Update to overview section

Author: Diptorup Deb

docs/source/overview.rst

@@ -4,16 +4,58 @@
 Overview
 ========
 
-Data Parallel Extension for Numba* (`numba-dpex`_) is an extension to
-the `Numba*`_ Python JIT compiler adding an architecture-agnostic kernel
-programming API, and a new front-end to compile the Data Parallel Extension
-for Numpy* (`dpnp`_) library. The ``dpnp`` Python library is a data-parallel
-implementation of `NumPy*`_'s API using the `SYCL*`_ language.
-
-.. ``numba-dpex``'s support for ``dpnp`` compilation is a new way for Numba* users
-.. to write code in a NumPy-like API that is already supported by Numba*, while at
-.. the same time automatically running such code parallelly on various types of
-.. architecture.
+Data Parallel Extension for Numba* (`numba-dpex`_) is a free and open-source
+LLVM-based code generator for portable accelerator programming in Python.
+numba_dpex defines a new kernel programming domain-specific language (DSL)
+in pure Python called `KAPI` that is modeled after the C++ embedded DSL
+`SYCL*`_.
+
+The following example illustrates a relatively simple pairwise distance matrix
+computation example written in KAPI.
+
+.. code-block:: python
+
+    from numba_dpex import kernel_api as kapi
+    import math
+    import numpy as np
+
+
+    def pairwise_distance_kernel(item: kapi.Item, data, distance):
+        i = item.get_id(0)
+        j = item.get_id(1)
+
+        data_dims = data.shape[1]
+
+        d = data.dtype.type(0.0)
+        for k in range(data_dims):
+            tmp = data[i, k] - data[j, k]
+            d += tmp * tmp
+
+        distance[j, i] = math.sqrt(d)
+
+
+    data = np.random.ranf((10000, 3)).astype(np.float32)
+    distance = np.empty(shape=(data.shape[0], data.shape[0]), dtype=np.float32)
+    exec_range = kapi.Range(data.shape[0], data.shape[0])
+    kapi.call_kernel(pairwise_distance_kernel, exec_range, data, distance)
+
+Skipping over much of the language details, at a high-level the
+``pairwise_distance_kernel`` can be viewed as a "data-parallel" function that
+gets executed individually by a set of "work items". That is, each work item
+runs the same function for a subset of the elements of the input ``data`` and
+``distance`` arrays. For programmers familiar with the CUDA or OpenCL languages,
+it is the same programming model referred to as Single Program Multiple Data
+(SPMD). As Python has no concept of a work item the KAPI function runs
+sequentially resulting in a very slow execution time. Experienced Python
+programmers will most probably write a much faster version of the function using
+NumPy*.
+
+However, using a JIT compiler numba-dpex can compile a function written in the
+KAPI language to a CPython native extension function that executes according to
+the SPMD programming model, speeding up the execution time by orders of
+magnitude. Currently, compilation of KAPI is possible for x86 CPU devices,
+Intel Gen9 integrated GPUs, Intel UHD integrated GPUs, and Intel discrete GPUs.
+
 
 ``numba-dpex`` is an open-source project and can be installed as part of `Intel
 AI Analytics Toolkit`_ or the `Intel Distribution for Python*`_. The package is