CGH0S7
714c6e90c6
Add !$omp parallel do collapse(2) directives to all triple-loop stencil kernels (fderivs, fdderivs, fdx/fdy/fdz, kodis, lopsided, enforce_ag/enforce_ga) across all ghost_width variants. Add !$omp parallel workshare to RK4/ICN/Euler whole-array update routines. Build system: add -qopenmp to compile and link flags, switch MKL from sequential to threaded (-lmkl_intel_thread -liomp5). Runtime: set OMP_NUM_THREADS=96, OMP_STACKSIZE=16M, OMP_PROC_BIND=close, OMP_PLACES=cores for 96-core server target. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
31 lines
1.8 KiB
PHP
Executable File
31 lines
1.8 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${MKLROOT}/include
|
|
|
|
## Using OpenMP-threaded MKL for parallel performance
|
|
## Added -lifcore for Intel Fortran runtime and -limf for Intel math library
|
|
LDLIBS = -L${MKLROOT}/lib -lmkl_intel_lp64 -lmkl_intel_thread -lmkl_core -liomp5 -lifcore -limf -lpthread -lm -ldl
|
|
|
|
## Aggressive optimization flags + PGO Phase 2 (profile-guided optimization)
|
|
## -fprofile-instr-use: use collected profile data to guide optimization decisions
|
|
## (branch prediction, basic block layout, inlining, loop unrolling)
|
|
PROFDATA = /home/amss/AMSS-NCKU/pgo_profile/default.profdata
|
|
CXXAPPFLAGS = -O3 -march=native -fp-model fast=2 -fma -ipo -qopenmp \
|
|
-DMPI_STUB -Dfortran3 -Dnewc -I${MKLROOT}/include
|
|
f90appflags = -O3 -march=native -fp-model fast=2 -fma -ipo -qopenmp \
|
|
-align array64byte -fpp -I${MKLROOT}/include
|
|
f90 = ifx
|
|
f77 = ifx
|
|
CXX = icpx
|
|
CC = icx
|
|
CLINKER = icpx
|
|
|
|
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
|