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

Enable OpenMP task parallelism for C kernels

Browse Source
This commit is contained in:
CGH0S7
2026-03-30 20:34:34 +08:00
parent 8c1f4d8108
commit 5f664716ab
9 changed files with 137 additions and 79 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
AMSS_NCKU_source/makefile
View File

@@ -16,7 +16,7 @@ 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 $(INTERP_LB_FLAGS)
-Dfortran3 -Dnewc -I${MKLROOT}/include $(INTERP_LB_FLAGS) $(OPENMP_FLAGS)
f90appflags = -O3 -xHost -fma -fprofile-instr-generate -ipo \
-align array64byte -fpp -I${MKLROOT}/include $(POLINT6_FLAG)
else
@@ -26,7 +26,7 @@ else
CXXAPPFLAGS = -O3 -xHost -fp-model fast=2 -fma -ipo \
-Dfortran3 -Dnewc -I${MKLROOT}/include $(INTERP_LB_FLAGS)
-Dfortran3 -Dnewc -I${MKLROOT}/include $(INTERP_LB_FLAGS) $(OPENMP_FLAGS)
f90appflags = -O3 -xHost -fp-model fast=2 -fma -ipo \
-align array64byte -fpp -I${MKLROOT}/include $(POLINT6_FLAG)
endif