diff --git a/Doc/user_guide.tex b/Doc/user_guide.tex
index e28ac836a..4aece316e 100644
--- a/Doc/user_guide.tex
+++ b/Doc/user_guide.tex
@@ -428,12 +428,11 @@ formerly PGI compiler, freely available for download.
 
 As a rule, \qe\ tries to keep compatibility with older compilers,
 avoiding nonstandard extensions and newer features that are not
-widespread or stabilized. If however your compiler is older say
-than $\sim 5$ years or so it is quite likely that something will
-not work. The same applies to mathematical and MPI libraries.
-For GPU compilation, get the most recent NVidia HPC SDK you can:
-while compilers from v. 17.4 on should work, several problems and
-limitations are known to exist for old compiler versions.
+widespread or stabilized. If however your compiler is older than
+a few ($\sim 5$) years, it is likely that something will not work.
+The same applies to mathematical and MPI libraries.
+For GPU compilation, you need v.19.10 or later of the NVidia HPC SDK
+(previous versions are no longer supported).
 
 Big computing centers typically provide a Fortran compiler complete
 with all needed libraries. Workstations or ``commodity'' machines
@@ -621,10 +620,11 @@ and the following optional packages:\\
 \end{tabular}\\
 \\
 In order to compile the code for GPU's you will need a recent version
--- the more recent, the better -- of the NVidia HPC software development
-kit (SDK). OpenMP must be enabled, and you may want to use a CUDA-aware MPI
-distribution if running on multiple GPUs in order to optimize the
-interprocess data transfer. The following \configure\ options are
+(v.19.10 or later: the more recent, the better) of the NVidia HPC software
+development kit (SDK). OpenMP should be enabled. Enabling faster communications
+between GPUs, via NVlink or Infiniband RDMA, is essential for optimal
+performance. If your MPI library is built to be CUDA-aware, then enable it
+with \texttt{--with-cuda-mpi=yes}. The following \configure\ options are
 available:\\
 \begin{tabular}{ll}
 \texttt{--with-cuda=value}&         enable compilation of GPU-accelerated subroutines.\\
@@ -640,10 +640,7 @@ available:\\
                                   & \texttt{value} must be consistent with the\\
                                   & CUDA Toolkit installed on the workstation \\
                                   & or available on the compute nodes of the HPC facility.\\
-\texttt{--enable-cuda-env-check=[yes]}& if set, sanity checks on the CUDA environment\\
-                                      & are performed (default: no).
-\end{tabular}\\
-
+\texttt{--with-cuda-mpi=value}    & enable usage of a CUDA-aware MPI library (default: no).\\
 
 To modify or extend \configure, see the Wiki pages on GitLab:
 \texttt{https://gitlab.com/QEF/q-e/-/wikis}.
@@ -662,7 +659,7 @@ libraries (e.g. you need to add \texttt{-D\_\_FFTW} to \texttt{DFLAGS}
 if you want to link internal FFTW). For a correct choice of preprocessing
 flags, refer to the documentation in \texttt{include/defs.h.README}.
 
-Even if \configure\ works, yuo may need to tweak the \texttt{make.inc}
+Even if \configure\ works, you may need to tweak the \texttt{make.inc}
 file. It is very simple, but please note that if you change any settings
 (e.g. preprocessing, compilation flags)
 after a previous, successful or failed, compilation, you must run
diff --git a/PW/src/setup.f90 b/PW/src/setup.f90
index 3754568db..95a4e6c78 100644
--- a/PW/src/setup.f90
+++ b/PW/src/setup.f90
@@ -808,35 +808,15 @@ END SUBROUTINE setup_para
 !
 !----------------------------------------------------------------------------
 LOGICAL FUNCTION check_gpu_support( )
-  !
-  ! FIXME: seems useless. If one has GPUs, one wants to run on GPUs.
-  !
+  ! Minimal case: returns true if compiled for GPUs
   IMPLICIT NONE
   !
-  LOGICAL, SAVE :: first = .TRUE.
-  LOGICAL, SAVE :: saved_value = .FALSE.
-  CHARACTER(len=255) :: gpu_env
-  INTEGER :: vlen, istat
-
 #if defined(__CUDA)
-  IF( .NOT. first ) THEN
-      check_gpu_support = saved_value
-      RETURN
-  END IF
-  first = .FALSE.
-  !
-  CALL get_environment_variable("USEGPU", gpu_env, vlen, istat, .true.)
-  IF (istat == 0) THEN
-     check_gpu_support = (gpu_env /= "no")
-  ELSE 
-     check_gpu_support = .TRUE.
-  END IF
-  saved_value = check_gpu_support
-  !
+  check_gpu_support = .TRUE.
 #else
   check_gpu_support = .FALSE.
 #endif
-  RETURN
+  !
 END FUNCTION check_gpu_support
 !
 !----------------------------------------------------------------------------
diff --git a/README_GPU.md b/README_GPU.md
index 909d25a76..27e00f43c 100644
--- a/README_GPU.md
+++ b/README_GPU.md
@@ -9,9 +9,9 @@ Installation
 ============
 
 This version requires the nvfortran (previously PGI) compiler from the
-freely available NVidia HPC SDK. You are advised to use the most recent
-version of NVidia software you can find. While any version later than 17.4
-should work, many glitches are known to exist in older versions. 
+NVidia HPC SDK, v.19.10 or later (freely downloadable from NVidia). 
+Earlier versions may or may not work and are no longer supported. 
+You are advised to use the most recent version of NVidia software you can find. 
 The `configure` script checks for the presence of the nvfortran compiler and 
 of a few cuda libraries. For this reason the path pointing to the cuda toolkit
 must be present in `LD_LIBRARY_PATH`.
@@ -19,7 +19,7 @@ must be present in `LD_LIBRARY_PATH`.
 A template for the configure command is:
 
 ```
-./configure --with-cuda=XX --with-cuda-runtime=YY --with-cuda-cc=ZZ --enable-openmp [--enable-openacc] [ --with-scalapack=no ]
+./configure --with-cuda=XX --with-cuda-runtime=YY --with-cuda-cc=ZZ --enable-openmp [ --with-scalapack=no ][ --with-cuda-mpi=yes ]
 ```
 
 where `XX` is the location of the CUDA Toolkit (in HPC environments is 
@@ -32,14 +32,21 @@ CUDA Driver Version:           11000
 Default Target:                cc70
 ...
 ```
-The version is returned as (1000 major + 10 minor). For example, CUDA 9.2 
-would be represented by 9020. For the above case, configure QE with:
+The version is returned as (1000 major + 10 minor). For example, CUDA 11.0
+is represented by 11000. For the above case, configure QE with:
 ```
 ./configure --with-cuda=$CUDA_HOME --with-cuda-cc=70 --with-cuda-runtime=11.0
 ```
 Alternatively, you may use the (deprecated) tool `get_device_props.py` in
 directory `dev-tools/`.
 
+Enabling faster communications between GPUs, via NVlink or Infiniband RDMA,
+is essential for optimal performance. If your MPI library is built to be
+CUDA-aware, then enable `--with-cuda-mpi=yes` (default: no). 
+
+Serial (no MPI) compilation is also supported: use `--disable-parallel`.
+
+Option --with-openacc is no longer honored: OpenACC is always needed.
 It is generally a good idea to disable Scalapack when running small test
 cases since the serial GPU eigensolver outperforms the parallel CPU
 eigensolver in many circumstances.
@@ -48,8 +55,6 @@ From time to time PGI links to the wrong CUDA libraries and fails reporting a
 problem in `cusolver` missing `GOmp` (GNU Openmp). This problem can be solved
 by removing the cuda toolkit from the `LD_LIBRARY_PATH` before compiling.
 
-Serial compilation is also supported.
-
 Execution
 =========
 
@@ -60,16 +65,5 @@ the beginning of the output
      GPU acceleration is ACTIVE.
 ```
 
-GPU acceleration can be switched off by setting the following environment
-variable:
-
-```
-$ export USEGPU=no
-```
-
-
-Testing
-=======
-
 The current GPU version passes all tests with both parallel and serial 
 compilation.
diff --git a/environment_variables b/environment_variables
index 0ee61b87c..a4ded58ab 100644
--- a/environment_variables
+++ b/environment_variables
@@ -108,7 +108,7 @@ export OMP_NUM_THREADS=1
 LC_ALL=C
 export LC_ALL
 
-NETWORK_PSEUDO=http://www.quantum-espresso.org/wp-content/uploads/upf_files/
+NETWORK_PSEUDO=https://www.quantum-espresso.org/wp-content/uploads/upf_files/
 
 # wget or curl needed if some PP has to be downloaded from web site
 # script wizard will surely find a better way to find what is available
diff --git a/install/configure b/install/configure
index 40952fe55..e675e542c 100755
--- a/install/configure
+++ b/install/configure
@@ -769,6 +769,7 @@ enable_static
 with_cuda
 with_cuda_cc
 with_cuda_runtime
+with_cuda_mpi
 enable_openacc
 with_libxc
 with_libxc_prefix
@@ -1438,6 +1439,7 @@ Optional Packages:
   --with-cuda-cc=VAL      GPU architecture (Kepler: 35, Pascal: 60, Volta: 70)
                           [default=35]
   --with-cuda-runtime=VAL CUDA runtime (Pascal: 8+, Volta: 9+) [default=10.1]
+  --with-cuda-mpi=VAL     CUDA-aware MPI (yes|no) [default=no]
   --with-libxc            (yes|no) Use libXC for some XC functionals (default:
                           no)
   --with-libxc-prefix=DIR Directory where libxc was installed.
@@ -4191,6 +4193,16 @@ else
 fi
 
 
+
+# Check whether --with-cuda-mpi was given.
+if test "${with_cuda_mpi+set}" = set; then :
+  withval=$with_cuda_mpi;
+else
+  with_cuda_mpi=no
+fi
+
+
+
 # Check whether --enable-openacc was given.
 if test "${enable_openacc+set}" = set; then :
   enableval=$enable_openacc;
@@ -4316,6 +4328,9 @@ ac_compiler_gnu=$ac_cv_c_compiler_gnu
    # Headers and libraries
    # -----------------------------------------
    try_dflags="$try_dflags -D__CUDA"
+   if test "$use_parallel" -eq 1 && test "$with_cuda_mpi" == "yes"; then
+      try_dflags="$try_dflags -D__GPU_MPI"
+   fi
    cuda_extlibs="devxlib"
    cuda_libs="$mMcudalib=cufft,cublas,cusolver,curand \$(TOPDIR)/external/devxlib/src/libdevXlib.a"
 
@@ -4328,21 +4343,17 @@ ac_compiler_gnu=$ac_cv_c_compiler_gnu
    runtime_major_version=`echo $with_cuda_runtime | cut -d. -f1`
    runtime_minor_version=`echo $with_cuda_runtime | cut -d. -f2`
    if test "$runtime_major_version" -lt 10 ||
-         ( "$runtime_major_version" -eq 10 && "$runtime_minor_version" -lt 1 )
+     (test "$runtime_major_version" -eq 10 && test "$runtime_minor_version" -lt 1 )
    then
-       # CUDA toolkit v < 10.1: new solver not available
-       cuda_fflags="$cuda_fflags \$(MOD_FLAG)\$(TOPDIR)/EIGENSOLVER_GPU/lib_eigsolve"
-       cuda_extlibs="$cuda_extlibs eigensolver"
-       cuda_libs="$cuda_libs \$(TOPDIR)/EIGENSOLVER_GPU/lib_eigsolve/lib_eigsolve.a"
-       { $as_echo "$as_me:${as_lineno-$LINENO}: WARNING: Using legacy custom solver." >&5
-$as_echo "$as_me: WARNING: Using legacy custom solver." >&2;}
+       # CUDA toolkit v < 10.1: cusolver not available
+       as_fn_error $? "Unsupported CUDA Toolkit, too old" "$LINENO" 5
    else
        try_dflags="$try_dflags -D__USE_CUSOLVER"
    fi
    # -----------------------------------------
-   # C flags - not sure whether they are suitable for old version as well
+   # C flags
    # -----------------------------------------
-   cuda_cflags=" -I$with_cuda/include -gpu=cc$with_cuda_cc,cuda$with_cuda_runtime"
+   cuda_cflags=" -I$with_cuda/include $mMcuda=cc$with_cuda_cc,cuda$with_cuda_runtime"
    ldflags="$ldflags $mMcuda=cc$with_cuda_cc,cuda$with_cuda_runtime"
    gpu_arch="$with_cuda_cc"
    cuda_runtime="$with_cuda_runtime"
@@ -4350,6 +4361,8 @@ $as_echo "$as_me: WARNING: Using legacy custom solver." >&2;}
       ldflags="$ldflags -acc"
       cuda_fflags="$cuda_fflags -acc"
       cuda_cflags="$cuda_cflags -acc"
+   else
+      as_fn_error $? "OpenACC must be enabled" "$LINENO" 5
    fi
 
 fi
diff --git a/install/m4/x_ac_qe_cuda.m4 b/install/m4/x_ac_qe_cuda.m4
index 73580bac9..9141ed897 100644
--- a/install/m4/x_ac_qe_cuda.m4
+++ b/install/m4/x_ac_qe_cuda.m4
@@ -48,6 +48,12 @@ AC_ARG_WITH([cuda-runtime],
    [AS_HELP_STRING([--with-cuda-runtime=VAL],[CUDA runtime (Pascal: 8+, Volta: 9+) @<:@default=10.1@:>@])],
    [],
    [with_cuda_runtime=10.1])
+   
+AC_ARG_WITH([cuda-mpi],
+   [AS_HELP_STRING([--with-cuda-mpi=VAL],[CUDA-aware MPI (yes|no) @<:@default=no@:>@])],
+   [],
+   [with_cuda_mpi=no])
+
 
 AC_ARG_ENABLE([openacc],
    [AS_HELP_STRING([--enable-openacc],[Enable compilation with OPENACC @<:@default=yes@:>@])],
@@ -81,6 +87,9 @@ then
    # Headers and libraries
    # -----------------------------------------
    try_dflags="$try_dflags -D__CUDA"
+   if test "$use_parallel" -eq 1 && test "$with_cuda_mpi" == "yes"; then 
+      try_dflags="$try_dflags -D__GPU_MPI"
+   fi
    cuda_extlibs="devxlib"
    cuda_libs="$mMcudalib=cufft,cublas,cusolver,curand \$(TOPDIR)/external/devxlib/src/libdevXlib.a"
    
@@ -93,20 +102,17 @@ then
    runtime_major_version=`echo $with_cuda_runtime | cut -d. -f1`
    runtime_minor_version=`echo $with_cuda_runtime | cut -d. -f2`
    if test "$runtime_major_version" -lt 10 || 
-         ( "$runtime_major_version" -eq 10 && "$runtime_minor_version" -lt 1 )
+     (test "$runtime_major_version" -eq 10 && test "$runtime_minor_version" -lt 1 )
    then
-       # CUDA toolkit v < 10.1: new solver not available
-       cuda_fflags="$cuda_fflags \$(MOD_FLAG)\$(TOPDIR)/EIGENSOLVER_GPU/lib_eigsolve"
-       cuda_extlibs="$cuda_extlibs eigensolver"
-       cuda_libs="$cuda_libs \$(TOPDIR)/EIGENSOLVER_GPU/lib_eigsolve/lib_eigsolve.a"
-       AC_MSG_WARN([Using legacy custom solver.])
+       # CUDA toolkit v < 10.1: cusolver not available
+       AC_MSG_ERROR([Unsupported CUDA Toolkit, too old])
    else
        try_dflags="$try_dflags -D__USE_CUSOLVER"
    fi
    # -----------------------------------------
-   # C flags - not sure whether they are suitable for old version as well
+   # C flags 
    # -----------------------------------------   
-   cuda_cflags=" -I$with_cuda/include -gpu=cc$with_cuda_cc,cuda$with_cuda_runtime"
+   cuda_cflags=" -I$with_cuda/include $mMcuda=cc$with_cuda_cc,cuda$with_cuda_runtime"
    ldflags="$ldflags $mMcuda=cc$with_cuda_cc,cuda$with_cuda_runtime"
    gpu_arch="$with_cuda_cc"
    cuda_runtime="$with_cuda_runtime"
@@ -114,6 +120,8 @@ then
       ldflags="$ldflags -acc"
       cuda_fflags="$cuda_fflags -acc"
       cuda_cflags="$cuda_cflags -acc"
+   else
+      AC_MSG_ERROR([OpenACC must be enabled])
    fi
 
 fi