Merge cjy-oneapi-opus-hotfix into main

AMSS_NCKU_source/makefile.inc

@@ -1,19 +1,30 @@
-
+## 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
 
-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/
+## Intel oneAPI version with oneMKL (Optimized for performance)
+filein  = -I/usr/include/ -I${MKLROOT}/include
 
-## LDLIBS  = -L/usr/lib/x86_64-linux-gnu -lmpich -L/usr/lib64 -L/usr/lib/gcc/x86_64-linux-gnu/11 -lgfortran
-LDLIBS  = -L/usr/lib/x86_64-linux-gnu -L/usr/lib64 -L/usr/lib/gcc/x86_64-linux-gnu/11 -lgfortran -lmpi -lgfortran
+## 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
 
-CXXAPPFLAGS  = -O0 -Wno-deprecated -Dfortran3 -Dnewc
-#f90appflags = -O0 -fpp
-f90appflags  = -O0 -x f95-cpp-input
-f90          = gfortran 
-f77          = gfortran 
-CXX          = g++
-CC           = gcc
-CLINKER      = mpic++ 
+## 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 -xHost -fp-model fast=2 -fma -ipo \
+               -fprofile-instr-use=$(PROFDATA) \
+               -Dfortran3 -Dnewc -I${MKLROOT}/include
+f90appflags  = -O3 -xHost -fp-model fast=2 -fma -ipo \
+               -fprofile-instr-use=$(PROFDATA) \
+               -align array64byte -fpp -I${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