tx258/lammps-gran-kokkos
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge pull request #3674 from rbberger/gpu_rocm_bugfix

Browse Source 
GPU package bugfix / cmake improvement
This commit is contained in:
Axel Kohlmeyer
2023-03-07 07:39:48 -05:00
committed by GitHub
parent 795227d376 f63eec6953
commit 6d7d0f78d5
2 changed files with 6 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files

23
cmake/Modules/Packages/GPU.cmake
View File

@ -285,7 +285,7 @@ elseif(GPU_API STREQUAL "HIP")
set(ENV{HIP_PLATFORM} ${HIP_PLATFORM})
if(HIP_PLATFORM STREQUAL "hcc" OR HIP_PLATFORM STREQUAL "amd")
if(HIP_PLATFORM STREQUAL "amd")
set(HIP_ARCH "gfx906" CACHE STRING "HIP target architecture")
elseif(HIP_PLATFORM STREQUAL "spirv")
set(HIP_ARCH "spirv" CACHE STRING "HIP target architecture")
@ -358,7 +358,7 @@ elseif(GPU_API STREQUAL "HIP")
set(CUBIN_FILE "${LAMMPS_LIB_BINARY_DIR}/gpu/${CU_NAME}.cubin")
set(CUBIN_H_FILE "${LAMMPS_LIB_BINARY_DIR}/gpu/${CU_NAME}_cubin.h")
if(HIP_PLATFORM STREQUAL "hcc" OR HIP_PLATFORM STREQUAL "amd")
if(HIP_PLATFORM STREQUAL "amd")
configure_file(${CU_FILE} ${CU_CPP_FILE} COPYONLY)
if(HIP_COMPILER STREQUAL "clang")
@ -412,7 +412,8 @@ elseif(GPU_API STREQUAL "HIP")
set_property(TARGET gpu PROPERTY CXX_STANDARD 14)
endif()
# add hipCUB
target_include_directories(gpu PRIVATE ${HIP_ROOT_DIR}/../include)
find_package(hipcub REQUIRED)
target_link_libraries(gpu PRIVATE hip::hipcub)
target_compile_definitions(gpu PRIVATE -DUSE_HIP_DEVICE_SORT)
if(HIP_PLATFORM STREQUAL "nvcc")
@ -461,30 +462,16 @@ elseif(GPU_API STREQUAL "HIP")
add_executable(hip_get_devices ${LAMMPS_LIB_SOURCE_DIR}/gpu/geryon/ucl_get_devices.cpp)
target_compile_definitions(hip_get_devices PRIVATE -DUCL_HIP)
target_link_libraries(hip_get_devices hip::host)
target_link_libraries(hip_get_devices PRIVATE hip::host)
if(HIP_PLATFORM STREQUAL "nvcc")
target_compile_definitions(gpu PRIVATE -D__HIP_PLATFORM_NVCC__)
target_include_directories(gpu PRIVATE ${HIP_ROOT_DIR}/../include)
target_include_directories(gpu PRIVATE ${CUDA_INCLUDE_DIRS})
target_link_libraries(gpu PRIVATE ${CUDA_LIBRARIES} ${CUDA_CUDA_LIBRARY})
target_compile_definitions(hip_get_devices PRIVATE -D__HIP_PLATFORM_NVCC__)
target_include_directories(hip_get_devices PRIVATE ${HIP_ROOT_DIR}/include)
target_include_directories(hip_get_devices PRIVATE ${CUDA_INCLUDE_DIRS})
target_link_libraries(hip_get_devices PRIVATE ${CUDA_LIBRARIES} ${CUDA_CUDA_LIBRARY})
elseif(HIP_PLATFORM STREQUAL "hcc")
target_compile_definitions(gpu PRIVATE -D__HIP_PLATFORM_HCC__)
target_include_directories(gpu PRIVATE ${HIP_ROOT_DIR}/../include)
target_compile_definitions(hip_get_devices PRIVATE -D__HIP_PLATFORM_HCC__)
target_include_directories(hip_get_devices PRIVATE ${HIP_ROOT_DIR}/../include)
elseif(HIP_PLATFORM STREQUAL "amd")
target_compile_definitions(gpu PRIVATE -D__HIP_PLATFORM_AMD__)
target_include_directories(gpu PRIVATE ${HIP_ROOT_DIR}/../include)
target_compile_definitions(hip_get_devices PRIVATE -D__HIP_PLATFORM_AMD__)
target_include_directories(hip_get_devices PRIVATE ${HIP_ROOT_DIR}/../include)
endif()
target_link_libraries(lammps PRIVATE gpu)

2
lib/gpu/lal_atom.cpp
View File

@ -403,7 +403,7 @@ double AtomT::host_memory_usage() const {
return _max_atoms*atom_bytes*sizeof(numtyp)+sizeof(Atom<numtyp,acctyp>);
}
#ifdef USE_CUDPP
#if defined(USE_CUDPP) || defined(USE_HIP_DEVICE_SORT)
#define USE_CUDPP_ARG(arg) arg
#else
#define USE_CUDPP_ARG(arg)