Merge branch 'master' into write-bonus-data

doc/src/Build_extras.rst

@@ -105,10 +105,10 @@ CMake build
                                 # generic (default) or intel (Intel CPU) or fermi, kepler, cypress (NVIDIA)
    -D GPU_ARCH=value            # primary GPU hardware choice for GPU_API=cuda
                                 # value = sm_XX, see below
-                                # default is sm_30
+                                # default is sm_50
    -D HIP_ARCH=value            # primary GPU hardware choice for GPU_API=hip
                                 # value depends on selected HIP_PLATFORM
-                                # default is 'gfx906' for HIP_PLATFORM=hcc and 'sm_30' for HIP_PLATFORM=nvcc
+                                # default is 'gfx906' for HIP_PLATFORM=hcc and 'sm_50' for HIP_PLATFORM=nvcc
    -D HIP_USE_DEVICE_SORT=value # enables GPU sorting
                                 # value = yes (default) or no
    -D CUDPP_OPT=value           # optimization setting for GPU_API=cuda
@@ -1255,6 +1255,15 @@ also typically :ref:`install the USER-OMP package <user-omp>`, as it can be
 used in tandem with the USER-INTEL package to good effect, as explained
 on the :doc:`Speed intel <Speed_intel>` doc page.
 
+When using Intel compilers version 16.0 or later is required.  You can
+also use the GNU or Clang compilers and they will provide performance
+improvements over regular styles and USER-OMP styles, but less so than
+with the Intel compilers.  Please also note, that some compilers have
+been found to apply memory alignment constraints incompletely or
+incorrectly and thus can cause segmentation faults in otherwise correct
+code when using features from the USER-INTEL package.
+
+
 CMake build
 ^^^^^^^^^^^
 

doc/src/Packages_details.rst

@@ -306,7 +306,8 @@ gpu" or "-suffix gpu" :doc:`command-line switches <Run_options>`.  See
 also the :ref:`KOKKOS <PKG-KOKKOS>` package, which has GPU-enabled styles.
 
 **Authors:** Mike Brown (Intel) while at Sandia and ORNL and Trung Nguyen
-(Northwestern U) while at ORNL.
+(Northwestern U) while at ORNL and later. AMD HIP support by Evgeny
+Kuznetsov, Vladimir Stegailov, and Vsevolod Nikolskiy (HSE University).
 
 **Install:**
 

doc/src/Speed_gpu.rst

@@ -50,6 +50,10 @@ but this can be overridden using the device option of the :doc:`package <package
 command. run lammps/lib/gpu/ocl_get_devices to get a list of available
 platforms and devices with a suitable ICD available.
 
+To compute and use this package in HIP mode, you have to have the AMD ROCm
+software installed. Versions of ROCm older than 3.5 are currently deprecated
+by AMD.
+
 **Building LAMMPS with the GPU package:**
 
 See the :ref:`Build extras <gpu>` doc page for

doc/src/Speed_intel.rst

@@ -138,10 +138,10 @@ For Intel Xeon Phi co-processors (Offload):
 
 **Required hardware/software:**
 
+When using Intel compilers version 16.0 or later is required.
+
 In order to use offload to co-processors, an Intel Xeon Phi
-co-processor and an Intel compiler are required. For this, the
-recommended version of the Intel compiler is 14.0.1.106 or
-versions 15.0.2.044 and higher.
+co-processor and an Intel compiler are required.
 
 Although any compiler can be used with the USER-INTEL package,
 currently, vectorization directives are disabled by default when