portelli/Grid
1
0
Fork 0
mirror of https://github.com/paboyle/Grid.git synced 2024-09-21 01:25:48 +01:00
Code Releases Activity
100323ab4d
Grid/configure-commands

9 lines
1.1 KiB
Plaintext
Raw Normal View History

clang++ 3.4/5/7 compile happy for AVX and SSE icpc compiles happy on MacOSX both with -xCOMMON-AV512 and native AVX gcc-5 does not compile happy; can work around by renaming lattice peek/poke/transpose/trace templates relative to tensor ones, but gcc goes into a recursive template instantiation due to matching error. I think this is a gcc bug and have filed a report https://gcc.gnu.org/bugzilla/show_bug.cgi?id=66153
2015-05-15 11:52:11 +01:00
CXX=icpc ./configure --enable-simd=AVX CXXFLAGS="-mavx -fopenmp -O3 -I/opt/local/include/openmpi-mp/ -std=c++11" LDFLAGS=-L/opt/local/lib/openmpi-mp/ LIBS="-lmpi -lmpi_cxx -fopenmp" --enable-comms=mpi
I have made the Cshift work successfully with open mp threading in every routine. Collapse(2) is now working under clang-omp++.
2015-05-13 00:31:00 +01:00
CXX=clang-omp++ ./configure --enable-simd=AVX CXXFLAGS="-mavx -fopenmp -O3 -I/opt/local/include/openmpi-mp/ -std=c++11" LDFLAGS=-L/opt/local/lib/openmpi-mp/ LIBS="-lmpi -lmpi_cxx -fopenmp" --enable-comms=mpi
Some popular configure commands
2015-04-06 11:28:00 +01:00
CXX=clang++ ./configure --enable-simd=AVX CXXFLAGS="-mavx -O3 -I/opt/local/include/openmpi-mp/ -std=c++11" LDFLAGS=-L/opt/local/lib/openmpi-mp/ LIBS="-lmpi -lmpi_cxx" --enable-comms=mpi
CXX=clang++ ./configure --enable-simd=AVX CXXFLAGS="-mavx -g -I/opt/local/include/openmpi-mp/ -std=c++11" LDFLAGS=-L/opt/local/lib/openmpi-mp/ LIBS="-lmpi -lmpi_cxx" --enable-comms=mpi
CXX=clang++ ./configure --enable-simd=AVX CXXFLAGS="-mavx -g -std=c++11" LDFLAGS= LIBS=-lmpi --enable-comms=fake
CXX=clang++ ./configure --enable-simd=AVX CXXFLAGS="-mavx -g -std=c++11" LDFLAGS= LIBS=-lmpi --enable-comms=none
clang++ 3.4/5/7 compile happy for AVX and SSE icpc compiles happy on MacOSX both with -xCOMMON-AV512 and native AVX gcc-5 does not compile happy; can work around by renaming lattice peek/poke/transpose/trace templates relative to tensor ones, but gcc goes into a recursive template instantiation due to matching error. I think this is a gcc bug and have filed a report https://gcc.gnu.org/bugzilla/show_bug.cgi?id=66153
2015-05-15 11:52:11 +01:00
CXX=/usr/local/clang-3.7/bin/clang++ ./configure --enable-simd=AVX512 CXXFLAGS="-mavx512f -O3 -std=c++11" LDFLAGS= LIBS= --enable-comms=none
Copy Permalink