commit 1c6d7546ce70545075363487e8d59ed27247e284 Author: dino Date: Mon Oct 20 15:32:15 2025 +0200 ex1 diff --git a/ex1/ABCEFG/.vscode/settings.json b/ex1/ABCEFG/.vscode/settings.json new file mode 100644 index 0000000..595c6de --- /dev/null +++ b/ex1/ABCEFG/.vscode/settings.json @@ -0,0 +1,64 @@ +{ + "files.associations": { + "algorithm": "cpp", + "format": "cpp", + "iostream": "cpp", + "ostream": "cpp", + "array": "cpp", + "atomic": "cpp", + "bit": "cpp", + "cctype": "cpp", + "charconv": "cpp", + "chrono": "cpp", + "clocale": "cpp", + "cmath": "cpp", + "compare": "cpp", + "concepts": "cpp", + "cstdarg": "cpp", + "cstddef": "cpp", + "cstdint": "cpp", + "cstdio": "cpp", + "cstdlib": "cpp", + "cstring": "cpp", + "ctime": "cpp", + "cwchar": "cpp", + "cwctype": "cpp", + "deque": "cpp", + "list": "cpp", + "string": "cpp", + "unordered_map": "cpp", + "vector": "cpp", + "exception": "cpp", + "functional": "cpp", + "iterator": "cpp", + "memory": "cpp", + "memory_resource": "cpp", + "numeric": "cpp", + "optional": "cpp", + "random": "cpp", + "ratio": "cpp", + "string_view": "cpp", + "system_error": "cpp", + "tuple": "cpp", + "type_traits": "cpp", + "utility": "cpp", + "fstream": "cpp", + "initializer_list": "cpp", + "iomanip": "cpp", + "iosfwd": "cpp", + "istream": "cpp", + "limits": "cpp", + "new": "cpp", + "numbers": "cpp", + "span": "cpp", + "sstream": "cpp", + "stdexcept": "cpp", + "streambuf": "cpp", + "cinttypes": "cpp", + "typeinfo": "cpp", + "variant": "cpp", + "thread": "cpp", + "semaphore": "cpp", + "stop_token": "cpp" + } +} \ No newline at end of file diff --git a/ex1/ABCEFG/CLANG_default.mk b/ex1/ABCEFG/CLANG_default.mk new file mode 100644 index 0000000..4bc290d --- /dev/null +++ b/ex1/ABCEFG/CLANG_default.mk @@ -0,0 +1,123 @@ +# Basic Defintions for using GNU-compiler suite sequentially +# requires setting of COMPILER=CLANG_ + +#CLANGPATH=//usr/lib/llvm-10/bin/ +CC = ${CLANGPATH}clang +CXX = ${CLANGPATH}clang++ +#CXX = ${CLANGPATH}clang++ -lomptarget -fopenmp-targets=nvptx64-nvidia-cuda --cuda-path=/opt/pgi/linux86-64/2017/cuda/8.0 +#F77 = gfortran +LINKER = ${CXX} + +#http://clang.llvm.org/docs/UsersManual.html#options-to-control-error-and-warning-messages +WARNINGS += -Weverything -Wno-c++98-compat -Wno-sign-conversion -Wno-date-time -Wno-shorten-64-to-32 -Wno-padded -ferror-limit=1 +WARNINGS += -Wdocumentation -Wconversion -Wshadow -Wfloat-conversion -pedantic +#-fsyntax-only -Wdocumentation -Wconversion -Wshadow -Wfloat-conversion -pedantic + +CXXFLAGS += -O3 -std=c++17 -ferror-limit=1 ${WARNINGS} +# don't use -Ofast +# -ftrapv +LINKFLAGS += -O3 + +# different libraries in Ubuntu or manajaró +ifndef UBUNTU +UBUNTU=1 +endif + +# BLAS, LAPACK +LINKFLAGS += -llapack -lblas +# -lopenblas +ifeq ($(UBUNTU),1) +# ubuntu +else +# on archlinux +LINKFLAGS += -lcblas +endif + +# interprocedural optimization +CXXFLAGS += -flto +LINKFLAGS += -flto + +# very good check +# http://clang.llvm.org/extra/clang-tidy/ +# good check, see: http://llvm.org/docs/CodingStandards.html#include-style +SWITCH_OFF=,-readability-magic-numbers,-readability-redundant-control-flow,-readability-redundant-member-init +SWITCH_OFF+=,-readability-redundant-member-init,-readability-isolate-declaration +#READABILITY=,readability*${SWITCH_OFF} +#TIDYFLAGS = -checks=llvm-*,-llvm-header-guard -header-filter=.* -enable-check-profile -extra-arg="-std=c++17" -extra-arg="-fopenmp" +TIDYFLAGS = -checks=llvm-*,-llvm-header-guard${READABILITY} -header-filter=.* -enable-check-profile -extra-arg="-std=c++17" -extra-arg="-fopenmp" +#TIDYFLAGS += -checks='modernize* +# ??? +#TIDYFLAGS = -checks='cert*' -header-filter=.* +# MPI checks ?? +#TIDYFLAGS = -checks='mpi*' +# ?? +#TIDYFLAGS = -checks='performance*' -header-filter=.* +#TIDYFLAGS = -checks='portability-*' -header-filter=.* +#TIDYFLAGS = -checks='readability-*' -header-filter=.* + +default: ${PROGRAM} + +${PROGRAM}: ${OBJECTS} + $(LINKER) $^ ${LINKFLAGS} -o $@ + +clean: + @rm -f ${PROGRAM} ${OBJECTS} + +clean_all:: clean + @rm -f *_ *~ *.bak *.log *.out *.tar + +codecheck: tidy_check +tidy_check: + clang-tidy ${SOURCES} ${TIDYFLAGS} -- ${SOURCES} +# see also http://clang-developers.42468.n3.nabble.com/Error-while-trying-to-load-a-compilation-database-td4049722.html + +run: clean ${PROGRAM} +# time ./${PROGRAM} ${PARAMS} + ./${PROGRAM} ${PARAMS} + +# tar the current directory +MY_DIR = `basename ${PWD}` +tar: clean_all + @echo "Tar the directory: " ${MY_DIR} + @cd .. ;\ + tar cf ${MY_DIR}.tar ${MY_DIR} *default.mk ;\ + cd ${MY_DIR} +# tar cf `basename ${PWD}`.tar * + +doc: + doxygen Doxyfile + +######################################################################### + +.cpp.o: + $(CXX) -c $(CXXFLAGS) -o $@ $< + +.c.o: + $(CC) -c $(CFLAGS) -o $@ $< + +.f.o: + $(F77) -c $(FFLAGS) -o $@ $< + +################################################################################################## +# some tools +# Cache behaviour (CXXFLAGS += -g tracks down to source lines; no -pg in linkflags) +cache: ${PROGRAM} + valgrind --tool=callgrind --simulate-cache=yes ./$^ ${PARAMS} +# kcachegrind callgrind.out. & + kcachegrind `ls -1tr callgrind.out.* |tail -1` + +# Check for wrong memory accesses, memory leaks, ... +# use smaller data sets +mem: ${PROGRAM} + valgrind -v --leak-check=yes --tool=memcheck --undef-value-errors=yes --track-origins=yes --log-file=$^.addr.out --show-reachable=yes ./$^ ${PARAMS} + +# Simple run time profiling of your code +# CXXFLAGS += -g -pg +# LINKFLAGS += -pg +prof: ${PROGRAM} + perf record ./$^ ${PARAMS} + perf report +# gprof -b ./$^ > gp.out +# kprof -f gp.out -p gprof & + +codecheck: tidy_check diff --git a/ex1/ABCEFG/GCC_AMD32_default.mk b/ex1/ABCEFG/GCC_AMD32_default.mk new file mode 100644 index 0000000..a911b6b --- /dev/null +++ b/ex1/ABCEFG/GCC_AMD32_default.mk @@ -0,0 +1,130 @@ +# Basic Defintions for using GNU-compiler suite sequentially +# requires setting of COMPILER=GCC_ + +CC = gcc +CXX = g++ +F77 = gfortran +LINKER = ${CXX} + +# on mephisto: +#CXXFLAGS += -I/share/apps/atlas/include +#LINKFLAGS += -L/share/apps/atlas/lib +#LINKFLAGS += -lcblas -latlas + +#LINKFLAGS += -lblas +# Der Header muss mit extern "C" versehen werden, damit g++ alles findet. + + +#WARNINGS = -pedantic -pedantic-errors -Wall -Wextra -Werror -Wconversion -Weffc++ -Woverloaded-virtual -Wfloat-equal -Wshadow +WARNINGS = -pedantic -Wall -Wextra -Wconversion -Weffc++ -Woverloaded-virtual -Wfloat-equal -Wshadow \ + -Wredundant-decls -Winline -fmax-errors=1 +# -Wunreachable-code +# -Wunreachable-code +CXXFLAGS += -ffast-math -O3 -march=native -std=c++17 ${WARNINGS} +#CXXFLAGS += -Ofast -funroll-all-loops -std=c++17 ${WARNINGS} +#-msse3 +# -ftree-vectorizer-verbose=2 -DNDEBUG +# -ftree-vectorizer-verbose=5 +# -ftree-vectorize -fdump-tree-vect-blocks=foo.dump -fdump-tree-pre=stderr + +# CFLAGS = -ffast-math -O3 -DNDEBUG -msse3 -fopenmp -fdump-tree-vect-details +# CFLAGS = -ffast-math -O3 -funroll-loops -DNDEBUG -msse3 -fopenmp -ftree-vectorizer-verbose=2 +# #CFLAGS = -ffast-math -O3 -DNDEBUG -msse3 -fopenmp +# FFLAGS = -ffast-math -O3 -DNDEBUG -msse3 -fopenmp +# LFLAGS = -ffast-math -O3 -DNDEBUG -msse3 -fopenmp +LINKFLAGS += -O3 + +# BLAS, LAPACK +OPENBLAS_DIR = /opt/openblas_GCCseq +#OPENBLAS_DIR = /opt/openblas_GCC +OPENBLAS_LIBDIR = ${OPENBLAS_DIR}/lib +OPENBLAS_INCDIR = ${OPENBLAS_DIR}/include +CXXFLAGS += -I${OPENBLAS_INCDIR} +LINKFLAGS += -L${OPENBLAS_LIBDIR} -lopenblas + +# interprocedural optimization +CXXFLAGS += -flto +LINKFLAGS += -flto + +# profiling tools +#CXXFLAGS += -pg +#LINKFLAGS += -pg + +default: ${PROGRAM} + +${PROGRAM}: ${OBJECTS} + $(LINKER) $^ ${LINKFLAGS} -o $@ + +clean: + @rm -f ${PROGRAM} ${OBJECTS} + +clean_all:: clean + -@rm -f *_ *~ *.bak *.log *.out *.tar *.orig + -@rm -r html + +run: clean ${PROGRAM} +# time ./${PROGRAM} +# ./${PROGRAM} + ( export LD_LIBRARY_PATH=${OPENBLAS_LIBDIR}:${LD_LIBRARY_PATH} ; ./${PROGRAM} ) +# or 'export LD_LIBRARY_PATH=/opt/openblas_gcc/lib:${LD_LIBRARY_PATH}' in your ~/.bashrc + +# tar the current directory +MY_DIR = `basename ${PWD}` +tar: + @echo "Tar the directory: " ${MY_DIR} + @cd .. ;\ + tar cf ${MY_DIR}.tar ${MY_DIR} *default.mk ;\ + cd ${MY_DIR} +# tar cf `basename ${PWD}`.tar * + +doc: + doxygen Doxyfile + +######################################################################### + +.cpp.o: + $(CXX) -c $(CXXFLAGS) -o $@ $< + +.c.o: + $(CC) -c $(CFLAGS) -o $@ $< + +.f.o: + $(F77) -c $(FFLAGS) -o $@ $< + +################################################################################################## +# some tools +# Cache behaviour (CXXFLAGS += -g tracks down to source lines; no -pg in linkflags) +cache: ${PROGRAM} + valgrind --tool=callgrind --simulate-cache=yes ./$^ +# kcachegrind callgrind.out. & + kcachegrind `ls -1tr callgrind.out.* |tail -1` + +# Check for wrong memory accesses, memory leaks, ... +# use smaller data sets +# no "-pg" in compile/link options +mem: ${PROGRAM} + valgrind -v --leak-check=yes --tool=memcheck --undef-value-errors=yes --track-origins=yes --log-file=$^.addr.out --show-reachable=yes ./$^ + +# Simple run time profiling of your code +# CXXFLAGS += -g -pg +# LINKFLAGS += -pg +prof: ${PROGRAM} + ./$^ + gprof -b ./$^ > gp.out +# kprof -f gp.out -p gprof & + +#Trace your heap: +#> heaptrack ./main.GCC_ +#> heaptrack_gui heaptrack.main.GCC_..gz +heap: ${PROGRAM} + heaptrack ./$^ 11 + heaptrack_gui `ls -1tr heaptrack.$^.* |tail -1` & + + + +######################################################################## +# get the detailed status of all optimization flags +info: + echo "detailed status of all optimization flags" + $(CXX) --version + $(CXX) -Q $(CXXFLAGS) --help=optimizers diff --git a/ex1/ABCEFG/GCC_default.mk b/ex1/ABCEFG/GCC_default.mk new file mode 100644 index 0000000..e05986d --- /dev/null +++ b/ex1/ABCEFG/GCC_default.mk @@ -0,0 +1,183 @@ +# Basic Defintions for using GNU-compiler suite sequentially +# requires setting of COMPILER=GCC_ + +CC = gcc +CXX = g++ +F77 = gfortran +LINKER = ${CXX} + +WARNINGS = -Wall -pedantic -Wextra -Weffc++ -Woverloaded-virtual -Wfloat-equal -Wshadow \ + -Wredundant-decls +# -Wunreachable-code +CXXFLAGS += -ffast-math -O3 -march=native -std=c++17 ${WARNINGS} +#CXXFLAGS += -Ofast -funroll-all-loops -std=c++17 ${WARNINGS} +#-msse3 +# -ftree-vectorizer-verbose=2 -DNDEBUG +# -ftree-vectorizer-verbose=5 +# -ftree-vectorize -fdump-tree-vect-blocks=foo.dump -fdump-tree-pre=stderr + +# CFLAGS = -ffast-math -O3 -DNDEBUG -msse3 -fopenmp -fdump-tree-vect-details +# CFLAGS = -ffast-math -O3 -funroll-loops -DNDEBUG -msse3 -fopenmp -ftree-vectorizer-verbose=2 +# #CFLAGS = -ffast-math -O3 -DNDEBUG -msse3 -fopenmp +# FFLAGS = -ffast-math -O3 -DNDEBUG -msse3 -fopenmp +# LFLAGS = -ffast-math -O3 -DNDEBUG -msse3 -fopenmp +LINKFLAGS += -O3 + +#architecture +#CPU = -march=znver2 +CXXFLAGS += ${CPU} +LINKFLAGS += ${CPU} + +# different libraries in Ubuntu or manajaró +ifndef UBUNTU +UBUNTU=1 +endif + +# BLAS, LAPACK +ifeq ($(UBUNTU),1) +LINKFLAGS += -llapack -lblas +# -lopenblas +else +# on archlinux +LINKFLAGS += -llapack -lopenblas -lcblas +endif + +# interprocedural optimization +CXXFLAGS += -flto +LINKFLAGS += -flto + +# for debugging purpose (save code) +# -fsanitize=leak # only one out the three can be used +# -fsanitize=address +# -fsanitize=thread +SANITARY = -fsanitize=address -fsanitize=undefined -fsanitize=null -fsanitize=return \ + -fsanitize=bounds -fsanitize=alignment -fsanitize=float-divide-by-zero -fsanitize=float-cast-overflow \ + -fsanitize=bool -fsanitize=enum -fsanitize=vptr +#CXXFLAGS += ${SANITARY} +#LINKFLAGS += ${SANITARY} + +# profiling tools +#CXXFLAGS += -pg +#LINKFLAGS += -pg + + +default: ${PROGRAM} + +${PROGRAM}: ${OBJECTS} + $(LINKER) $^ ${LINKFLAGS} -o $@ + +clean: + @rm -f ${PROGRAM} ${OBJECTS} + +clean_all:: clean + -@rm -f *_ *~ *.bak *.log *.out *.tar *.orig *.optrpt + -@rm -rf html + +run: clean ${PROGRAM} +#run: ${PROGRAM} +# time ./${PROGRAM} ${PARAMS} + ./${PROGRAM} ${PARAMS} + +# tar the current directory +MY_DIR = `basename ${PWD}` +tar: clean_all + @echo "Tar the directory: " ${MY_DIR} + @cd .. ;\ + tar cf ${MY_DIR}.tar ${MY_DIR} *default.mk ;\ + cd ${MY_DIR} +# tar cf `basename ${PWD}`.tar * +#find . -size +10M > large_files +#--exclude-from ${MY_DIR}/large_files + +zip: clean + @echo "Zip the directory: " ${MY_DIR} + @cd .. ;\ + zip -r ${MY_DIR}.zip ${MY_DIR} *default.mk ;\ + cd ${MY_DIR} + +doc: + doxygen Doxyfile + +######################################################################### +.SUFFIXES: .f90 + +.cpp.o: + $(CXX) -c $(CXXFLAGS) -o $@ $< +# $(CXX) -c $(CXXFLAGS) -o $@ $< 2>&1 | tee -a $<.log +# $(CXX) -c $(CXXFLAGS) -o $@ $< 2>&1 | tee -a $(<:.cpp=.log) + +.c.o: + $(CC) -c $(CFLAGS) -o $@ $< + +.f.o: + $(F77) -c $(FFLAGS) -o $@ $< + +.f90.o: + $(F77) -c $(FFLAGS) -o $@ $< + +################################################################################################## +# some tools +# Cache behaviour (CXXFLAGS += -g tracks down to source lines; no -pg in linkflags) +cache: ${PROGRAM} + valgrind --tool=callgrind --simulate-cache=yes ./$^ ${PARAMS} +# kcachegrind callgrind.out. & + kcachegrind `ls -1tr callgrind.out.* |tail -1` + +# Check for wrong memory accesses, memory leaks, ... +# use smaller data sets +# no "-pg" in compile/link options +mem: ${PROGRAM} + valgrind -v --leak-check=yes --tool=memcheck --undef-value-errors=yes --track-origins=yes --log-file=$^.addr.out --show-reachable=yes ./$^ ${PARAMS} +# Graphical interface +# valkyrie + +# Simple run time profiling of your code +# CXXFLAGS += -g -pg +# LINKFLAGS += -pg +prof: ${PROGRAM} + perf record ./$^ ${PARAMS} + perf report +# gprof -b ./$^ > gp.out +# kprof -f gp.out -p gprof & + +# perf in Ubuntu 20.04: https://www.howtoforge.com/how-to-install-perf-performance-analysis-tool-on-ubuntu-20-04/ +# * install +# * sudo vi /etc/sysctl.conf +# add kernel.perf_event_paranoid = 0 + +#Trace your heap: +#> heaptrack ./main.GCC_ +#> heaptrack_gui heaptrack.main.GCC_..gz +heap: ${PROGRAM} + heaptrack ./$^ ${PARAMS} + heaptrack_gui `ls -1tr heaptrack.$^.* |tail -1` & + +codecheck: $(SOURCES) + cppcheck --enable=all --inconclusive --std=c++17 --suppress=missingIncludeSystem $^ + + +######################################################################## +# get the detailed status of all optimization flags +info: + echo "detailed status of all optimization flags" + $(CXX) --version + $(CXX) -Q $(CXXFLAGS) --help=optimizers + lscpu + inxi -C + lstopo + +# Excellent hardware info +# hardinfo +# Life monitoring of CPU frequency etc. +# sudo i7z + +# Memory consumption +# vmstat -at -SM 3 +# xfce4-taskmanager + + +# https://www.tecmint.com/check-linux-cpu-information/ +#https://www.tecmint.com/monitor-cpu-and-gpu-temperature-in-ubuntu/ + +# Debugging: +# https://wiki.archlinux.org/index.php/Debugging diff --git a/ex1/ABCEFG/ICC_default.mk b/ex1/ABCEFG/ICC_default.mk new file mode 100644 index 0000000..d4bd4db --- /dev/null +++ b/ex1/ABCEFG/ICC_default.mk @@ -0,0 +1,137 @@ +# Basic Defintions for using INTEL compiler suite sequentially +# requires setting of COMPILER=ICC_ + +#BINDIR = /opt/intel/bin/ + +# special on my sony [GH] +#BINDIR = /opt/save.intel/bin/ +# very special on my sony [GH] +# FIND_LIBS = -L /opt/save.intel/composer_xe_2013.1.117/mkl/lib/intel64/libmkl_intel_lp64.so + +# Error with g++-4.8 using icpc14.0,x: +# find directory wherein bits/c++config.h is located +# 'locate bits/c++config.h' +#FOUND_CONFIG = -I/usr/include/x86_64-linux-gnu/c++/4.8 + + +CC = ${BINDIR}icc +CXX = ${BINDIR}icpc +F77 = ${BINDIR}ifort +LINKER = ${CXX} + + +WARNINGS = -Wall -Weffc++ -Woverloaded-virtual -Wfloat-equal -Wshadow -wd2015,2012 -wn3 +# -Winline -Wredundant-decls -Wunreachable-code +CXXFLAGS += -O3 -fargument-noalias -std=c++17 -DNDEBUG ${WARNINGS} -mkl ${FOUND_CONFIG} +# profiling tools +#CXXFLAGS += -pg +#LINKFLAGS += -pg +# -vec-report=3 +# -qopt-report=5 -qopt-report-phase=vec +# -guide -parallel +# -guide-opts=string -guide-par[=n] -guide-vec[=n] +# -auto-p32 -simd +CXXFLAGS += -align + +# use MKL by INTEL +# https://software.intel.com/content/www/us/en/develop/documentation/mkl-linux-developer-guide/top/linking-your-application-with-the-intel-math-kernel-library/linking-quick-start/using-the-mkl-compiler-option.html +# https://software.intel.com/content/www/us/en/develop/articles/intel-mkl-link-line-advisor.html +# LINKFLAGS += -L${BINDIR}../composer_xe_2013.1.117/mkl/lib/intel64 -lmkl_intel_lp64 -lmkl_sequential -lmkl_core -lpthread +#LINKFLAGS += -O3 -L/opt/intel/mkl/lib -mkl +LINKFLAGS += -O3 -mkl=sequential + +# interprocedural optimization +CXXFLAGS += -ipo +LINKFLAGS += -ipo + +# annotated assembler file +ANNOTED = -fsource-asm -S + +default: ${PROGRAM} + +${PROGRAM}: ${OBJECTS} + $(LINKER) $^ ${LINKFLAGS} -o $@ + +clean: + rm -f ${PROGRAM} ${OBJECTS} + +clean_all:: clean + @rm -f *_ *~ *.bak *.log *.out *.tar + +run: clean ${PROGRAM} + ./${PROGRAM} + +# tar the current directory +MY_DIR = `basename ${PWD}` +tar: clean_all + @echo "Tar the directory: " ${MY_DIR} + @cd .. ;\ + tar cf ${MY_DIR}.tar ${MY_DIR} *default.mk ;\ + cd ${MY_DIR} +# tar cf `basename ${PWD}`.tar * + +doc: + doxygen Doxyfile + +######################################################################### + +.cpp.o: + $(CXX) -c $(CXXFLAGS) -o $@ $< + +.c.o: + $(CC) -c $(CFLAGS) -o $@ $< + +.f.o: + $(F77) -c $(FFLAGS) -o $@ $< + +################################################################################################## +# # some tools +# # Cache behaviour (CXXFLAGS += -g tracks down to source lines) +# cache: ${PROGRAM} +# valgrind --tool=callgrind --simulate-cache=yes ./$^ +# # kcachegrind callgrind.out. & +# +# # Check for wrong memory accesses, memory leaks, ... +# # use smaller data sets +# mem: ${PROGRAM} +# valgrind -v --leak-check=yes --tool=memcheck --undef-value-errors=yes --track-origins=yes --log-file=$^.addr.out --show-reachable=yes ./$^ +# +# # Simple run time profiling of your code +# # CXXFLAGS += -g -pg +# # LINKFLAGS += -pg +# prof: ${PROGRAM} +# ./$^ +# gprof -b ./$^ > gp.out +# # kprof -f gp.out -p gprof & +# + + +mem: inspector +prof: amplifier +cache: amplifier + +gap_par_report: + ${CXX} -c -guide -parallel $(SOURCES) 2> gap.txt + +# GUI for performance report +amplifier: ${PROGRAM} + echo 0 | sudo tee /proc/sys/kernel/yama/ptrace_scope +# alternatively to the solution above: + #edit file /etc/sysctl.d/10-ptrace.conf and set variable kernel.yama.ptrace_scope variable to 0 . + amplxe-gui & + +# GUI for Memory and Thread analyzer (race condition) +inspector: ${PROGRAM} + echo 0 | sudo tee /proc/sys/kernel/yama/ptrace_scope + inspxe-gui & + +advisor: + echo 0 | sudo tee /proc/sys/kernel/yama/ptrace_scope + advixe-gui & + +icc-info: + icpc -# main.cpp + + + + diff --git a/ex1/ABCEFG/ONEAPI_default.mk b/ex1/ABCEFG/ONEAPI_default.mk new file mode 100644 index 0000000..fe7b3fe --- /dev/null +++ b/ex1/ABCEFG/ONEAPI_default.mk @@ -0,0 +1,176 @@ +# Basic Defintions for using INTEL compiler suite sequentially +# requires setting of COMPILER=ONEAPI_ + +# https://software.intel.com/content/www/us/en/develop/tools/oneapi/components/onemkl/link-line-advisor.html +# requires +# source /opt/intel/oneapi/setvars.sh +# on AMD: export MKL_DEBUG_CPU_TYPE=5 + +#BINDIR = /opt/intel/oneapi/compiler/latest/linux/bin/ +#MKL_ROOT = /opt/intel/oneapi/mkl/latest/ +#export KMP_AFFINITY=verbose,compact + +CC = ${BINDIR}icc +CXX = ${BINDIR}dpcpp +F77 = ${BINDIR}ifort +LINKER = ${CXX} + +## Compiler flags +WARNINGS = -Wall -Weffc++ -Woverloaded-virtual -Wfloat-equal -Wshadow -pedantic +WARNINGS += -Wpessimizing-move -Wredundant-move +#-wd2015,2012,2014 -wn3 +# -Winline -Wredundant-decls -Wunreachable-code +# -qopt-subscript-in-range +# -vec-threshold0 + +CXXFLAGS += -O3 -std=c++17 ${WARNINGS} +#CXXFLAGS += -DMKL_ILP64 -I"${MKLROOT}/include" +#CXXFLAGS += -DMKL_ILP32 -I"${MKLROOT}/include" +LINKFLAGS += -O3 + +# interprocedural optimization +CXXFLAGS += -ipo +LINKFLAGS += -ipo +LINKFLAGS += -flto + +# annotated Assembler file +ANNOTED = -fsource-asm -S + +#architecture +CPU = -march=core-avx2 +#CPU += -mtp=zen +# -xCORE-AVX2 +# -axcode COMMON-AVX512 -axcode MIC-AVX512 -axcode CORE-AVX512 -axcode CORE-AVX2 +CXXFLAGS += ${CPU} +LINKFLAGS += ${CPU} + +# use MKL by INTEL +# https://software.intel.com/content/www/us/en/develop/tools/oneapi/components/onemkl/link-line-advisor.html +# sequential MKL +# use the 32 bit interface (LP64) instead of 64 bit interface (ILP64) +CXXFLAGS += -qmkl=sequential -UMKL_ILP64 +LINKFLAGS += -O3 -qmkl=sequential -lmkl_intel_lp64 -lmkl_sequential -lmkl_core -lpthread +#LINKFLAGS += -O3 -lmkl_intel_lp64 -lmkl_sequential -lmkl_core -lpthread + +# shared libs: https://aur.archlinux.org/packages/intel-oneapi-compiler-static +# install intel-oneapi-compiler-static +# or +LINKFLAGS += -shared-intel + + +OPENMP = -qopenmp +CXXFLAGS += ${OPENMP} +LINKFLAGS += ${OPENMP} + + +# profiling tools +#CXXFLAGS += -pg +#LINKFLAGS += -pg +# -vec-report=3 +# -qopt-report=5 -qopt-report-phase=vec -qopt-report-phase=openmp +# -guide -parallel +# -guide-opts=string -guide-par[=n] -guide-vec[=n] +# -auto-p32 -simd + +# Reports: https://software.intel.com/en-us/articles/getting-the-most-out-of-your-intel-compiler-with-the-new-optimization-reports +#CXXFLAGS += -qopt-report=5 -qopt-report-phase=vec,par +#CXXFLAGS += -qopt-report=5 -qopt-report-phase=cg +# Redirect report from *.optrpt to stderr +# -qopt-report-file=stderr +# Guided paralellization +# -guide -parallel +# -guide-opts=string -guide-par[=n] -guide-vec[=n] +# -auto-p32 -simd + +## run time checks +# https://www.intel.com/content/www/us/en/develop/documentation/fortran-compiler-oneapi-dev-guide-and-reference/top/compiler-reference/compiler-options/offload-openmp-and-parallel-processing-options/par-runtime-control-qpar-runtime-control.html + + +default: ${PROGRAM} + +${PROGRAM}: ${OBJECTS} + $(LINKER) $^ ${LINKFLAGS} -o $@ + +clean: + rm -f ${PROGRAM} ${OBJECTS} *.optrpt + +clean_all:: clean + @rm -f *_ *~ *.bak *.log *.out *.tar + +run: clean ${PROGRAM} + ./${PROGRAM} + +# tar the current directory +MY_DIR = `basename ${PWD}` +tar: clean_all + @echo "Tar the directory: " ${MY_DIR} + @cd .. ;\ + tar cf ${MY_DIR}.tar ${MY_DIR} *default.mk ;\ + cd ${MY_DIR} +# tar cf `basename ${PWD}`.tar * + +doc: + doxygen Doxyfile + +######################################################################### + +.cpp.o: + $(CXX) -c $(CXXFLAGS) -o $@ $< + +.c.o: + $(CC) -c $(CFLAGS) -o $@ $< + +.f.o: + $(F77) -c $(FFLAGS) -o $@ $< + +################################################################################################## +# some tools +# Cache behaviour (CXXFLAGS += -g tracks down to source lines) +# https://software.intel.com/content/www/us/en/develop/documentation/vtune-help/top/analyze-performance/microarchitecture-analysis-group/memory-access-analysis.html + +mem: inspector +prof: vtune +cache: inspector + +gap_par_report: + ${CXX} -c -guide -parallel $(SOURCES) 2> gap.txt + +# GUI for performance report +amplifier: ${PROGRAM} + echo 0 | sudo tee /proc/sys/kernel/yama/ptrace_scope + echo 0 | sudo tee /proc/sys/kernel/perf_event_paranoid + amplxe-gui & + +# GUI for Memory and Thread analyzer (race condition) +inspector: ${PROGRAM} + echo 0 | sudo tee /proc/sys/kernel/yama/ptrace_scope +# inspxe-gui & + vtune-gui ./${PROGRAM} & + +advisor: + source /opt/intel/oneapi/advisor/2021.2.0/advixe-vars.sh +# /opt/intel/oneapi/advisor/latest/bin64/advixe-gui & + advisor --collect=survey ./${PROGRAM} +# advisor --collect=roofline ./${PROGRAM} + advisor --report=survey --project-dir=./ src:r=./ --format=csv --report-output=./out/survey.csv + +vtune: + echo 0 | sudo tee /proc/sys/kernel/yama/ptrace_scope +# https://software.intel.com/en-us/articles/intel-advisor-2017-update-1-what-s-new + export ADVIXE_EXPERIMENTAL=roofline + vtune -collect hotspots ./${PROGRAM} + vtune -report hotspots -r r000hs > vtune.out +# vtune-gui ./${PROGRAM} & + +icc-info: + icpc -# main.cpp + +# MKL on AMD +# https://www.computerbase.de/2019-11/mkl-workaround-erhoeht-leistung-auf-amd-ryzen/ +# +# https://sites.google.com/a/uci.edu/mingru-yang/programming/mkl-has-bad-performance-on-an-amd-cpu +# export MKL_DEBUG_CPU_TYPE=5 +# export MKL_NUM_THRAEDS=1 +# export MKL_DYNAMIC=false +# on Intel compiler +# http://publicclu2.blogspot.com/2013/05/intel-complier-suite-reference-card.html diff --git a/ex1/ABCEFG/PGI_default.mk b/ex1/ABCEFG/PGI_default.mk new file mode 100644 index 0000000..40760e5 --- /dev/null +++ b/ex1/ABCEFG/PGI_default.mk @@ -0,0 +1,93 @@ +# Basic Defintions for using PGI-compiler suite sequentially +# requires setting of COMPILER=PGI_ +# OPTIRUN = optirun + + +CC = pgcc +CXX = pgc++ +F77 = pgfortran +LINKER = ${CXX} + +# on mephisto: +#CXXFLAGS += -I/share/apps/atlas/include +#LINKFLAGS += -L/share/apps/atlas/lib +#LINKFLAGS += -lcblas -latlas + +#LINKFLAGS += -lblas +# Der Header muss mit extern "C" versehen werden, damit g++ alles findet. + +WARNINGS = -Minform=warn +# -Wall -pedantic -Wextra -Weffc++ -Woverloaded-virtual -W -Wfloat-equal -Wshadow -Wredundant-decls +# -pedantic -Wunreachable-code -Wextra -Winline +# -Wunreachable-code + +#PGI_PROFILING = -Minfo=ccff,loop,vect,opt,intensity,mp,accel +PGI_PROFILING = -Minfo=ccff,accel,ipa,loop,lre,mp,opt,par,unified,vect,intensity +# -Minfo +# -Mprof=time +# -Mprof=lines +# take care with option -Msafeptr +CXXFLAGS += -O3 -std=c++17 ${WARNINGS} +#CXXFLAGS += -O3 -std=c++11 -DNDEBUG ${PGI_PROFILING} ${WARNINGS} +# -fastsse -fargument-noalias ${WARNINGS} -msse3 -vec-report=3 + +default: ${PROGRAM} + +${PROGRAM}: ${OBJECTS} + $(LINKER) $^ ${LINKFLAGS} -o $@ + +clean: + @rm -f ${PROGRAM} ${OBJECTS} + +clean_all:: clean + @rm -f *_ *~ *.bak *.log *.out *.tar + +run: clean ${PROGRAM} + ./${PROGRAM} + +# tar the current directory +MY_DIR = `basename ${PWD}` +tar: clean_all + @echo "Tar the directory: " ${MY_DIR} + @cd .. ;\ + tar cf ${MY_DIR}.tar ${MY_DIR} *default.mk ;\ + cd ${MY_DIR} +# tar cf `basename ${PWD}`.tar * + +doc: + doxygen Doxyfile + +######################################################################### + +.cpp.o: + $(CXX) -c $(CXXFLAGS) -o $@ $< + +.c.o: + $(CC) -c $(CFLAGS) -o $@ $< + +.f.o: + $(F77) -c $(FFLAGS) -o $@ $< + +################################################################################################## +# # some tools +# # Simple run time profiling of your code +# # CXXFLAGS += -g -pg +# # LINKFLAGS += -pg + + +# Profiling options PGI, see: pgcollect -help +# CPU_PROF = -allcache +CPU_PROF = -time +# GPU_PROF = -cuda=gmem,branch,cc13 -cudainit +#GPU_PROF = -cuda=branch:cc20 +# +PROF_FILE = pgprof.out + +cache: prof + +prof: ${PROGRAM} + ${OPTIRUN} ${BINDIR}pgcollect $(CPU_PROF) ./$^ + ${OPTIRUN} ${BINDIR}pgprof -exe ./$^ $(PROF_FILE) & + +info: + pgaccelinfo -v diff --git a/ex1/ABCEFG/skalar_stl/.swo b/ex1/ABCEFG/skalar_stl/.swo new file mode 100644 index 0000000..c60ad69 Binary files /dev/null and b/ex1/ABCEFG/skalar_stl/.swo differ diff --git a/ex1/ABCEFG/skalar_stl/.swp b/ex1/ABCEFG/skalar_stl/.swp new file mode 100644 index 0000000..e1166b6 Binary files /dev/null and b/ex1/ABCEFG/skalar_stl/.swp differ diff --git a/ex1/ABCEFG/skalar_stl/.vscode/settings.json b/ex1/ABCEFG/skalar_stl/.vscode/settings.json new file mode 100644 index 0000000..222e42e --- /dev/null +++ b/ex1/ABCEFG/skalar_stl/.vscode/settings.json @@ -0,0 +1,63 @@ +{ + "files.associations": { + "iostream": "cpp", + "array": "cpp", + "atomic": "cpp", + "bit": "cpp", + "*.tcc": "cpp", + "cctype": "cpp", + "charconv": "cpp", + "chrono": "cpp", + "clocale": "cpp", + "cmath": "cpp", + "compare": "cpp", + "complex": "cpp", + "concepts": "cpp", + "cstdarg": "cpp", + "cstddef": "cpp", + "cstdint": "cpp", + "cstdio": "cpp", + "cstdlib": "cpp", + "cstring": "cpp", + "ctime": "cpp", + "cwchar": "cpp", + "cwctype": "cpp", + "deque": "cpp", + "string": "cpp", + "unordered_map": "cpp", + "vector": "cpp", + "exception": "cpp", + "algorithm": "cpp", + "functional": "cpp", + "iterator": "cpp", + "memory": "cpp", + "memory_resource": "cpp", + "numeric": "cpp", + "optional": "cpp", + "random": "cpp", + "ratio": "cpp", + "string_view": "cpp", + "system_error": "cpp", + "tuple": "cpp", + "type_traits": "cpp", + "utility": "cpp", + "format": "cpp", + "initializer_list": "cpp", + "iomanip": "cpp", + "iosfwd": "cpp", + "istream": "cpp", + "limits": "cpp", + "new": "cpp", + "numbers": "cpp", + "ostream": "cpp", + "span": "cpp", + "sstream": "cpp", + "stdexcept": "cpp", + "streambuf": "cpp", + "cinttypes": "cpp", + "typeinfo": "cpp", + "variant": "cpp", + "cassert": "cpp", + "fstream": "cpp" + } +} \ No newline at end of file diff --git a/ex1/ABCEFG/skalar_stl/.vscode/tasks.json b/ex1/ABCEFG/skalar_stl/.vscode/tasks.json new file mode 100644 index 0000000..05054c5 --- /dev/null +++ b/ex1/ABCEFG/skalar_stl/.vscode/tasks.json @@ -0,0 +1,28 @@ +{ + "tasks": [ + { + "type": "cppbuild", + "label": "C/C++: g++ build active file", + "command": "/usr/bin/g++", + "args": [ + "-fdiagnostics-color=always", + "-g", + "${file}", + "-o", + "${fileDirname}/${fileBasenameNoExtension}" + ], + "options": { + "cwd": "${fileDirname}" + }, + "problemMatcher": [ + "$gcc" + ], + "group": { + "kind": "build", + "isDefault": true + }, + "detail": "Task generated by Debugger." + } + ], + "version": "2.0.0" +} \ No newline at end of file diff --git a/ex1/ABCEFG/skalar_stl/DenseMatrix.cpp b/ex1/ABCEFG/skalar_stl/DenseMatrix.cpp new file mode 100644 index 0000000..175a71b --- /dev/null +++ b/ex1/ABCEFG/skalar_stl/DenseMatrix.cpp @@ -0,0 +1,7 @@ + +#include +#include +#include +#include +using namespace std; + diff --git a/ex1/ABCEFG/skalar_stl/DenseMatrix.h b/ex1/ABCEFG/skalar_stl/DenseMatrix.h new file mode 100644 index 0000000..3235712 --- /dev/null +++ b/ex1/ABCEFG/skalar_stl/DenseMatrix.h @@ -0,0 +1,4 @@ +#pragma once + +#include +using namespace std; diff --git a/ex1/ABCEFG/skalar_stl/DenseMatrix.o b/ex1/ABCEFG/skalar_stl/DenseMatrix.o new file mode 100644 index 0000000..b18fd03 Binary files /dev/null and b/ex1/ABCEFG/skalar_stl/DenseMatrix.o differ diff --git a/ex1/ABCEFG/skalar_stl/Makefile b/ex1/ABCEFG/skalar_stl/Makefile new file mode 100644 index 0000000..f5bc097 --- /dev/null +++ b/ex1/ABCEFG/skalar_stl/Makefile @@ -0,0 +1,30 @@ +# +# use GNU-Compiler tools +COMPILER=GCC_ +# alternatively from the shell +# export COMPILER=GCC_ +# or, alternatively from the shell +# make COMPILER=GCC_ + +# use Intel compilers +#COMPILER=ICC_ + +# use PGI compilers +# COMPILER=PGI_ + + +SOURCES = main.cpp mylib.cpp +OBJECTS = $(SOURCES:.cpp=.o) + +PROGRAM = main.${COMPILER} + +# uncomment the next to lines for debugging and detailed performance analysis +CXXFLAGS += -g +LINKFLAGS += -g +# do not use -pg with PGI compilers + +ifndef COMPILER + COMPILER=GCC_ +endif + +include ../${COMPILER}default.mk diff --git a/ex1/ABCEFG/skalar_stl/data_1.txt b/ex1/ABCEFG/skalar_stl/data_1.txt new file mode 100644 index 0000000..301caaf --- /dev/null +++ b/ex1/ABCEFG/skalar_stl/data_1.txt @@ -0,0 +1,500 @@ +141 +261 +87 +430 +258 +298 +425 +120 +496 +707 +244 +786 +75 +394 +4 +221 +2 +190 +143 +269 +175 +139 +599 +902 +940 +222 +483 +377 +524 +265 +69 +437 +174 +27 +955 +431 +962 +763 +8 +681 +706 +646 +553 +219 +773 +229 +371 +891 +857 +403 +319 +609 +911 +910 +592 +333 +854 +443 +905 +34 +533 +717 +180 +337 +188 +322 +404 +549 +49 +553 +275 +242 +244 +155 +957 +936 +819 +729 +176 +361 +189 +2 +317 +700 +626 +544 +440 +288 +502 +762 +763 +577 +748 +646 +124 +505 +348 +93 +148 +199 +673 +432 +695 +257 +10 +533 +280 +947 +907 +393 +25 +672 +838 +972 +57 +451 +583 +687 +720 +651 +727 +374 +582 +117 +58 +980 +285 +595 +963 +186 +194 +342 +933 +391 +274 +152 +398 +375 +132 +436 +92 +615 +11 +574 +790 +236 +449 +570 +62 +497 +643 +222 +838 +972 +847 +506 +279 +747 +237 +958 +621 +601 +173 +91 +256 +859 +912 +700 +726 +230 +577 +811 +404 +989 +90 +321 +512 +61 +726 +557 +530 +830 +859 +790 +318 +453 +753 +110 +110 +270 +525 +973 +711 +312 +292 +851 +912 +640 +256 +89 +839 +585 +949 +62 +585 +286 +828 +191 +443 +394 +827 +677 +208 +319 +134 +672 +571 +170 +148 +477 +909 +553 +33 +54 +806 +452 +383 +790 +365 +533 +712 +872 +329 +651 +975 +76 +588 +414 +310 +264 +759 +996 +187 +782 +196 +993 +803 +425 +729 +499 +809 +357 +74 +591 +911 +194 +433 +750 +40 +947 +764 +559 +184 +498 +518 +995 +855 +963 +679 +404 +935 +480 +232 +397 +706 +559 +757 +996 +963 +536 +964 +116 +52 +305 +581 +531 +902 +541 +432 +543 +713 +17 +801 +143 +479 +257 +370 +662 +170 +279 +199 +196 +327 +881 +472 +404 +180 +969 +408 +845 +616 +377 +878 +785 +465 +814 +899 +430 +335 +597 +902 +703 +378 +735 +955 +543 +541 +312 +72 +182 +93 +464 +10 +916 +643 +2 +31 +209 +455 +128 +9 +728 +355 +781 +437 +437 +50 +50 +92 +595 +242 +842 +858 +964 +489 +221 +227 +537 +763 +348 +462 +640 +918 +162 +716 +578 +434 +885 +394 +179 +634 +625 +328 +803 +1000 +981 +128 +233 +24 +608 +111 +408 +885 +549 +370 +209 +441 +957 +125 +471 +857 +44 +692 +979 +284 +134 +686 +910 +611 +900 +194 +755 +347 +419 +156 +820 +625 +739 +806 +68 +951 +498 +756 +743 +832 +157 +458 +619 +933 +836 +896 +583 +583 +855 +35 +886 +408 +37 +747 +155 +144 +606 +255 +325 +402 +407 +387 +610 +167 +189 +95 +324 +770 +235 +741 +693 +825 +828 +294 +310 +524 +326 +832 +811 +557 +263 +681 +234 +457 +385 +539 +992 +756 +981 +235 +529 +52 +757 +602 +858 +989 +930 +410 +1 +541 +208 +220 +326 +96 +748 +749 +544 +339 +833 +553 +958 +893 +357 +547 +347 +623 +797 +746 +126 +823 +26 +415 +732 +782 +368 \ No newline at end of file diff --git a/ex1/ABCEFG/skalar_stl/main.GCC_ b/ex1/ABCEFG/skalar_stl/main.GCC_ new file mode 100755 index 0000000..563c943 Binary files /dev/null and b/ex1/ABCEFG/skalar_stl/main.GCC_ differ diff --git a/ex1/ABCEFG/skalar_stl/main.cpp b/ex1/ABCEFG/skalar_stl/main.cpp new file mode 100644 index 0000000..35e679c --- /dev/null +++ b/ex1/ABCEFG/skalar_stl/main.cpp @@ -0,0 +1,290 @@ +#include "mylib.h" +#include "timing.h" +#include "DenseMatrix.h" + +#include // assert +#include +#include +#include +#include +#include +#include +#include +#include +#include +using namespace std; + +void task_a() { + printf("\n\n-------------- Task A --------------\n\n"); + + auto [a,b,c] = means0(1,4,16); + auto [d,e,f] = means0(2,3,5); + auto [g,h,i] = means0(1000,4000,16000); + printf("means(1,4,16) = (%f, %f, %f)\n", a, b, c); + printf("means(2,3,5) = (%f, %f, %f)\n", d, e, f); + printf("means(1000,4000,16000) = (%f, %f, %f)\n", g, h, i); + + vector v = {4,8,15,16,23,42}; + auto [j,k,l] = means(v); + printf("means(4,8,15,16,23,42) = (%f, %f, %f)\n", j, k, l); + + +} + +void task_b() { + printf("\n\n-------------- Task B --------------\n\n"); + + // Read vector + vector a; + read_vector_from_file("data_1.txt", a); + + // Print numbers + // for (unsigned int k=0; k b = {*min,*max,x,y,z,deviation}; + write_vector_to_file("out_1.txt", b); + +} + +void task_c() { + printf("\n\n-------------- Task C --------------\n\n"); + + vector n_values = {15, 1001, 1432987}; + + for (int n : n_values) { + printf("n = %d\n", n); + double sum = 0; + double loops = 1000; + + // Timing first function + tic(); + for (int i=0; i vec(n); + list lst(n); + + // Initialize + for (int i = 1; i < n+1; ++i) { + vec.push_back(i); + lst.push_back(i); + } + + // Insert into vector + tic(); + insert_into_vector(vec, n); + double sec1 = toc(); + printf("Vector insertion time for n = %d: %.f microseconds.\n", n, sec1*1000*1000); + + // Insert into list + tic(); + insert_into_list(lst, n); + double sec2 = toc(); + printf("List insertion time for n = %d: %.f microseconds.\n", n, sec2*1000*1000); + } +} + +void task_f() { + printf("\n\n-------------- Task F --------------\n\n"); + + // single_goldbach(k) + int k = 694; + printf("single_goldbach(k = %d) = %d\n", k, single_goldbach(k)); + + // Prints decompositions + print_decomps(k); + + // count_goldbach(n) + printf("\nNOTE: For n=2'000'000 it will take ~30 seconds.\n"); + for (int n : {10'000, 100'000, 400'000, 1'000'000}) { //, 2'000'000}) { + tic(); + vector counts = count_goldbach(n); + double sec = toc(); + + auto max = max_element(counts.begin(), counts.end()); + printf("count_goldbach(n = %d): k = %ld, decompositions = %d, time elapsed: %f milliseconds\n", n, max-counts.begin(), *max, sec*1000); + } + + // Results + // count_goldbach(n = 10'000): k = 9240, decompositions = 329, time elapsed: 1.235096 milliseconds + // count_goldbach(n = 100'000): k = 99330, decompositions = 2168, time elapsed: 39.003922 milliseconds + // count_goldbach(n = 400'000): k = 390390, decompositions = 7094, time elapsed: 497.282572 milliseconds + // count_goldbach(n = 1'000'000): k = 990990, decompositions = 15594, time elapsed: 3236.044944 milliseconds + // count_goldbach(n = 2'000'000): k = 1981980, decompositions = 27988, time elapsed: 29864.384370 milliseconds + // count_goldbach(n = 10'000'000): k = 9699690, decompositions = 124180, time elapsed: 825392.110981 milliseconds + +} + +void task_g() { + printf("\n\n-------------- Task G --------------\n\n"); + + DenseMatrix const M(5,3); + + vector const u{{1,2,3}}; + vector f1 = M.Mult(u); + + vector const v{{-1,2,-3,4,-5}}; + vector f2 = M.MultT(v); + + + cout << "M = " << endl; + M.print(); + cout << endl << "u = "; + for (size_t i=0; i w(n,0); + for (int i=0; i f3 = M2.Mult(w); + for (int k=1; k f4 = M2.MultT(w); + for (int k=1; k 1e-4) + { + cout << "Resulting vectors are not equal" << endl; + } + } +// ################################################ + + // Time initialization + tic(); + vector x(n,0); + for (int i=0; i f5 = M3.Mult(w); + for (int k=1; k f6 = M3.MultT(w); + for (int k=1; k 1e-4) + { + cout << "Resulting vectors are not equal" << endl; + } + } + + printf("\nNOTE: difference in runtime noticable with n=10.000 (~30 seconds)\n"); + + +} + + +int main(){ + + task_a(); + task_b(); + task_c(); + task_d(); + task_e(); + task_f(); + task_g(); + + return 0; +}; \ No newline at end of file diff --git a/ex1/ABCEFG/skalar_stl/main.o b/ex1/ABCEFG/skalar_stl/main.o new file mode 100644 index 0000000..9b88548 Binary files /dev/null and b/ex1/ABCEFG/skalar_stl/main.o differ diff --git a/ex1/ABCEFG/skalar_stl/mayer_primes.h b/ex1/ABCEFG/skalar_stl/mayer_primes.h new file mode 100644 index 0000000..6c6dc23 --- /dev/null +++ b/ex1/ABCEFG/skalar_stl/mayer_primes.h @@ -0,0 +1,73 @@ +#pragma once + +#include //memset +#include +//using namespace std; + +/** \brief Determines all prime numbers in interval [2, @p max]. + * + * The sieve of Eratosthenes is used. + * + * The implementation originates from Florian Mayer. + * + * \param[in] max end of interval for the prime number search. + * \return vector of prime numbers @f$2,3,5, ..., p<=max @f$. + * + * \copyright + * Copyright (c) 2008 Florian Mayer (adapted by Gundolf Haase 2018) + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, + * INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. + * + */ +template +std::vector get_primes(T max) +{ + std::vector primes; + char *sieve; + sieve = new char[max / 8 + 1]; + // Fill sieve with 1 + memset(sieve, 0xFF, (max / 8 + 1) * sizeof(char)); + for (T x = 2; x <= max; x++) + { + if (sieve[x / 8] & (0x01 << (x % 8))) { + primes.push_back(x); + // Is prime. Mark multiplicates. + for (T j = 2 * x; j <= max; j += x) + { + sieve[j / 8] &= ~(0x01 << (j % 8)); + } + } + } + delete[] sieve; + return primes; +} + +//--------------------------------------------------------------- +//int main() // by Florian Mayer +//{g++ -O3 -std=c++14 -fopenmp main.cpp && ./a.out +// vector primes; +// primes = get_primes(10000000); +// // return 0; +// // Print out result. +// vector::iterator it; +// for(it=primes.begin(); it < primes.end(); it++) +// cout << *it << " "; +// +// cout << endl; +// return 0; +//} diff --git a/ex1/ABCEFG/skalar_stl/mylib.cpp b/ex1/ABCEFG/skalar_stl/mylib.cpp new file mode 100644 index 0000000..d7ac4b4 --- /dev/null +++ b/ex1/ABCEFG/skalar_stl/mylib.cpp @@ -0,0 +1,312 @@ +#include "mylib.h" +#include "mayer_primes.h" +#include "DenseMatrix.h" + +#include // assert +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +using namespace std; + +// -------------- Task A -------------- + +tuple means0(double a, double b, double c){ + double arith = (a+b+c) / 3; + double geo = pow((a*b*c), 1.0f/3); + double harm = 3 / ((1.0f/a) + (1.0f/b) + (1.0f/c)); + return make_tuple(arith, geo, harm); +} + +tuple means(const vector& v){ + int n = v.size(); + double sum = 0; + double prod = 1; + double invsum = 0; + + for (int i = 0; i& v) +{ + double d=0; + while ( istr >> d) v.push_back(d); // Einlesen + if (!istr.eof()) + { // Fehlerbehandlung + cout << " Error handling \n"; + if ( istr.bad() ) throw runtime_error("Schwerer Fehler in istr"); + if ( istr.fail() ) // Versuch des Aufraeumens + { + cout << " Failed in reading all data.\n"; + istr.clear(); + } + } + v.shrink_to_fit(); // C++11 + return; +} + + +void read_vector_from_file(const string& file_name, vector& v) +{ + ifstream fin(file_name); // Oeffne das File im ASCII-Modus + if( fin.is_open() ) // File gefunden: + { + v.clear(); // Vektor leeren + fill_vector(fin, v); + } + else // File nicht gefunden: + { + cout << "\nFile " << file_name << " has not been found.\n\n" ; + assert( fin.is_open() && "File not found." ); // exeption handling for the poor programmer + } + + return; +} + +void write_vector_to_file(const string& file_name, const vector& v) +{ + ofstream fout(file_name); // Oeffne das File im ASCII-Modus + if( fout.is_open() ) + { + for (unsigned int k=0; k& vec, int n) { + random_device rd; // random device + mt19937 gen(rd()); // seed + uniform_int_distribution<> dist(1, n); // define range + + for (int i = 0; i < n; ++i) { + int rand_num = dist(gen); + auto pos = lower_bound(vec.begin(), vec.end(), rand_num); + vec.insert(pos, rand_num); + } + assert(is_sorted(vec.begin(), vec.end())); +} + +void insert_into_list(list& lst, int n) { + random_device rd; + mt19937 gen(rd()); + uniform_int_distribution<> dist(1, n); + + for (int i = 0; i < n; ++i) { + int rand_num = dist(gen); + auto pos = lower_bound(lst.begin(), lst.end(), rand_num); + lst.insert(pos, rand_num); + } + assert(is_sorted(lst.begin(), lst.end())); +} + +// -------------- Task F -------------- + +int single_goldbach(int k) { + const vector primes = get_primes(k); + int count = 0; + + for (size_t i = 0; i < primes.size(); i++) { + for (size_t j = i; j < primes.size(); j++) { + if (primes[i] + primes[j] == k) { + count++; + } + } + } + + return count; +} + +vector count_goldbach(int n) { + const vector primes = get_primes(n); + vector counts(n+1); + + for (size_t i = 1; i < primes.size(); i++) { + for (size_t j = i; j < primes.size(); j++) { + int sum = primes[i] + primes[j]; + if (sum <= n) { + counts[sum]++; + } + } + } + + return counts; +} + + +void print_decomps(int k) { + const vector primes = get_primes(k); + cout << "\nDecompositions for k = " << k << ": "; + + for (size_t i = 0; i < primes.size(); i++) { + for (size_t j = i; j < primes.size(); j++) { + if (primes[i] + primes[j] == k) { + cout << primes[i] << " + " << primes[j] << ", "; + } + } + } + cout << endl; +} + +// -------------- Task G -------------- + + +double sigmoid(double x) +{ + return 1.0 / (1.0 + std::exp(-x)); +} + +double DenseMatrix::sigmoid(double x) +{ + return 1.0 / (1.0 + exp(-x)); +} + +DenseMatrix::DenseMatrix(int n, int m) : rows(n), cols(m), matrix(n*m) +{ + int nm = max(n, m); + for (size_t i = 0; i < rows; i++) + { + for (size_t j = 0; j < cols; j++) + { + double x_i = 10.0*i/(nm-1) - 5.0; + double x_j = 10.0*j/(nm-1) - 5.0; + matrix[i*cols + j] = sigmoid(x_i) * sigmoid(x_j); + } + } +} + +vector DenseMatrix::Mult(const vector& vec) const +{ + assert(vec.size() == cols); + vector result(rows, 0.0); + + for (size_t i = 0; i < rows; ++i) + { + for (size_t j = 0; j < cols; ++j) + { + result[i] += matrix[i*cols + j] * vec[j]; + } + } + return result; +} + +vector DenseMatrix::MultT(const vector& vec) const +{ + assert(vec.size() == rows); + vector result(cols, 0.0); + + for (size_t i = 0; i < cols; ++i) + { + for (size_t j = 0; j < rows; ++j) + { + result[i] += matrix[j*cols + i] * vec[j]; + } + } + return result; +} + +void DenseMatrix::print() const { + int count(0); + cout.precision(5); + for (double val : matrix) { + printf("%.6f ", val); + + count++; + if(count%cols == 0){cout << endl;} + } +} + +// ################################################# + +DenseMatrix2::DenseMatrix2(vector const u, vector const v) : rows(u.size()), cols(v.size()), u_(u), v_(v) {} + +vector DenseMatrix2::Mult(const vector& vec) const +{ + assert(vec.size() == cols); + vector result(rows, 0.0); + + double scalar(0.0); + for (size_t i = 0; i < vec.size(); i++) + { + scalar += v_[i] * vec[i]; + } + for (size_t i = 0; i < u_.size(); i++) + { + result[i] = scalar*u_[i]; + } + + return result; +} + +vector DenseMatrix2::MultT(const vector& vec) const +{ + assert(vec.size() == rows); + vector result(cols, 0.0); + + double scalar(0.0); + for (size_t i = 0; i < u_.size(); i++) + { + scalar += u_[i] * vec[i]; + } + for (size_t i = 0; i < v_.size(); i++) + { + result[i] = scalar*v_[i]; + } + + return result; +} \ No newline at end of file diff --git a/ex1/ABCEFG/skalar_stl/mylib.h b/ex1/ABCEFG/skalar_stl/mylib.h new file mode 100644 index 0000000..554a1f5 --- /dev/null +++ b/ex1/ABCEFG/skalar_stl/mylib.h @@ -0,0 +1,112 @@ +#pragma once + +#include // assert +#include +#include +#include +#include +#include +#include +#include +#include +#include +using namespace std; + +// -------------- Task A -------------- + +// Returns arithmetic, geometric and harmonic mean for 3 values a,b,c. +tuple means0(double a, double b, double c); + +// Returns arithmetic, geometric and harmonic mean for a vector. +tuple means(const vector& v); + +// -------------- Task B -------------- + +/** + This function opens the ASCII-file named @p file_name and reads the + double data into the C++ vector @p v. + If the file @p file_name does not exist then the code stops with an appropriate message. + @param[in] file_name name of the ASCII-file + @param[out] v C++ vector with double values +*/ + +void read_vector_from_file(const string& file_name, vector& v); + + +/** + This function opens the ASCII-file named @p file_name and rewrites its with the + double data from the C++ vector @p v. + If there are problems in opening/generating file @p file_name + then the code stops with an appropriate message. + @param[in] file_name name of the ASCII-file + @param[in] v C++ vector with double values +*/ + +void write_vector_to_file(const string& file_name, const vector& v); + +/** + Fills the double-vector @p v with data from an input stream @p istr until this input stream + ends regularily. The vector is cleared and its memory is automatically allocated. + @param[in] istr input stream + @param[out] v C++ vector with double values + @warning An exception is thrown in case of wrong data format or corrupted data. +*/ +void fill_vector(istream& istr, vector& v); + +// -------------- Task C -------------- + +// Sums up all positive integers less or equal n which are multiples of 3 or of 5 (including or!) by brute force. +double sum_of_spec(int n); + +// Sums up all positive integers less or equal n which are multiples of 3 or of 5 (including or!) by inclusion-exclusion principle. +double formula(int n); + +// -------------- Task E -------------- + +// Inserts n random numbers into sorted vector v such that v remains sorted. +void insert_into_vector(vector& vec, int n); + +// Inserts n random numbers into sorted list such that the list remains sorted. +void insert_into_list(list& lst, int n); + + +// -------------- Task F -------------- + +// Counts number of possible decompositions with 2 primes that sum up to k. +int single_goldbach(int k); + +// Counts number of possible decompositions with 2 primes that sum up to k for all even numbers k \in {4,...,n}. +vector count_goldbach(int n); + +// Prints all decompositions of k. +void print_decomps(int k); + +// -------------- Task G -------------- + +// Sigmoid function 1/(1+exp(-x)) +double sigmoid(double x); + +class DenseMatrix { +private: + double sigmoid(double x); + size_t rows; + size_t cols; + vector matrix; +public: + DenseMatrix(int n, int m); // Constructor + vector Mult(const vector& vec) const; + vector MultT(const vector& vec) const; + void print() const; +}; + +class DenseMatrix2 { +private: + size_t rows; + size_t cols; + vector u_; + vector v_; +public: + DenseMatrix2(vector const u, vector const v); // Constructor + vector Mult(const vector& vec) const; + vector MultT(const vector& vec) const; +}; \ No newline at end of file diff --git a/ex1/ABCEFG/skalar_stl/mylib.o b/ex1/ABCEFG/skalar_stl/mylib.o new file mode 100644 index 0000000..6dfc4c1 Binary files /dev/null and b/ex1/ABCEFG/skalar_stl/mylib.o differ diff --git a/ex1/ABCEFG/skalar_stl/out_1.txt b/ex1/ABCEFG/skalar_stl/out_1.txt new file mode 100644 index 0000000..fc78d82 --- /dev/null +++ b/ex1/ABCEFG/skalar_stl/out_1.txt @@ -0,0 +1,6 @@ +1 +1000 +498.184 +inf +95.6857 +287.905 diff --git a/ex1/ABCEFG/skalar_stl/timing.h b/ex1/ABCEFG/skalar_stl/timing.h new file mode 100644 index 0000000..7e52921 --- /dev/null +++ b/ex1/ABCEFG/skalar_stl/timing.h @@ -0,0 +1,51 @@ +// +// Gundolf Haase, Oct 18 2024 +// +#pragma once +#include // timing +#include + +//using Clock = std::chrono::system_clock; //!< The wall clock timer chosen +using Clock = std::chrono::high_resolution_clock; +using TPoint= std::chrono::time_point; + +// [Galowicz, C++17 STL Cookbook, p. 29] +inline +std::stack MyStopWatch; //!< starting time of stopwatch + +/** Starts stopwatch timer. + * Use as @code tic(); myfunction(...) ; double tsec = toc(); @endcode + * + * The timining can be nested and the recent time point is stored on top of the stack. + * + * @return recent time point + * @see toc + */ +inline auto tic() +{ + MyStopWatch.push(Clock::now()); + return MyStopWatch.top(); +} + +/** Returns the elapsed time from stopwatch. + * + * The time point from top of the stack is used + * if time point @p t_b is not passed as input parameter. + * Use as @code tic(); myfunction(...) ; double tsec = toc(); @endcode + * or as @code auto t_b = tic(); myfunction(...) ; double tsec = toc(t_b); @endcode + * The last option is to be used in the case of + * non-nested but overlapping time measurements. + * + * @param[in] t_b start time of some stop watch + * @return elapsed time in seconds. + * +*/ +inline double toc(TPoint const &t_b = MyStopWatch.top()) +{ + // https://en.cppreference.com/w/cpp/chrono/treat_as_floating_point + using Unit = std::chrono::seconds; + using FpSeconds = std::chrono::duration; + auto t_e = Clock::now(); + MyStopWatch.pop(); + return FpSeconds(t_e-t_b).count(); +} diff --git a/ex1/D/.vscode/settings.json b/ex1/D/.vscode/settings.json new file mode 100644 index 0000000..c661792 --- /dev/null +++ b/ex1/D/.vscode/settings.json @@ -0,0 +1,60 @@ +{ + "files.associations": { + "array": "cpp", + "atomic": "cpp", + "bit": "cpp", + "cctype": "cpp", + "charconv": "cpp", + "chrono": "cpp", + "clocale": "cpp", + "cmath": "cpp", + "compare": "cpp", + "complex": "cpp", + "concepts": "cpp", + "cstdarg": "cpp", + "cstddef": "cpp", + "cstdint": "cpp", + "cstdio": "cpp", + "cstdlib": "cpp", + "cstring": "cpp", + "ctime": "cpp", + "cwchar": "cpp", + "cwctype": "cpp", + "deque": "cpp", + "string": "cpp", + "unordered_map": "cpp", + "vector": "cpp", + "exception": "cpp", + "algorithm": "cpp", + "functional": "cpp", + "iterator": "cpp", + "memory": "cpp", + "memory_resource": "cpp", + "numeric": "cpp", + "optional": "cpp", + "random": "cpp", + "ratio": "cpp", + "string_view": "cpp", + "system_error": "cpp", + "tuple": "cpp", + "type_traits": "cpp", + "utility": "cpp", + "format": "cpp", + "initializer_list": "cpp", + "iomanip": "cpp", + "iosfwd": "cpp", + "iostream": "cpp", + "istream": "cpp", + "limits": "cpp", + "new": "cpp", + "numbers": "cpp", + "ostream": "cpp", + "span": "cpp", + "sstream": "cpp", + "stdexcept": "cpp", + "streambuf": "cpp", + "cinttypes": "cpp", + "typeinfo": "cpp", + "variant": "cpp" + } +} \ No newline at end of file diff --git a/ex1/D/CLANG_default.mk b/ex1/D/CLANG_default.mk new file mode 100644 index 0000000..4bc290d --- /dev/null +++ b/ex1/D/CLANG_default.mk @@ -0,0 +1,123 @@ +# Basic Defintions for using GNU-compiler suite sequentially +# requires setting of COMPILER=CLANG_ + +#CLANGPATH=//usr/lib/llvm-10/bin/ +CC = ${CLANGPATH}clang +CXX = ${CLANGPATH}clang++ +#CXX = ${CLANGPATH}clang++ -lomptarget -fopenmp-targets=nvptx64-nvidia-cuda --cuda-path=/opt/pgi/linux86-64/2017/cuda/8.0 +#F77 = gfortran +LINKER = ${CXX} + +#http://clang.llvm.org/docs/UsersManual.html#options-to-control-error-and-warning-messages +WARNINGS += -Weverything -Wno-c++98-compat -Wno-sign-conversion -Wno-date-time -Wno-shorten-64-to-32 -Wno-padded -ferror-limit=1 +WARNINGS += -Wdocumentation -Wconversion -Wshadow -Wfloat-conversion -pedantic +#-fsyntax-only -Wdocumentation -Wconversion -Wshadow -Wfloat-conversion -pedantic + +CXXFLAGS += -O3 -std=c++17 -ferror-limit=1 ${WARNINGS} +# don't use -Ofast +# -ftrapv +LINKFLAGS += -O3 + +# different libraries in Ubuntu or manajaró +ifndef UBUNTU +UBUNTU=1 +endif + +# BLAS, LAPACK +LINKFLAGS += -llapack -lblas +# -lopenblas +ifeq ($(UBUNTU),1) +# ubuntu +else +# on archlinux +LINKFLAGS += -lcblas +endif + +# interprocedural optimization +CXXFLAGS += -flto +LINKFLAGS += -flto + +# very good check +# http://clang.llvm.org/extra/clang-tidy/ +# good check, see: http://llvm.org/docs/CodingStandards.html#include-style +SWITCH_OFF=,-readability-magic-numbers,-readability-redundant-control-flow,-readability-redundant-member-init +SWITCH_OFF+=,-readability-redundant-member-init,-readability-isolate-declaration +#READABILITY=,readability*${SWITCH_OFF} +#TIDYFLAGS = -checks=llvm-*,-llvm-header-guard -header-filter=.* -enable-check-profile -extra-arg="-std=c++17" -extra-arg="-fopenmp" +TIDYFLAGS = -checks=llvm-*,-llvm-header-guard${READABILITY} -header-filter=.* -enable-check-profile -extra-arg="-std=c++17" -extra-arg="-fopenmp" +#TIDYFLAGS += -checks='modernize* +# ??? +#TIDYFLAGS = -checks='cert*' -header-filter=.* +# MPI checks ?? +#TIDYFLAGS = -checks='mpi*' +# ?? +#TIDYFLAGS = -checks='performance*' -header-filter=.* +#TIDYFLAGS = -checks='portability-*' -header-filter=.* +#TIDYFLAGS = -checks='readability-*' -header-filter=.* + +default: ${PROGRAM} + +${PROGRAM}: ${OBJECTS} + $(LINKER) $^ ${LINKFLAGS} -o $@ + +clean: + @rm -f ${PROGRAM} ${OBJECTS} + +clean_all:: clean + @rm -f *_ *~ *.bak *.log *.out *.tar + +codecheck: tidy_check +tidy_check: + clang-tidy ${SOURCES} ${TIDYFLAGS} -- ${SOURCES} +# see also http://clang-developers.42468.n3.nabble.com/Error-while-trying-to-load-a-compilation-database-td4049722.html + +run: clean ${PROGRAM} +# time ./${PROGRAM} ${PARAMS} + ./${PROGRAM} ${PARAMS} + +# tar the current directory +MY_DIR = `basename ${PWD}` +tar: clean_all + @echo "Tar the directory: " ${MY_DIR} + @cd .. ;\ + tar cf ${MY_DIR}.tar ${MY_DIR} *default.mk ;\ + cd ${MY_DIR} +# tar cf `basename ${PWD}`.tar * + +doc: + doxygen Doxyfile + +######################################################################### + +.cpp.o: + $(CXX) -c $(CXXFLAGS) -o $@ $< + +.c.o: + $(CC) -c $(CFLAGS) -o $@ $< + +.f.o: + $(F77) -c $(FFLAGS) -o $@ $< + +################################################################################################## +# some tools +# Cache behaviour (CXXFLAGS += -g tracks down to source lines; no -pg in linkflags) +cache: ${PROGRAM} + valgrind --tool=callgrind --simulate-cache=yes ./$^ ${PARAMS} +# kcachegrind callgrind.out. & + kcachegrind `ls -1tr callgrind.out.* |tail -1` + +# Check for wrong memory accesses, memory leaks, ... +# use smaller data sets +mem: ${PROGRAM} + valgrind -v --leak-check=yes --tool=memcheck --undef-value-errors=yes --track-origins=yes --log-file=$^.addr.out --show-reachable=yes ./$^ ${PARAMS} + +# Simple run time profiling of your code +# CXXFLAGS += -g -pg +# LINKFLAGS += -pg +prof: ${PROGRAM} + perf record ./$^ ${PARAMS} + perf report +# gprof -b ./$^ > gp.out +# kprof -f gp.out -p gprof & + +codecheck: tidy_check diff --git a/ex1/D/GCC_AMD32_default.mk b/ex1/D/GCC_AMD32_default.mk new file mode 100644 index 0000000..a911b6b --- /dev/null +++ b/ex1/D/GCC_AMD32_default.mk @@ -0,0 +1,130 @@ +# Basic Defintions for using GNU-compiler suite sequentially +# requires setting of COMPILER=GCC_ + +CC = gcc +CXX = g++ +F77 = gfortran +LINKER = ${CXX} + +# on mephisto: +#CXXFLAGS += -I/share/apps/atlas/include +#LINKFLAGS += -L/share/apps/atlas/lib +#LINKFLAGS += -lcblas -latlas + +#LINKFLAGS += -lblas +# Der Header muss mit extern "C" versehen werden, damit g++ alles findet. + + +#WARNINGS = -pedantic -pedantic-errors -Wall -Wextra -Werror -Wconversion -Weffc++ -Woverloaded-virtual -Wfloat-equal -Wshadow +WARNINGS = -pedantic -Wall -Wextra -Wconversion -Weffc++ -Woverloaded-virtual -Wfloat-equal -Wshadow \ + -Wredundant-decls -Winline -fmax-errors=1 +# -Wunreachable-code +# -Wunreachable-code +CXXFLAGS += -ffast-math -O3 -march=native -std=c++17 ${WARNINGS} +#CXXFLAGS += -Ofast -funroll-all-loops -std=c++17 ${WARNINGS} +#-msse3 +# -ftree-vectorizer-verbose=2 -DNDEBUG +# -ftree-vectorizer-verbose=5 +# -ftree-vectorize -fdump-tree-vect-blocks=foo.dump -fdump-tree-pre=stderr + +# CFLAGS = -ffast-math -O3 -DNDEBUG -msse3 -fopenmp -fdump-tree-vect-details +# CFLAGS = -ffast-math -O3 -funroll-loops -DNDEBUG -msse3 -fopenmp -ftree-vectorizer-verbose=2 +# #CFLAGS = -ffast-math -O3 -DNDEBUG -msse3 -fopenmp +# FFLAGS = -ffast-math -O3 -DNDEBUG -msse3 -fopenmp +# LFLAGS = -ffast-math -O3 -DNDEBUG -msse3 -fopenmp +LINKFLAGS += -O3 + +# BLAS, LAPACK +OPENBLAS_DIR = /opt/openblas_GCCseq +#OPENBLAS_DIR = /opt/openblas_GCC +OPENBLAS_LIBDIR = ${OPENBLAS_DIR}/lib +OPENBLAS_INCDIR = ${OPENBLAS_DIR}/include +CXXFLAGS += -I${OPENBLAS_INCDIR} +LINKFLAGS += -L${OPENBLAS_LIBDIR} -lopenblas + +# interprocedural optimization +CXXFLAGS += -flto +LINKFLAGS += -flto + +# profiling tools +#CXXFLAGS += -pg +#LINKFLAGS += -pg + +default: ${PROGRAM} + +${PROGRAM}: ${OBJECTS} + $(LINKER) $^ ${LINKFLAGS} -o $@ + +clean: + @rm -f ${PROGRAM} ${OBJECTS} + +clean_all:: clean + -@rm -f *_ *~ *.bak *.log *.out *.tar *.orig + -@rm -r html + +run: clean ${PROGRAM} +# time ./${PROGRAM} +# ./${PROGRAM} + ( export LD_LIBRARY_PATH=${OPENBLAS_LIBDIR}:${LD_LIBRARY_PATH} ; ./${PROGRAM} ) +# or 'export LD_LIBRARY_PATH=/opt/openblas_gcc/lib:${LD_LIBRARY_PATH}' in your ~/.bashrc + +# tar the current directory +MY_DIR = `basename ${PWD}` +tar: + @echo "Tar the directory: " ${MY_DIR} + @cd .. ;\ + tar cf ${MY_DIR}.tar ${MY_DIR} *default.mk ;\ + cd ${MY_DIR} +# tar cf `basename ${PWD}`.tar * + +doc: + doxygen Doxyfile + +######################################################################### + +.cpp.o: + $(CXX) -c $(CXXFLAGS) -o $@ $< + +.c.o: + $(CC) -c $(CFLAGS) -o $@ $< + +.f.o: + $(F77) -c $(FFLAGS) -o $@ $< + +################################################################################################## +# some tools +# Cache behaviour (CXXFLAGS += -g tracks down to source lines; no -pg in linkflags) +cache: ${PROGRAM} + valgrind --tool=callgrind --simulate-cache=yes ./$^ +# kcachegrind callgrind.out. & + kcachegrind `ls -1tr callgrind.out.* |tail -1` + +# Check for wrong memory accesses, memory leaks, ... +# use smaller data sets +# no "-pg" in compile/link options +mem: ${PROGRAM} + valgrind -v --leak-check=yes --tool=memcheck --undef-value-errors=yes --track-origins=yes --log-file=$^.addr.out --show-reachable=yes ./$^ + +# Simple run time profiling of your code +# CXXFLAGS += -g -pg +# LINKFLAGS += -pg +prof: ${PROGRAM} + ./$^ + gprof -b ./$^ > gp.out +# kprof -f gp.out -p gprof & + +#Trace your heap: +#> heaptrack ./main.GCC_ +#> heaptrack_gui heaptrack.main.GCC_..gz +heap: ${PROGRAM} + heaptrack ./$^ 11 + heaptrack_gui `ls -1tr heaptrack.$^.* |tail -1` & + + + +######################################################################## +# get the detailed status of all optimization flags +info: + echo "detailed status of all optimization flags" + $(CXX) --version + $(CXX) -Q $(CXXFLAGS) --help=optimizers diff --git a/ex1/D/GCC_default.mk b/ex1/D/GCC_default.mk new file mode 100644 index 0000000..b730641 --- /dev/null +++ b/ex1/D/GCC_default.mk @@ -0,0 +1,183 @@ +# Basic Defintions for using GNU-compiler suite sequentially +# requires setting of COMPILER=GCC_ + +CC = gcc +CXX = g++ +F77 = gfortran +LINKER = ${CXX} + +WARNINGS = -Wall -pedantic -Wextra -Weffc++ -Woverloaded-virtual -Wfloat-equal -Wshadow \ + -Wredundant-decls -Winline -fmax-errors=1 +# -Wunreachable-code +CXXFLAGS += -ffast-math -O1 -march=native -std=c++17 ${WARNINGS} +#CXXFLAGS += -Ofast -funroll-all-loops -std=c++17 ${WARNINGS} +#-msse3 +# -ftree-vectorizer-verbose=2 -DNDEBUG +# -ftree-vectorizer-verbose=5 +# -ftree-vectorize -fdump-tree-vect-blocks=foo.dump -fdump-tree-pre=stderr + +# CFLAGS = -ffast-math -O3 -DNDEBUG -msse3 -fopenmp -fdump-tree-vect-details +# CFLAGS = -ffast-math -O3 -funroll-loops -DNDEBUG -msse3 -fopenmp -ftree-vectorizer-verbose=2 +# #CFLAGS = -ffast-math -O3 -DNDEBUG -msse3 -fopenmp +# FFLAGS = -ffast-math -O3 -DNDEBUG -msse3 -fopenmp +# LFLAGS = -ffast-math -O3 -DNDEBUG -msse3 -fopenmp +LINKFLAGS += -O1 + +#architecture +#CPU = -march=znver2 +CXXFLAGS += ${CPU} +LINKFLAGS += ${CPU} + +# different libraries in Ubuntu or manajaró +ifndef UBUNTU +UBUNTU=1 +endif + +# BLAS, LAPACK +ifeq ($(UBUNTU),1) +LINKFLAGS += -llapack -lblas +# -lopenblas +else +# on archlinux +LINKFLAGS += -llapack -lopenblas -lcblas +endif + +# interprocedural optimization +CXXFLAGS += -flto +LINKFLAGS += -flto + +# for debugging purpose (save code) +# -fsanitize=leak # only one out the three can be used +# -fsanitize=address +# -fsanitize=thread +SANITARY = -fsanitize=address -fsanitize=undefined -fsanitize=null -fsanitize=return \ + -fsanitize=bounds -fsanitize=alignment -fsanitize=float-divide-by-zero -fsanitize=float-cast-overflow \ + -fsanitize=bool -fsanitize=enum -fsanitize=vptr +#CXXFLAGS += ${SANITARY} +#LINKFLAGS += ${SANITARY} + +# profiling tools +#CXXFLAGS += -pg +#LINKFLAGS += -pg + + +default: ${PROGRAM} + +${PROGRAM}: ${OBJECTS} + $(LINKER) $^ ${LINKFLAGS} -o $@ + +clean: + @rm -f ${PROGRAM} ${OBJECTS} + +clean_all:: clean + -@rm -f *_ *~ *.bak *.log *.out *.tar *.orig *.optrpt + -@rm -rf html + +run: clean ${PROGRAM} +#run: ${PROGRAM} +# time ./${PROGRAM} ${PARAMS} + ./${PROGRAM} ${PARAMS} + +# tar the current directory +MY_DIR = `basename ${PWD}` +tar: clean_all + @echo "Tar the directory: " ${MY_DIR} + @cd .. ;\ + tar cf ${MY_DIR}.tar ${MY_DIR} *default.mk ;\ + cd ${MY_DIR} +# tar cf `basename ${PWD}`.tar * +#find . -size +10M > large_files +#--exclude-from ${MY_DIR}/large_files + +zip: clean + @echo "Zip the directory: " ${MY_DIR} + @cd .. ;\ + zip -r ${MY_DIR}.zip ${MY_DIR} *default.mk ;\ + cd ${MY_DIR} + +doc: + doxygen Doxyfile + +######################################################################### +.SUFFIXES: .f90 + +.cpp.o: + $(CXX) -c $(CXXFLAGS) -o $@ $< +# $(CXX) -c $(CXXFLAGS) -o $@ $< 2>&1 | tee -a $<.log +# $(CXX) -c $(CXXFLAGS) -o $@ $< 2>&1 | tee -a $(<:.cpp=.log) + +.c.o: + $(CC) -c $(CFLAGS) -o $@ $< + +.f.o: + $(F77) -c $(FFLAGS) -o $@ $< + +.f90.o: + $(F77) -c $(FFLAGS) -o $@ $< + +################################################################################################## +# some tools +# Cache behaviour (CXXFLAGS += -g tracks down to source lines; no -pg in linkflags) +cache: ${PROGRAM} + valgrind --tool=callgrind --simulate-cache=yes ./$^ ${PARAMS} +# kcachegrind callgrind.out. & + kcachegrind `ls -1tr callgrind.out.* |tail -1` + +# Check for wrong memory accesses, memory leaks, ... +# use smaller data sets +# no "-pg" in compile/link options +mem: ${PROGRAM} + valgrind -v --leak-check=yes --tool=memcheck --undef-value-errors=yes --track-origins=yes --log-file=$^.addr.out --show-reachable=yes ./$^ ${PARAMS} +# Graphical interface +# valkyrie + +# Simple run time profiling of your code +# CXXFLAGS += -g -pg +# LINKFLAGS += -pg +prof: ${PROGRAM} + perf record ./$^ ${PARAMS} + perf report +# gprof -b ./$^ > gp.out +# kprof -f gp.out -p gprof & + +# perf in Ubuntu 20.04: https://www.howtoforge.com/how-to-install-perf-performance-analysis-tool-on-ubuntu-20-04/ +# * install +# * sudo vi /etc/sysctl.conf +# add kernel.perf_event_paranoid = 0 + +#Trace your heap: +#> heaptrack ./main.GCC_ +#> heaptrack_gui heaptrack.main.GCC_..gz +heap: ${PROGRAM} + heaptrack ./$^ ${PARAMS} + heaptrack_gui `ls -1tr heaptrack.$^.* |tail -1` & + +codecheck: $(SOURCES) + cppcheck --enable=all --inconclusive --std=c++17 --suppress=missingIncludeSystem $^ + + +######################################################################## +# get the detailed status of all optimization flags +info: + echo "detailed status of all optimization flags" + $(CXX) --version + $(CXX) -Q $(CXXFLAGS) --help=optimizers + lscpu + inxi -C + lstopo + +# Excellent hardware info +# hardinfo +# Life monitoring of CPU frequency etc. +# sudo i7z + +# Memory consumption +# vmstat -at -SM 3 +# xfce4-taskmanager + + +# https://www.tecmint.com/check-linux-cpu-information/ +#https://www.tecmint.com/monitor-cpu-and-gpu-temperature-in-ubuntu/ + +# Debugging: +# https://wiki.archlinux.org/index.php/Debugging diff --git a/ex1/D/ICC_default.mk b/ex1/D/ICC_default.mk new file mode 100644 index 0000000..d4bd4db --- /dev/null +++ b/ex1/D/ICC_default.mk @@ -0,0 +1,137 @@ +# Basic Defintions for using INTEL compiler suite sequentially +# requires setting of COMPILER=ICC_ + +#BINDIR = /opt/intel/bin/ + +# special on my sony [GH] +#BINDIR = /opt/save.intel/bin/ +# very special on my sony [GH] +# FIND_LIBS = -L /opt/save.intel/composer_xe_2013.1.117/mkl/lib/intel64/libmkl_intel_lp64.so + +# Error with g++-4.8 using icpc14.0,x: +# find directory wherein bits/c++config.h is located +# 'locate bits/c++config.h' +#FOUND_CONFIG = -I/usr/include/x86_64-linux-gnu/c++/4.8 + + +CC = ${BINDIR}icc +CXX = ${BINDIR}icpc +F77 = ${BINDIR}ifort +LINKER = ${CXX} + + +WARNINGS = -Wall -Weffc++ -Woverloaded-virtual -Wfloat-equal -Wshadow -wd2015,2012 -wn3 +# -Winline -Wredundant-decls -Wunreachable-code +CXXFLAGS += -O3 -fargument-noalias -std=c++17 -DNDEBUG ${WARNINGS} -mkl ${FOUND_CONFIG} +# profiling tools +#CXXFLAGS += -pg +#LINKFLAGS += -pg +# -vec-report=3 +# -qopt-report=5 -qopt-report-phase=vec +# -guide -parallel +# -guide-opts=string -guide-par[=n] -guide-vec[=n] +# -auto-p32 -simd +CXXFLAGS += -align + +# use MKL by INTEL +# https://software.intel.com/content/www/us/en/develop/documentation/mkl-linux-developer-guide/top/linking-your-application-with-the-intel-math-kernel-library/linking-quick-start/using-the-mkl-compiler-option.html +# https://software.intel.com/content/www/us/en/develop/articles/intel-mkl-link-line-advisor.html +# LINKFLAGS += -L${BINDIR}../composer_xe_2013.1.117/mkl/lib/intel64 -lmkl_intel_lp64 -lmkl_sequential -lmkl_core -lpthread +#LINKFLAGS += -O3 -L/opt/intel/mkl/lib -mkl +LINKFLAGS += -O3 -mkl=sequential + +# interprocedural optimization +CXXFLAGS += -ipo +LINKFLAGS += -ipo + +# annotated assembler file +ANNOTED = -fsource-asm -S + +default: ${PROGRAM} + +${PROGRAM}: ${OBJECTS} + $(LINKER) $^ ${LINKFLAGS} -o $@ + +clean: + rm -f ${PROGRAM} ${OBJECTS} + +clean_all:: clean + @rm -f *_ *~ *.bak *.log *.out *.tar + +run: clean ${PROGRAM} + ./${PROGRAM} + +# tar the current directory +MY_DIR = `basename ${PWD}` +tar: clean_all + @echo "Tar the directory: " ${MY_DIR} + @cd .. ;\ + tar cf ${MY_DIR}.tar ${MY_DIR} *default.mk ;\ + cd ${MY_DIR} +# tar cf `basename ${PWD}`.tar * + +doc: + doxygen Doxyfile + +######################################################################### + +.cpp.o: + $(CXX) -c $(CXXFLAGS) -o $@ $< + +.c.o: + $(CC) -c $(CFLAGS) -o $@ $< + +.f.o: + $(F77) -c $(FFLAGS) -o $@ $< + +################################################################################################## +# # some tools +# # Cache behaviour (CXXFLAGS += -g tracks down to source lines) +# cache: ${PROGRAM} +# valgrind --tool=callgrind --simulate-cache=yes ./$^ +# # kcachegrind callgrind.out. & +# +# # Check for wrong memory accesses, memory leaks, ... +# # use smaller data sets +# mem: ${PROGRAM} +# valgrind -v --leak-check=yes --tool=memcheck --undef-value-errors=yes --track-origins=yes --log-file=$^.addr.out --show-reachable=yes ./$^ +# +# # Simple run time profiling of your code +# # CXXFLAGS += -g -pg +# # LINKFLAGS += -pg +# prof: ${PROGRAM} +# ./$^ +# gprof -b ./$^ > gp.out +# # kprof -f gp.out -p gprof & +# + + +mem: inspector +prof: amplifier +cache: amplifier + +gap_par_report: + ${CXX} -c -guide -parallel $(SOURCES) 2> gap.txt + +# GUI for performance report +amplifier: ${PROGRAM} + echo 0 | sudo tee /proc/sys/kernel/yama/ptrace_scope +# alternatively to the solution above: + #edit file /etc/sysctl.d/10-ptrace.conf and set variable kernel.yama.ptrace_scope variable to 0 . + amplxe-gui & + +# GUI for Memory and Thread analyzer (race condition) +inspector: ${PROGRAM} + echo 0 | sudo tee /proc/sys/kernel/yama/ptrace_scope + inspxe-gui & + +advisor: + echo 0 | sudo tee /proc/sys/kernel/yama/ptrace_scope + advixe-gui & + +icc-info: + icpc -# main.cpp + + + + diff --git a/ex1/D/ONEAPI_default.mk b/ex1/D/ONEAPI_default.mk new file mode 100644 index 0000000..fe7b3fe --- /dev/null +++ b/ex1/D/ONEAPI_default.mk @@ -0,0 +1,176 @@ +# Basic Defintions for using INTEL compiler suite sequentially +# requires setting of COMPILER=ONEAPI_ + +# https://software.intel.com/content/www/us/en/develop/tools/oneapi/components/onemkl/link-line-advisor.html +# requires +# source /opt/intel/oneapi/setvars.sh +# on AMD: export MKL_DEBUG_CPU_TYPE=5 + +#BINDIR = /opt/intel/oneapi/compiler/latest/linux/bin/ +#MKL_ROOT = /opt/intel/oneapi/mkl/latest/ +#export KMP_AFFINITY=verbose,compact + +CC = ${BINDIR}icc +CXX = ${BINDIR}dpcpp +F77 = ${BINDIR}ifort +LINKER = ${CXX} + +## Compiler flags +WARNINGS = -Wall -Weffc++ -Woverloaded-virtual -Wfloat-equal -Wshadow -pedantic +WARNINGS += -Wpessimizing-move -Wredundant-move +#-wd2015,2012,2014 -wn3 +# -Winline -Wredundant-decls -Wunreachable-code +# -qopt-subscript-in-range +# -vec-threshold0 + +CXXFLAGS += -O3 -std=c++17 ${WARNINGS} +#CXXFLAGS += -DMKL_ILP64 -I"${MKLROOT}/include" +#CXXFLAGS += -DMKL_ILP32 -I"${MKLROOT}/include" +LINKFLAGS += -O3 + +# interprocedural optimization +CXXFLAGS += -ipo +LINKFLAGS += -ipo +LINKFLAGS += -flto + +# annotated Assembler file +ANNOTED = -fsource-asm -S + +#architecture +CPU = -march=core-avx2 +#CPU += -mtp=zen +# -xCORE-AVX2 +# -axcode COMMON-AVX512 -axcode MIC-AVX512 -axcode CORE-AVX512 -axcode CORE-AVX2 +CXXFLAGS += ${CPU} +LINKFLAGS += ${CPU} + +# use MKL by INTEL +# https://software.intel.com/content/www/us/en/develop/tools/oneapi/components/onemkl/link-line-advisor.html +# sequential MKL +# use the 32 bit interface (LP64) instead of 64 bit interface (ILP64) +CXXFLAGS += -qmkl=sequential -UMKL_ILP64 +LINKFLAGS += -O3 -qmkl=sequential -lmkl_intel_lp64 -lmkl_sequential -lmkl_core -lpthread +#LINKFLAGS += -O3 -lmkl_intel_lp64 -lmkl_sequential -lmkl_core -lpthread + +# shared libs: https://aur.archlinux.org/packages/intel-oneapi-compiler-static +# install intel-oneapi-compiler-static +# or +LINKFLAGS += -shared-intel + + +OPENMP = -qopenmp +CXXFLAGS += ${OPENMP} +LINKFLAGS += ${OPENMP} + + +# profiling tools +#CXXFLAGS += -pg +#LINKFLAGS += -pg +# -vec-report=3 +# -qopt-report=5 -qopt-report-phase=vec -qopt-report-phase=openmp +# -guide -parallel +# -guide-opts=string -guide-par[=n] -guide-vec[=n] +# -auto-p32 -simd + +# Reports: https://software.intel.com/en-us/articles/getting-the-most-out-of-your-intel-compiler-with-the-new-optimization-reports +#CXXFLAGS += -qopt-report=5 -qopt-report-phase=vec,par +#CXXFLAGS += -qopt-report=5 -qopt-report-phase=cg +# Redirect report from *.optrpt to stderr +# -qopt-report-file=stderr +# Guided paralellization +# -guide -parallel +# -guide-opts=string -guide-par[=n] -guide-vec[=n] +# -auto-p32 -simd + +## run time checks +# https://www.intel.com/content/www/us/en/develop/documentation/fortran-compiler-oneapi-dev-guide-and-reference/top/compiler-reference/compiler-options/offload-openmp-and-parallel-processing-options/par-runtime-control-qpar-runtime-control.html + + +default: ${PROGRAM} + +${PROGRAM}: ${OBJECTS} + $(LINKER) $^ ${LINKFLAGS} -o $@ + +clean: + rm -f ${PROGRAM} ${OBJECTS} *.optrpt + +clean_all:: clean + @rm -f *_ *~ *.bak *.log *.out *.tar + +run: clean ${PROGRAM} + ./${PROGRAM} + +# tar the current directory +MY_DIR = `basename ${PWD}` +tar: clean_all + @echo "Tar the directory: " ${MY_DIR} + @cd .. ;\ + tar cf ${MY_DIR}.tar ${MY_DIR} *default.mk ;\ + cd ${MY_DIR} +# tar cf `basename ${PWD}`.tar * + +doc: + doxygen Doxyfile + +######################################################################### + +.cpp.o: + $(CXX) -c $(CXXFLAGS) -o $@ $< + +.c.o: + $(CC) -c $(CFLAGS) -o $@ $< + +.f.o: + $(F77) -c $(FFLAGS) -o $@ $< + +################################################################################################## +# some tools +# Cache behaviour (CXXFLAGS += -g tracks down to source lines) +# https://software.intel.com/content/www/us/en/develop/documentation/vtune-help/top/analyze-performance/microarchitecture-analysis-group/memory-access-analysis.html + +mem: inspector +prof: vtune +cache: inspector + +gap_par_report: + ${CXX} -c -guide -parallel $(SOURCES) 2> gap.txt + +# GUI for performance report +amplifier: ${PROGRAM} + echo 0 | sudo tee /proc/sys/kernel/yama/ptrace_scope + echo 0 | sudo tee /proc/sys/kernel/perf_event_paranoid + amplxe-gui & + +# GUI for Memory and Thread analyzer (race condition) +inspector: ${PROGRAM} + echo 0 | sudo tee /proc/sys/kernel/yama/ptrace_scope +# inspxe-gui & + vtune-gui ./${PROGRAM} & + +advisor: + source /opt/intel/oneapi/advisor/2021.2.0/advixe-vars.sh +# /opt/intel/oneapi/advisor/latest/bin64/advixe-gui & + advisor --collect=survey ./${PROGRAM} +# advisor --collect=roofline ./${PROGRAM} + advisor --report=survey --project-dir=./ src:r=./ --format=csv --report-output=./out/survey.csv + +vtune: + echo 0 | sudo tee /proc/sys/kernel/yama/ptrace_scope +# https://software.intel.com/en-us/articles/intel-advisor-2017-update-1-what-s-new + export ADVIXE_EXPERIMENTAL=roofline + vtune -collect hotspots ./${PROGRAM} + vtune -report hotspots -r r000hs > vtune.out +# vtune-gui ./${PROGRAM} & + +icc-info: + icpc -# main.cpp + +# MKL on AMD +# https://www.computerbase.de/2019-11/mkl-workaround-erhoeht-leistung-auf-amd-ryzen/ +# +# https://sites.google.com/a/uci.edu/mingru-yang/programming/mkl-has-bad-performance-on-an-amd-cpu +# export MKL_DEBUG_CPU_TYPE=5 +# export MKL_NUM_THRAEDS=1 +# export MKL_DYNAMIC=false +# on Intel compiler +# http://publicclu2.blogspot.com/2013/05/intel-complier-suite-reference-card.html diff --git a/ex1/D/PGI_default.mk b/ex1/D/PGI_default.mk new file mode 100644 index 0000000..40760e5 --- /dev/null +++ b/ex1/D/PGI_default.mk @@ -0,0 +1,93 @@ +# Basic Defintions for using PGI-compiler suite sequentially +# requires setting of COMPILER=PGI_ +# OPTIRUN = optirun + + +CC = pgcc +CXX = pgc++ +F77 = pgfortran +LINKER = ${CXX} + +# on mephisto: +#CXXFLAGS += -I/share/apps/atlas/include +#LINKFLAGS += -L/share/apps/atlas/lib +#LINKFLAGS += -lcblas -latlas + +#LINKFLAGS += -lblas +# Der Header muss mit extern "C" versehen werden, damit g++ alles findet. + +WARNINGS = -Minform=warn +# -Wall -pedantic -Wextra -Weffc++ -Woverloaded-virtual -W -Wfloat-equal -Wshadow -Wredundant-decls +# -pedantic -Wunreachable-code -Wextra -Winline +# -Wunreachable-code + +#PGI_PROFILING = -Minfo=ccff,loop,vect,opt,intensity,mp,accel +PGI_PROFILING = -Minfo=ccff,accel,ipa,loop,lre,mp,opt,par,unified,vect,intensity +# -Minfo +# -Mprof=time +# -Mprof=lines +# take care with option -Msafeptr +CXXFLAGS += -O3 -std=c++17 ${WARNINGS} +#CXXFLAGS += -O3 -std=c++11 -DNDEBUG ${PGI_PROFILING} ${WARNINGS} +# -fastsse -fargument-noalias ${WARNINGS} -msse3 -vec-report=3 + +default: ${PROGRAM} + +${PROGRAM}: ${OBJECTS} + $(LINKER) $^ ${LINKFLAGS} -o $@ + +clean: + @rm -f ${PROGRAM} ${OBJECTS} + +clean_all:: clean + @rm -f *_ *~ *.bak *.log *.out *.tar + +run: clean ${PROGRAM} + ./${PROGRAM} + +# tar the current directory +MY_DIR = `basename ${PWD}` +tar: clean_all + @echo "Tar the directory: " ${MY_DIR} + @cd .. ;\ + tar cf ${MY_DIR}.tar ${MY_DIR} *default.mk ;\ + cd ${MY_DIR} +# tar cf `basename ${PWD}`.tar * + +doc: + doxygen Doxyfile + +######################################################################### + +.cpp.o: + $(CXX) -c $(CXXFLAGS) -o $@ $< + +.c.o: + $(CC) -c $(CFLAGS) -o $@ $< + +.f.o: + $(F77) -c $(FFLAGS) -o $@ $< + +################################################################################################## +# # some tools +# # Simple run time profiling of your code +# # CXXFLAGS += -g -pg +# # LINKFLAGS += -pg + + +# Profiling options PGI, see: pgcollect -help +# CPU_PROF = -allcache +CPU_PROF = -time +# GPU_PROF = -cuda=gmem,branch,cc13 -cudainit +#GPU_PROF = -cuda=branch:cc20 +# +PROF_FILE = pgprof.out + +cache: prof + +prof: ${PROGRAM} + ${OPTIRUN} ${BINDIR}pgcollect $(CPU_PROF) ./$^ + ${OPTIRUN} ${BINDIR}pgprof -exe ./$^ $(PROF_FILE) & + +info: + pgaccelinfo -v diff --git a/ex1/D/skalar_stl/Doxyfile b/ex1/D/skalar_stl/Doxyfile new file mode 100644 index 0000000..58d8e68 --- /dev/null +++ b/ex1/D/skalar_stl/Doxyfile @@ -0,0 +1,2563 @@ +# Doxyfile 1.8.20 + +# This file describes the settings to be used by the documentation system +# doxygen (www.doxygen.org) for a project. +# +# All text after a double hash (##) is considered a comment and is placed in +# front of the TAG it is preceding. +# +# All text after a single hash (#) is considered a comment and will be ignored. +# The format is: +# TAG = value [value, ...] +# For lists, items can also be appended using: +# TAG += value [value, ...] +# Values that contain spaces should be placed between quotes (\" \"). + +#--------------------------------------------------------------------------- +# Project related configuration options +#--------------------------------------------------------------------------- + +# This tag specifies the encoding used for all characters in the configuration +# file that follow. The default is UTF-8 which is also the encoding used for all +# text before the first occurrence of this tag. Doxygen uses libiconv (or the +# iconv built into libc) for the transcoding. See +# https://www.gnu.org/software/libiconv/ for the list of possible encodings. +# The default value is: UTF-8. + +DOXYFILE_ENCODING = UTF-8 + +# The PROJECT_NAME tag is a single word (or a sequence of words surrounded by +# double-quotes, unless you are using Doxywizard) that should identify the +# project for which the documentation is generated. This name is used in the +# title of most generated pages and in a few other places. +# The default value is: My Project. + +PROJECT_NAME = Skalar_seq_stl + +# The PROJECT_NUMBER tag can be used to enter a project or revision number. This +# could be handy for archiving the generated documentation or if some version +# control system is used. + +PROJECT_NUMBER = + +# Using the PROJECT_BRIEF tag one can provide an optional one line description +# for a project that appears at the top of each page and should give viewer a +# quick idea about the purpose of the project. Keep the description short. + +PROJECT_BRIEF = + +# With the PROJECT_LOGO tag one can specify a logo or an icon that is included +# in the documentation. The maximum height of the logo should not exceed 55 +# pixels and the maximum width should not exceed 200 pixels. Doxygen will copy +# the logo to the output directory. + +PROJECT_LOGO = + +# The OUTPUT_DIRECTORY tag is used to specify the (relative or absolute) path +# into which the generated documentation will be written. If a relative path is +# entered, it will be relative to the location where doxygen was started. If +# left blank the current directory will be used. + +OUTPUT_DIRECTORY = + +# If the CREATE_SUBDIRS tag is set to YES then doxygen will create 4096 sub- +# directories (in 2 levels) under the output directory of each output format and +# will distribute the generated files over these directories. Enabling this +# option can be useful when feeding doxygen a huge amount of source files, where +# putting all generated files in the same directory would otherwise causes +# performance problems for the file system. +# The default value is: NO. + +CREATE_SUBDIRS = NO + +# If the ALLOW_UNICODE_NAMES tag is set to YES, doxygen will allow non-ASCII +# characters to appear in the names of generated files. If set to NO, non-ASCII +# characters will be escaped, for example _xE3_x81_x84 will be used for Unicode +# U+3044. +# The default value is: NO. + +ALLOW_UNICODE_NAMES = NO + +# The OUTPUT_LANGUAGE tag is used to specify the language in which all +# documentation generated by doxygen is written. Doxygen will use this +# information to generate all constant output in the proper language. +# Possible values are: Afrikaans, Arabic, Armenian, Brazilian, Catalan, Chinese, +# Chinese-Traditional, Croatian, Czech, Danish, Dutch, English (United States), +# Esperanto, Farsi (Persian), Finnish, French, German, Greek, Hungarian, +# Indonesian, Italian, Japanese, Japanese-en (Japanese with English messages), +# Korean, Korean-en (Korean with English messages), Latvian, Lithuanian, +# Macedonian, Norwegian, Persian (Farsi), Polish, Portuguese, Romanian, Russian, +# Serbian, Serbian-Cyrillic, Slovak, Slovene, Spanish, Swedish, Turkish, +# Ukrainian and Vietnamese. +# The default value is: English. + +OUTPUT_LANGUAGE = English + +# The OUTPUT_TEXT_DIRECTION tag is used to specify the direction in which all +# documentation generated by doxygen is written. Doxygen will use this +# information to generate all generated output in the proper direction. +# Possible values are: None, LTR, RTL and Context. +# The default value is: None. + +OUTPUT_TEXT_DIRECTION = None + +# If the BRIEF_MEMBER_DESC tag is set to YES, doxygen will include brief member +# descriptions after the members that are listed in the file and class +# documentation (similar to Javadoc). Set to NO to disable this. +# The default value is: YES. + +BRIEF_MEMBER_DESC = YES + +# If the REPEAT_BRIEF tag is set to YES, doxygen will prepend the brief +# description of a member or function before the detailed description +# +# Note: If both HIDE_UNDOC_MEMBERS and BRIEF_MEMBER_DESC are set to NO, the +# brief descriptions will be completely suppressed. +# The default value is: YES. + +REPEAT_BRIEF = YES + +# This tag implements a quasi-intelligent brief description abbreviator that is +# used to form the text in various listings. Each string in this list, if found +# as the leading text of the brief description, will be stripped from the text +# and the result, after processing the whole list, is used as the annotated +# text. Otherwise, the brief description is used as-is. If left blank, the +# following values are used ($name is automatically replaced with the name of +# the entity):The $name class, The $name widget, The $name file, is, provides, +# specifies, contains, represents, a, an and the. + +ABBREVIATE_BRIEF = "The $name class" \ + "The $name widget" \ + "The $name file" \ + is \ + provides \ + specifies \ + contains \ + represents \ + a \ + an \ + the + +# If the ALWAYS_DETAILED_SEC and REPEAT_BRIEF tags are both set to YES then +# doxygen will generate a detailed section even if there is only a brief +# description. +# The default value is: NO. + +ALWAYS_DETAILED_SEC = NO + +# If the INLINE_INHERITED_MEMB tag is set to YES, doxygen will show all +# inherited members of a class in the documentation of that class as if those +# members were ordinary class members. Constructors, destructors and assignment +# operators of the base classes will not be shown. +# The default value is: NO. + +INLINE_INHERITED_MEMB = NO + +# If the FULL_PATH_NAMES tag is set to YES, doxygen will prepend the full path +# before files name in the file list and in the header files. If set to NO the +# shortest path that makes the file name unique will be used +# The default value is: YES. + +FULL_PATH_NAMES = YES + +# The STRIP_FROM_PATH tag can be used to strip a user-defined part of the path. +# Stripping is only done if one of the specified strings matches the left-hand +# part of the path. The tag can be used to show relative paths in the file list. +# If left blank the directory from which doxygen is run is used as the path to +# strip. +# +# Note that you can specify absolute paths here, but also relative paths, which +# will be relative from the directory where doxygen is started. +# This tag requires that the tag FULL_PATH_NAMES is set to YES. + +STRIP_FROM_PATH = + +# The STRIP_FROM_INC_PATH tag can be used to strip a user-defined part of the +# path mentioned in the documentation of a class, which tells the reader which +# header file to include in order to use a class. If left blank only the name of +# the header file containing the class definition is used. Otherwise one should +# specify the list of include paths that are normally passed to the compiler +# using the -I flag. + +STRIP_FROM_INC_PATH = + +# If the SHORT_NAMES tag is set to YES, doxygen will generate much shorter (but +# less readable) file names. This can be useful is your file systems doesn't +# support long names like on DOS, Mac, or CD-ROM. +# The default value is: NO. + +SHORT_NAMES = NO + +# If the JAVADOC_AUTOBRIEF tag is set to YES then doxygen will interpret the +# first line (until the first dot) of a Javadoc-style comment as the brief +# description. If set to NO, the Javadoc-style will behave just like regular Qt- +# style comments (thus requiring an explicit @brief command for a brief +# description.) +# The default value is: NO. + +JAVADOC_AUTOBRIEF = NO + +# If the JAVADOC_BANNER tag is set to YES then doxygen will interpret a line +# such as +# /*************** +# as being the beginning of a Javadoc-style comment "banner". If set to NO, the +# Javadoc-style will behave just like regular comments and it will not be +# interpreted by doxygen. +# The default value is: NO. + +JAVADOC_BANNER = NO + +# If the QT_AUTOBRIEF tag is set to YES then doxygen will interpret the first +# line (until the first dot) of a Qt-style comment as the brief description. If +# set to NO, the Qt-style will behave just like regular Qt-style comments (thus +# requiring an explicit \brief command for a brief description.) +# The default value is: NO. + +QT_AUTOBRIEF = NO + +# The MULTILINE_CPP_IS_BRIEF tag can be set to YES to make doxygen treat a +# multi-line C++ special comment block (i.e. a block of //! or /// comments) as +# a brief description. This used to be the default behavior. The new default is +# to treat a multi-line C++ comment block as a detailed description. Set this +# tag to YES if you prefer the old behavior instead. +# +# Note that setting this tag to YES also means that rational rose comments are +# not recognized any more. +# The default value is: NO. + +MULTILINE_CPP_IS_BRIEF = NO + +# By default Python docstrings are displayed as preformatted text and doxygen's +# special commands cannot be used. By setting PYTHON_DOCSTRING to NO the +# doxygen's special commands can be used and the contents of the docstring +# documentation blocks is shown as doxygen documentation. +# The default value is: YES. + +PYTHON_DOCSTRING = YES + +# If the INHERIT_DOCS tag is set to YES then an undocumented member inherits the +# documentation from any documented member that it re-implements. +# The default value is: YES. + +INHERIT_DOCS = YES + +# If the SEPARATE_MEMBER_PAGES tag is set to YES then doxygen will produce a new +# page for each member. If set to NO, the documentation of a member will be part +# of the file/class/namespace that contains it. +# The default value is: NO. + +SEPARATE_MEMBER_PAGES = NO + +# The TAB_SIZE tag can be used to set the number of spaces in a tab. Doxygen +# uses this value to replace tabs by spaces in code fragments. +# Minimum value: 1, maximum value: 16, default value: 4. + +TAB_SIZE = 8 + +# This tag can be used to specify a number of aliases that act as commands in +# the documentation. An alias has the form: +# name=value +# For example adding +# "sideeffect=@par Side Effects:\n" +# will allow you to put the command \sideeffect (or @sideeffect) in the +# documentation, which will result in a user-defined paragraph with heading +# "Side Effects:". You can put \n's in the value part of an alias to insert +# newlines (in the resulting output). You can put ^^ in the value part of an +# alias to insert a newline as if a physical newline was in the original file. +# When you need a literal { or } or , in the value part of an alias you have to +# escape them by means of a backslash (\), this can lead to conflicts with the +# commands \{ and \} for these it is advised to use the version @{ and @} or use +# a double escape (\\{ and \\}) + +ALIASES = + +# Set the OPTIMIZE_OUTPUT_FOR_C tag to YES if your project consists of C sources +# only. Doxygen will then generate output that is more tailored for C. For +# instance, some of the names that are used will be different. The list of all +# members will be omitted, etc. +# The default value is: NO. + +OPTIMIZE_OUTPUT_FOR_C = NO + +# Set the OPTIMIZE_OUTPUT_JAVA tag to YES if your project consists of Java or +# Python sources only. Doxygen will then generate output that is more tailored +# for that language. For instance, namespaces will be presented as packages, +# qualified scopes will look different, etc. +# The default value is: NO. + +OPTIMIZE_OUTPUT_JAVA = NO + +# Set the OPTIMIZE_FOR_FORTRAN tag to YES if your project consists of Fortran +# sources. Doxygen will then generate output that is tailored for Fortran. +# The default value is: NO. + +OPTIMIZE_FOR_FORTRAN = NO + +# Set the OPTIMIZE_OUTPUT_VHDL tag to YES if your project consists of VHDL +# sources. Doxygen will then generate output that is tailored for VHDL. +# The default value is: NO. + +OPTIMIZE_OUTPUT_VHDL = NO + +# Set the OPTIMIZE_OUTPUT_SLICE tag to YES if your project consists of Slice +# sources only. Doxygen will then generate output that is more tailored for that +# language. For instance, namespaces will be presented as modules, types will be +# separated into more groups, etc. +# The default value is: NO. + +OPTIMIZE_OUTPUT_SLICE = NO + +# Doxygen selects the parser to use depending on the extension of the files it +# parses. With this tag you can assign which parser to use for a given +# extension. Doxygen has a built-in mapping, but you can override or extend it +# using this tag. The format is ext=language, where ext is a file extension, and +# language is one of the parsers supported by doxygen: IDL, Java, JavaScript, +# Csharp (C#), C, C++, D, PHP, md (Markdown), Objective-C, Python, Slice, VHDL, +# Fortran (fixed format Fortran: FortranFixed, free formatted Fortran: +# FortranFree, unknown formatted Fortran: Fortran. In the later case the parser +# tries to guess whether the code is fixed or free formatted code, this is the +# default for Fortran type files). For instance to make doxygen treat .inc files +# as Fortran files (default is PHP), and .f files as C (default is Fortran), +# use: inc=Fortran f=C. +# +# Note: For files without extension you can use no_extension as a placeholder. +# +# Note that for custom extensions you also need to set FILE_PATTERNS otherwise +# the files are not read by doxygen. + +EXTENSION_MAPPING = + +# If the MARKDOWN_SUPPORT tag is enabled then doxygen pre-processes all comments +# according to the Markdown format, which allows for more readable +# documentation. See https://daringfireball.net/projects/markdown/ for details. +# The output of markdown processing is further processed by doxygen, so you can +# mix doxygen, HTML, and XML commands with Markdown formatting. Disable only in +# case of backward compatibilities issues. +# The default value is: YES. + +MARKDOWN_SUPPORT = YES + +# When the TOC_INCLUDE_HEADINGS tag is set to a non-zero value, all headings up +# to that level are automatically included in the table of contents, even if +# they do not have an id attribute. +# Note: This feature currently applies only to Markdown headings. +# Minimum value: 0, maximum value: 99, default value: 5. +# This tag requires that the tag MARKDOWN_SUPPORT is set to YES. + +TOC_INCLUDE_HEADINGS = 5 + +# When enabled doxygen tries to link words that correspond to documented +# classes, or namespaces to their corresponding documentation. Such a link can +# be prevented in individual cases by putting a % sign in front of the word or +# globally by setting AUTOLINK_SUPPORT to NO. +# The default value is: YES. + +AUTOLINK_SUPPORT = YES + +# If you use STL classes (i.e. std::string, std::vector, etc.) but do not want +# to include (a tag file for) the STL sources as input, then you should set this +# tag to YES in order to let doxygen match functions declarations and +# definitions whose arguments contain STL classes (e.g. func(std::string); +# versus func(std::string) {}). This also make the inheritance and collaboration +# diagrams that involve STL classes more complete and accurate. +# The default value is: NO. + +BUILTIN_STL_SUPPORT = NO + +# If you use Microsoft's C++/CLI language, you should set this option to YES to +# enable parsing support. +# The default value is: NO. + +CPP_CLI_SUPPORT = NO + +# Set the SIP_SUPPORT tag to YES if your project consists of sip (see: +# https://www.riverbankcomputing.com/software/sip/intro) sources only. Doxygen +# will parse them like normal C++ but will assume all classes use public instead +# of private inheritance when no explicit protection keyword is present. +# The default value is: NO. + +SIP_SUPPORT = NO + +# For Microsoft's IDL there are propget and propput attributes to indicate +# getter and setter methods for a property. Setting this option to YES will make +# doxygen to replace the get and set methods by a property in the documentation. +# This will only work if the methods are indeed getting or setting a simple +# type. If this is not the case, or you want to show the methods anyway, you +# should set this option to NO. +# The default value is: YES. + +IDL_PROPERTY_SUPPORT = YES + +# If member grouping is used in the documentation and the DISTRIBUTE_GROUP_DOC +# tag is set to YES then doxygen will reuse the documentation of the first +# member in the group (if any) for the other members of the group. By default +# all members of a group must be documented explicitly. +# The default value is: NO. + +DISTRIBUTE_GROUP_DOC = NO + +# If one adds a struct or class to a group and this option is enabled, then also +# any nested class or struct is added to the same group. By default this option +# is disabled and one has to add nested compounds explicitly via \ingroup. +# The default value is: NO. + +GROUP_NESTED_COMPOUNDS = NO + +# Set the SUBGROUPING tag to YES to allow class member groups of the same type +# (for instance a group of public functions) to be put as a subgroup of that +# type (e.g. under the Public Functions section). Set it to NO to prevent +# subgrouping. Alternatively, this can be done per class using the +# \nosubgrouping command. +# The default value is: YES. + +SUBGROUPING = YES + +# When the INLINE_GROUPED_CLASSES tag is set to YES, classes, structs and unions +# are shown inside the group in which they are included (e.g. using \ingroup) +# instead of on a separate page (for HTML and Man pages) or section (for LaTeX +# and RTF). +# +# Note that this feature does not work in combination with +# SEPARATE_MEMBER_PAGES. +# The default value is: NO. + +INLINE_GROUPED_CLASSES = NO + +# When the INLINE_SIMPLE_STRUCTS tag is set to YES, structs, classes, and unions +# with only public data fields or simple typedef fields will be shown inline in +# the documentation of the scope in which they are defined (i.e. file, +# namespace, or group documentation), provided this scope is documented. If set +# to NO, structs, classes, and unions are shown on a separate page (for HTML and +# Man pages) or section (for LaTeX and RTF). +# The default value is: NO. + +INLINE_SIMPLE_STRUCTS = NO + +# When TYPEDEF_HIDES_STRUCT tag is enabled, a typedef of a struct, union, or +# enum is documented as struct, union, or enum with the name of the typedef. So +# typedef struct TypeS {} TypeT, will appear in the documentation as a struct +# with name TypeT. When disabled the typedef will appear as a member of a file, +# namespace, or class. And the struct will be named TypeS. This can typically be +# useful for C code in case the coding convention dictates that all compound +# types are typedef'ed and only the typedef is referenced, never the tag name. +# The default value is: NO. + +TYPEDEF_HIDES_STRUCT = NO + +# The size of the symbol lookup cache can be set using LOOKUP_CACHE_SIZE. This +# cache is used to resolve symbols given their name and scope. Since this can be +# an expensive process and often the same symbol appears multiple times in the +# code, doxygen keeps a cache of pre-resolved symbols. If the cache is too small +# doxygen will become slower. If the cache is too large, memory is wasted. The +# cache size is given by this formula: 2^(16+LOOKUP_CACHE_SIZE). The valid range +# is 0..9, the default is 0, corresponding to a cache size of 2^16=65536 +# symbols. At the end of a run doxygen will report the cache usage and suggest +# the optimal cache size from a speed point of view. +# Minimum value: 0, maximum value: 9, default value: 0. + +LOOKUP_CACHE_SIZE = 0 + +# The NUM_PROC_THREADS specifies the number threads doxygen is allowed to use +# during processing. When set to 0 doxygen will based this on the number of +# cores available in the system. You can set it explicitly to a value larger +# than 0 to get more control over the balance between CPU load and processing +# speed. At this moment only the input processing can be done using multiple +# threads. Since this is still an experimental feature the default is set to 1, +# which efficively disables parallel processing. Please report any issues you +# encounter. Generating dot graphs in parallel is controlled by the +# DOT_NUM_THREADS setting. +# Minimum value: 0, maximum value: 32, default value: 1. + +NUM_PROC_THREADS = 1 + +#--------------------------------------------------------------------------- +# Build related configuration options +#--------------------------------------------------------------------------- + +# If the EXTRACT_ALL tag is set to YES, doxygen will assume all entities in +# documentation are documented, even if no documentation was available. Private +# class members and static file members will be hidden unless the +# EXTRACT_PRIVATE respectively EXTRACT_STATIC tags are set to YES. +# Note: This will also disable the warnings about undocumented members that are +# normally produced when WARNINGS is set to YES. +# The default value is: NO. + +EXTRACT_ALL = YES + +# If the EXTRACT_PRIVATE tag is set to YES, all private members of a class will +# be included in the documentation. +# The default value is: NO. + +EXTRACT_PRIVATE = NO + +# If the EXTRACT_PRIV_VIRTUAL tag is set to YES, documented private virtual +# methods of a class will be included in the documentation. +# The default value is: NO. + +EXTRACT_PRIV_VIRTUAL = NO + +# If the EXTRACT_PACKAGE tag is set to YES, all members with package or internal +# scope will be included in the documentation. +# The default value is: NO. + +EXTRACT_PACKAGE = NO + +# If the EXTRACT_STATIC tag is set to YES, all static members of a file will be +# included in the documentation. +# The default value is: NO. + +EXTRACT_STATIC = NO + +# If the EXTRACT_LOCAL_CLASSES tag is set to YES, classes (and structs) defined +# locally in source files will be included in the documentation. If set to NO, +# only classes defined in header files are included. Does not have any effect +# for Java sources. +# The default value is: YES. + +EXTRACT_LOCAL_CLASSES = YES + +# This flag is only useful for Objective-C code. If set to YES, local methods, +# which are defined in the implementation section but not in the interface are +# included in the documentation. If set to NO, only methods in the interface are +# included. +# The default value is: NO. + +EXTRACT_LOCAL_METHODS = NO + +# If this flag is set to YES, the members of anonymous namespaces will be +# extracted and appear in the documentation as a namespace called +# 'anonymous_namespace{file}', where file will be replaced with the base name of +# the file that contains the anonymous namespace. By default anonymous namespace +# are hidden. +# The default value is: NO. + +EXTRACT_ANON_NSPACES = NO + +# If the HIDE_UNDOC_MEMBERS tag is set to YES, doxygen will hide all +# undocumented members inside documented classes or files. If set to NO these +# members will be included in the various overviews, but no documentation +# section is generated. This option has no effect if EXTRACT_ALL is enabled. +# The default value is: NO. + +HIDE_UNDOC_MEMBERS = NO + +# If the HIDE_UNDOC_CLASSES tag is set to YES, doxygen will hide all +# undocumented classes that are normally visible in the class hierarchy. If set +# to NO, these classes will be included in the various overviews. This option +# has no effect if EXTRACT_ALL is enabled. +# The default value is: NO. + +HIDE_UNDOC_CLASSES = NO + +# If the HIDE_FRIEND_COMPOUNDS tag is set to YES, doxygen will hide all friend +# declarations. If set to NO, these declarations will be included in the +# documentation. +# The default value is: NO. + +HIDE_FRIEND_COMPOUNDS = NO + +# If the HIDE_IN_BODY_DOCS tag is set to YES, doxygen will hide any +# documentation blocks found inside the body of a function. If set to NO, these +# blocks will be appended to the function's detailed documentation block. +# The default value is: NO. + +HIDE_IN_BODY_DOCS = NO + +# The INTERNAL_DOCS tag determines if documentation that is typed after a +# \internal command is included. If the tag is set to NO then the documentation +# will be excluded. Set it to YES to include the internal documentation. +# The default value is: NO. + +INTERNAL_DOCS = NO + +# If the CASE_SENSE_NAMES tag is set to NO then doxygen will only generate file +# names in lower-case letters. If set to YES, upper-case letters are also +# allowed. This is useful if you have classes or files whose names only differ +# in case and if your file system supports case sensitive file names. Windows +# (including Cygwin) and Mac users are advised to set this option to NO. +# The default value is: system dependent. + +CASE_SENSE_NAMES = NO + +# If the HIDE_SCOPE_NAMES tag is set to NO then doxygen will show members with +# their full class and namespace scopes in the documentation. If set to YES, the +# scope will be hidden. +# The default value is: NO. + +HIDE_SCOPE_NAMES = NO + +# If the HIDE_COMPOUND_REFERENCE tag is set to NO (default) then doxygen will +# append additional text to a page's title, such as Class Reference. If set to +# YES the compound reference will be hidden. +# The default value is: NO. + +HIDE_COMPOUND_REFERENCE= NO + +# If the SHOW_INCLUDE_FILES tag is set to YES then doxygen will put a list of +# the files that are included by a file in the documentation of that file. +# The default value is: YES. + +SHOW_INCLUDE_FILES = YES + +# If the SHOW_GROUPED_MEMB_INC tag is set to YES then Doxygen will add for each +# grouped member an include statement to the documentation, telling the reader +# which file to include in order to use the member. +# The default value is: NO. + +SHOW_GROUPED_MEMB_INC = NO + +# If the FORCE_LOCAL_INCLUDES tag is set to YES then doxygen will list include +# files with double quotes in the documentation rather than with sharp brackets. +# The default value is: NO. + +FORCE_LOCAL_INCLUDES = NO + +# If the INLINE_INFO tag is set to YES then a tag [inline] is inserted in the +# documentation for inline members. +# The default value is: YES. + +INLINE_INFO = YES + +# If the SORT_MEMBER_DOCS tag is set to YES then doxygen will sort the +# (detailed) documentation of file and class members alphabetically by member +# name. If set to NO, the members will appear in declaration order. +# The default value is: YES. + +SORT_MEMBER_DOCS = YES + +# If the SORT_BRIEF_DOCS tag is set to YES then doxygen will sort the brief +# descriptions of file, namespace and class members alphabetically by member +# name. If set to NO, the members will appear in declaration order. Note that +# this will also influence the order of the classes in the class list. +# The default value is: NO. + +SORT_BRIEF_DOCS = NO + +# If the SORT_MEMBERS_CTORS_1ST tag is set to YES then doxygen will sort the +# (brief and detailed) documentation of class members so that constructors and +# destructors are listed first. If set to NO the constructors will appear in the +# respective orders defined by SORT_BRIEF_DOCS and SORT_MEMBER_DOCS. +# Note: If SORT_BRIEF_DOCS is set to NO this option is ignored for sorting brief +# member documentation. +# Note: If SORT_MEMBER_DOCS is set to NO this option is ignored for sorting +# detailed member documentation. +# The default value is: NO. + +SORT_MEMBERS_CTORS_1ST = NO + +# If the SORT_GROUP_NAMES tag is set to YES then doxygen will sort the hierarchy +# of group names into alphabetical order. If set to NO the group names will +# appear in their defined order. +# The default value is: NO. + +SORT_GROUP_NAMES = NO + +# If the SORT_BY_SCOPE_NAME tag is set to YES, the class list will be sorted by +# fully-qualified names, including namespaces. If set to NO, the class list will +# be sorted only by class name, not including the namespace part. +# Note: This option is not very useful if HIDE_SCOPE_NAMES is set to YES. +# Note: This option applies only to the class list, not to the alphabetical +# list. +# The default value is: NO. + +SORT_BY_SCOPE_NAME = NO + +# If the STRICT_PROTO_MATCHING option is enabled and doxygen fails to do proper +# type resolution of all parameters of a function it will reject a match between +# the prototype and the implementation of a member function even if there is +# only one candidate or it is obvious which candidate to choose by doing a +# simple string match. By disabling STRICT_PROTO_MATCHING doxygen will still +# accept a match between prototype and implementation in such cases. +# The default value is: NO. + +STRICT_PROTO_MATCHING = NO + +# The GENERATE_TODOLIST tag can be used to enable (YES) or disable (NO) the todo +# list. This list is created by putting \todo commands in the documentation. +# The default value is: YES. + +GENERATE_TODOLIST = YES + +# The GENERATE_TESTLIST tag can be used to enable (YES) or disable (NO) the test +# list. This list is created by putting \test commands in the documentation. +# The default value is: YES. + +GENERATE_TESTLIST = YES + +# The GENERATE_BUGLIST tag can be used to enable (YES) or disable (NO) the bug +# list. This list is created by putting \bug commands in the documentation. +# The default value is: YES. + +GENERATE_BUGLIST = YES + +# The GENERATE_DEPRECATEDLIST tag can be used to enable (YES) or disable (NO) +# the deprecated list. This list is created by putting \deprecated commands in +# the documentation. +# The default value is: YES. + +GENERATE_DEPRECATEDLIST= YES + +# The ENABLED_SECTIONS tag can be used to enable conditional documentation +# sections, marked by \if ... \endif and \cond +# ... \endcond blocks. + +ENABLED_SECTIONS = + +# The MAX_INITIALIZER_LINES tag determines the maximum number of lines that the +# initial value of a variable or macro / define can have for it to appear in the +# documentation. If the initializer consists of more lines than specified here +# it will be hidden. Use a value of 0 to hide initializers completely. The +# appearance of the value of individual variables and macros / defines can be +# controlled using \showinitializer or \hideinitializer command in the +# documentation regardless of this setting. +# Minimum value: 0, maximum value: 10000, default value: 30. + +MAX_INITIALIZER_LINES = 30 + +# Set the SHOW_USED_FILES tag to NO to disable the list of files generated at +# the bottom of the documentation of classes and structs. If set to YES, the +# list will mention the files that were used to generate the documentation. +# The default value is: YES. + +SHOW_USED_FILES = YES + +# Set the SHOW_FILES tag to NO to disable the generation of the Files page. This +# will remove the Files entry from the Quick Index and from the Folder Tree View +# (if specified). +# The default value is: YES. + +SHOW_FILES = YES + +# Set the SHOW_NAMESPACES tag to NO to disable the generation of the Namespaces +# page. This will remove the Namespaces entry from the Quick Index and from the +# Folder Tree View (if specified). +# The default value is: YES. + +SHOW_NAMESPACES = YES + +# The FILE_VERSION_FILTER tag can be used to specify a program or script that +# doxygen should invoke to get the current version for each file (typically from +# the version control system). Doxygen will invoke the program by executing (via +# popen()) the command command input-file, where command is the value of the +# FILE_VERSION_FILTER tag, and input-file is the name of an input file provided +# by doxygen. Whatever the program writes to standard output is used as the file +# version. For an example see the documentation. + +FILE_VERSION_FILTER = + +# The LAYOUT_FILE tag can be used to specify a layout file which will be parsed +# by doxygen. The layout file controls the global structure of the generated +# output files in an output format independent way. To create the layout file +# that represents doxygen's defaults, run doxygen with the -l option. You can +# optionally specify a file name after the option, if omitted DoxygenLayout.xml +# will be used as the name of the layout file. +# +# Note that if you run doxygen from a directory containing a file called +# DoxygenLayout.xml, doxygen will parse it automatically even if the LAYOUT_FILE +# tag is left empty. + +LAYOUT_FILE = + +# The CITE_BIB_FILES tag can be used to specify one or more bib files containing +# the reference definitions. This must be a list of .bib files. The .bib +# extension is automatically appended if omitted. This requires the bibtex tool +# to be installed. See also https://en.wikipedia.org/wiki/BibTeX for more info. +# For LaTeX the style of the bibliography can be controlled using +# LATEX_BIB_STYLE. To use this feature you need bibtex and perl available in the +# search path. See also \cite for info how to create references. + +CITE_BIB_FILES = + +#--------------------------------------------------------------------------- +# Configuration options related to warning and progress messages +#--------------------------------------------------------------------------- + +# The QUIET tag can be used to turn on/off the messages that are generated to +# standard output by doxygen. If QUIET is set to YES this implies that the +# messages are off. +# The default value is: NO. + +QUIET = NO + +# The WARNINGS tag can be used to turn on/off the warning messages that are +# generated to standard error (stderr) by doxygen. If WARNINGS is set to YES +# this implies that the warnings are on. +# +# Tip: Turn warnings on while writing the documentation. +# The default value is: YES. + +WARNINGS = YES + +# If the WARN_IF_UNDOCUMENTED tag is set to YES then doxygen will generate +# warnings for undocumented members. If EXTRACT_ALL is set to YES then this flag +# will automatically be disabled. +# The default value is: YES. + +WARN_IF_UNDOCUMENTED = YES + +# If the WARN_IF_DOC_ERROR tag is set to YES, doxygen will generate warnings for +# potential errors in the documentation, such as not documenting some parameters +# in a documented function, or documenting parameters that don't exist or using +# markup commands wrongly. +# The default value is: YES. + +WARN_IF_DOC_ERROR = YES + +# This WARN_NO_PARAMDOC option can be enabled to get warnings for functions that +# are documented, but have no documentation for their parameters or return +# value. If set to NO, doxygen will only warn about wrong or incomplete +# parameter documentation, but not about the absence of documentation. If +# EXTRACT_ALL is set to YES then this flag will automatically be disabled. +# The default value is: NO. + +WARN_NO_PARAMDOC = NO + +# If the WARN_AS_ERROR tag is set to YES then doxygen will immediately stop when +# a warning is encountered. +# The default value is: NO. + +WARN_AS_ERROR = NO + +# The WARN_FORMAT tag determines the format of the warning messages that doxygen +# can produce. The string should contain the $file, $line, and $text tags, which +# will be replaced by the file and line number from which the warning originated +# and the warning text. Optionally the format may contain $version, which will +# be replaced by the version of the file (if it could be obtained via +# FILE_VERSION_FILTER) +# The default value is: $file:$line: $text. + +WARN_FORMAT = "$file:$line: $text" + +# The WARN_LOGFILE tag can be used to specify a file to which warning and error +# messages should be written. If left blank the output is written to standard +# error (stderr). + +WARN_LOGFILE = + +#--------------------------------------------------------------------------- +# Configuration options related to the input files +#--------------------------------------------------------------------------- + +# The INPUT tag is used to specify the files and/or directories that contain +# documented source files. You may enter file names like myfile.cpp or +# directories like /usr/src/myproject. Separate the files or directories with +# spaces. See also FILE_PATTERNS and EXTENSION_MAPPING +# Note: If this tag is empty the current directory is searched. + +INPUT = + +# This tag can be used to specify the character encoding of the source files +# that doxygen parses. Internally doxygen uses the UTF-8 encoding. Doxygen uses +# libiconv (or the iconv built into libc) for the transcoding. See the libiconv +# documentation (see: https://www.gnu.org/software/libiconv/) for the list of +# possible encodings. +# The default value is: UTF-8. + +INPUT_ENCODING = UTF-8 + +# If the value of the INPUT tag contains directories, you can use the +# FILE_PATTERNS tag to specify one or more wildcard patterns (like *.cpp and +# *.h) to filter out the source-files in the directories. +# +# Note that for custom extensions or not directly supported extensions you also +# need to set EXTENSION_MAPPING for the extension otherwise the files are not +# read by doxygen. +# +# If left blank the following patterns are tested:*.c, *.cc, *.cxx, *.cpp, +# *.c++, *.java, *.ii, *.ixx, *.ipp, *.i++, *.inl, *.idl, *.ddl, *.odl, *.h, +# *.hh, *.hxx, *.hpp, *.h++, *.cs, *.d, *.php, *.php4, *.php5, *.phtml, *.inc, +# *.m, *.markdown, *.md, *.mm, *.dox (to be provided as doxygen C comment), +# *.doc (to be provided as doxygen C comment), *.txt (to be provided as doxygen +# C comment), *.py, *.pyw, *.f90, *.f95, *.f03, *.f08, *.f18, *.f, *.for, *.vhd, +# *.vhdl, *.ucf, *.qsf and *.ice. + +FILE_PATTERNS = *.c \ + *.cc \ + *.cxx \ + *.cpp \ + *.c++ \ + *.d \ + *.java \ + *.ii \ + *.ixx \ + *.ipp \ + *.i++ \ + *.inl \ + *.h \ + *.hh \ + *.hxx \ + *.hpp \ + *.h++ \ + *.idl \ + *.odl \ + *.cs \ + *.php \ + *.php3 \ + *.inc \ + *.m \ + *.markdown \ + *.md \ + *.mm \ + *.dox \ + *.py \ + *.f90 \ + *.f \ + *.for \ + *.vhd \ + *.vhdl + +# The RECURSIVE tag can be used to specify whether or not subdirectories should +# be searched for input files as well. +# The default value is: NO. + +RECURSIVE = NO + +# The EXCLUDE tag can be used to specify files and/or directories that should be +# excluded from the INPUT source files. This way you can easily exclude a +# subdirectory from a directory tree whose root is specified with the INPUT tag. +# +# Note that relative paths are relative to the directory from which doxygen is +# run. + +EXCLUDE = + +# The EXCLUDE_SYMLINKS tag can be used to select whether or not files or +# directories that are symbolic links (a Unix file system feature) are excluded +# from the input. +# The default value is: NO. + +EXCLUDE_SYMLINKS = NO + +# If the value of the INPUT tag contains directories, you can use the +# EXCLUDE_PATTERNS tag to specify one or more wildcard patterns to exclude +# certain files from those directories. +# +# Note that the wildcards are matched against the file with absolute path, so to +# exclude all test directories for example use the pattern */test/* + +EXCLUDE_PATTERNS = + +# The EXCLUDE_SYMBOLS tag can be used to specify one or more symbol names +# (namespaces, classes, functions, etc.) that should be excluded from the +# output. The symbol name can be a fully qualified name, a word, or if the +# wildcard * is used, a substring. Examples: ANamespace, AClass, +# AClass::ANamespace, ANamespace::*Test +# +# Note that the wildcards are matched against the file with absolute path, so to +# exclude all test directories use the pattern */test/* + +EXCLUDE_SYMBOLS = + +# The EXAMPLE_PATH tag can be used to specify one or more files or directories +# that contain example code fragments that are included (see the \include +# command). + +EXAMPLE_PATH = + +# If the value of the EXAMPLE_PATH tag contains directories, you can use the +# EXAMPLE_PATTERNS tag to specify one or more wildcard pattern (like *.cpp and +# *.h) to filter out the source-files in the directories. If left blank all +# files are included. + +EXAMPLE_PATTERNS = * + +# If the EXAMPLE_RECURSIVE tag is set to YES then subdirectories will be +# searched for input files to be used with the \include or \dontinclude commands +# irrespective of the value of the RECURSIVE tag. +# The default value is: NO. + +EXAMPLE_RECURSIVE = NO + +# The IMAGE_PATH tag can be used to specify one or more files or directories +# that contain images that are to be included in the documentation (see the +# \image command). + +IMAGE_PATH = + +# The INPUT_FILTER tag can be used to specify a program that doxygen should +# invoke to filter for each input file. Doxygen will invoke the filter program +# by executing (via popen()) the command: +# +# +# +# where is the value of the INPUT_FILTER tag, and is the +# name of an input file. Doxygen will then use the output that the filter +# program writes to standard output. If FILTER_PATTERNS is specified, this tag +# will be ignored. +# +# Note that the filter must not add or remove lines; it is applied before the +# code is scanned, but not when the output code is generated. If lines are added +# or removed, the anchors will not be placed correctly. +# +# Note that for custom extensions or not directly supported extensions you also +# need to set EXTENSION_MAPPING for the extension otherwise the files are not +# properly processed by doxygen. + +INPUT_FILTER = + +# The FILTER_PATTERNS tag can be used to specify filters on a per file pattern +# basis. Doxygen will compare the file name with each pattern and apply the +# filter if there is a match. The filters are a list of the form: pattern=filter +# (like *.cpp=my_cpp_filter). See INPUT_FILTER for further information on how +# filters are used. If the FILTER_PATTERNS tag is empty or if none of the +# patterns match the file name, INPUT_FILTER is applied. +# +# Note that for custom extensions or not directly supported extensions you also +# need to set EXTENSION_MAPPING for the extension otherwise the files are not +# properly processed by doxygen. + +FILTER_PATTERNS = + +# If the FILTER_SOURCE_FILES tag is set to YES, the input filter (if set using +# INPUT_FILTER) will also be used to filter the input files that are used for +# producing the source files to browse (i.e. when SOURCE_BROWSER is set to YES). +# The default value is: NO. + +FILTER_SOURCE_FILES = NO + +# The FILTER_SOURCE_PATTERNS tag can be used to specify source filters per file +# pattern. A pattern will override the setting for FILTER_PATTERN (if any) and +# it is also possible to disable source filtering for a specific pattern using +# *.ext= (so without naming a filter). +# This tag requires that the tag FILTER_SOURCE_FILES is set to YES. + +FILTER_SOURCE_PATTERNS = + +# If the USE_MDFILE_AS_MAINPAGE tag refers to the name of a markdown file that +# is part of the input, its contents will be placed on the main page +# (index.html). This can be useful if you have a project on for instance GitHub +# and want to reuse the introduction page also for the doxygen output. + +USE_MDFILE_AS_MAINPAGE = + +#--------------------------------------------------------------------------- +# Configuration options related to source browsing +#--------------------------------------------------------------------------- + +# If the SOURCE_BROWSER tag is set to YES then a list of source files will be +# generated. Documented entities will be cross-referenced with these sources. +# +# Note: To get rid of all source code in the generated output, make sure that +# also VERBATIM_HEADERS is set to NO. +# The default value is: NO. + +SOURCE_BROWSER = YES + +# Setting the INLINE_SOURCES tag to YES will include the body of functions, +# classes and enums directly into the documentation. +# The default value is: NO. + +INLINE_SOURCES = YES + +# Setting the STRIP_CODE_COMMENTS tag to YES will instruct doxygen to hide any +# special comment blocks from generated source code fragments. Normal C, C++ and +# Fortran comments will always remain visible. +# The default value is: YES. + +STRIP_CODE_COMMENTS = YES + +# If the REFERENCED_BY_RELATION tag is set to YES then for each documented +# entity all documented functions referencing it will be listed. +# The default value is: NO. + +REFERENCED_BY_RELATION = NO + +# If the REFERENCES_RELATION tag is set to YES then for each documented function +# all documented entities called/used by that function will be listed. +# The default value is: NO. + +REFERENCES_RELATION = NO + +# If the REFERENCES_LINK_SOURCE tag is set to YES and SOURCE_BROWSER tag is set +# to YES then the hyperlinks from functions in REFERENCES_RELATION and +# REFERENCED_BY_RELATION lists will link to the source code. Otherwise they will +# link to the documentation. +# The default value is: YES. + +REFERENCES_LINK_SOURCE = YES + +# If SOURCE_TOOLTIPS is enabled (the default) then hovering a hyperlink in the +# source code will show a tooltip with additional information such as prototype, +# brief description and links to the definition and documentation. Since this +# will make the HTML file larger and loading of large files a bit slower, you +# can opt to disable this feature. +# The default value is: YES. +# This tag requires that the tag SOURCE_BROWSER is set to YES. + +SOURCE_TOOLTIPS = YES + +# If the USE_HTAGS tag is set to YES then the references to source code will +# point to the HTML generated by the htags(1) tool instead of doxygen built-in +# source browser. The htags tool is part of GNU's global source tagging system +# (see https://www.gnu.org/software/global/global.html). You will need version +# 4.8.6 or higher. +# +# To use it do the following: +# - Install the latest version of global +# - Enable SOURCE_BROWSER and USE_HTAGS in the configuration file +# - Make sure the INPUT points to the root of the source tree +# - Run doxygen as normal +# +# Doxygen will invoke htags (and that will in turn invoke gtags), so these +# tools must be available from the command line (i.e. in the search path). +# +# The result: instead of the source browser generated by doxygen, the links to +# source code will now point to the output of htags. +# The default value is: NO. +# This tag requires that the tag SOURCE_BROWSER is set to YES. + +USE_HTAGS = NO + +# If the VERBATIM_HEADERS tag is set the YES then doxygen will generate a +# verbatim copy of the header file for each class for which an include is +# specified. Set to NO to disable this. +# See also: Section \class. +# The default value is: YES. + +VERBATIM_HEADERS = YES + +#--------------------------------------------------------------------------- +# Configuration options related to the alphabetical class index +#--------------------------------------------------------------------------- + +# If the ALPHABETICAL_INDEX tag is set to YES, an alphabetical index of all +# compounds will be generated. Enable this if the project contains a lot of +# classes, structs, unions or interfaces. +# The default value is: YES. + +ALPHABETICAL_INDEX = YES + +# The COLS_IN_ALPHA_INDEX tag can be used to specify the number of columns in +# which the alphabetical index list will be split. +# Minimum value: 1, maximum value: 20, default value: 5. +# This tag requires that the tag ALPHABETICAL_INDEX is set to YES. + +COLS_IN_ALPHA_INDEX = 5 + +# In case all classes in a project start with a common prefix, all classes will +# be put under the same header in the alphabetical index. The IGNORE_PREFIX tag +# can be used to specify a prefix (or a list of prefixes) that should be ignored +# while generating the index headers. +# This tag requires that the tag ALPHABETICAL_INDEX is set to YES. + +IGNORE_PREFIX = + +#--------------------------------------------------------------------------- +# Configuration options related to the HTML output +#--------------------------------------------------------------------------- + +# If the GENERATE_HTML tag is set to YES, doxygen will generate HTML output +# The default value is: YES. + +GENERATE_HTML = YES + +# The HTML_OUTPUT tag is used to specify where the HTML docs will be put. If a +# relative path is entered the value of OUTPUT_DIRECTORY will be put in front of +# it. +# The default directory is: html. +# This tag requires that the tag GENERATE_HTML is set to YES. + +HTML_OUTPUT = html + +# The HTML_FILE_EXTENSION tag can be used to specify the file extension for each +# generated HTML page (for example: .htm, .php, .asp). +# The default value is: .html. +# This tag requires that the tag GENERATE_HTML is set to YES. + +HTML_FILE_EXTENSION = .html + +# The HTML_HEADER tag can be used to specify a user-defined HTML header file for +# each generated HTML page. If the tag is left blank doxygen will generate a +# standard header. +# +# To get valid HTML the header file that includes any scripts and style sheets +# that doxygen needs, which is dependent on the configuration options used (e.g. +# the setting GENERATE_TREEVIEW). It is highly recommended to start with a +# default header using +# doxygen -w html new_header.html new_footer.html new_stylesheet.css +# YourConfigFile +# and then modify the file new_header.html. See also section "Doxygen usage" +# for information on how to generate the default header that doxygen normally +# uses. +# Note: The header is subject to change so you typically have to regenerate the +# default header when upgrading to a newer version of doxygen. For a description +# of the possible markers and block names see the documentation. +# This tag requires that the tag GENERATE_HTML is set to YES. + +HTML_HEADER = + +# The HTML_FOOTER tag can be used to specify a user-defined HTML footer for each +# generated HTML page. If the tag is left blank doxygen will generate a standard +# footer. See HTML_HEADER for more information on how to generate a default +# footer and what special commands can be used inside the footer. See also +# section "Doxygen usage" for information on how to generate the default footer +# that doxygen normally uses. +# This tag requires that the tag GENERATE_HTML is set to YES. + +HTML_FOOTER = + +# The HTML_STYLESHEET tag can be used to specify a user-defined cascading style +# sheet that is used by each HTML page. It can be used to fine-tune the look of +# the HTML output. If left blank doxygen will generate a default style sheet. +# See also section "Doxygen usage" for information on how to generate the style +# sheet that doxygen normally uses. +# Note: It is recommended to use HTML_EXTRA_STYLESHEET instead of this tag, as +# it is more robust and this tag (HTML_STYLESHEET) will in the future become +# obsolete. +# This tag requires that the tag GENERATE_HTML is set to YES. + +HTML_STYLESHEET = + +# The HTML_EXTRA_STYLESHEET tag can be used to specify additional user-defined +# cascading style sheets that are included after the standard style sheets +# created by doxygen. Using this option one can overrule certain style aspects. +# This is preferred over using HTML_STYLESHEET since it does not replace the +# standard style sheet and is therefore more robust against future updates. +# Doxygen will copy the style sheet files to the output directory. +# Note: The order of the extra style sheet files is of importance (e.g. the last +# style sheet in the list overrules the setting of the previous ones in the +# list). For an example see the documentation. +# This tag requires that the tag GENERATE_HTML is set to YES. + +HTML_EXTRA_STYLESHEET = + +# The HTML_EXTRA_FILES tag can be used to specify one or more extra images or +# other source files which should be copied to the HTML output directory. Note +# that these files will be copied to the base HTML output directory. Use the +# $relpath^ marker in the HTML_HEADER and/or HTML_FOOTER files to load these +# files. In the HTML_STYLESHEET file, use the file name only. Also note that the +# files will be copied as-is; there are no commands or markers available. +# This tag requires that the tag GENERATE_HTML is set to YES. + +HTML_EXTRA_FILES = + +# The HTML_COLORSTYLE_HUE tag controls the color of the HTML output. Doxygen +# will adjust the colors in the style sheet and background images according to +# this color. Hue is specified as an angle on a colorwheel, see +# https://en.wikipedia.org/wiki/Hue for more information. For instance the value +# 0 represents red, 60 is yellow, 120 is green, 180 is cyan, 240 is blue, 300 +# purple, and 360 is red again. +# Minimum value: 0, maximum value: 359, default value: 220. +# This tag requires that the tag GENERATE_HTML is set to YES. + +HTML_COLORSTYLE_HUE = 220 + +# The HTML_COLORSTYLE_SAT tag controls the purity (or saturation) of the colors +# in the HTML output. For a value of 0 the output will use grayscales only. A +# value of 255 will produce the most vivid colors. +# Minimum value: 0, maximum value: 255, default value: 100. +# This tag requires that the tag GENERATE_HTML is set to YES. + +HTML_COLORSTYLE_SAT = 100 + +# The HTML_COLORSTYLE_GAMMA tag controls the gamma correction applied to the +# luminance component of the colors in the HTML output. Values below 100 +# gradually make the output lighter, whereas values above 100 make the output +# darker. The value divided by 100 is the actual gamma applied, so 80 represents +# a gamma of 0.8, The value 220 represents a gamma of 2.2, and 100 does not +# change the gamma. +# Minimum value: 40, maximum value: 240, default value: 80. +# This tag requires that the tag GENERATE_HTML is set to YES. + +HTML_COLORSTYLE_GAMMA = 80 + +# If the HTML_TIMESTAMP tag is set to YES then the footer of each generated HTML +# page will contain the date and time when the page was generated. Setting this +# to YES can help to show when doxygen was last run and thus if the +# documentation is up to date. +# The default value is: NO. +# This tag requires that the tag GENERATE_HTML is set to YES. + +HTML_TIMESTAMP = YES + +# If the HTML_DYNAMIC_MENUS tag is set to YES then the generated HTML +# documentation will contain a main index with vertical navigation menus that +# are dynamically created via JavaScript. If disabled, the navigation index will +# consists of multiple levels of tabs that are statically embedded in every HTML +# page. Disable this option to support browsers that do not have JavaScript, +# like the Qt help browser. +# The default value is: YES. +# This tag requires that the tag GENERATE_HTML is set to YES. + +HTML_DYNAMIC_MENUS = YES + +# If the HTML_DYNAMIC_SECTIONS tag is set to YES then the generated HTML +# documentation will contain sections that can be hidden and shown after the +# page has loaded. +# The default value is: NO. +# This tag requires that the tag GENERATE_HTML is set to YES. + +HTML_DYNAMIC_SECTIONS = NO + +# With HTML_INDEX_NUM_ENTRIES one can control the preferred number of entries +# shown in the various tree structured indices initially; the user can expand +# and collapse entries dynamically later on. Doxygen will expand the tree to +# such a level that at most the specified number of entries are visible (unless +# a fully collapsed tree already exceeds this amount). So setting the number of +# entries 1 will produce a full collapsed tree by default. 0 is a special value +# representing an infinite number of entries and will result in a full expanded +# tree by default. +# Minimum value: 0, maximum value: 9999, default value: 100. +# This tag requires that the tag GENERATE_HTML is set to YES. + +HTML_INDEX_NUM_ENTRIES = 100 + +# If the GENERATE_DOCSET tag is set to YES, additional index files will be +# generated that can be used as input for Apple's Xcode 3 integrated development +# environment (see: https://developer.apple.com/xcode/), introduced with OSX +# 10.5 (Leopard). To create a documentation set, doxygen will generate a +# Makefile in the HTML output directory. Running make will produce the docset in +# that directory and running make install will install the docset in +# ~/Library/Developer/Shared/Documentation/DocSets so that Xcode will find it at +# startup. See https://developer.apple.com/library/archive/featuredarticles/Doxy +# genXcode/_index.html for more information. +# The default value is: NO. +# This tag requires that the tag GENERATE_HTML is set to YES. + +GENERATE_DOCSET = NO + +# This tag determines the name of the docset feed. A documentation feed provides +# an umbrella under which multiple documentation sets from a single provider +# (such as a company or product suite) can be grouped. +# The default value is: Doxygen generated docs. +# This tag requires that the tag GENERATE_DOCSET is set to YES. + +DOCSET_FEEDNAME = "Doxygen generated docs" + +# This tag specifies a string that should uniquely identify the documentation +# set bundle. This should be a reverse domain-name style string, e.g. +# com.mycompany.MyDocSet. Doxygen will append .docset to the name. +# The default value is: org.doxygen.Project. +# This tag requires that the tag GENERATE_DOCSET is set to YES. + +DOCSET_BUNDLE_ID = org.doxygen.Project + +# The DOCSET_PUBLISHER_ID tag specifies a string that should uniquely identify +# the documentation publisher. This should be a reverse domain-name style +# string, e.g. com.mycompany.MyDocSet.documentation. +# The default value is: org.doxygen.Publisher. +# This tag requires that the tag GENERATE_DOCSET is set to YES. + +DOCSET_PUBLISHER_ID = org.doxygen.Publisher + +# The DOCSET_PUBLISHER_NAME tag identifies the documentation publisher. +# The default value is: Publisher. +# This tag requires that the tag GENERATE_DOCSET is set to YES. + +DOCSET_PUBLISHER_NAME = Publisher + +# If the GENERATE_HTMLHELP tag is set to YES then doxygen generates three +# additional HTML index files: index.hhp, index.hhc, and index.hhk. The +# index.hhp is a project file that can be read by Microsoft's HTML Help Workshop +# (see: https://www.microsoft.com/en-us/download/details.aspx?id=21138) on +# Windows. +# +# The HTML Help Workshop contains a compiler that can convert all HTML output +# generated by doxygen into a single compiled HTML file (.chm). Compiled HTML +# files are now used as the Windows 98 help format, and will replace the old +# Windows help format (.hlp) on all Windows platforms in the future. Compressed +# HTML files also contain an index, a table of contents, and you can search for +# words in the documentation. The HTML workshop also contains a viewer for +# compressed HTML files. +# The default value is: NO. +# This tag requires that the tag GENERATE_HTML is set to YES. + +GENERATE_HTMLHELP = NO + +# The CHM_FILE tag can be used to specify the file name of the resulting .chm +# file. You can add a path in front of the file if the result should not be +# written to the html output directory. +# This tag requires that the tag GENERATE_HTMLHELP is set to YES. + +CHM_FILE = + +# The HHC_LOCATION tag can be used to specify the location (absolute path +# including file name) of the HTML help compiler (hhc.exe). If non-empty, +# doxygen will try to run the HTML help compiler on the generated index.hhp. +# The file has to be specified with full path. +# This tag requires that the tag GENERATE_HTMLHELP is set to YES. + +HHC_LOCATION = + +# The GENERATE_CHI flag controls if a separate .chi index file is generated +# (YES) or that it should be included in the main .chm file (NO). +# The default value is: NO. +# This tag requires that the tag GENERATE_HTMLHELP is set to YES. + +GENERATE_CHI = NO + +# The CHM_INDEX_ENCODING is used to encode HtmlHelp index (hhk), content (hhc) +# and project file content. +# This tag requires that the tag GENERATE_HTMLHELP is set to YES. + +CHM_INDEX_ENCODING = + +# The BINARY_TOC flag controls whether a binary table of contents is generated +# (YES) or a normal table of contents (NO) in the .chm file. Furthermore it +# enables the Previous and Next buttons. +# The default value is: NO. +# This tag requires that the tag GENERATE_HTMLHELP is set to YES. + +BINARY_TOC = NO + +# The TOC_EXPAND flag can be set to YES to add extra items for group members to +# the table of contents of the HTML help documentation and to the tree view. +# The default value is: NO. +# This tag requires that the tag GENERATE_HTMLHELP is set to YES. + +TOC_EXPAND = NO + +# If the GENERATE_QHP tag is set to YES and both QHP_NAMESPACE and +# QHP_VIRTUAL_FOLDER are set, an additional index file will be generated that +# can be used as input for Qt's qhelpgenerator to generate a Qt Compressed Help +# (.qch) of the generated HTML documentation. +# The default value is: NO. +# This tag requires that the tag GENERATE_HTML is set to YES. + +GENERATE_QHP = NO + +# If the QHG_LOCATION tag is specified, the QCH_FILE tag can be used to specify +# the file name of the resulting .qch file. The path specified is relative to +# the HTML output folder. +# This tag requires that the tag GENERATE_QHP is set to YES. + +QCH_FILE = + +# The QHP_NAMESPACE tag specifies the namespace to use when generating Qt Help +# Project output. For more information please see Qt Help Project / Namespace +# (see: https://doc.qt.io/archives/qt-4.8/qthelpproject.html#namespace). +# The default value is: org.doxygen.Project. +# This tag requires that the tag GENERATE_QHP is set to YES. + +QHP_NAMESPACE = org.doxygen.Project + +# The QHP_VIRTUAL_FOLDER tag specifies the namespace to use when generating Qt +# Help Project output. For more information please see Qt Help Project / Virtual +# Folders (see: https://doc.qt.io/archives/qt-4.8/qthelpproject.html#virtual- +# folders). +# The default value is: doc. +# This tag requires that the tag GENERATE_QHP is set to YES. + +QHP_VIRTUAL_FOLDER = doc + +# If the QHP_CUST_FILTER_NAME tag is set, it specifies the name of a custom +# filter to add. For more information please see Qt Help Project / Custom +# Filters (see: https://doc.qt.io/archives/qt-4.8/qthelpproject.html#custom- +# filters). +# This tag requires that the tag GENERATE_QHP is set to YES. + +QHP_CUST_FILTER_NAME = + +# The QHP_CUST_FILTER_ATTRS tag specifies the list of the attributes of the +# custom filter to add. For more information please see Qt Help Project / Custom +# Filters (see: https://doc.qt.io/archives/qt-4.8/qthelpproject.html#custom- +# filters). +# This tag requires that the tag GENERATE_QHP is set to YES. + +QHP_CUST_FILTER_ATTRS = + +# The QHP_SECT_FILTER_ATTRS tag specifies the list of the attributes this +# project's filter section matches. Qt Help Project / Filter Attributes (see: +# https://doc.qt.io/archives/qt-4.8/qthelpproject.html#filter-attributes). +# This tag requires that the tag GENERATE_QHP is set to YES. + +QHP_SECT_FILTER_ATTRS = + +# The QHG_LOCATION tag can be used to specify the location of Qt's +# qhelpgenerator. If non-empty doxygen will try to run qhelpgenerator on the +# generated .qhp file. +# This tag requires that the tag GENERATE_QHP is set to YES. + +QHG_LOCATION = + +# If the GENERATE_ECLIPSEHELP tag is set to YES, additional index files will be +# generated, together with the HTML files, they form an Eclipse help plugin. To +# install this plugin and make it available under the help contents menu in +# Eclipse, the contents of the directory containing the HTML and XML files needs +# to be copied into the plugins directory of eclipse. The name of the directory +# within the plugins directory should be the same as the ECLIPSE_DOC_ID value. +# After copying Eclipse needs to be restarted before the help appears. +# The default value is: NO. +# This tag requires that the tag GENERATE_HTML is set to YES. + +GENERATE_ECLIPSEHELP = NO + +# A unique identifier for the Eclipse help plugin. When installing the plugin +# the directory name containing the HTML and XML files should also have this +# name. Each documentation set should have its own identifier. +# The default value is: org.doxygen.Project. +# This tag requires that the tag GENERATE_ECLIPSEHELP is set to YES. + +ECLIPSE_DOC_ID = org.doxygen.Project + +# If you want full control over the layout of the generated HTML pages it might +# be necessary to disable the index and replace it with your own. The +# DISABLE_INDEX tag can be used to turn on/off the condensed index (tabs) at top +# of each HTML page. A value of NO enables the index and the value YES disables +# it. Since the tabs in the index contain the same information as the navigation +# tree, you can set this option to YES if you also set GENERATE_TREEVIEW to YES. +# The default value is: NO. +# This tag requires that the tag GENERATE_HTML is set to YES. + +DISABLE_INDEX = NO + +# The GENERATE_TREEVIEW tag is used to specify whether a tree-like index +# structure should be generated to display hierarchical information. If the tag +# value is set to YES, a side panel will be generated containing a tree-like +# index structure (just like the one that is generated for HTML Help). For this +# to work a browser that supports JavaScript, DHTML, CSS and frames is required +# (i.e. any modern browser). Windows users are probably better off using the +# HTML help feature. Via custom style sheets (see HTML_EXTRA_STYLESHEET) one can +# further fine-tune the look of the index. As an example, the default style +# sheet generated by doxygen has an example that shows how to put an image at +# the root of the tree instead of the PROJECT_NAME. Since the tree basically has +# the same information as the tab index, you could consider setting +# DISABLE_INDEX to YES when enabling this option. +# The default value is: NO. +# This tag requires that the tag GENERATE_HTML is set to YES. + +GENERATE_TREEVIEW = NO + +# The ENUM_VALUES_PER_LINE tag can be used to set the number of enum values that +# doxygen will group on one line in the generated HTML documentation. +# +# Note that a value of 0 will completely suppress the enum values from appearing +# in the overview section. +# Minimum value: 0, maximum value: 20, default value: 4. +# This tag requires that the tag GENERATE_HTML is set to YES. + +ENUM_VALUES_PER_LINE = 4 + +# If the treeview is enabled (see GENERATE_TREEVIEW) then this tag can be used +# to set the initial width (in pixels) of the frame in which the tree is shown. +# Minimum value: 0, maximum value: 1500, default value: 250. +# This tag requires that the tag GENERATE_HTML is set to YES. + +TREEVIEW_WIDTH = 250 + +# If the EXT_LINKS_IN_WINDOW option is set to YES, doxygen will open links to +# external symbols imported via tag files in a separate window. +# The default value is: NO. +# This tag requires that the tag GENERATE_HTML is set to YES. + +EXT_LINKS_IN_WINDOW = NO + +# If the HTML_FORMULA_FORMAT option is set to svg, doxygen will use the pdf2svg +# tool (see https://github.com/dawbarton/pdf2svg) or inkscape (see +# https://inkscape.org) to generate formulas as SVG images instead of PNGs for +# the HTML output. These images will generally look nicer at scaled resolutions. +# Possible values are: png (the default) and svg (looks nicer but requires the +# pdf2svg or inkscape tool). +# The default value is: png. +# This tag requires that the tag GENERATE_HTML is set to YES. + +HTML_FORMULA_FORMAT = png + +# Use this tag to change the font size of LaTeX formulas included as images in +# the HTML documentation. When you change the font size after a successful +# doxygen run you need to manually remove any form_*.png images from the HTML +# output directory to force them to be regenerated. +# Minimum value: 8, maximum value: 50, default value: 10. +# This tag requires that the tag GENERATE_HTML is set to YES. + +FORMULA_FONTSIZE = 10 + +# Use the FORMULA_TRANSPARENT tag to determine whether or not the images +# generated for formulas are transparent PNGs. Transparent PNGs are not +# supported properly for IE 6.0, but are supported on all modern browsers. +# +# Note that when changing this option you need to delete any form_*.png files in +# the HTML output directory before the changes have effect. +# The default value is: YES. +# This tag requires that the tag GENERATE_HTML is set to YES. + +FORMULA_TRANSPARENT = YES + +# The FORMULA_MACROFILE can contain LaTeX \newcommand and \renewcommand commands +# to create new LaTeX commands to be used in formulas as building blocks. See +# the section "Including formulas" for details. + +FORMULA_MACROFILE = + +# Enable the USE_MATHJAX option to render LaTeX formulas using MathJax (see +# https://www.mathjax.org) which uses client side JavaScript for the rendering +# instead of using pre-rendered bitmaps. Use this if you do not have LaTeX +# installed or if you want to formulas look prettier in the HTML output. When +# enabled you may also need to install MathJax separately and configure the path +# to it using the MATHJAX_RELPATH option. +# The default value is: NO. +# This tag requires that the tag GENERATE_HTML is set to YES. + +USE_MATHJAX = YES + +# When MathJax is enabled you can set the default output format to be used for +# the MathJax output. See the MathJax site (see: +# http://docs.mathjax.org/en/latest/output.html) for more details. +# Possible values are: HTML-CSS (which is slower, but has the best +# compatibility), NativeMML (i.e. MathML) and SVG. +# The default value is: HTML-CSS. +# This tag requires that the tag USE_MATHJAX is set to YES. + +MATHJAX_FORMAT = HTML-CSS + +# When MathJax is enabled you need to specify the location relative to the HTML +# output directory using the MATHJAX_RELPATH option. The destination directory +# should contain the MathJax.js script. For instance, if the mathjax directory +# is located at the same level as the HTML output directory, then +# MATHJAX_RELPATH should be ../mathjax. The default value points to the MathJax +# Content Delivery Network so you can quickly see the result without installing +# MathJax. However, it is strongly recommended to install a local copy of +# MathJax from https://www.mathjax.org before deployment. +# The default value is: https://cdn.jsdelivr.net/npm/mathjax@2. +# This tag requires that the tag USE_MATHJAX is set to YES. + +MATHJAX_RELPATH = http://cdn.mathjax.org/mathjax/latest + +# The MATHJAX_EXTENSIONS tag can be used to specify one or more MathJax +# extension names that should be enabled during MathJax rendering. For example +# MATHJAX_EXTENSIONS = TeX/AMSmath TeX/AMSsymbols +# This tag requires that the tag USE_MATHJAX is set to YES. + +MATHJAX_EXTENSIONS = + +# The MATHJAX_CODEFILE tag can be used to specify a file with javascript pieces +# of code that will be used on startup of the MathJax code. See the MathJax site +# (see: http://docs.mathjax.org/en/latest/output.html) for more details. For an +# example see the documentation. +# This tag requires that the tag USE_MATHJAX is set to YES. + +MATHJAX_CODEFILE = + +# When the SEARCHENGINE tag is enabled doxygen will generate a search box for +# the HTML output. The underlying search engine uses javascript and DHTML and +# should work on any modern browser. Note that when using HTML help +# (GENERATE_HTMLHELP), Qt help (GENERATE_QHP), or docsets (GENERATE_DOCSET) +# there is already a search function so this one should typically be disabled. +# For large projects the javascript based search engine can be slow, then +# enabling SERVER_BASED_SEARCH may provide a better solution. It is possible to +# search using the keyboard; to jump to the search box use + S +# (what the is depends on the OS and browser, but it is typically +# , /