CGH0S7
0992e2219a
Replace Intel compilers (ifx/icpx/icx) with AOCC (flang/clang++/clang), Intel MPI (mpiicpx) with AOCC-built OpenMPI (mpicxx), and Intel MKL with AOCL BLIS/libFLAME. Replace -xHost with -march=znver4, -ipo with -flto, -fp-model fast=2 with -ffast-math, -qopenmp with -fopenmp. Remove PGO, TBB allocator, and Intel-specific runtime libraries. Fix MKL-specific includes in TwoPunctures.C and gaussj.C to use standard CBLAS/LAPACKE headers from AOCL. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
62 lines
2.3 KiB
PHP
Executable File
62 lines
2.3 KiB
PHP
Executable File
## AMD AOCC version with AOCL (Optimized for AMD EPYC Zen 4)
|
|
|
|
## AOCL root path for includes and libraries
|
|
AOCL_ROOT ?= /home/gh0s7/AOCC/aocl/5.2.0/aocc
|
|
|
|
## AOCC-built OpenMPI prefix
|
|
OMPI_PREFIX ?= /home/gh0s7/AOCC/aocc-openmpi
|
|
|
|
filein = -I/usr/include/ -I$(AOCL_ROOT)/include
|
|
|
|
## Using AOCL BLIS + libFLAME for BLAS/LAPACK
|
|
## AOCC Fortran runtime: -lflang (includes FortranRuntime)
|
|
## AOCC OpenMP runtime: -lomp (LLVM OpenMP)
|
|
LDLIBS = -L$(AOCL_ROOT)/lib -lblis -lflame -lamdlibm -lflang -lpgmath -lpthread -lm -ldl -lomp
|
|
|
|
## 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
|
|
|
|
## BSSN-EScalar RHS switch
|
|
## 1 (default) : use BSSN-EScalar C wrapper on the normal patch path
|
|
## 0 : keep the original Fortran BSSN-EScalar RHS for precision-safe runs
|
|
## Note: this requires USE_CXX_KERNELS=1 because the wrapper reuses the C BSSN kernel.
|
|
USE_CXX_ESCALAR_KERNEL ?= 1
|
|
|
|
## Cached transfer switch
|
|
## auto (default): enable for BSSN vacuum, keep other paths on the safe uncached path
|
|
## 1 : force cached Sync/Restrict/OutBd transfer on evolution hot paths
|
|
## 0 : force the original uncached transfer path
|
|
USE_TRANSFER_CACHE ?= auto
|
|
|
|
## RK4 kernel implementation switch
|
|
## 1 (default) : use C/C++ rewrite of rungekutta4_rout (for optimization experiments)
|
|
## 0 : use original Fortran rungekutta4_rout.o
|
|
USE_CXX_RK4 ?= 1
|
|
|
|
f90 = flang
|
|
f77 = flang
|
|
CXX = clang++
|
|
CC = clang
|
|
CLINKER = $(OMPI_PREFIX)/bin/mpicxx
|
|
|
|
Cu = nvcc
|
|
CUDA_LIB_PATH = -L/usr/lib/cuda/lib64 -I/usr/include -I/usr/lib/cuda/include
|
|
#CUDA_APP_FLAGS = -c -g -O3 --ptxas-options=-v -arch compute_13 -code compute_13,sm_13 -Dfortran3 -Dnewc
|
|
CUDA_APP_FLAGS = -c -g -O3 --ptxas-options=-v -Dfortran3 -Dnewc
|