更新 PGO profdata 并为 ABE 插桩编译添加 PGO_MODE 开关

- 更新 pgo_profile/default.profdata 为最新收集的 profile 数据
- 备份旧 profdata 至 default.profdata.backup2
- makefile: 新增 PGO_MODE 开关（默认 opt），支持 make PGO_MODE=instrument
  切换到 Phase 1 插桩模式重新收集数据，无需手动修改 flags
- makefile: TwoPunctureABE 独立使用 TP_OPTFLAGS，不受 PGO_MODE 影响
- makefile: PROFDATA 路径改为 /home/$(shell whoami)/AMSS-NCKU/pgo_profile/default.profdata
- makefile.inc: 移除硬编码的编译 flags，改由 makefile 中的 ifeq 逻辑管理

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

AMSS_NCKU_source/makefile

@@ -2,6 +2,27 @@
 
 include makefile.inc
 
+## ABE build flags selected by PGO_MODE (set in makefile.inc, default: opt)
+##   make                        -> opt  (PGO-guided, maximum performance)
+##   make PGO_MODE=instrument    -> instrument (Phase 1: collect fresh profile data)
+PROFDATA = /home/$(shell whoami)/AMSS-NCKU/pgo_profile/default.profdata
+
+ifeq ($(PGO_MODE),instrument)
+## Phase 1: instrumentation — omit -ipo/-fp-model fast=2 for faster build and numerical stability
+CXXAPPFLAGS = -O2 -xHost -fma -fprofile-instr-generate \
+              -Dfortran3 -Dnewc -I${MKLROOT}/include
+f90appflags = -O2 -xHost -fma -fprofile-instr-generate \
+              -align array64byte -fpp -I${MKLROOT}/include
+else
+## opt (default): maximum performance with PGO profile data
+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
+endif
+
 .SUFFIXES: .o .f90 .C .for .cu
 
 .f90.o:
@@ -16,11 +37,14 @@ include makefile.inc
 .cu.o:
 	$(Cu) $(CUDA_APP_FLAGS) -c $< -o $@ $(CUDA_LIB_PATH)
 
+## TwoPunctureABE uses fixed optimal flags, independent of CXXAPPFLAGS (which may be PGO-instrumented)
+TP_OPTFLAGS = -O3 -xHost -fp-model fast=2 -fma -ipo -Dfortran3 -Dnewc -I${MKLROOT}/include
+
 TwoPunctures.o: TwoPunctures.C
-	${CXX} $(CXXAPPFLAGS) -qopenmp -c $< -o $@
+	${CXX} $(TP_OPTFLAGS) -qopenmp -c $< -o $@
 
 TwoPunctureABE.o: TwoPunctureABE.C
-	${CXX} $(CXXAPPFLAGS) -qopenmp -c $< -o $@
+	${CXX} $(TP_OPTFLAGS) -qopenmp -c $< -o $@
 
 # Input files
 C++FILES = ABE.o Ansorg.o Block.o misc.o monitor.o Parallel.o MPatch.o var.o\
@@ -102,7 +126,7 @@ ABEGPU: $(C++FILES_GPU) $(F90FILES) $(F77FILES) $(AHFDOBJS) $(CUDAFILES)
 	$(CLINKER) $(CXXAPPFLAGS) -o $@ $(C++FILES_GPU) $(F90FILES) $(F77FILES) $(AHFDOBJS) $(CUDAFILES) $(LDLIBS)
 
 TwoPunctureABE: $(TwoPunctureFILES)
-	$(CLINKER) $(CXXAPPFLAGS) -qopenmp -o $@ $(TwoPunctureFILES) $(LDLIBS)
+	$(CLINKER) $(TP_OPTFLAGS) -qopenmp -o $@ $(TwoPunctureFILES) $(LDLIBS)
 
 clean:
 	rm *.o ABE ABEGPU TwoPunctureABE make.log -f