[Review] Update readme and docstrings to indicate GPU support

README.md

@@ -22,6 +22,7 @@ if you need it.
 * **Your data - your queries**: Use Python user-defined functions (UDFs) in SQL without any performance drawback and extend your SQL queries with the large number of Python libraries, e.g. machine learning, different complicated input formats, complex statistics.
 * **Easy to install and maintain**: `dask-sql` is just a pip/conda install away (or a docker run if you prefer). No need for complicated cluster setups - `dask-sql` will run out of the box on your machine and can be easily connected to your computing cluster.
 * **Use SQL from wherever you like**: `dask-sql` integrates with your jupyter notebook, your normal Python module or can be used as a standalone SQL server from any BI tool. It even integrates natively with [Apache Hue](https://gethue.com/).
+* **GPU Support**: `dask-sql` has _experimental_ support for running SQL queries on CUDA-enabled GPUs by utilizing [RAPIDS](https://rapids.ai) libraries like [`cuDF`](https://github.com/rapidsai/cudf), enabling accelerated compute for SQL.
 
 Read more in the [documentation](https://dask-sql.readthedocs.io/en/latest/).
 
@@ -71,9 +72,6 @@ Have a look into the [documentation](https://dask-sql.readthedocs.io/en/latest/)
 > `dask-sql` is currently under development and does so far not understand all SQL commands (but a large fraction).
 We are actively looking for feedback, improvements and contributors!
 
-If you would like to utilize GPUs for your SQL queries, have a look into the [blazingSQL](https://github.com/BlazingDB/blazingsql) project.
-
-
 ## Installation
 
 `dask-sql` can be installed via `conda` (preferred) or `pip` - or in a development environment.

docs/index.rst

@@ -13,6 +13,7 @@ if you need it.
 * **Your data - your queries**: Use Python user-defined functions (UDFs) in SQL without any performance drawback and extend your SQL queries with the large number of Python libraries, e.g. machine learning, different complicated input formats, complex statistics.
 * **Easy to install and maintain**: ``dask-sql`` is just a pip/conda install away (or a docker run if you prefer). No need for complicated cluster setups - ``dask-sql`` will run out of the box on your machine and can be easily connected to your computing cluster.
 * **Use SQL from wherever you like**: ``dask-sql`` integrates with your jupyter notebook, your normal Python module or can be used as a standalone SQL server from any BI tool. It even integrates natively with `Apache Hue <https://gethue.com/>`_.
+* **GPU Support**: ``dask-sql`` has `experimental` support for running SQL queries on CUDA-enabled GPUs by utilizing `RAPIDS <https://rapids.ai>`_ libraries like `cuDF <https://github.com/rapidsai/cudf>`_ , enabling accelerated compute for SQL.
 
 
 Example
@@ -54,9 +55,6 @@ Any pandas or dask dataframe can be used as input and ``dask-sql`` understands a
    # ... or use it for any other dask calculation
    print(result.x.mean().compute())
 
-The API of ``dask-sql`` is very similar to the one from `blazingsql <http://blazingsql.com/>`_,
-which makes interchanging distributed CPU and GPU calculation easy.
-
 
 .. toctree::
    :maxdepth: 1

docs/pages/custom.rst

@@ -34,7 +34,7 @@ After registration, the function can be used as any other usual SQL function:
 Scalar functions can have one or more input parameters and can combine columns and literal values.
 
 Row-Wise Pandas UDFs
-----------------
+--------------------
 In some cases it may be easier to write custom functions which process a dict like row object, such as those consumed by ``pandas.DataFrame.apply``.
 These functions may be registered as above and flagged as row UDFs using the `row_udf` keyword argument: