Fix kernels bug hopefully (#931)

Co-authored-by: Spencer Bryngelson <sbryngelson@gmail.com>

Author: prathi-wind

docs/documentation/readme.md

@@ -9,6 +9,7 @@
 - [Running MFC](running.md)
 - [Flow Visualization](visualization.md)
 - [Performance](expectedPerformance.md)
+- [GPU Parallelization](gpuParallelization.md)
 - [MFC's Authors](authors.md)
 - [References](references.md)
 

src/simulation/m_data_output.fpp

@@ -316,14 +316,14 @@ contains
             Rc_min_loc = minval(Rc_sf)
         end if
 #else
-        !$acc kernels
-        icfl_max_loc = maxval(icfl_sf)
-        !$acc end kernels
+        #:call GPU_PARALLEL(copyout='[icfl_max_loc]', copyin='[icfl_sf]')
+            icfl_max_loc = maxval(icfl_sf)
+        #:endcall GPU_PARALLEL
         if (viscous) then
-            !$acc kernels
-            vcfl_max_loc = maxval(vcfl_sf)
-            Rc_min_loc = minval(Rc_sf)
-            !$acc end kernels
+            #:call GPU_PARALLEL(copyout='[vcfl_max_loc, Rc_min_loc]', copyin='[vcfl_sf,Rc_sf]')
+                vcfl_max_loc = maxval(vcfl_sf)
+                Rc_min_loc = minval(Rc_sf)
+            #:endcall GPU_PARALLEL
         end if
 #endif
 

src/simulation/m_time_steppers.fpp

@@ -993,9 +993,9 @@ contains
             end do
         end do
 
-        !$acc kernels
-        dt_local = minval(max_dt)
-        !$acc end kernels
+        #:call GPU_PARALLEL(copyout='[dt_local]', copyin='[max_dt]')
+            dt_local = minval(max_dt)
+        #:endcall GPU_PARALLEL
 
         if (num_procs == 1) then
             dt = dt_local