devtools/eigen
1
0
Fork 0
mirror of https://gitlab.com/libeigen/eigen.git synced 2026-04-10 11:34:33 +08:00
Code Issues Packages Projects Releases Wiki Activity

merging the CUDA and HIP implementation for the Tensor directory and the unit tests

Browse Source
This commit is contained in:
Deven Desai
2018-06-20 16:44:58 -04:00
parent cfdabbcc8f
commit 1bb6fa99a3
22 changed files with 1208 additions and 804 deletions
Download Patch File Download Diff File Expand all files Collapse all files

47
unsupported/test/CMakeLists.txt
View File

@@ -274,24 +274,24 @@ if(CUDA_FOUND AND EIGEN_TEST_CUDA)
cuda_include_directories("${CMAKE_CURRENT_BINARY_DIR}" "${CUDA_TOOLKIT_ROOT_DIR}/include")
set(EIGEN_ADD_TEST_FILENAME_EXTENSION "cu")
ei_add_test(cxx11_tensor_complex_cuda)
ei_add_test(cxx11_tensor_complex_cwise_ops_cuda)
ei_add_test(cxx11_tensor_reduction_cuda)
ei_add_test(cxx11_tensor_argmax_cuda)
ei_add_test(cxx11_tensor_cast_float16_cuda)
ei_add_test(cxx11_tensor_scan_cuda)
ei_add_test(cxx11_tensor_complex_gpu)
ei_add_test(cxx11_tensor_complex_cwise_ops_gpu)
ei_add_test(cxx11_tensor_reduction_gpu)
ei_add_test(cxx11_tensor_argmax_gpu)
ei_add_test(cxx11_tensor_cast_float16_gpu)
ei_add_test(cxx11_tensor_scan_gpu)
# Contractions require arch 3.0 or higher
if (${EIGEN_CUDA_COMPUTE_ARCH} GREATER 29)
ei_add_test(cxx11_tensor_device)
ei_add_test(cxx11_tensor_cuda)
ei_add_test(cxx11_tensor_contract_cuda)
ei_add_test(cxx11_tensor_of_float16_cuda)
ei_add_test(cxx11_tensor_gpu)
ei_add_test(cxx11_tensor_contract_gpu)
ei_add_test(cxx11_tensor_of_float16_gpu)
endif()
# The random number generation code requires arch 3.5 or greater.
if (${EIGEN_CUDA_COMPUTE_ARCH} GREATER 34)
ei_add_test(cxx11_tensor_random_cuda)
ei_add_test(cxx11_tensor_random_gpu)
endif()
@@ -318,18 +318,23 @@ if (EIGEN_TEST_HIP)
include_directories(${HIP_PATH}/include)
set(EIGEN_ADD_TEST_FILENAME_EXTENSION "cu")
#
# complex datatype is not yet supported by HIP
# so leaving out those tests for now
#
# ei_add_test(cxx11_tensor_complex_gpu)
# ei_add_test(cxx11_tensor_complex_cwise_ops_gpu)
#
ei_add_test(cxx11_tensor_reduction_gpu)
ei_add_test(cxx11_tensor_argmax_gpu)
ei_add_test(cxx11_tensor_cast_float16_gpu)
ei_add_test(cxx11_tensor_scan_gpu)
ei_add_test(cxx11_tensor_device)
# ei_add_test(cxx11_tensor_complex_hip)
# ei_add_test(cxx11_tensor_complex_cwise_ops_hip)
ei_add_test(cxx11_tensor_reduction_hip)
ei_add_test(cxx11_tensor_argmax_hip)
ei_add_test(cxx11_tensor_cast_float16_hip)
ei_add_test(cxx11_tensor_scan_hip)
ei_add_test(cxx11_tensor_device_hip)
ei_add_test(cxx11_tensor_hip)
ei_add_test(cxx11_tensor_contract_hip)
ei_add_test(cxx11_tensor_of_float16_hip)
ei_add_test(cxx11_tensor_random_hip)
ei_add_test(cxx11_tensor_gpu)
ei_add_test(cxx11_tensor_contract_gpu)
ei_add_test(cxx11_tensor_of_float16_gpu)
ei_add_test(cxx11_tensor_random_gpu)
unset(EIGEN_ADD_TEST_FILENAME_EXTENSION)