生成完整的LAPACK
KML_LAPACK依赖于开源的Netlib LAPACK以提供完整的LAPACK接口功能。因此安装KML_LAPACK后需自行获取开源的Netlib LAPACK v3.12.0的源代码包。
操作步骤
- 下载Netlib LAPACK v3.12.0的源代码包v3.12.0.tar.gz。解压后保存在编译机器可访问的路径中,假设位于“/data/Download/lapack-3.12.0”,通过以下命令设置环境变量指定Netlib LAPACK源码路径。
export LAPACK_SRC_DIR=/data/Download/lapack-3.12.0
- 假设libklapack.so位于“/usr/local/kml/lib/neon/libklapack.so”,使用以下脚本编译生成功能完整的libklapack_full.so。
set -eE # Some helper functions -------------------------------------------------------- function INFORM { printf "\n====== $1\n" ; } function DIE { printf "\nFATAL ERROR: $*\n" ; exit 1 ; } INFORM "Define and check build and test parameters ($0)" echo "LIBKLAPACK_SO ${LIBKLAPACK_SO:=/usr/local/kml/lib/neon/libklapack.so}" echo "LIBKBLAS_SO ${LIBKBLAS_SO:=$(dirname ${LIBKLAPACK_SO})/kblas/multi/libkblas.so}" echo "LAPACK_SRC_DIR ${LAPACK_SRC_DIR:=/undefined/LAPACK_SRC_DIR}" echo "BUILD_DIR ${BUILD_DIR:=${PWD}/tmp-build-lapack}" echo "CMAKE_BUILD_TYPE ${CMAKE_BUILD_TYPE:=Release}" echo "CTEST_PARALLEL_LEVEL ${CTEST_PARALLEL_LEVEL:=8}" echo "OMP_NUM_THREADS ${OMP_NUM_THREADS:=8}" echo "LDFLAGS_EXTRA ${LDFLAGS_EXTRA}" echo "CMAKEFLAGS_EXTRA ${CMAKEFLAGS_EXTRA}" # result echo "LIBKLAPACK_FULL_SO ${LIBKLAPACK_FULL_SO:=./libklapack_full.so}" export CMAKE_BUILD_TYPE CTEST_PARALLEL_LEVEL OMP_NUM_THREADS test -x ${LIBKLAPACK_SO} || DIE "invalid LIBKLAPACK_SO" test -x ${LIBKBLAS_SO} || DIE "invalid LIBKBLAS_SO" test -r ${LAPACK_SRC_DIR}/SRC/dgetrf.f || DIE "invalid LAPACK_SRC_DIR Download hint: git clone https://github.com/Reference-LAPACK/lapack ${LAPACK_SRC_DIR} " #------------------------------------------------------------------------------- kmlver=$(strings ${LIBKLAPACK_SO/klapack.so*/kservice.so} | grep -o 'VERSION.*COMPILER.*') INFORM "Check if compilers are compatible with KML '${kmlver}'" function check_compiler { local name=$1 parlor=$2 case `${!name} --version 2>/dev/null` in *${parlor}*) echo " Using ${name}=${!name}" ;; '') DIE "Missing compiler ${name}=${!name}" ;; *) DIE "Wrong compiler ${name}=${!name}" ;; esac } case ${kmlver} in *COMPILER:GNU*) export CC=${CC:-gcc} FC=${FC:-gfortran} check_compiler CC 'gcc' check_compiler FC 'GNU Fortran' ;; *COMPILER:Clang*) export CC=${CC:-clang} FC=${FC:-flang} check_compiler CC 'clang' check_compiler FC '?lang' ;; *) DIE "Unknown KML version ${kmlver}" ;; esac #------------------------------------------------------------------------------- INFORM "Configure BUILD_DIR for building STATIC liblapack.a and liblapacke.a" cmake_flags=( -DBLAS_LIBRARIES=NO -DBLASLIB="${LIBKBLAS_SO}" -DBUILD_DEPRECATED=ON -DBUILD_SHARED_LIBS=OFF -DBUILD_TESTING=OFF -DCMAKE_BUILD_TYPE=${CMAKE_BUILD_TYPE} -DCMAKE_INSTALL_PREFIX=/dev/null -DCMAKE_POSITION_INDEPENDENT_CODE=ON -DCMAKE_RULE_MESSAGES=OFF -DLAPACKE=ON -DUSE_OPTIMIZED_BLAS=ON ${CMAKEFLAGS_EXTRA} ) ( set -x ; mkdir -p ${BUILD_DIR} ) ( set -x ; cd ${BUILD_DIR} ; cmake ${LAPACK_SRC_DIR} "${cmake_flags[@]}" ) #------------------------------------------------------------------------------- INFORM "Build adapted liblapack.a, and liblapacke.a" rm ${BUILD_DIR}/lib/liblapack.a || true rm ${BUILD_DIR}/lib/liblapacke.a || true ( set -x ; cd ${BUILD_DIR} ; cmake --build . --parallel || cmake --build . --parallel 1 -v ) ar d ${BUILD_DIR}/lib/liblapack.a xerbla.f.o # ------------------------------------------------------------------------------ INFORM "Get symbols defined BOTH in KLAPACK and in Reference LAPACK" nm -g ${BUILD_DIR}/lib/liblapack.a | grep -oP ' T \K\w+(?=_$)' | sort | uniq > netlib.sym nm -g ${LIBKLAPACK_SO/klapack.so*/klapack.a} | grep -oP ' T \K\w+(?=_$)' | sort | uniq > klapack.sym comm -12 klapack.sym netlib.sym > comm.sym # ------------------------------------------------------------------------------ INFORM "Extract relevant modules and update symbol names" ( set -x ; mkdir -p ${BUILD_DIR}/mods ) while read sym; do ( cd ${BUILD_DIR}/mods tloc=$(nm -gA --defined-only ${BUILD_DIR}/lib/liblapack.a | grep " T ${sym}_\$") if [[ -n "${tloc}" ]]; then libmod=${tloc%:*} mod=${libmod#*:} ( set -x ; ar x ${BUILD_DIR}/lib/liblapack.a ${mod} ) ( set -x ; objcopy --redefine-sym ${sym}_=${sym}_netlib_ ${mod} ) fi ) & done < comm.sym wait ar d ${BUILD_DIR}/lib/liblapack.a $(cd ${BUILD_DIR}/mods ; ls *.o) ( cd ${BUILD_DIR}/mods ; ar ru ${BUILD_DIR}/lib/liblapack.a *.o ) ( cd ${BUILD_DIR}/mods ; rm *.o ) #------------------------------------------------------------------------------- INFORM "Amend libkservice.a before building libklapack_full.so" libkservice_fixed_a=${BUILD_DIR}/lib/libkservice_fixed.a ( set -x ; cp -p ${LIBKLAPACK_SO/klapack.so*/kservice.a} ${libkservice_fixed_a}) ( set -x ; ar d ${libkservice_fixed_a} timer.c.o || true ) #------------------------------------------------------------------------------- INFORM "Create libklapack_full.so" ( set -x ; mkdir -p $(dirname ${LIBKLAPACK_FULL_SO})) ldflags=( -Wl,--whole-archive -Wl,--start-group ${LIBKLAPACK_SO/klapack.so*/klapack.a} ${BUILD_DIR}/lib/liblapack.a ${BUILD_DIR}/lib/liblapacke.a ${libkservice_fixed_a} -Wl,--end-group -Wl,--no-whole-archive ${LDFLAGS_EXTRA} ) case ${kmlver} in *COMPILER:GNU*) ( set -x ; ${FC} "${ldflags[@]}" -lstdc++ -shared -o ${LIBKLAPACK_FULL_SO} ) ;; *COMPILER:Clang*) ( set -x ; ${FC} "${ldflags[@]}" -lc++ -shared -o ${LIBKLAPACK_FULL_SO} ) ;; esac #------------------------------------------------------------------------------- if [[ "$1" == "test" ]]; then INFORM "Run tests with libklapack_full.so" function tests { local tmp_dir=$1 lapack_libs=$2 cmake_flags=( -DBUILD_TESTING=ON -DUSE_OPTIMIZED_BLAS=ON -DUSE_OPTIMIZED_LAPACK=ON -DBLAS_LIBRARIES="${LIBKBLAS_SO}" -DLAPACK_LIBRARIES="${lapack_libs}" -DCMAKE_RULE_MESSAGES=OFF -DLAPACKE=ON ) mkdir -p ${tmp_dir} ( set -x ; cd ${tmp_dir} ; cmake ${LAPACK_SRC_DIR} "${cmake_flags[@]}" ) ( set -x ; cd ${tmp_dir} ; cmake --build . --parallel || cmake --build . --parallel 1 -v ) ( set -x ; cd ${tmp_dir} ; ctest --output-on-failure ) echo "FINISHED LAPACK TESTS IN ${tmp_dir}" } tests ${BUILD_DIR}-tests "${LIBKLAPACK_FULL_SO};${LIBKBLAS_SO};-fopenmp" fi # Report build results --------------------------------------------------------- cat <<EOF -------------------------------------------------------------------------------- FOR THIS KLAPACK LIBRARY (${kmlver}): $(ls -lU ${LIBKLAPACK_SO} ${LIBKLAPACK_SO/klapack.so*/klapack.a}) WE HAVE BUILT FULL LAPACK+LAPACKE LIBRARY: $(ls -lU ${LIBKLAPACK_FULL_SO}) USE THESE HEADER FILES: $(ls -lU ${BUILD_DIR}/include/*.h) -------------------------------------------------------------------------------- EOF
- 执行完成后会在目录下会生成libklapack_full.so,可以单独链接此so得到LAPACK-3.12.0的全部接口功能。
此时仍然需要单独链接KML_BLAS库以及libgfortran等系统库。
安装后验证
使用时,假设环境变量KML_LAPACK_ROOT为libklapack.*所在目录,ADAPT_ROOT为适配后Netlib LAPACK库所在目录。用户应用可以选择使用动态链接库或静态链接库。编译应用源代码时需要链接到KML_LAPACK、Netlib LAPACK、Netlib BLAS和gfortran库并开启OpenMP支持。
- 场景一:协同KML_BLAS场景(高性能)假设KML_BLAS已构建的库(libkblas.a和libkblas.so)位于KML_BLAS_ROOT中,为获得最高性能请使用KML_BLAS单线程版本。当使用KML_BLAS时,仍然需要上一节最后获得Netlib LAPACK适配的liblapack_adapt.a,但不再需要Netlib LAPACK中的libblas.a。
KML_LAPACK多线程调用KML_BLAS,因此不可以使用nolocking版本的KML_BLAS,推荐使用omp版本,即/usr/local/kml/lib/neon/kblas/omp/libkblas.so。
- 使用动态链接库
此场景下由于适配的Netlib LAPACK只有静态库liblapack_adapt.a,因此总是静态链接到此库。不再需要链接Netlib LAPACK的libblas.a。
gcc app.c -o app -fopenmp -I $KML_LAPACK_ROOT/include -L /usr/local/kml/lib/neon -lklapack -L $ADAPT_ROOT -l:liblapack_adapt.a -L $KML_BLAS_ROOT -lkblas -lgfortran -lm -lkservice
运行时需能找到KML_LAPACK所需的这些动态链接库,或者将/usr/local/kml/lib/neon/和$KML_BLAS_ROOT加入LD_LIBRARY_PATH。
export LD_LIBRARY_PATH=/usr/local/kml/lib/neon/:$KML_BLAS_ROOT:$LD_LIBRARY_PATH
- 使用静态链接库
此场景不再需要链接Netlib LAPACK的libblas.a。
gcc app.c -o app -fopenmp -I $KML_LAPACK_ROOT/include/kml-0.3.0 -L /usr/local/kml/lib/neon -l:libklapack.a -L $ADAPT_ROOT -l:liblapack_adapt.a -L $KML_BLAS_ROOT -l:libkblas.a -l:libkservice.a -l:libgfortran.a -lm
- 使用动态链接库
- 场景二:无KML_BLAS场景(依赖Netlib LAPACK中自带的BLAS,性能较低)
- 使用动态链接库
gcc app.c -o app -fopenmp -I $KML_LAPACK_ROOT/include/ -L /usr/local/kml/lib/neon -lklapack -L $ADAPT_ROOT -l:liblapack_adapt.a -lblas -lgfortran -lm -lkservice
运行时需能找到KML_LAPACK所需的这些动态链接库,或者将/usr/local/kml/lib和$ADAPT_ROOT加入LD_LIBRARY_PATH。
export LD_LIBRARY_PATH=/usr/local/kml/lib/neon:$ADAPT_ROOT:$LD_LIBRARY_PATH
- 使用静态链接库
gcc app.c -o app -fopenmp -I $KML_LAPACK_ROOT/include/ -L /usr/local/kml/lib/neon -l:libklapack.a -L $ADAPT_ROOT -l:liblapack_adapt.a -l:libblas.a -l:libkservice.a -l:libgfortran.a -lm
- 使用动态链接库
父主题: 如何使用KML