Merge branch release-2016

Conflicts:
	admin/builds/pre-submit-matrix.txt

Checked that intent of test configs is implemented appropriately in
new context. The cuda-8 config newly introduced in release-2016
is already covered in this branch, so we don't need to have that
new configuration here.

	src/gromacs/gpu_utils/gpu_utils.cu
	src/gromacs/simd/impl_ibm_qpx/impl_ibm_qpx_simd4_double.h
	src/gromacs/domdec/domdec.cpp

Trivial

Change-Id: I9b06bb476f5b62c9652c0e5186340ed11b0c31cc

diff --cc admin/builds/pre-submit-matrix.txt
index b99a7dc66fe4da7e108a42b207fef79cde070dbe,b935c179829cf9cf05321ac94ef4234f7d06d3bd..1dd25a6eebfa46510314a05c96a9a6e3a0f04347
--- 1/admin/builds/pre-submit-matrix.txt
--- 2/admin/builds/pre-submit-matrix.txt
+++ b/admin/builds/pre-submit-matrix.txt
@@@ -18,9 -18,9 +18,10 @@@ gcc-4.8 gpu cuda-6.5 mpi npme=1 nranks=
  
  # Test newest gcc supported by newest CUDA at time of release
  # Test thread-MPI with CUDA
- gcc-5 gpu cuda-8.0 openmp release
 -gcc-4.8 gpu cuda-7.5 openmp release
++# Test SIMD (AVX2_256) GPU code-path
++gcc-5 gpu cuda-8.0 openmp release simd=avx2_256
  
 -# Test with ThreadSanitizer
 +# Test with ThreadSanitizer (without OpenMP, because of Redmine #1850)
  # Test AVX2_256 SIMD
  # Test fftpack fallback
  gcc-4.9 tsan fftpack simd=avx2_256

diff --cc cmake/gmxManageNvccConfig.cmake
index c8561f44febf6f6e004c7c838a56a0d0e54cf0b8,706343c1f8e03082f17dedc63a1624189d601092..fc974647a67f66e9ba1794b33220877630314453
--- 1/cmake/gmxManageNvccConfig.cmake
--- 2/cmake/gmxManageNvccConfig.cmake
+++ b/cmake/gmxManageNvccConfig.cmake
@@@ -171,8 -189,16 +171,12 @@@ gmx_dependent_cache_variable(GMX_CUDA_T
  # assemble the CUDA flags
  list(APPEND GMX_CUDA_NVCC_FLAGS "${GMX_CUDA_NVCC_GENCODE_FLAGS}")
  list(APPEND GMX_CUDA_NVCC_FLAGS "-use_fast_math")
+ if (CUDA_VERSION VERSION_EQUAL "8.0")
+     # requesting sm_20 triggers deprecation messages with nvcc 8.0 which we better avoid
+     list(APPEND GMX_CUDA_NVCC_FLAGS "-Wno-deprecated-gpu-targets")
+ endif()
  
  # assemble the CUDA host compiler flags
 -# with CMake <2.8.10 the host compiler needs to be set on the nvcc command line
 -if (CMAKE_VERSION VERSION_LESS "2.8.10")
 -    list(APPEND GMX_CUDA_NVCC_FLAGS "-ccbin=${CUDA_HOST_COMPILER}")
 -endif()
  list(APPEND GMX_CUDA_NVCC_FLAGS "${CUDA_HOST_COMPILER_OPTIONS}")
  
  # The flags are set as local variables which shadow the cache variables. The cache variables

diff --cc docs/CMakeLists.txt
Simple merge

diff --cc docs/dev-manual/build-system.rst
Simple merge

diff --cc docs/dev-manual/language-features.rst
Simple merge

diff --cc docs/install-guide/index.rst
Simple merge

diff --cc src/gromacs/domdec/domdec.cpp
Simple merge

diff --cc src/gromacs/gmxana/gmx_make_edi.cpp
Simple merge

diff --cc src/gromacs/gmxpreprocess/readir.cpp
Simple merge

diff --cc src/gromacs/gpu_utils/gpu_utils.cu
Simple merge

diff --cc src/gromacs/pulling/pull.cpp
index d430f8a609ab02040c1c8a182c333b5738fc083f,b77a7fcacf8d2357d3b7d1fd132f4408a7644692..a944b712ebe1d87e583d07cc31ce232526c1caae
--- 1/src/gromacs/pulling/pull.cpp
--- 2/src/gromacs/pulling/pull.cpp
+++ b/src/gromacs/pulling/pull.cpp
@@@ -1325,9 -1325,10 +1325,10 @@@ static void do_constraint(struct pull_
              continue;
          }
  
-         pcrd->f_scal = dr_tot[c]/((pull->group[pcrd->params.group[0]].invtm + pull->group[pcrd->params.group[1]].invtm)*dt*dt);
+         /* Accumulate the forces, in case we have multiple constraint steps */
+         pcrd->f_scal += dr_tot[c]/((pull->group[pcrd->params.group[0]].invtm + pull->group[pcrd->params.group[1]].invtm)*dt*dt);
  
 -        if (vir != NULL && pcrd->params.eGeom != epullgDIRPBC && bMaster)
 +        if (vir != nullptr && pcrd->params.eGeom != epullgDIRPBC && bMaster)
          {
              double f_invr;
  

diff --cc src/gromacs/simd/impl_ibm_qpx/impl_ibm_qpx_simd4_double.h
index c93403685207532e12a47eeb0be02ae9696090ab,9223492f29b385a9f3abb2600c0c49d60408e20b..e3e146bfb00a68d951474f2bdeed7909d25b4187
--- 1/src/gromacs/simd/impl_ibm_qpx/impl_ibm_qpx_simd4_double.h
--- 2/src/gromacs/simd/impl_ibm_qpx/impl_ibm_qpx_simd4_double.h
+++ b/src/gromacs/simd/impl_ibm_qpx/impl_ibm_qpx_simd4_double.h
@@@ -1,7 -1,7 +1,7 @@@
  /*
   * This file is part of the GROMACS molecular simulation package.
   *
-  * Copyright (c) 2014,2015,2016, by the GROMACS development team, led by
 - * Copyright (c) 2014,2015,2017, by the GROMACS development team, led by
++ * Copyright (c) 2014,2015,2016,2017, by the GROMACS development team, led by
   * Mark Abraham, David van der Spoel, Berk Hess, and Erik Lindahl,
   * and including many others, as listed in the AUTHORS file in the
   * top-level source directory and at http://www.gromacs.org.

diff --cc src/programs/mdrun/md.cpp
Simple merge