merge develop

example/08_conv3d_fwd/CMakeLists.txt

+add_example_executable(example_conv3d_fwd_xdl conv3d_fwd_xdl.cpp)

example/09_convnd_fwd/CMakeLists.txt

+add_example_executable(example_convnd_fwd_xdl convnd_fwd_xdl.cpp)

example/11_convnd_fwd_xdl/convnd_fwd_xdl.cpp → example/09_convnd_fwd/convnd_fwd_xdl.cpp

@@ -2,7 +2,6 @@
 #include <iostream>
 #include <numeric>
 #include <type_traits>
-
 #include "config.hpp"
 #include "conv_utils.hpp"
 #include "device.hpp"

example/10_conv2d_bwd_data/CMakeLists.txt

+add_example_executable(example_conv2d_bwd_data_xdl conv2d_bwd_data_xdl.cpp)

example/11_conv2d_bwd_wgt/CMakeLists.txt

+add_example_executable(example_conv2d_bwd_wgt_xdl conv2d_bwd_wgt_xdl.cpp)

example/12_reduce/CMakeLists.txt

+add_example_executable(example_reduce_blockwise reduce_blockwise.cpp)