75be0968fc
Major changes: - Update makefile.inc for CUDA 13.1 with sm_89 architecture (RTX 4050) - Replace deprecated cudaThreadSynchronize() with cudaDeviceSynchronize() - Add CUDA_SAFE_CALL macro for CUDA 13 compatibility - Fix duplicate function definitions (compare_result_gpu, SHStep) - Fix syntax error in bssn_step_gpu.C - Enable GPU calculation in AMSS_NCKU_Input.py - Successfully build ABEGPU executable
23 lines
1.2 KiB
PHP
Executable File
23 lines
1.2 KiB
PHP
Executable File
|
|
filein = -I/usr/include -I/usr/include/openmpi-x86_64 -I/usr/lib/gcc/x86_64-linux-gnu/11/ -I/usr/include/c++/11/
|
|
|
|
##filein = -I/usr/include/ -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/ -I/usr/lib/cuda/include
|
|
|
|
LDLIBS = -L/usr/lib64/openmpi/lib -Wl,-rpath,/usr/lib64/openmpi/lib -lmpi -lgfortran -L/usr/local/cuda-13.1/lib64 -Wl,-rpath,/usr/local/cuda-13.1/lib64 -lcudart -lcuda
|
|
##LDLIBS = -L/usr/lib/x86_64-linux-gnu -L/usr/lib64 -L/usr/lib/gcc/x86_64-linux-gnu/11 -lgfortran -L/usr/lib/cuda/lib64 -lcudart -lmpi -lgfortran
|
|
|
|
CXXAPPFLAGS = -O3 -Wno-deprecated -Dfortran3 -Dnewc
|
|
#f90appflags = -O3 -fpp
|
|
f90appflags = -O3 -x f95-cpp-input
|
|
f90 = gfortran
|
|
f77 = gfortran
|
|
CXX = g++
|
|
CC = gcc
|
|
CLINKER = mpic++
|
|
|
|
Cu = /usr/local/cuda-13.1/bin/nvcc
|
|
CUDA_LIB_PATH = -L/usr/local/cuda-13.1/lib64 -I/usr/include -I/usr/local/cuda-13.1/include
|
|
#CUDA_APP_FLAGS = -c -g -O3 --ptxas-options=-v -arch compute_13 -code compute_13,sm_13 -Dfortran3 -Dnewc
|
|
# RTX 4050 uses Ada Lovelace architecture (compute capability 8.9)
|
|
CUDA_APP_FLAGS = -c -g -O3 --ptxas-options=-v -arch=sm_89 -Dfortran3 -Dnewc
|