diff --git a/README.md b/README.md
index 13dd6996..86506f52 100644
--- a/README.md
+++ b/README.md
@@ -187,10 +187,11 @@ Alternatively, some CPU codenames can be directly used:
 | `<code>`    | Description                            |
 | ----------- | -------------------------------------- |
 | `KNL`       | [Intel Xeon Phi codename Knights Landing](http://ark.intel.com/products/codename/48999/Knights-Landing) |
+| `SKL`       | [Intel Skylake with AVX512 extensions](https://ark.intel.com/products/codename/37572/Skylake#@server) |
 | `BGQ`       | Blue Gene/Q                            |
 
 #### Notes:
-- We currently support AVX512 only for the Intel compiler. Support for GCC and clang will appear in future versions of Grid when the AVX512 support within GCC and clang will be more advanced.
+- We currently support AVX512 for the Intel compiler and GCC (KNL and SKL target). Support for clang will appear in future versions of Grid when the AVX512 support in the compiler will be more advanced.
 - For BG/Q only [bgclang](http://trac.alcf.anl.gov/projects/llvm-bgq) is supported. We do not presently plan to support more compilers for this platform.
 - BG/Q performances are currently rather poor. This is being investigated for future versions.
 - The vector size for the `GEN` target can be specified with the `configure` script option `--enable-gen-simd-width`.
diff --git a/extras/Hadrons/Modules/MGauge/FundtoHirep.cc b/extras/Hadrons/Modules/MGauge/FundtoHirep.cc
index f15a3b7c..31c5a34d 100644
--- a/extras/Hadrons/Modules/MGauge/FundtoHirep.cc
+++ b/extras/Hadrons/Modules/MGauge/FundtoHirep.cc
@@ -57,7 +57,7 @@ std::vector<std::string> TFundtoHirep<Rep>::getOutput(void)
 template <typename Rep>
 void TFundtoHirep<Rep>::setup(void)
 {
-    env().template registerLattice<typename Rep::LatticeField>(getName());
+    envCreateLat(typename Rep::LatticeField, getName());
 }
 
 // execution ///////////////////////////////////////////////////////////////////
@@ -70,6 +70,6 @@ void TFundtoHirep<Rep>::execute(void)
     Rep TargetRepresentation(U._grid);
     TargetRepresentation.update_representation(U);
 
-   typename Rep::LatticeField &URep = *env().template createLattice<typename Rep::LatticeField>(getName());
+    auto &URep = envGet(typename Rep::LatticeField, getName());
     URep = TargetRepresentation.U;
 }
diff --git a/lib/communicator/SharedMemoryMPI.cc b/lib/communicator/SharedMemoryMPI.cc
index d7bd7c65..2a62b7ac 100644
--- a/lib/communicator/SharedMemoryMPI.cc
+++ b/lib/communicator/SharedMemoryMPI.cc
@@ -182,6 +182,7 @@ void GlobalSharedMemory::OptimalCommunicator(const std::vector<int> &processors,
 #ifdef GRID_MPI3_SHMMMAP
 void GlobalSharedMemory::SharedMemoryAllocate(uint64_t bytes, int flags)
 {
+  std::cout << "SharedMemoryAllocate "<< bytes<< " MMAP implementation "<<std::endl;
   assert(_ShmSetup==1);
   assert(_ShmAlloc==0);
   //////////////////////////////////////////////////////////////////////////////////////////////////////////
@@ -218,6 +219,7 @@ void GlobalSharedMemory::SharedMemoryAllocate(uint64_t bytes, int flags)
     assert(((uint64_t)ptr&0x3F)==0);
     close(fd);
     WorldShmCommBufs[r] =ptr;
+    std::cout << "Set WorldShmCommBufs["<<r<<"]="<<ptr<< "("<< bytes<< "bytes)"<<std::endl;
   }
   _ShmAlloc=1;
   _ShmAllocBytes  = bytes;
@@ -232,6 +234,7 @@ void GlobalSharedMemory::SharedMemoryAllocate(uint64_t bytes, int flags)
 ////////////////////////////////////////////////////////////////////////////////////////////
 void GlobalSharedMemory::SharedMemoryAllocate(uint64_t bytes, int flags)
 { 
+  std::cout << "SharedMemoryAllocate "<< bytes<< " SHMOPEN implementation "<<std::endl;
   assert(_ShmSetup==1);
   assert(_ShmAlloc==0); 
   MPI_Barrier(WorldShmComm);
@@ -259,7 +262,11 @@ void GlobalSharedMemory::SharedMemoryAllocate(uint64_t bytes, int flags)
 #endif
       void * ptr =  mmap(NULL,size, PROT_READ | PROT_WRITE, mmap_flag, fd, 0);
       
-      if ( ptr == (void * )MAP_FAILED ) {       perror("failed mmap");      assert(0);    }
+      std::cout << "Set WorldShmCommBufs["<<r<<"]="<<ptr<< "("<< size<< "bytes)"<<std::endl;
+      if ( ptr == (void * )MAP_FAILED ) {       
+	perror("failed mmap");     
+	assert(0);    
+      }
       assert(((uint64_t)ptr&0x3F)==0);
       
       WorldShmCommBufs[r] =ptr;
@@ -318,11 +325,12 @@ void SharedMemory::SetCommunicator(Grid_MPI_Comm comm)
   heap_size = GlobalSharedMemory::ShmAllocBytes();
   for(int r=0;r<ShmSize;r++){
 
-    uint32_t sr = (r==ShmRank) ? GlobalSharedMemory::WorldRank : 0 ;
+    uint32_t wsr = (r==ShmRank) ? GlobalSharedMemory::WorldShmRank : 0 ;
 
-    MPI_Allreduce(MPI_IN_PLACE,&sr,1,MPI_UINT32_T,MPI_SUM,comm);
+    MPI_Allreduce(MPI_IN_PLACE,&wsr,1,MPI_UINT32_T,MPI_SUM,ShmComm);
 
-    ShmCommBufs[r] = GlobalSharedMemory::WorldShmCommBufs[sr];
+    ShmCommBufs[r] = GlobalSharedMemory::WorldShmCommBufs[wsr];
+    //    std::cout << "SetCommunicator ShmCommBufs ["<< r<< "] = "<< ShmCommBufs[r]<< "  wsr = "<<wsr<<std::endl;
   }
   ShmBufferFreeAll();