Add C implementations of shell-patch derivative kernels (WithShell support)
New files provide C equivalents of Fortran diff_new_sh.f90 and kodiss_sh.f90: - fderivs_sh_c.C: first derivatives in shell (rho, sigma, R) coords - fdderivs_sh_c.C: second derivatives in shell coords - fderivs_shc_c.C: shell first derivs + chain rule to Cartesian - fdderivs_shc_c.C: shell second derivs + chain rule to Cartesian - kodiss_sh_c.C: Kreiss-Oliger dissipation on shell patches Also add symmetry_stbd() C implementation and shell fh indexing to share_func.h. Controlled by USE_CXX_SHELL_KERNELS switch (default 0, experimental). Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
@@ -1,5 +1,5 @@
|
||||
|
||||
|
||||
|
||||
|
||||
include makefile.inc
|
||||
|
||||
-include AMSS_NCKU_build.mk
|
||||
@@ -44,9 +44,9 @@ ESCALAR_KERNEL_FLAG = -DBSSN_USE_ESCALAR_C_KERNEL=$(EFFECTIVE_USE_CXX_ESCALAR_KE
|
||||
## make -> opt (PGO-guided, maximum performance)
|
||||
## make PGO_MODE=instrument -> instrument (Phase 1: collect fresh profile data)
|
||||
PROFDATA = /home/$(shell whoami)/AMSS-NCKU/pgo_profile/default.profdata
|
||||
|
||||
ifeq ($(PGO_MODE),instrument)
|
||||
## Phase 1: instrumentation — omit -ipo/-fp-model fast=2 for faster build and numerical stability
|
||||
|
||||
ifeq ($(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) \
|
||||
$(TRANSFER_CACHE_FLAG) $(ESCALAR_KERNEL_FLAG)
|
||||
@@ -64,65 +64,81 @@ CXXAPPFLAGS = -O3 -xHost -fp-model fast=2 -fma -ipo \
|
||||
f90appflags = -O3 -xHost -fp-model fast=2 -fma -ipo \
|
||||
-align array64byte -fpp -I${MKLROOT}/include $(POLINT6_FLAG)
|
||||
endif
|
||||
|
||||
.SUFFIXES: .o .f90 .C .for .cu
|
||||
|
||||
.f90.o:
|
||||
$(f90) $(f90appflags) -c $< -o $@
|
||||
|
||||
.C.o:
|
||||
${CXX} $(CXXAPPFLAGS) -c $< $(filein) -o $@
|
||||
|
||||
# ShellPatch.C uses OpenMP for setupintintstuff search loops
|
||||
ShellPatch.o: ShellPatch.C
|
||||
${CXX} $(CXXAPPFLAGS) $(OMP_FLAG) -c $< $(filein) -o $@
|
||||
|
||||
.for.o:
|
||||
$(f77) -c $< -o $@
|
||||
|
||||
.cu.o:
|
||||
$(Cu) $(CUDA_APP_FLAGS) -c $< -o $@ $(CUDA_LIB_PATH)
|
||||
|
||||
# C rewrite of BSSN RHS kernel and helpers
|
||||
|
||||
.SUFFIXES: .o .f90 .C .for .cu
|
||||
|
||||
.f90.o:
|
||||
$(f90) $(f90appflags) -c $< -o $@
|
||||
|
||||
.C.o:
|
||||
${CXX} $(CXXAPPFLAGS) -c $< $(filein) -o $@
|
||||
|
||||
# ShellPatch.C uses OpenMP for setupintintstuff search loops
|
||||
ShellPatch.o: ShellPatch.C
|
||||
${CXX} $(CXXAPPFLAGS) $(OMP_FLAG) -c $< $(filein) -o $@
|
||||
|
||||
.for.o:
|
||||
$(f77) -c $< -o $@
|
||||
|
||||
.cu.o:
|
||||
$(Cu) $(CUDA_APP_FLAGS) -c $< -o $@ $(CUDA_LIB_PATH)
|
||||
|
||||
# C rewrite of BSSN RHS kernel and helpers
|
||||
bssn_rhs_c.o: bssn_rhs_c.C
|
||||
${CXX} $(CXXAPPFLAGS) -c $< $(filein) -o $@
|
||||
|
||||
fderivs_c.o: fderivs_c.C
|
||||
${CXX} $(CXXAPPFLAGS) -c $< $(filein) -o $@
|
||||
|
||||
fdderivs_c.o: fdderivs_c.C
|
||||
${CXX} $(CXXAPPFLAGS) -c $< $(filein) -o $@
|
||||
|
||||
kodiss_c.o: kodiss_c.C
|
||||
${CXX} $(CXXAPPFLAGS) -c $< $(filein) -o $@
|
||||
|
||||
|
||||
fdderivs_c.o: fdderivs_c.C
|
||||
${CXX} $(CXXAPPFLAGS) -c $< $(filein) -o $@
|
||||
|
||||
kodiss_c.o: kodiss_c.C
|
||||
${CXX} $(CXXAPPFLAGS) -c $< $(filein) -o $@
|
||||
|
||||
lopsided_c.o: lopsided_c.C
|
||||
${CXX} $(CXXAPPFLAGS) -c $< $(filein) -o $@
|
||||
|
||||
lopsided_kodis_c.o: lopsided_kodis_c.C
|
||||
${CXX} $(CXXAPPFLAGS) -c $< $(filein) -o $@
|
||||
|
||||
# C rewrite of shell-patch derivative kernels
|
||||
fderivs_sh_c.o: fderivs_sh_c.C
|
||||
${CXX} $(CXXAPPFLAGS) -c $< $(filein) -o $@
|
||||
|
||||
fdderivs_sh_c.o: fdderivs_sh_c.C
|
||||
${CXX} $(CXXAPPFLAGS) -c $< $(filein) -o $@
|
||||
|
||||
fderivs_shc_c.o: fderivs_shc_c.C
|
||||
${CXX} $(CXXAPPFLAGS) -c $< $(filein) -o $@
|
||||
|
||||
fdderivs_shc_c.o: fdderivs_shc_c.C
|
||||
${CXX} $(CXXAPPFLAGS) -c $< $(filein) -o $@
|
||||
|
||||
kodiss_sh_c.o: kodiss_sh_c.C
|
||||
${CXX} $(CXXAPPFLAGS) -c $< $(filein) -o $@
|
||||
|
||||
z4c_rhs_c.o: z4c_rhs_c.C
|
||||
${CXX} $(CXXAPPFLAGS) -c $< $(filein) -o $@
|
||||
|
||||
#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 $@
|
||||
|
||||
# Input files
|
||||
|
||||
## Kernel implementation switch (set USE_CXX_KERNELS=0 to fall back to Fortran)
|
||||
|
||||
## TwoPunctureABE uses fixed optimal flags with its own PGO profile, independent of CXXAPPFLAGS
|
||||
TP_PROFDATA = /home/$(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 $@
|
||||
|
||||
# Input files
|
||||
|
||||
## Kernel implementation switch (set USE_CXX_KERNELS=0 to fall back to Fortran)
|
||||
ifeq ($(USE_CXX_KERNELS),0)
|
||||
# Fortran mode: no C rewrite files; bssn_rhs.o is included via F90FILES below
|
||||
CFILES =
|
||||
@@ -148,95 +164,106 @@ RK4_F90_OBJ =
|
||||
else
|
||||
RK4_F90_OBJ = rungekutta4_rout.o
|
||||
endif
|
||||
|
||||
C++FILES = ABE.o Ansorg.o Block.o misc.o monitor.o Parallel.o MPatch.o var.o\
|
||||
cgh.o bssn_class.o surface_integral.o ShellPatch.o\
|
||||
bssnEScalar_class.o perf.o Z4c_class.o NullShellPatch.o\
|
||||
bssnEM_class.o cpbc_util.o z4c_rhs_point.o checkpoint.o\
|
||||
Parallel_bam.o scalar_class.o transpbh.o NullShellPatch2.o\
|
||||
NullShellPatch2_Evo.o writefile_f.o interp_lb_profile.o
|
||||
|
||||
C++FILES_GPU = ABE.o Ansorg.o Block.o misc.o monitor.o Parallel.o MPatch.o var.o\
|
||||
cgh.o surface_integral.o ShellPatch.o\
|
||||
bssnEScalar_class.o perf.o Z4c_class.o NullShellPatch.o\
|
||||
bssnEM_class.o cpbc_util.o z4c_rhs_point.o checkpoint.o\
|
||||
Parallel_bam.o scalar_class.o transpbh.o NullShellPatch2.o\
|
||||
NullShellPatch2_Evo.o \
|
||||
bssn_gpu_class.o bssn_step_gpu.o bssn_macro.o writefile_f.o
|
||||
|
||||
|
||||
## Shell-patch derivative kernel switch (independent from USE_CXX_KERNELS)
|
||||
## 1 : use C++ rewrite of shell derivative functions (experimental)
|
||||
## 0 : use original Fortran diff_new_sh.o and kodiss_sh.o (default)
|
||||
USE_CXX_SHELL_KERNELS ?= 0
|
||||
ifeq ($(USE_CXX_SHELL_KERNELS),1)
|
||||
CFILES += fderivs_sh_c.o fdderivs_sh_c.o fderivs_shc_c.o fdderivs_shc_c.o kodiss_sh_c.o
|
||||
SH_F90_OBJ =
|
||||
else
|
||||
SH_F90_OBJ = diff_new_sh.o kodiss_sh.o point_diff_new_sh.o
|
||||
endif
|
||||
|
||||
C++FILES = ABE.o Ansorg.o Block.o misc.o monitor.o Parallel.o MPatch.o var.o\
|
||||
cgh.o bssn_class.o surface_integral.o ShellPatch.o\
|
||||
bssnEScalar_class.o perf.o Z4c_class.o NullShellPatch.o\
|
||||
bssnEM_class.o cpbc_util.o z4c_rhs_point.o checkpoint.o\
|
||||
Parallel_bam.o scalar_class.o transpbh.o NullShellPatch2.o\
|
||||
NullShellPatch2_Evo.o writefile_f.o interp_lb_profile.o
|
||||
|
||||
C++FILES_GPU = ABE.o Ansorg.o Block.o misc.o monitor.o Parallel.o MPatch.o var.o\
|
||||
cgh.o surface_integral.o ShellPatch.o\
|
||||
bssnEScalar_class.o perf.o Z4c_class.o NullShellPatch.o\
|
||||
bssnEM_class.o cpbc_util.o z4c_rhs_point.o checkpoint.o\
|
||||
Parallel_bam.o scalar_class.o transpbh.o NullShellPatch2.o\
|
||||
NullShellPatch2_Evo.o \
|
||||
bssn_gpu_class.o bssn_step_gpu.o bssn_macro.o writefile_f.o
|
||||
|
||||
F90FILES_BASE = enforce_algebra.o fmisc.o initial_puncture.o prolongrestrict.o\
|
||||
prolongrestrict_cell.o prolongrestrict_vertex.o\
|
||||
$(RK4_F90_OBJ) diff_new.o kodiss.o kodiss_sh.o\
|
||||
lopsidediff.o sommerfeld_rout.o getnp4.o diff_new_sh.o\
|
||||
$(RK4_F90_OBJ) diff_new.o kodiss.o\
|
||||
lopsidediff.o sommerfeld_rout.o getnp4.o $(SH_F90_OBJ)\
|
||||
shellfunctions.o bssn_rhs_ss.o Set_Rho_ADM.o\
|
||||
getnp4EScalar.o bssnEScalar_rhs.o bssn_constraint.o ricci_gamma.o\
|
||||
fadmquantites_bssn.o $(Z4C_F90_OBJ) Z4c_rhs_ss.o point_diff_new_sh.o\
|
||||
fadmquantites_bssn.o $(Z4C_F90_OBJ) Z4c_rhs_ss.o\
|
||||
cpbc.o getnp4old.o NullEvol.o initial_null.o initial_maxwell.o\
|
||||
getnpem2.o empart.o NullNews.o fourdcurvature.o\
|
||||
bssn2adm.o adm_constraint.o adm_ricci_gamma.o\
|
||||
scalar_rhs.o initial_scalar.o NullEvol2.o initial_null2.o\
|
||||
NullNews2.o tool_f.o
|
||||
|
||||
ifeq ($(USE_CXX_KERNELS),0)
|
||||
# Fortran mode: include original bssn_rhs.o
|
||||
F90FILES = $(F90FILES_BASE) bssn_rhs.o
|
||||
else
|
||||
# C++ mode (default): bssn_rhs.o replaced by C++ kernel
|
||||
F90FILES = $(F90FILES_BASE)
|
||||
endif
|
||||
|
||||
F77FILES = zbesh.o
|
||||
|
||||
AHFDOBJS = expansion.o expansion_Jacobian.o patch.o coords.o patch_info.o patch_interp.o patch_system.o \
|
||||
tgrid.o fd_grid.o ghost_zone.o array.o round.o norm.o fuzzy.o error_exit.o miscfp.o \
|
||||
linear_map.o cpm_map.o BH_diagnostics.o setup.o horizon_sequence.o find_horizons.o \
|
||||
initial_guess.o Newton.o Jacobian.o ilucg.o IntPnts0.o IntPnts.o
|
||||
|
||||
TwoPunctureFILES = TwoPunctureABE.o TwoPunctures.o
|
||||
|
||||
CUDAFILES = bssn_gpu.o bssn_gpu_rhs_ss.o
|
||||
|
||||
# file dependences
|
||||
$(C++FILES) $(C++FILES_GPU) $(F90FILES) $(CFILES) $(AHFDOBJS) $(CUDAFILES): macrodef.fh
|
||||
|
||||
$(C++FILES): Block.h enforce_algebra.h fmisc.h initial_puncture.h macrodef.h\
|
||||
misc.h monitor.h MyList.h Parallel.h MPatch.h prolongrestrict.h\
|
||||
rungekutta4_rout.h var.h bssn_class.h bssn_rhs.h sommerfeld_rout.h\
|
||||
cgh.h surface_integral.h ShellPatch.h shellfunctions.h perf.h\
|
||||
fadmquantites_bssn.h cpbc.h getnp4.h initial_null.h NullEvol.h\
|
||||
NullShellPatch.h initial_maxwell.h bssnEM_class.h getnpem2.h\
|
||||
empart.h NullNews.h kodiss.h Parallel_bam.h ricci_gamma.h\
|
||||
initial_null2.h NullShellPatch2.h
|
||||
|
||||
$(C++FILES_GPU): Block.h enforce_algebra.h fmisc.h initial_puncture.h macrodef.h\
|
||||
misc.h monitor.h MyList.h Parallel.h MPatch.h prolongrestrict.h\
|
||||
rungekutta4_rout.h var.h bssn_rhs.h sommerfeld_rout.h\
|
||||
cgh.h surface_integral.h ShellPatch.h shellfunctions.h perf.h\
|
||||
fadmquantites_bssn.h cpbc.h getnp4.h initial_null.h NullEvol.h\
|
||||
NullShellPatch.h initial_maxwell.h bssnEM_class.h getnpem2.h\
|
||||
empart.h NullNews.h kodiss.h Parallel_bam.h ricci_gamma.h\
|
||||
initial_null2.h NullShellPatch2.h \
|
||||
bssn_gpu_class.h bssn_macro.h
|
||||
|
||||
$(AHFDOBJS): cctk.h cctk_Config.h cctk_Types.h cctk_Constants.h myglobal.h
|
||||
|
||||
$(C++FILES) $(C++FILES_GPU) $(CFILES) $(AHFDOBJS) $(CUDAFILES): macrodef.h
|
||||
|
||||
TwoPunctureFILES: TwoPunctures.h
|
||||
|
||||
$(CUDAFILES): bssn_gpu.h gpu_mem.h gpu_rhsSS_mem.h
|
||||
|
||||
misc.o : zbesh.o
|
||||
|
||||
# projects
|
||||
ABE: $(C++FILES) $(CFILES) $(F90FILES) $(F77FILES) $(AHFDOBJS)
|
||||
$(CLINKER) $(CXXAPPFLAGS) -o $@ $(C++FILES) $(CFILES) $(F90FILES) $(F77FILES) $(AHFDOBJS) $(LDLIBS)
|
||||
|
||||
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) $(LDLIBS)
|
||||
|
||||
clean:
|
||||
rm *.o ABE ABEGPU TwoPunctureABE make.log -f
|
||||
scalar_rhs.o initial_scalar.o NullEvol2.o initial_null2.o\
|
||||
NullNews2.o tool_f.o
|
||||
|
||||
ifeq ($(USE_CXX_KERNELS),0)
|
||||
# Fortran mode: include original bssn_rhs.o
|
||||
F90FILES = $(F90FILES_BASE) bssn_rhs.o
|
||||
else
|
||||
# C++ mode (default): bssn_rhs.o replaced by C++ kernel
|
||||
F90FILES = $(F90FILES_BASE)
|
||||
endif
|
||||
|
||||
F77FILES = zbesh.o
|
||||
|
||||
AHFDOBJS = expansion.o expansion_Jacobian.o patch.o coords.o patch_info.o patch_interp.o patch_system.o \
|
||||
tgrid.o fd_grid.o ghost_zone.o array.o round.o norm.o fuzzy.o error_exit.o miscfp.o \
|
||||
linear_map.o cpm_map.o BH_diagnostics.o setup.o horizon_sequence.o find_horizons.o \
|
||||
initial_guess.o Newton.o Jacobian.o ilucg.o IntPnts0.o IntPnts.o
|
||||
|
||||
TwoPunctureFILES = TwoPunctureABE.o TwoPunctures.o
|
||||
|
||||
CUDAFILES = bssn_gpu.o bssn_gpu_rhs_ss.o
|
||||
|
||||
# file dependences
|
||||
$(C++FILES) $(C++FILES_GPU) $(F90FILES) $(CFILES) $(AHFDOBJS) $(CUDAFILES): macrodef.fh
|
||||
|
||||
$(C++FILES): Block.h enforce_algebra.h fmisc.h initial_puncture.h macrodef.h\
|
||||
misc.h monitor.h MyList.h Parallel.h MPatch.h prolongrestrict.h\
|
||||
rungekutta4_rout.h var.h bssn_class.h bssn_rhs.h sommerfeld_rout.h\
|
||||
cgh.h surface_integral.h ShellPatch.h shellfunctions.h perf.h\
|
||||
fadmquantites_bssn.h cpbc.h getnp4.h initial_null.h NullEvol.h\
|
||||
NullShellPatch.h initial_maxwell.h bssnEM_class.h getnpem2.h\
|
||||
empart.h NullNews.h kodiss.h Parallel_bam.h ricci_gamma.h\
|
||||
initial_null2.h NullShellPatch2.h
|
||||
|
||||
$(C++FILES_GPU): Block.h enforce_algebra.h fmisc.h initial_puncture.h macrodef.h\
|
||||
misc.h monitor.h MyList.h Parallel.h MPatch.h prolongrestrict.h\
|
||||
rungekutta4_rout.h var.h bssn_rhs.h sommerfeld_rout.h\
|
||||
cgh.h surface_integral.h ShellPatch.h shellfunctions.h perf.h\
|
||||
fadmquantites_bssn.h cpbc.h getnp4.h initial_null.h NullEvol.h\
|
||||
NullShellPatch.h initial_maxwell.h bssnEM_class.h getnpem2.h\
|
||||
empart.h NullNews.h kodiss.h Parallel_bam.h ricci_gamma.h\
|
||||
initial_null2.h NullShellPatch2.h \
|
||||
bssn_gpu_class.h bssn_macro.h
|
||||
|
||||
$(AHFDOBJS): cctk.h cctk_Config.h cctk_Types.h cctk_Constants.h myglobal.h
|
||||
|
||||
$(C++FILES) $(C++FILES_GPU) $(CFILES) $(AHFDOBJS) $(CUDAFILES): macrodef.h
|
||||
|
||||
TwoPunctureFILES: TwoPunctures.h
|
||||
|
||||
$(CUDAFILES): bssn_gpu.h gpu_mem.h gpu_rhsSS_mem.h
|
||||
|
||||
misc.o : zbesh.o
|
||||
|
||||
# projects
|
||||
ABE: $(C++FILES) $(CFILES) $(F90FILES) $(F77FILES) $(AHFDOBJS)
|
||||
$(CLINKER) $(CXXAPPFLAGS) -o $@ $(C++FILES) $(CFILES) $(F90FILES) $(F77FILES) $(AHFDOBJS) $(LDLIBS)
|
||||
|
||||
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)
|
||||
|
||||
clean:
|
||||
rm *.o ABE ABEGPU TwoPunctureABE make.log -f
|
||||
|
||||
Reference in New Issue
Block a user