Adding missing Kokkos file

git-svn-id: svn://svn.icms.temple.edu/lammps-ro/trunk@13636 f3b2605a-c512-4ea7-a41b-209d697bcdaa
This commit is contained in:
stamoor 2015-07-17 16:17:51 +00:00
parent c5bb851384
commit 4e757218e4
1 changed files with 185 additions and 0 deletions

185
lib/kokkos/config/nvcc_wrapper Executable file
View File

@ -0,0 +1,185 @@
#!/bin/bash
#
# This shell script (nvcc_wrapper) wraps both the host compiler and
# NVCC, if you are building Trilinos with CUDA enabled. The script
# remedies some differences between the interface of NVCC and that of
# the host compiler, in particular for linking. It also means that
# Trilinos doesn't need separate .cu files; it can just use .cpp
# files.
#
# Hopefully, at some point, NVIDIA may fix NVCC so as to make this
# script obsolete. For now, this script exists and if you want to
# build Trilinos with CUDA enabled, you must use this script as your
# compiler.
# Default settings: change those according to your machine. For
# example, you may have have two different wrappers with either icpc
# or g++ as their back-end compiler. The defaults can be overwritten
# by using the usual arguments (e.g., -arch=sm_30 -ccbin icpc).
default_arch="sm_35"
#default_arch="sm_50"
#
# The default C++ compiler.
#
default_compiler=${NVCC_WRAPPER_DEFAULT_COMPILER:-"g++"}
#default_compiler="icpc"
#default_compiler="/usr/local/gcc/4.8.3/bin/g++"
#default_compiler="/usr/local/gcc/4.9.1/bin/g++"
#
# Internal variables
#
cpp_files=""
xcompiler_args=""
cuda_arg=""
xlinker_args=""
object_files=""
object_files_xlinker=""
first_host_option=1
arch_set=0
ccbin_set=0
nvcc_error_code=0
dry_run=0
replace_pragma_ident=0
#echo "Arguments: $# $@"
while [ $# -gt 0 ]
do
case $1 in
#show the executed command
--show)
dry_run=1
;;
#replace '#pragma ident' with '#ident' this is needed to compile OpenMPI due to a configure script bug and a non standardized behaviour of pragma with macros
--replace-pragma-ident)
replace_pragma_ident=1
;;
#handle source files to be compiled as cuda files
*.cpp|*.cxx|*.cc|*.C|*.c++|*.cu)
cpp_files="$cpp_files $1"
;;
#Handle known nvcc args
-O*|-D*|-gencode*|-c|-I*|-L*|-l*|-g|--help|--version|--dryrun|--verbose|--keep-dir|-E|-M|-G|--relocatable-device-code*|-shared|-lineinfo|-expt-extended-lambda|--resource-usage)
cuda_args="$cuda_args $1"
;;
#Handle c++11 setting
--std=c++11|-std=c++11)
cuda_args="$cuda_args $1"
;;
#strip of -std=c++98 due to nvcc warnings and Tribits will place both -std=c++11 and -std=c++98
-std=c++98|--std=c++98)
;;
#Handle known nvcc args that have an argument
-o|-rdc|-maxrregcount|--default-stream)
cuda_args="$cuda_args $1 $2"
shift
;;
#strip of pedantic because it produces endless warnings about #LINE added by the preprocessor
-pedantic|-Wpedantic|-ansi)
;;
#strip -Xcompiler because we add it
-Xcompiler)
;;
#strip of "-x cu" because we add that
-x)
if [[ $2 != "cu" ]]; then
xcompiler_args="$xcompiler_args,-x,$2"
fi
shift
;;
#Handle -ccbin (if its not set we can set it to a default value)
-ccbin)
cuda_args="$cuda_args $1 $2"
ccbin_set=1
shift
;;
#Handle -arch argument (if its not set use a default
-arch*)
cuda_args="$cuda_args $1"
arch_set=1
;;
#Handle -Xcudafe argument
-Xcudafe)
cuda_args="$cuda_args -Xcudafe $2"
shift
;;
#Handle args that should be sent to the linker
-Wl*)
xlinker_args="$xlinker_args -Xlinker ${1:4:${#1}}"
;;
#Handle object files: -x cu applies to all input files, so give them to linker, except if only linking
*.a|*.so|*.o|*.obj)
object_files="$object_files $1"
object_files_xlinker="$object_files_xlinker -Xlinker $1"
;;
#Handle object files: -x cu applies to all input files, so give them to linker, except if only linking
*.so.*|*.dylib)
object_files_xlinker="$object_files_xlinker -Xlinker $1"
object_files="$object_files -Xlinker $1"
;;
#All other args are sent to the host compiler
*)
if [ $first_host_option -eq 0 ]; then
xcompiler_args="$xcompiler_args,$1"
else
xcompiler_args="-Xcompiler $1"
first_host_option=0
fi
;;
esac
shift
done
#Add default host compiler if necessary
if [ $ccbin_set -ne 1 ]; then
cuda_args="$cuda_args -ccbin $default_compiler"
fi
#Add architecture command
if [ $arch_set -ne 1 ]; then
cuda_args="$cuda_args -arch=$default_arch"
fi
#Compose compilation command
command="nvcc $cuda_args $xlinker_args $xcompiler_args"
#nvcc does not accept '#pragma ident SOME_MACRO_STRING' but it does accept '#ident SOME_MACRO_STRING'
if [ $replace_pragma_ident -eq 1 ]; then
cpp_files2=""
for file in $cpp_files
do
var=`grep pragma ${file} | grep ident | grep "#"`
if [ "${#var}" -gt 0 ]
then
sed 's/#[\ \t]*pragma[\ \t]*ident/#ident/g' $file > /tmp/nvcc_wrapper_tmp_$file
cpp_files2="$cpp_files2 /tmp/nvcc_wrapper_tmp_$file"
else
cpp_files2="$cpp_files2 $file"
fi
done
cpp_files=$cpp_files2
echo $cpp_files
fi
if [ "$cpp_files" ]; then
command="$command $object_files_xlinker -x cu $cpp_files"
else
command="$command $object_files"
fi
#Print command for dryrun
if [ $dry_run -eq 1 ]; then
echo $command
exit 0
fi
#Run compilation command
$command
nvcc_error_code=$?
#Report error code
exit $nvcc_error_code