diff --git a/doc/source/Decomp.txt b/doc/source/Decomp.txt
index 4a3289d271f..5c1b291ab2d 100644
--- a/doc/source/Decomp.txt
+++ b/doc/source/Decomp.txt
@@ -42,8 +42,7 @@ only one IO task.  Since this technique does not guarantee that data
 on the IO node represents a contiguous block of data on the file it
 may require multiple calls to the underlying (NetCDF) IO library.
 
-As an example suppose we have a global two dimensional grid of size 4x5 decomposed over 5 tasks. We represent the 
-two dimensional grid in terms of offset from the initial element ie
+As an example suppose we have a global two dimensional grid of size 4x5 decomposed over 5 tasks. We represent the two dimensional grid in terms of offset from the initial element ie
 <pre>
      0  1  2  3 
      4  5  6  7 
diff --git a/doc/source/Installing.txt b/doc/source/Installing.txt
index e7449df3ddb..be27f177991 100644
--- a/doc/source/Installing.txt
+++ b/doc/source/Installing.txt
@@ -112,7 +112,7 @@ Once the tests have been built, you may run tests with:
     > ctest
 
 
-_If you have not run `make tests` before you run `ctest`, then you will see
+_Note: If you have not run `make tests` before you run `ctest`, then you will see
 all of the tests fail._
 
 Alternatively, you may build the test executables and then run tests 
@@ -124,7 +124,7 @@ immediately with:
 
 (similar to the typical `make check` Autotools target).
 
-*NOTE:* These tests are designed to run in parallel.
+*ANOTHER NOTE:* These tests are designed to run in parallel.
 If you are on one of the supported supercomputing platforms (i.e., NERSC, NWSC, ALCF, 
 etc.), then the `ctest` command will assume that the tests will be run in an appropriately configured and scheduled parallel job.  This can be done by requesting an interactive session from the login nodes and then running `ctest` from within the interactive terminal.  Alternatively, this can be done by running the `ctest` command from a job submission script.  It is important to understand, however, that `ctest` itself will preface all of the test executable commands with the appropriate `mpirun`/`mpiexec`/`runjob`/etc. Hence, you should not further preface the `ctest` command with these MPI launchers.
 
diff --git a/src/flib/CMakeLists.txt b/src/flib/CMakeLists.txt
index 380956c10c3..535ac5d7d0c 100644
--- a/src/flib/CMakeLists.txt
+++ b/src/flib/CMakeLists.txt
@@ -51,6 +51,9 @@ target_compile_definitions (piof
 if ("${CMAKE_Fortran_COMPILER_ID}" STREQUAL "GNU")
     target_compile_options (piof
         PRIVATE -ffree-line-length-none)
+elseif (CMAKE_Fortran_COMPILER_ID MATCHES "NAG")
+   target_compile_options (piof
+       PUBLIC -mismatch_all)
 endif()
 
 # Look for c_sizeof capability
@@ -263,4 +266,4 @@ endif ()
 if (NOT PnetCDF_Fortran_FOUND AND NOT NetCDF_Fortran_FOUND)
     message (FATAL_ERROR "Must have PnetCDF and/or NetCDF Fortran libraries")
 endif ()
-     
\ No newline at end of file
+     
diff --git a/src/gptl/CMakeLists.txt b/src/gptl/CMakeLists.txt
index ac3265276a2..93358858560 100644
--- a/src/gptl/CMakeLists.txt
+++ b/src/gptl/CMakeLists.txt
@@ -44,6 +44,11 @@ endif ()
 target_compile_definitions (gptl
     PUBLIC ${CMAKE_Fortran_COMPILER_DIRECTIVE})
 
+if (CMAKE_Fortran_COMPILER_ID MATCHES "NAG")
+   target_compile_options (gptl
+       PUBLIC -mismatch_all)
+endif ()
+
 #==============================================================================
 #  DEFINE THE INSTALL
 #==============================================================================
diff --git a/tests/performance/pioperformance.F90 b/tests/performance/pioperformance.F90
index ae0e6d46c85..cb49016ebc9 100644
--- a/tests/performance/pioperformance.F90
+++ b/tests/performance/pioperformance.F90
@@ -308,7 +308,8 @@ subroutine pioperformancetest(filename, piotypes, mype, npe_base, rearrangers, n
 #ifdef VARDOUBLE
                    nvarmult = nvarmult+2
 #endif
-                   print *, 'write ',rearr_name(rearr), varsize, ntasks, nvars, nvarmult*nvars*nframes*gmaplen*4.0/(1048576.0*wall(2))
+                   print *, 'write ',rearr_name(rearr), varsize, ntasks, nvars, &
+                                     nvarmult*nvars*nframes*gmaplen*4.0/(1048576.0*wall(2))
 #ifdef BGQTRY
   call print_memusage()
 #endif