Merge branch 'cjy-oneapi-opus-hotfix'

This commit is contained in:
2026-02-27 15:13:40 +08:00
31 changed files with 3278 additions and 246 deletions

View File

@@ -8,18 +8,31 @@ filein = -I/usr/include/ -I${MKLROOT}/include
## Using sequential MKL (OpenMP disabled for better single-threaded performance)
## Added -lifcore for Intel Fortran runtime and -limf for Intel math library
LDLIBS = -L${MKLROOT}/lib -lmkl_intel_lp64 -lmkl_sequential -lmkl_core -lifcore -limf -lpthread -lm -ldl
LDLIBS = -L${MKLROOT}/lib -lmkl_intel_lp64 -lmkl_sequential -lmkl_core -lifcore -limf -lpthread -lm -ldl -liomp5
## Aggressive optimization flags + PGO Phase 2 (profile-guided optimization)
## -fprofile-instr-use: use collected profile data to guide optimization decisions
## (branch prediction, basic block layout, inlining, loop unrolling)
PROFDATA = ../../pgo_profile/default.profdata
CXXAPPFLAGS = -O3 -xHost -fp-model fast=2 -fma -ipo \
-fprofile-instr-use=$(PROFDATA) \
-Dfortran3 -Dnewc -I${MKLROOT}/include
f90appflags = -O3 -xHost -fp-model fast=2 -fma -ipo \
-fprofile-instr-use=$(PROFDATA) \
-align array64byte -fpp -I${MKLROOT}/include
## PGO build mode switch (ABE only; TwoPunctureABE always uses opt flags)
## opt : (default) maximum performance with PGO profile-guided optimization
## instrument : PGO Phase 1 instrumentation to collect fresh profile data
PGO_MODE ?= opt
## Interp_Points load balance profiling mode
## off : (default) no load balance instrumentation
## profile : Pass 1 — instrument Interp_Points to collect timing profile
## optimize : Pass 2 — read profile and apply block rebalancing
INTERP_LB_MODE ?= off
ifeq ($(INTERP_LB_MODE),profile)
INTERP_LB_FLAGS = -DINTERP_LB_PROFILE
else ifeq ($(INTERP_LB_MODE),optimize)
INTERP_LB_FLAGS = -DINTERP_LB_OPTIMIZE
else
INTERP_LB_FLAGS =
endif
## Kernel implementation switch
## 1 (default) : use C++ rewrite of bssn_rhs and helper kernels (faster)
## 0 : fall back to original Fortran kernels
USE_CXX_KERNELS ?= 1
f90 = ifx
f77 = ifx
CXX = icpx