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

perf(polint): add switchable barycentric ordn=6 path

Browse Source
This commit is contained in:
CGH0S7
2026-03-01 13:20:46 +08:00
committed by ianchb
parent 01b4cf71d1
commit 8dad910c6c
2 changed files with 85 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files

48
AMSS_NCKU_source/makefile
View File

@@ -1,27 +1,33 @@
include makefile.inc
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
## 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
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${MKLROOT}/include
endif
ifeq ($(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