduce_op.reduce_abssum
   tilelang.ascend.language.reduce_op.reduce_absmax
   tilelang.ascend.language.reduce_op.reduce_bitand
   tilelang.ascend.language.reduce_op.reduce_bitor
   tilelang.ascend.language.reduce_op.reduce_bitxor


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

.. py:function:: reduce(buffer, out, reduce_type, dim, clear, batch = 1, annotations = None)

   Common :func:`tilelang.language.reduce_op.reduce` plus the SimdVF path.


.. py:function:: reduce_max(buffer, out, dim = -1, clear = True, batch = 1, annotations = None)

   See :func:`tilelang.language.reduce_op.reduce_max`.


.. py:function:: reduce_min(buffer, out, dim = -1, clear = True, batch = 1, annotations = None)

   See :func:`tilelang.language.reduce_op.reduce_min`.


.. py:function:: reduce_sum(buffer, out, dim = -1, clear = True, batch = 1, annotations = None)

   See :func:`tilelang.language.reduce_op.reduce_sum`.


.. py:function:: reduce_abssum(buffer, out, dim = -1, batch = 1, annotations = None)

   See :func:`tilelang.language.reduce_op.reduce_abssum`.


.. py:function:: reduce_absmax(buffer, out, dim = -1, clear = True, batch = 1, annotations = None)

   See :func:`tilelang.language.reduce_op.reduce_absmax`.


.. py:function:: reduce_bitand(buffer, out, dim = -1, clear = True, batch = 1, annotations = None)

   See :func:`tilelang.language.reduce_op.reduce_bitand`.


.. py:function:: reduce_bitor(buffer, out, dim = -1, clear = True, batch = 1, annotations = None)

   See :func:`tilelang.language.reduce_op.reduce_bitor`.


.. py:function:: reduce_bitxor(buffer, out, dim = -1, clear = True, batch = 1, annotations = None)

   See :func:`tilelang.language.reduce_op.reduce_bitxor`.