diff --git a/Grid_config.h b/Grid_config.h
index bb885708..deb6c74c 100644
--- a/Grid_config.h
+++ b/Grid_config.h
@@ -11,10 +11,10 @@
 /* #undef AVX512 */
 
 /* GRID_COMMS_MPI */
-#define GRID_COMMS_MPI 1
+/* #undef GRID_COMMS_MPI */
 
 /* GRID_COMMS_NONE */
-/* #undef GRID_COMMS_NONE */
+#define GRID_COMMS_NONE 1
 
 /* Define to 1 if you have the `gettimeofday' function. */
 #define HAVE_GETTIMEOFDAY 1
diff --git a/Grid_main.cc b/Grid_main.cc
index 1676a07b..770de9a3 100644
--- a/Grid_main.cc
+++ b/Grid_main.cc
@@ -407,7 +407,5 @@ int main (int argc, char ** argv)
 
    } // loop for lat
  } // loop for omp
-
- MPI_Finalize();
-
+ Grid_finalize();
 }
diff --git a/Grid_stencil.h b/Grid_stencil.h
index 4d73f436..e10cabaa 100644
--- a/Grid_stencil.h
+++ b/Grid_stencil.h
@@ -1,3 +1,5 @@
+#ifndef GRID_STENCIL_H
+#define GRID_STENCIL_H
 //////////////////////////////////////////////////////////////////////////////////////////
 // Must not lose sight that goal is to be able to construct really efficient
 // gather to a point stencil code. CSHIFT is not the best way, so probably need
@@ -45,14 +47,12 @@ namespace Grid {
       void Stencil_local     (int dimension,int shift,int cbmask);
       void Stencil_comms     (int dimension,int shift,int cbmask);
       void Stencil_comms_simd(int dimension,int shift,int cbmask);
+
       // Will need to implement actions for
-      //
       Copy_plane;
       Copy_plane_permute;
       Gather_plane;
 
-
-
       // The offsets to all neibours in stencil in each direction
       int                               _checkerboard;
       int                               _npoints; // Move to template param?
@@ -360,3 +360,4 @@ namespace Grid {
 
 
 };
+#endif
diff --git a/Grid_vComplexD.h b/Grid_vComplexD.h
index 88d69ecb..3278b15e 100644
--- a/Grid_vComplexD.h
+++ b/Grid_vComplexD.h
@@ -186,15 +186,6 @@ namespace Grid {
 	  Gextract<vComplexD,ComplexD>(y,extracted);
 	}
 
-	////////////////////////////////////////////////////////////////////////
-	// FIXME:  gonna remove these load/store, get, set, prefetch
-	////////////////////////////////////////////////////////////////////////
-        void vload(zvec& a){
-          this->v = a;
-        }
-        zvec vget(){
-          return this->v ;
-        }
         ///////////////////////
         // Splat
         ///////////////////////
diff --git a/Grid_vRealD.h b/Grid_vRealD.h
index a5b59be3..c51e41cf 100644
--- a/Grid_vRealD.h
+++ b/Grid_vRealD.h
@@ -128,15 +128,6 @@ namespace Grid {
 	  Gextract<vRealD,RealD>(y,extracted);
 	}
 
-	////////////////////////////////////////////////////////////////////////
-	// FIXME:  gonna remove these load/store, get, set, prefetch
-	////////////////////////////////////////////////////////////////////////
-        void vload(dvec& a){
-          this->v = a;
-        }
-        dvec vget(){
-          return this->v ;
-        }
         
         friend inline void vsplat(vRealD &ret,double a){
 #if defined (AVX1)|| defined (AVX2)
diff --git a/TODO b/TODO
index fb7d177a..5297e213 100644
--- a/TODO
+++ b/TODO
@@ -1,12 +1,12 @@
 
 * FIXME audit
-* Remove vload/store etc..
-* Replace vset with a call to merge.
-* Replace vset with a call to merge.
+* Replace vset with a call to merge.; 
+* care in Gmerge,Gextract over set.
 * Const audit
 * extract / merge extra implementation removal
 
-* Conditional execution, where etc...         -----DONE, simple test
+
+* Conditional execution, where etc...                -----DONE, simple test
 * Integer relational support                         -----DONE
 * Coordinate information, integers etc...            -----DONE
 * Integer type padding/union to vector.              -----DONE 
@@ -22,18 +22,32 @@
                                                      -----Suggests generalised cartesian subblocking
                                                           sums, returning modified grid.
 
-    Two classes of subset;
-i) red black parit subsetting.
-   (pick checkerboard).
+i)  Two classes of subset;   red black parity subsetting (pick checkerboard).
+                             cartesian sub-block subsetting
+
 
 ii) Need to be able to project one Grid to another Grid.
+
+Interface: (?)
+
+Lattice<vobj> coarse_data SubBlockSum (GridBase *CoarseGrid, Lattice<vobj> &fine_data)
+
+Operation ensure either:
+ rd[dim] divide rd[dim] fine_data
+
+This will give a distributed array over mpi ranks in a given dim IF coarse gd != 1 and _processors[d]>1
+Dimension can be *replicated* on all ranks in dimension. Need a "replicated" option on GridCartesian etc..
+
+This will give "slice" summation and fourier projection assistance.
+
     Generic concept is to subdivide (based on RD so applies to red/black or full).
     Return a type on SUB-grid from CellSum TOP-grid
     SUB-grid need not distribute but be replicated in some dims if that is how the
     cartesian communicator works.
 
-iii) No general permutation map.
+Instead of subsetting 
 
+iii) No general permutation map.
 
 * Consider switch std::vector to boost arrays.
   boost::multi_array<type, 3> A()...    to replace multi1d, multi2d etc..
@@ -41,15 +55,12 @@ iii) No general permutation map.
 *? Cell definition <-> sliceSum.
  ? Replicated arrays.
 
-
-
 * Check for missing functionality                    - partially audited against QDP++ layout
 
 * Optimise the extract/merge SIMD routines; Azusa??
 
- -- I have collated into single location at least.
-
- -- Need to use _mm_*insert/extract routines.
+ - I have collated into single location at least.
+ - Need to use _mm_*insert/extract routines.
 
 * Conformable test in Cshift routines.