Loading Build/Makefile.local +3 −3 Original line number Diff line number Diff line Loading @@ -2,9 +2,9 @@ CC = gcc CXX = g++ MPICC = mpicc MPIC++ = mpiCC MPIC++ = mpic++ OPTIMIZE = -O4 -fopenmp -march=native -mavx -mavx2 OPTIMIZE = -O3 -fopenmp -march=native -mavx -mavx2 OMP_GPU = -mp=multicore,gpu -gpu=cuda12.0 -gpu=cc86 CUDA_INC = -I/opt/nvidia/hpc_sdk/Linux_x86_64/23.1/cuda/12.0/include Loading @@ -31,7 +31,7 @@ MPICHLIB = CLANG = clang CLANG++ = clang++ OPTIMIZE_AMD = -O3 -Ofast -fopenmp -march=native -mavx -mavx2 -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target=amdgcn-amd-amdhsa --offload-arch=gfx90a OPTIMIZE_AMD = -O3 -Ofast -fopenmp -march=native -mavx -mavx2 -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target=amdgcn-amd-amdhsa -march=gfx90a RCCL_INCL= -I/opt/rocm-5.2.3/rccl/include RCCL_LIB= -L/opt/rocm-5.2.3/rccl/lib Loading Loading
Build/Makefile.local +3 −3 Original line number Diff line number Diff line Loading @@ -2,9 +2,9 @@ CC = gcc CXX = g++ MPICC = mpicc MPIC++ = mpiCC MPIC++ = mpic++ OPTIMIZE = -O4 -fopenmp -march=native -mavx -mavx2 OPTIMIZE = -O3 -fopenmp -march=native -mavx -mavx2 OMP_GPU = -mp=multicore,gpu -gpu=cuda12.0 -gpu=cc86 CUDA_INC = -I/opt/nvidia/hpc_sdk/Linux_x86_64/23.1/cuda/12.0/include Loading @@ -31,7 +31,7 @@ MPICHLIB = CLANG = clang CLANG++ = clang++ OPTIMIZE_AMD = -O3 -Ofast -fopenmp -march=native -mavx -mavx2 -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target=amdgcn-amd-amdhsa --offload-arch=gfx90a OPTIMIZE_AMD = -O3 -Ofast -fopenmp -march=native -mavx -mavx2 -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target=amdgcn-amd-amdhsa -march=gfx90a RCCL_INCL= -I/opt/rocm-5.2.3/rccl/include RCCL_LIB= -L/opt/rocm-5.2.3/rccl/lib Loading