document new CUDA_MPS_SUPPORT option in CMake

cmake/README.md

@@ -1503,6 +1503,16 @@ target API.
   </dl>
   </td>
 </tr>
+<tr>
+  <td><code>CUDA_MPS_SUPPORT</code> (CUDA only)</td>
+  <td>Enable tweaks for running with Nvidia CUDA Multi-process services daemon</td>
+  <td>
+  <dl>
+    <dt><code>on</code></dt>
+    <dt><code>off</code> (default)</dt>
+  </dl>
+  </td>
+</tr>
 <tr>
   <td><code>BIN2C</code> (CUDA only)</td>
   <td>Path to bin2c executable, will automatically pick up the first one in your $PATH.</td>

doc/src/Build_extras.txt

@@ -92,7 +92,9 @@ which GPU hardware to build for.
                           # default is Cuda-compiler dependent, but typically sm_20
 -D CUDPP_OPT=value        # optimization setting for GPU_API=cuda
                           # enables CUDA Performance Primitives Optimizations
-                      # yes (default) or no :pre
+                          # value = yes (default) or no
+-D CUDA_MPS_SUPPORT=value # enables some tweaks required to run with active nvidia-cuda-mps daemon
+                          # value = yes or no (default)
 
 GPU_ARCH settings for different GPU hardware is as follows: