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

Add switchable C RK4 kernel and build toggle

Browse Source 
(cherry picked from commit b91cfff301)
This commit is contained in:
CGH0S7
2026-02-28 21:12:19 +08:00
committed by ianchb
parent 71f6eb7b44
commit b185f84cce
3 changed files with 197 additions and 28 deletions
Download Patch File Download Diff File Expand all files Collapse all files

64
AMSS_NCKU_source/makefile
View File

@@ -1,33 +1,33 @@
include makefile.inc
## polint(ordn=6) kernel selector:
## 1 (default): barycentric fast path
## 0 : fallback to Neville path
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
include makefile.inc
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 $(POLINT6_FLAG)
else
## opt (default): maximum performance with PGO profile data
CXXAPPFLAGS = -O3 -xHost -fp-model fast=2 -fma -ipo \
-fprofile-instr-use=$(PROFDATA) \
-Dfortran3 -Dnewc -I${MKLROOT}/include $(INTERP_LB_FLAGS)
f90appflags = -O3 -xHost -fp-model fast=2 -fma -ipo \
-fprofile-instr-use=$(PROFDATA) \
-align array64byte -fpp -I${MKLROOT}/include $(POLINT6_FLAG)
endif
## polint(ordn=6) kernel selector:
## 1 (default): barycentric fast path
## 0 : fallback to Neville path
POLINT6_USE_BARY ?= 1
POLINT6_FLAG = -DPOLINT6_USE_BARYCENTRIC=$(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 $(POLINT6_FLAG)
else
## opt (default): maximum performance with PGO profile data
CXXAPPFLAGS = -O3 -xHost -fp-model fast=2 -fma -ipo \
-fprofile-instr-use=$(PROFDATA) \
-Dfortran3 -Dnewc -I${MKLROOT}/include $(INTERP_LB_FLAGS)
f90appflags = -O3 -xHost -fp-model fast=2 -fma -ipo \
-fprofile-instr-use=$(PROFDATA) \
-align array64byte -fpp -I${MKLROOT}/include $(POLINT6_FLAG)
endif
.SUFFIXES: .o .f90 .C .for .cu
@@ -92,6 +92,14 @@ endif
# CUDA rewrite: bssn_rhs_cuda.o replaces all CFILES (stencils are built-in)
CFILES_CUDA = bssn_rhs_cuda.o
## RK4 kernel switch (independent from USE_CXX_KERNELS)
ifeq ($(USE_CXX_RK4),1)
CFILES += rungekutta4_rout_c.o
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\
@@ -109,7 +117,7 @@ C++FILES_GPU = ABE.o Ansorg.o Block.o misc.o monitor.o Parallel.o MPatch.o var.o
F90FILES_BASE = enforce_algebra.o fmisc.o initial_puncture.o prolongrestrict.o\
prolongrestrict_cell.o prolongrestrict_vertex.o\
rungekutta4_rout.o diff_new.o kodiss.o kodiss_sh.o\
$(RK4_F90_OBJ) diff_new.o kodiss.o kodiss_sh.o\
lopsidediff.o sommerfeld_rout.o getnp4.o diff_new_sh.o\
shellfunctions.o bssn_rhs_ss.o Set_Rho_ADM.o\
getnp4EScalar.o bssnEScalar_rhs.o bssn_constraint.o ricci_gamma.o\