tilelang.cuda.language.math
===========================

.. py:module:: tilelang.cuda.language.math

.. autoapi-nested-parse::

   CUDA-specific floating-point arithmetic intrinsics.



Functions
---------

.. autoapisummary::

   tilelang.cuda.language.math.fmul
   tilelang.cuda.language.math.fma


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

.. py:function:: fmul(x, y)

   Multiply with CUDA round-to-nearest semantics.

   Unlike the ``*`` operator, this intrinsic preserves an explicit multiply
   boundary during CUDA lowering. Vectorized loops may lower it to packed
   multiply instructions when the target supports them.


.. py:function:: fma(x, y, z)

   Compute ``x * y + z`` as one CUDA fused multiply-add operation.

   The result uses round-to-nearest semantics. Vectorized loops may lower the
   operation to packed FMA instructions when the target supports them.