diff --git a/docs/index.md b/docs/index.md
index 7b09939..0c593d6 100644
--- a/docs/index.md
+++ b/docs/index.md
@@ -28,7 +28,8 @@
   2. **Multiple execution modes**, including Spark MLContext, Spark Batch, Standalone, and JMLC.
   3. **Automatic optimization** based on data and cluster characteristics to ensure both efficiency and scalability.
 
-This version of SystemDS supports: Java 8+,  Python 3.5+, Hadoop 2.6+ (Not 3.X), and Spark 2.1+ (Not 3.X).
+This version of SystemDS supports: Java 8+,  Python 3.5+, Hadoop 2.6+ (Not 3.X), and Spark 2.1+ (Not 3.X) Nvidia CUDA 10.2
+ (CuDNN 7.x) Intel MKL (<=2019.x).
 
 # Links
 
diff --git a/docs/site/run.md b/docs/site/run.md
index 2b7032b..427da2e 100644
--- a/docs/site/run.md
+++ b/docs/site/run.md
@@ -92,8 +92,8 @@
 
 ## Using Intel MKL native instructions
 
-To use the MKL acceleration download and install the latest MKL library from [1],
-set the environment variables with the MKL-provided script `$ compilervars.sh intel64` and set
-the option `sysds.native.blas` in `SystemDS-config.xml`.
+To use the MKL acceleration download and install the latest supported MKL library (<=2019.5) from [1],
+set the environment variables with the MKL-provided script `. /opt/intel/bin/compilervars.sh intel64` (note the dot and 
+the default install location) and set the option `sysds.native.blas` in `SystemDS-config.xml` to mkl.
 
 [1]: https://software.intel.com/mkl "Intel Math Kernel Library"
\ No newline at end of file