You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I got the following MKL linking errors when I try to build the Intel Docker image for retinanet (with applied workaround for the pybind11 problem suggested in #12) using this script:
982.3 [ 85%] Building CXX object CMakeFiles/mlperf_runner.dir/kmp_launcher.cpp.o
982.7 [100%] Linking CXX executable bin/mlperf_runner
983.3 /opt/rh/gcc-toolset-11/root/usr/bin/ld: /opt/conda/lib/libmkl_intel_lp64.so: undefined reference to `mkl_lapack_ssbevd_2stage'
983.3 /opt/rh/gcc-toolset-11/root/usr/bin/ld: /opt/conda/lib/libmkl_intel_lp64.so: undefined reference to `mkl_lapack_csyconv'
983.3 /opt/rh/gcc-toolset-11/root/usr/bin/ld: /opt/conda/lib/libmkl_intel_lp64.so: undefined reference to `mkl_lapack_cspmv'
983.3 /opt/rh/gcc-toolset-11/root/usr/bin/ld: /opt/conda/lib/libmkl_intel_lp64.so: undefined reference to `mkl_lapack_slaqr5'
983.3 /opt/rh/gcc-toolset-11/root/usr/bin/ld: /opt/conda/lib/libmkl_intel_lp64.so: undefined reference to `mkl_lapack_zlagsy'
983.3 /opt/rh/gcc-toolset-11/root/usr/bin/ld: /opt/conda/lib/libmkl_intel_lp64.so: undefined reference to `mkl_blas_zdotu'
983.3 /opt/rh/gcc-toolset-11/root/usr/bin/ld: /opt/conda/lib/libmkl_intel_lp64.so: undefined reference to `mkl_feast_dfeast_scsrev'
983.3 /opt/rh/gcc-toolset-11/root/usr/bin/ld: /opt/conda/lib/libmkl_intel_lp64.so: undefined reference to `mkl_lapack_zlacrt'
983.3 /opt/rh/gcc-toolset-11/root/usr/bin/ld: /opt/conda/lib/libmkl_intel_lp64.so: undefined reference to `mkl_lapack_cpotrs'
983.3 /opt/rh/gcc-toolset-11/root/usr/bin/ld: /opt/conda/lib/libmkl_intel_lp64.so: undefined reference to `mkl_lapack_dcombssq'
983.3 /opt/rh/gcc-toolset-11/root/usr/bin/ld: /opt/conda/lib/libmkl_intel_lp64.so: undefined reference to `mkl_lapack_zgeev'
983.3 /opt/rh/gcc-toolset-11/root/usr/bin/ld: /opt/conda/lib/libmkl_intel_lp64.so: undefined reference to `mkl_lapack_strrfs'
983.3 /opt/rh/gcc-toolset-11/root/usr/bin/ld: /opt/conda/lib/libmkl_intel_lp64.so: undefined reference to `mkl_spblas_lp64_mkl_dcsrcoo'
983.3 /opt/rh/gcc-toolset-11/root/usr/bin/ld: /opt/conda/lib/libmkl_intel_lp64.so: undefined reference to `mkl_lapack_cgbcon'
983.3 /opt/rh/gcc-toolset-11/root/usr/bin/ld: /opt/conda/lib/libmkl_intel_lp64.so: undefined reference to `mkl_lapack_sspevx'
983.3 /opt/rh/gcc-toolset-11/root/usr/bin/ld: /opt/conda/lib/libmkl_intel_lp64.so: undefined reference to `mkl_lapack_clarfb'
983.3 /opt/rh/gcc-toolset-11/root/usr/bin/ld: /opt/conda/lib/libmkl_intel_lp64.so: undefined reference to `mkl_lapack_dlasd8'
983.3 /opt/rh/gcc-toolset-11/root/usr/bin/ld: /opt/conda/lib/libmkl_intel_lp64.so: undefined reference to `mkl_sparse_d_create_csc_i4'
983.3 /opt/rh/gcc-toolset-11/root/usr/bin/ld: /opt/conda/lib/libmkl_intel_lp64.so: undefined reference to `mkl_lapack_cla_syrcond_c'
983.3 /opt/rh/gcc-toolset-11/root/usr/bin/ld: /opt/conda/lib/libmkl_intel_lp64.so: undefined reference to `mkl_blas_zgemv_batch_strided'
983.3 /opt/rh/gcc-toolset-11/root/usr/bin/ld: /opt/conda/lib/libmkl_intel_lp64.so: undefined reference to `mkl_lapack_stzrzf'
983.3 /opt/rh/gcc-toolset-11/root/usr/bin/ld: /opt/conda/lib/libmkl_intel_lp64.so: undefined reference to `mkl_lapack_zhetrs_rook'
983.3 /opt/rh/gcc-toolset-11/root/usr/bin/ld: /opt/conda/lib/libmkl_intel_lp64.so: undefined reference to `mkl_lapack_slarrv'
983.3 /opt/rh/gcc-toolset-11/root/usr/bin/ld: /opt/conda/lib/libmkl_intel_lp64.so: undefined reference to `mkl_serv_get_cpu_clocks'
983.3 /opt/rh/gcc-toolset-11/root/usr/bin/ld: /opt/conda/lib/libmkl_intel_lp64.so: undefined reference to `mkl_spblas_lp64_mkl_zdiatrsv'
983.3 /opt/rh/gcc-toolset-11/root/usr/bin/ld: /opt/conda/lib/libmkl_intel_lp64.so: undefined reference to `mkl_lapack_zlaqgb'
...
Can anybody suggest a solution/workaround for this?
The text was updated successfully, but these errors were encountered:
I got the following MKL linking errors when I try to build the Intel Docker image for retinanet (with applied workaround for the pybind11 problem suggested in #12) using this script:
Can anybody suggest a solution/workaround for this?
The text was updated successfully, but these errors were encountered: