CGH0S7
e157ea3a23
- 合并 chb-replace 分支，引入 bssn_rhs_c.C / fderivs_c.C / fdderivs_c.C / kodiss_c.C / lopsided_c.C 五个 C++ 算子实现 - 添加 USE_CXX_KERNELS 开关（默认 1），设为 0 可回退到原始 Fortran bssn_rhs.o - TwoPunctureABE 改用独立的 TwoPunctureABE.profdata 而非 default.profdata Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
32 lines
1.7 KiB
PHP
Executable File
32 lines
1.7 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 (Optimized for performance)
|
|
filein = -I/usr/include/ -I${MKLROOT}/include
|
|
|
|
## Using sequential MKL (OpenMP disabled for better single-threaded performance)
|
|
## Added -lifcore for Intel Fortran runtime and -limf for Intel math library
|
|
LDLIBS = -L${MKLROOT}/lib -lmkl_intel_lp64 -lmkl_sequential -lmkl_core -lifcore -limf -lpthread -lm -ldl -liomp5
|
|
|
|
## 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
|
|
|
|
## Kernel implementation switch
|
|
## 1 (default) : use C++ rewrite of bssn_rhs and helper kernels (faster)
|
|
## 0 : fall back to original Fortran kernels
|
|
USE_CXX_KERNELS ?= 1
|
|
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
|