merge

example/27_layernorm2d_fwd/CMakeLists.txt

+add_example_executable(example_layernorm2d_fwd_fp16 layernorm2d_fwd_fp16.cpp)
+add_example_executable(example_layernorm2d_fwd_splitk_fp16 layernorm2d_fwd_splitk_fp16.cpp)

example/27_layernorm/common.hpp → example/27_layernorm2d_fwd/common.hpp

@@ -10,8 +10,8 @@
 #include <getopt.h>
 
 #include "ck/ck.hpp"
-#include "ck/tensor_operation/gpu/device/impl/device_normalization_impl.hpp"
-#include "ck/tensor_operation/gpu/device/impl/device_normalization_splitk_impl.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_normalization_fwd_impl.hpp"
+#include "ck/tensor_operation/gpu/device/impl/device_normalization_fwd_splitk_impl.hpp"
 
 #include "ck/library/utility/check_err.hpp"
 #include "ck/library/utility/device_memory.hpp"

example/30_grouped_conv_fwd_multiple_d/README.md

@@ -4,7 +4,7 @@ arg1: verification (0=no, 1=yes)
 arg2: initialization (0=no init, 1=integer value, 2=decimal value)
 arg3: time kernel (0=no, 1=yes)
 Following arguments (depending on number of spatial dims):
- Number of spatial dimensions (1=Conv1d, 2=Conv2d, 3=Conv3d)
+ Number of spatial dimensions (1=Conv1D, 2=Conv2D, 3=Conv3D)
  G, N, K, C,
  <filter spatial dimensions>, (ie Y, X for 2D)
  <input image spatial dimensions>, (ie Hi, Wi for 2D)