.. _tut-gemv-03-memcpy:

GEMV Tutorial 3: Memcpy
=======================

We've already written a program that launches a kernel and
copies the result back to the host, so lets extend this to
copying the initial tensors from the host to the device.

This program will now have three phases:

1. Host-to-device memcpy of ``A``, ``x``, and ``b``
2. Kernel launch
3. Device-to-host memcpy of ``y``

Learning objectives
-------------------
.. include:: objectives.rst

Example overview
----------------
.. include:: overview.rst

Modifying the CSL
-----------------
.. include:: device-code.rst

Modifying the host code
-----------------------
.. include:: host-code.rst

Compiling and running the program
---------------------------------
.. include:: running.rst

Exercises
---------
.. include:: exercises.rst

Next
----

In the next tutorial, we expand this program to use
data structure descriptors (DSDs), a core language feature of CSL.