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

Add runnable GPU main-path prototype

Browse Source
This commit is contained in:
CGH0S7
2026-04-08 19:14:37 +08:00
parent 8c1f4d8108
commit ea470737db
10 changed files with 1068 additions and 39 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
AMSS_NCKU_source/makefile.inc
View File

@@ -9,6 +9,7 @@ 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 -liomp5
CUDA_LDLIBS = -L/usr/local/cuda-12.9/targets/x86_64-linux/lib -lcudart
## Memory allocator switch
## 1 (default) : link Intel oneTBB allocator (libtbbmalloc)
@@ -24,6 +25,8 @@ ifeq ($(USE_TBBMALLOC),1)
LDLIBS := $(TBBMALLOC_LIBS) $(LDLIBS)
endif
LDLIBS := $(CUDA_LDLIBS) $(LDLIBS)
## 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