I just installed Intel® Parallel Studio XE Cluster Edition for Linux* 2019 and am trying to use OpenMP to offload to a Xeon Phi accelerator. I am using cmake, with flags
CC=~/intel/bin/icc CXX=~/intel/bin/icpc CMAKE_CXX_FLAGS="-qopenmp-offload" cmake ..
This sets everything up without any issues. However, when I run make I get the following error:
ld: warning: libcoi_device.so.0, needed by /opt/software/icc/2018.1.163-GCC-6.4.0-2.28/compilers_and_libraries_2018.1.163/linux/compiler/lib/intel64/libioffload_target.so.5, not found (try using -rpath or -rpath-link)
/opt/software/icc/2018.1.163-GCC-6.4.0-2.28/compilers_and_libraries_2018.1.163/linux/compiler/lib/intel64/libioffload_target.so.5: undefined reference to `COIPerfGetCycleFrequency@COI_1.0'
/opt/software/icc/2018.1.163-GCC-6.4.0-2.28/compilers_and_libraries_2018.1.163/linux/compiler/lib/intel64/libioffload_target.so.5: undefined reference to `COIBufferAddRef@COI_1.0'
/opt/software/icc/2018.1.163-GCC-6.4.0-2.28/compilers_and_libraries_2018.1.163/linux/compiler/lib/intel64/libioffload_target.so.5: undefined reference to `COIPipelineStartExecutingRunFunctions@COI_1.0'
/opt/software/icc/2018.1.163-GCC-6.4.0-2.28/compilers_and_libraries_2018.1.163/linux/compiler/lib/intel64/libioffload_target.so.5: undefined reference to `COIEngineGetIndex@COI_1.0'
/opt/software/icc/2018.1.163-GCC-6.4.0-2.28/compilers_and_libraries_2018.1.163/linux/compiler/lib/intel64/libioffload_target.so.5: undefined reference to `COIBufferReleaseRef@COI_1.0'
/opt/software/icc/2018.1.163-GCC-6.4.0-2.28/compilers_and_libraries_2018.1.163/linux/compiler/lib/intel64/libioffload_target.so.5: undefined reference to `COIProcessWaitForShutdown@COI_1.0'
make[2]: *** [GPU] Error 1
make[1]: *** [CMakeFiles/GPU.dir/all] Error 2
make: *** [all] Error 2
Upon further inspection I found that in both the /opt and ~/intel installs of the intel compiler libioffload_target.so.5 is missing libcoi_device.so.0 => not found.
Any ideas on why this might be?
