64-BitBrainstorm_2026/AMSS-NCKU
8
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Switch legacy build to GCC and OpenMPI

Browse Source
This commit is contained in:
CGH0S7
2026-04-13 19:39:30 +08:00
parent 9c31384b2f
commit 3f3f16e881
7 changed files with 224 additions and 186 deletions
Download Patch File Download Diff File Expand all files Collapse all files

52
AMSS_NCKU_source/makefile
View File

@@ -8,27 +8,16 @@ include makefile.inc
POLINT6_USE_BARY ?= 1
POLINT6_FLAG = -DPOLINT6_USE_BARYCENTRIC=$(POLINT6_USE_BARY)
## ABE build flags selected by PGO_MODE (set in makefile.inc, default: opt)
## make -> opt (PGO-guided, maximum performance)
## make PGO_MODE=instrument -> instrument (Phase 1: collect fresh profile data)
PROFDATA = /home/$(shell whoami)/AMSS-NCKU/pgo_profile/default.profdata
ifeq ($(PGO_MODE),instrument)
## Phase 1: instrumentation — omit -ipo/-fp-model fast=2 for faster build and numerical stability
CXXAPPFLAGS = -O3 -xHost -fma -fprofile-instr-generate -ipo \
-Dfortran3 -Dnewc -I${MKLROOT}/include $(INTERP_LB_FLAGS)
f90appflags = -O3 -xHost -fma -fprofile-instr-generate -ipo \
-align array64byte -fpp -I${MKLROOT}/include $(POLINT6_FLAG)
## Legacy GNU/OpenMPI flags
CXXBASEFLAGS = -O3 -march=native -Wno-deprecated -Dfortran3 -Dnewc $(INTERP_LB_FLAGS)
F90BASEFLAGS = -O3 -march=native -cpp -fallow-argument-mismatch $(POLINT6_FLAG)
ifeq ($(PGO_MODE),instrument)
CXXAPPFLAGS = $(CXXBASEFLAGS)
f90appflags = $(F90BASEFLAGS)
else
## opt (default): maximum performance with PGO profile data -fprofile-instr-use=$(PROFDATA) \
## PGO has been turned off, now tested and found to be negative optimization
## INTERP_LB_FLAGS has been turned off too, now tested and found to be negative optimization
CXXAPPFLAGS = -O3 -xHost -fp-model fast=2 -fma -ipo \
-Dfortran3 -Dnewc -I${MKLROOT}/include $(INTERP_LB_FLAGS)
f90appflags = -O3 -xHost -fp-model fast=2 -fma -ipo \
-align array64byte -fpp -I${MKLROOT}/include $(POLINT6_FLAG)
CXXAPPFLAGS = $(CXXBASEFLAGS)
f90appflags = $(F90BASEFLAGS)
endif
.SUFFIXES: .o .f90 .C .for .cu
@@ -67,17 +56,14 @@ lopsided_kodis_c.o: lopsided_kodis_c.C
#interp_lb_profile.o: interp_lb_profile.C interp_lb_profile.h
# ${CXX} $(CXXAPPFLAGS) -c $< $(filein) -o $@
## TwoPunctureABE uses fixed optimal flags with its own PGO profile, independent of CXXAPPFLAGS
TP_PROFDATA = /home/$(shell whoami)/AMSS-NCKU/pgo_profile/TwoPunctureABE.profdata
TP_OPTFLAGS = -O3 -xHost -fp-model fast=2 -fma -ipo \
-fprofile-instr-use=$(TP_PROFDATA) \
-Dfortran3 -Dnewc -I${MKLROOT}/include
TwoPunctures.o: TwoPunctures.C
${CXX} $(TP_OPTFLAGS) -qopenmp -c $< -o $@
TwoPunctureABE.o: TwoPunctureABE.C
${CXX} $(TP_OPTFLAGS) -qopenmp -c $< -o $@
## TwoPunctureABE uses fixed optimal flags with its own PGO profile, independent of CXXAPPFLAGS
TP_OPTFLAGS = $(CXXBASEFLAGS) $(TP_OPENMP_FLAGS)
TwoPunctures.o: TwoPunctures.C
${CXX} $(TP_OPTFLAGS) -c $< -o $@
TwoPunctureABE.o: TwoPunctureABE.C
${CXX} $(TP_OPTFLAGS) -c $< -o $@
# Input files
@@ -184,8 +170,8 @@ ABE: $(C++FILES) $(CFILES) $(F90FILES) $(F77FILES) $(AHFDOBJS)
ABEGPU: $(C++FILES_GPU) $(CFILES) $(F90FILES) $(F77FILES) $(AHFDOBJS) $(CUDAFILES)
$(CLINKER) $(CXXAPPFLAGS) -o $@ $(C++FILES_GPU) $(CFILES) $(F90FILES) $(F77FILES) $(AHFDOBJS) $(CUDAFILES) $(LDLIBS)
TwoPunctureABE: $(TwoPunctureFILES)
$(CLINKER) $(TP_OPTFLAGS) -qopenmp -o $@ $(TwoPunctureFILES) $(LDLIBS)
TwoPunctureABE: $(TwoPunctureFILES)
$(CLINKER) $(TP_OPTFLAGS) -o $@ $(TwoPunctureFILES) $(LDLIBS)
clean:
rm *.o ABE ABEGPU TwoPunctureABE make.log -f