64-BitBrainstorm_2026/AMSS-NCKU
8
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Switch legacy build to GCC and OpenMPI

Browse Source
This commit is contained in:
CGH0S7
2026-04-13 19:39:30 +08:00
parent 9c31384b2f
commit 3f3f16e881
7 changed files with 224 additions and 186 deletions
Download Patch File Download Diff File Expand all files Collapse all files

56
AMSS_NCKU_source/makefile.inc Executable file → Normal file
View File

@@ -1,33 +1,27 @@
## GCC version (commented out)
## filein = -I/usr/include -I/usr/lib/x86_64-linux-gnu/mpich/include -I/usr/lib/x86_64-linux-gnu/openmpi/lib/ -I/usr/lib/gcc/x86_64-linux-gnu/11/ -I/usr/include/c++/11/
## filein = -I/usr/include/ -I/usr/include/openmpi-x86_64/ -I/usr/lib/x86_64-linux-gnu/openmpi/include/ -I/usr/lib/x86_64-linux-gnu/openmpi/lib/ -I/usr/lib/gcc/x86_64-linux-gnu/11/ -I/usr/include/c++/11/
## LDLIBS = -L/usr/lib/x86_64-linux-gnu -L/usr/lib64 -L/usr/lib/gcc/x86_64-linux-gnu/11 -lgfortran -lmpi -lgfortran
## Legacy GNU/OpenMPI toolchain configuration
## Intel oneAPI version with oneMKL (Optimized for performance)
filein = -I/usr/include/ -I${MKLROOT}/include
## OpenMPI wrappers are installed but may not be on PATH.
OMPI_BIN ?= /usr/lib64/openmpi/bin
## Using sequential MKL (OpenMP disabled for better single-threaded performance)
## Added -lifcore for Intel Fortran runtime and -limf for Intel math library
LDLIBS = -L${MKLROOT}/lib -lmkl_intel_lp64 -lmkl_sequential -lmkl_core -lifcore -limf -lpthread -lm -ldl -liomp5
## Wrapper compilers
f90 = $(OMPI_BIN)/mpifort
f77 = $(OMPI_BIN)/mpifort
CXX = $(OMPI_BIN)/mpicxx
CC = $(OMPI_BIN)/mpicc
CLINKER = $(OMPI_BIN)/mpicxx
## Memory allocator switch
## 1 (default) : link Intel oneTBB allocator (libtbbmalloc)
## 0 : use system default allocator (ptmalloc)
USE_TBBMALLOC ?= 1
TBBMALLOC_SO ?= /home/intel/oneapi/2025.3/lib/libtbbmalloc.so
ifneq ($(wildcard $(TBBMALLOC_SO)),)
TBBMALLOC_LIBS = -Wl,--no-as-needed $(TBBMALLOC_SO) -Wl,--as-needed
else
TBBMALLOC_LIBS = -Wl,--no-as-needed -ltbbmalloc -Wl,--as-needed
endif
ifeq ($(USE_TBBMALLOC),1)
LDLIBS := $(TBBMALLOC_LIBS) $(LDLIBS)
endif
## Extra include flags are not needed when using the OpenMPI wrappers.
filein =
## PGO build mode switch (ABE only; TwoPunctureABE always uses opt flags)
## opt : (default) maximum performance with PGO profile-guided optimization
## instrument : PGO Phase 1 instrumentation to collect fresh profile data
PGO_MODE ?= opt
## BLAS/LAPACK backend:
## OpenBLAS on this system provides BLAS, CBLAS and LAPACK symbols.
BLAS_LAPACK_LIB ?= /lib64/libopenblaso.so.0
LDLIBS = $(BLAS_LAPACK_LIB) -lgfortran -lpthread -lm -ldl
## PGO build mode switch
## off : default legacy GNU build without PGO
## instrument : accepted for compatibility, currently same as off
PGO_MODE ?= off
## Interp_Points load balance profiling mode
## off : (default) no load balance instrumentation
@@ -49,17 +43,13 @@ endif
USE_CXX_KERNELS ?= 1
## RK4 kernel implementation switch
## 1 (default) : use C/C++ rewrite of rungekutta4_rout (for optimization experiments)
## 1 (default) : use C/C++ rewrite of rungekutta4_rout
## 0 : use original Fortran rungekutta4_rout.o
USE_CXX_RK4 ?= 1
f90 = ifx
f77 = ifx
CXX = icpx
CC = icx
CLINKER = mpiicpx
## OpenMP is only used for TwoPunctures on the legacy toolchain.
TP_OPENMP_FLAGS ?= -fopenmp
Cu = nvcc
CUDA_LIB_PATH = -L/usr/lib/cuda/lib64 -I/usr/include -I/usr/lib/cuda/include
#CUDA_APP_FLAGS = -c -g -O3 --ptxas-options=-v -arch compute_13 -code compute_13,sm_13 -Dfortran3 -Dnewc
CUDA_APP_FLAGS = -c -g -O3 --ptxas-options=-v -Dfortran3 -Dnewc