cb252f5ea2
- FFT.f90: Replace hand-written Cooley-Tukey FFT with oneMKL DFTI - ilucg.f90: Replace manual dot product loop with BLAS DDOT - gaussj.C: Replace Gauss-Jordan elimination with LAPACK dgesv/dgetri - makefile.inc: Add MKL include paths and library linking All optimizations maintain mathematical equivalence and numerical precision.
24 lines
1.2 KiB
PHP
Executable File
24 lines
1.2 KiB
PHP
Executable File
## 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
|
|
|
|
## Intel oneAPI version with oneMKL
|
|
filein = -I/usr/include/ -I${MKLROOT}/include
|
|
|
|
LDLIBS = -L/usr/lib/x86_64-linux-gnu -L/usr/lib64 -lifcore -limf -lmpi \
|
|
-L${MKLROOT}/lib -lmkl_intel_lp64 -lmkl_sequential -lmkl_core -lpthread -lm -ldl
|
|
|
|
CXXAPPFLAGS = -O3 -Dfortran3 -Dnewc -I${MKLROOT}/include
|
|
f90appflags = -O3 -fpp -I${MKLROOT}/include
|
|
f90 = ifx
|
|
f77 = ifx
|
|
CXX = icpx
|
|
CC = icx
|
|
CLINKER = mpiicpx
|
|
|
|
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
|