diff --git a/docs/download.md b/docs/download.md
index f743eddfb38..647da901b68 100644
--- a/docs/download.md
+++ b/docs/download.md
@@ -4,6 +4,205 @@ title: Download
 nav_order: 3
 ---
 
+
+## Download link and version matrix
+
+<table border=0 cellpadding=0 cellspacing=0 width=1442 style='border-collapse:
+ collapse;table-layout:fixed;width:1081pt'>
+ <col width=160 style='mso-width-source:userset;mso-width-alt:5120;width:120pt'>
+ <col width=91 style='mso-width-source:userset;mso-width-alt:2901;width:68pt'>
+ <col width=167 style='mso-width-source:userset;mso-width-alt:5333;width:125pt'>
+ <col width=217 style='mso-width-source:userset;mso-width-alt:6954;width:163pt'>
+ <col width=227 style='mso-width-source:userset;mso-width-alt:7253;width:170pt'>
+ <col width=145 style='mso-width-source:userset;mso-width-alt:4650;width:109pt'>
+ <col width=56 style='mso-width-source:userset;mso-width-alt:1792;width:42pt'>
+ <col width=48 style='mso-width-source:userset;mso-width-alt:1536;width:36pt'>
+ <col width=52 style='mso-width-source:userset;mso-width-alt:1664;width:39pt'>
+ <col width=171 style='mso-width-source:userset;mso-width-alt:5461;width:128pt'>
+ <col width=108 style='mso-width-source:userset;mso-width-alt:3456;width:81pt'>
+ <tr class=xl65 height=72 style='height:54.0pt'>
+  <td height=72 class=xl68 width=160 style='height:54.0pt;width:120pt'>RAPIDS
+  Accelerator For <br>
+    Apache Spark<font class="font5"><sup>1</sup></font></td>
+  <td class=xl68 width=91 style='border-left:none;width:68pt'>RAPIDS<br>
+    (cuDF)<font class="font5"><sup>2</sup></font></td>
+  <td class=xl67 width=167 style='border-left:none;width:125pt'>CUDA &amp;
+  NVIDIA Driver<font class="font5"><sup>3</sup></font></td>
+  <td class=xl67 width=217 style='border-left:none;width:163pt'>Spark</td>
+  <td class=xl67 width=227 style='border-left:none;width:170pt'>Hadoop</td>
+  <td class=xl67 width=145 style='border-left:none;width:109pt'>OS</td>
+  <td class=xl67 width=56 style='border-left:none;width:42pt'>Python</td>
+  <td class=xl67 width=48 style='border-left:none;width:36pt'>Scala</td>
+  <td class=xl67 width=52 style='border-left:none;width:39pt'>JAVA</td>
+  <td class=xl67 width=171 style='border-left:none;width:128pt'>GPU Requirement</td>
+  <td class=xl67 width=108 style='border-left:none;width:81pt'>GPU Tested</td>
+ </tr>
+ <tr class=xl65 height=55 style='mso-height-source:userset;height:41.0pt'>
+  <td rowspan=2 height=107 class=xl70 style='height:80.0pt;border-top:none'><a
+  href="https://repo1.maven.org/maven2/com/nvidia/rapids-4-spark_2.12/0.1.0/rapids-4-spark_2.12-0.1.0.jar">0.1</a></td>
+  <td class=xl70 style='border-top:none;border-left:none'><a
+  href="https://repo1.maven.org/maven2/ai/rapids/cudf/0.14/cudf-0.14-cuda10-1.jar">0.14</a></td>
+  <td class=xl66 style='border-top:none;border-left:none'>10.1.2 &amp; 418.87+</td>
+  <td rowspan=2 class=xl72 style='border-top:none'>3.0</td>
+  <td rowspan=2 class=xl71 width=227 style='border-top:none;width:170pt'>2.10+,
+  3.1.1+<br>
+    3.1.1 for nvidia-docker version 2</td>
+  <td rowspan=2 class=xl69 width=145 style='border-top:none;width:109pt'>Ubuntu
+  16.04<br>
+    Ubuntu 18.04<br>
+    CentOS 7</td>
+  <td rowspan=2 class=xl66 style='border-top:none'>3.x</td>
+  <td rowspan=2 class=xl66 style='border-top:none'>2.12</td>
+  <td rowspan=2 class=xl66 style='border-top:none'>8</td>
+  <td rowspan=2 class=xl66 style='border-top:none'>NVIDIA Pascal™ or better</td>
+  <td rowspan=2 class=xl69 width=108 style='border-top:none;width:81pt'>V100,
+  T4</td>
+ </tr>
+ <tr height=52 style='mso-height-source:userset;height:39.0pt'>
+  <td height=52 class=xl70 style='height:39.0pt;border-top:none;border-left:
+  none'><a
+  href="https://repo1.maven.org/maven2/ai/rapids/cudf/0.14/cudf-0.14-cuda10-2.jar">0.14</a></td>
+  <td class=xl69 width=167 style='border-top:none;border-left:none;width:125pt'>10.2
+  &amp; 440.33+</td>
+ </tr>
+ <tr height=52 style='mso-height-source:userset;height:39.0pt'>
+  <td rowspan=3 height=172 class=xl70 style='height:129.0pt;border-top:none'><a
+  href="https://repo1.maven.org/maven2/com/nvidia/rapids-4-spark_2.12/0.2.0/rapids-4-spark_2.12-0.2.0.jar">0.2</a></td>
+  <td class=xl70 style='border-top:none;border-left:none'><a
+  href="https://repo1.maven.org/maven2/ai/rapids/cudf/0.15/cudf-0.15-cuda10-1.jar">0.15</a></td>
+  <td class=xl66 style='border-top:none;border-left:none'>10.1.2 &amp; 418.87+</td>
+  <td rowspan=3 class=xl71 width=217 style='border-top:none;width:163pt'>3.0,
+  3.0.1</td>
+  <td rowspan=3 class=xl71 width=227 style='border-top:none;width:170pt'>2.10+,
+  3.1.1+<br>
+    3.1.1 for nvidia-docker version 2</td>
+  <td rowspan=3 class=xl69 width=145 style='border-top:none;width:109pt'>Ubuntu
+  16.04<br>
+    Ubuntu 18.04<br>
+    CentOS 7</td>
+  <td rowspan=3 class=xl66 style='border-top:none'>3.x</td>
+  <td rowspan=3 class=xl66 style='border-top:none'>2.12</td>
+  <td rowspan=3 class=xl66 style='border-top:none'>8</td>
+  <td rowspan=3 class=xl66 style='border-top:none'>NVIDIA Pascal™ or better</td>
+  <td rowspan=3 class=xl69 width=108 style='border-top:none;width:81pt'>V100,
+  T4,A100</td>
+ </tr>
+ <tr height=52 style='mso-height-source:userset;height:39.0pt'>
+  <td height=52 class=xl70 style='height:39.0pt;border-top:none;border-left:
+  none'><a
+  href="https://repo1.maven.org/maven2/ai/rapids/cudf/0.15/cudf-0.15-cuda10-2.jar">0.15</a></td>
+  <td class=xl69 width=167 style='border-top:none;border-left:none;width:125pt'>10.2
+  &amp; 440.33+</td>
+ </tr>
+ <tr height=68 style='mso-height-source:userset;height:51.0pt'>
+  <td height=68 class=xl70 style='height:51.0pt;border-top:none;border-left:
+  none'><a
+  href="https://repo1.maven.org/maven2/ai/rapids/cudf/0.15/cudf-0.15-cuda11.jar">0.15</a></td>
+  <td class=xl69 width=167 style='border-top:none;border-left:none;width:125pt'>11.0
+  &amp; 450.36+</td>
+ </tr>
+ <tr height=68 style='mso-height-source:userset;height:51.0pt'>
+  <td rowspan=3 height=204 class=xl70 style='height:153.0pt;border-top:none'><a
+  href="https://repo1.maven.org/maven2/com/nvidia/rapids-4-spark_2.12/0.3.0/rapids-4-spark_2.12-0.3.0.jar">0.3</a></td>
+  <td class=xl70 style='border-top:none;border-left:none'><a
+  href="https://repo1.maven.org/maven2/ai/rapids/cudf/0.17/cudf-0.17-cuda10-1.jar">0.17</a></td>
+  <td class=xl66 style='border-top:none;border-left:none'>10.1.2 &amp; 418.87+</td>
+  <td rowspan=3 class=xl71 width=217 style='border-top:none;width:163pt'>3.0,
+  3.0.1<br>
+    Databricks 7.3 ML LTS Runtime<br>
+    GCP Dataproc 2.0<span style='mso-spacerun:yes'> </span></td>
+  <td rowspan=3 class=xl71 width=227 style='border-top:none;width:170pt'>2.10+,
+  3.1.1+<br>
+    3.1.1 for nvidia-docker version 2</td>
+  <td rowspan=3 class=xl69 width=145 style='border-top:none;width:109pt'>Ubuntu
+  16.04<br>
+    Ubuntu 18.04<br>
+    CentOS 7</td>
+  <td rowspan=3 class=xl66 style='border-top:none'>3.6+</td>
+  <td rowspan=3 class=xl66 style='border-top:none'>2.12</td>
+  <td rowspan=3 class=xl66 style='border-top:none'>8</td>
+  <td rowspan=3 class=xl66 style='border-top:none'>NVIDIA Pascal™ or better</td>
+  <td rowspan=3 class=xl69 width=108 style='border-top:none;width:81pt'>V100,
+  T4,A100</td>
+ </tr>
+ <tr height=68 style='mso-height-source:userset;height:51.0pt'>
+  <td height=68 class=xl70 style='height:51.0pt;border-top:none;border-left:
+  none'><a
+  href="https://repo1.maven.org/maven2/ai/rapids/cudf/0.17/cudf-0.17-cuda10-2.jar">0.17</a></td>
+  <td class=xl69 width=167 style='border-top:none;border-left:none;width:125pt'>10.2
+  &amp; 440.33+</td>
+ </tr>
+ <tr height=68 style='mso-height-source:userset;height:51.0pt'>
+  <td height=68 class=xl70 style='height:51.0pt;border-top:none;border-left:
+  none'><a
+  href="https://repo1.maven.org/maven2/ai/rapids/cudf/0.17/cudf-0.17-cuda11.jar">0.17</a></td>
+  <td class=xl69 width=167 style='border-top:none;border-left:none;width:125pt'>11.0
+  &amp; 450.36+</td>
+ </tr>
+ <tr height=68 style='mso-height-source:userset;height:51.0pt'>
+  <td rowspan=3 height=204 class=xl70 style='height:153.0pt;border-top:none'><a
+  href="https://repo1.maven.org/maven2/com/nvidia/rapids-4-spark_2.12/0.4.0/rapids-4-spark_2.12-0.4.0.jar">0.4</a></td>
+  <td class=xl70 style='border-top:none;border-left:none'><a
+  href="https://repo1.maven.org/maven2/ai/rapids/cudf/0.18/cudf-0.18-cuda10-1.jar">0.18</a></td>
+  <td class=xl66 style='border-top:none;border-left:none'>10.1.2 &amp; 418.87+</td>
+  <td rowspan=3 class=xl71 width=217 style='border-top:none;width:163pt'>3.0,
+  3.0.1, 3.0.2, 3.1.1<br>
+    Databricks 7.3 ML LTS Runtime<br>
+    GCP Dataproc 2.0 <br>
+    AWS EMR 6.3.0 (?)</td>
+  <td rowspan=3 class=xl71 width=227 style='border-top:none;width:170pt'>2.10+
+  ,3.1.1+<br>
+    3.1.1 for nvidia-docker version 2</td>
+  <td rowspan=3 class=xl69 width=145 style='border-top:none;width:109pt'>Ubuntu
+  16.04<br>
+    Ubuntu 18.04<br>
+    CentOS 7</td>
+  <td rowspan=3 class=xl66 style='border-top:none'>3.6+</td>
+  <td rowspan=3 class=xl66 style='border-top:none'>2.12</td>
+  <td rowspan=3 class=xl66 style='border-top:none'>8</td>
+  <td rowspan=3 class=xl66 style='border-top:none'>NVIDIA Pascal™ or better</td>
+  <td rowspan=3 class=xl69 width=108 style='border-top:none;width:81pt'>V100,
+  T4,A100</td>
+ </tr>
+ <tr height=68 style='mso-height-source:userset;height:51.0pt'>
+  <td height=68 class=xl70 style='height:51.0pt;border-top:none;border-left:
+  none'><a
+  href="https://repo1.maven.org/maven2/ai/rapids/cudf/0.18/cudf-0.18-cuda10-2.jar">0.18</a></td>
+  <td class=xl69 width=167 style='border-top:none;border-left:none;width:125pt'>10.2
+  &amp; 440.33+</td>
+ </tr>
+ <tr height=68 style='mso-height-source:userset;height:51.0pt'>
+  <td height=68 class=xl70 style='height:51.0pt;border-top:none;border-left:
+  none'><a
+  href="https://repo1.maven.org/maven2/ai/rapids/cudf/0.18/cudf-0.18-cuda11.jar">0.18</a></td>
+  <td class=xl69 width=167 style='border-top:none;border-left:none;width:125pt'>11.0
+  &amp; 450.36+</td>
+ </tr>
+ <![if supportMisalignedColumns]>
+ <tr height=0 style='display:none'>
+  <td width=160 style='width:120pt'></td>
+  <td width=91 style='width:68pt'></td>
+  <td width=167 style='width:125pt'></td>
+  <td width=217 style='width:163pt'></td>
+  <td width=227 style='width:170pt'></td>
+  <td width=145 style='width:109pt'></td>
+  <td width=56 style='width:42pt'></td>
+  <td width=48 style='width:36pt'></td>
+  <td width=52 style='width:39pt'></td>
+  <td width=171 style='width:128pt'></td>
+  <td width=108 style='width:81pt'></td>
+ </tr>
+ <![endif]>
+</table>
+
+* Note 1:	[RAPIDS Accelerator For Apache Spark](https://github.com/NVIDIA/spark-rapids) provides a set of plugins for Apache Spark that leverage GPUs to accelerate processing via the RAPIDS libraries and UCX.
+
+* Note 2:	[RAPIDS cuDF](https://github.com/rapidsai/cudf) project is the cornerstone for "RAPIDS Accelerator For Apache Spark".
+
+* Note 3:	CUDA and NVIDIA Driver need to be installed on the machines where CUDA-capable GPU is attached.
+
+* Note 4:	Spark job needs 2 jars -- "RAPIDS Accelerator For Apache Spark" jar, and "RAPIDS cuDF" jar based on corresponding CUDA&NVIDIA Driver version.
+
 ## Release v0.4.0
 
 New functionality for the release includes
@@ -45,11 +244,6 @@ Software Requirements:
 	
 	Python 3.6+, Scala 2.12, Java 8 
 
-### Download v0.4.0
-* [RAPIDS Spark Package](https://repo1.maven.org/maven2/com/nvidia/rapids-4-spark_2.12/0.4.0/rapids-4-spark_2.12-0.4.0.jar)
-* [cuDF 11.0 Package](https://repo1.maven.org/maven2/ai/rapids/cudf/0.18/cudf-0.18-cuda11.jar)
-* [cuDF 10.2 Package](https://repo1.maven.org/maven2/ai/rapids/cudf/0.18/cudf-0.18-cuda10-2.jar)
-* [cuDF 10.1 Package](https://repo1.maven.org/maven2/ai/rapids/cudf/0.18/cudf-0.18-cuda10-1.jar)
 
 ## Release v0.3.0
 This release includes additional performance improvements, including
@@ -88,12 +282,6 @@ Software Requirements:
 	
 	Python 3.6+, Scala 2.12, Java 8 
 
-### Download v0.3.0
-* [RAPIDS Spark Package](https://repo1.maven.org/maven2/com/nvidia/rapids-4-spark_2.12/0.3.0/rapids-4-spark_2.12-0.3.0.jar)
-* [cuDF 11.0 Package](https://repo1.maven.org/maven2/ai/rapids/cudf/0.17/cudf-0.17-cuda11.jar)
-* [cuDF 10.2 Package](https://repo1.maven.org/maven2/ai/rapids/cudf/0.17/cudf-0.17-cuda10-2.jar)
-* [cuDF 10.1 Package](https://repo1.maven.org/maven2/ai/rapids/cudf/0.17/cudf-0.17-cuda10-1.jar)
-
 ## Release v0.2.0
 This is the second release of the RAPIDS Accelerator for Apache Spark.  Adaptive Query Execution
 [SPARK-31412](https://issues.apache.org/jira/browse/SPARK-31412) is a new enhancement that was
@@ -134,11 +322,6 @@ Software Requirements:
 	
 	Python 3.x, Scala 2.12, Java 8 
 
-### Download v0.2.0
-* [RAPIDS Spark Package](https://repo1.maven.org/maven2/com/nvidia/rapids-4-spark_2.12/0.2.0/rapids-4-spark_2.12-0.2.0.jar)
-* [cuDF 11.0 Package](https://repo1.maven.org/maven2/ai/rapids/cudf/0.15/cudf-0.15-cuda11.jar)
-* [cuDF 10.2 Package](https://repo1.maven.org/maven2/ai/rapids/cudf/0.15/cudf-0.15-cuda10-2.jar)
-* [cuDF 10.1 Package](https://repo1.maven.org/maven2/ai/rapids/cudf/0.15/cudf-0.15-cuda10-1.jar)
 
 ## Release v0.1.0
 
@@ -160,10 +343,5 @@ Software Requirements:
     Python 3.x, Scala 2.12, Java 8 
 
 
-### Download v0.1.0
-* [RAPIDS Spark Package](https://repo1.maven.org/maven2/com/nvidia/rapids-4-spark_2.12/0.1.0/rapids-4-spark_2.12-0.1.0.jar)
-* [cuDF 10.2 Package](https://repo1.maven.org/maven2/ai/rapids/cudf/0.14/cudf-0.14-cuda10-2.jar)
-* [cuDF 10.1 Package](https://repo1.maven.org/maven2/ai/rapids/cudf/0.14/cudf-0.14-cuda10-1.jar)
-