Merge branch 'develop' into dl_conv_multiple_d

test/grouped_gemm/grouped_gemm_fp16.cpp

@@ -3,7 +3,7 @@
 
 #include <iostream>
 
-#include "profiler/include/profile_grouped_gemm_impl.hpp"
+#include "profiler/profile_grouped_gemm_impl.hpp"
 
 namespace {
 

test/normalization/test_groupnorm_fp16.cpp

@@ -2,7 +2,7 @@
 // Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.
 
 #include "gtest/gtest.h"
-#include "profiler/include/profile_groupnorm_impl.hpp"
+#include "profiler/profile_groupnorm_impl.hpp"
 
 using F16 = ck::half_t;
 using F32 = float;

test/normalization/test_groupnorm_fp32.cpp

@@ -2,7 +2,7 @@
 // Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.
 
 #include "gtest/gtest.h"
-#include "profiler/include/profile_groupnorm_impl.hpp"
+#include "profiler/profile_groupnorm_impl.hpp"
 
 using F16 = ck::half_t;
 using F32 = float;

test/normalization/test_layernorm2d_fp16.cpp

@@ -2,7 +2,7 @@
 // Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.
 
 #include "gtest/gtest.h"
-#include "profiler/include/profile_layernorm_impl.hpp"
+#include "profiler/profile_layernorm_impl.hpp"
 
 using F16 = ck::half_t;
 using F32 = float;

test/normalization/test_layernorm2d_fp32.cpp

@@ -2,7 +2,7 @@
 // Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.
 
 #include "gtest/gtest.h"
-#include "profiler/include/profile_layernorm_impl.hpp"
+#include "profiler/profile_layernorm_impl.hpp"
 
 using F16 = ck::half_t;
 using F32 = float;

test/reduce/reduce_no_index.cpp

@@ -4,7 +4,7 @@
 #include <getopt.h>
 
 #include "ck/library/utility/host_common_util.hpp"
-#include "profiler/include/profile_reduce_impl.hpp"
+#include "profiler/profile_reduce_impl.hpp"
 
 using namespace ck;
 

test/reduce/reduce_with_index.cpp

@@ -4,7 +4,7 @@
 #include <getopt.h>
 
 #include "ck/library/utility/host_common_util.hpp"
-#include "profiler/include/profile_reduce_impl.hpp"
+#include "profiler/profile_reduce_impl.hpp"
 
 using namespace ck;
 

test/softmax/test_softmax_util.hpp

@@ -13,7 +13,7 @@
 #include "ck/tensor_operation/gpu/device/impl/device_softmax_impl.hpp"
 #include "ck/tensor_operation/gpu/element/element_wise_operation.hpp"
 #include "include/ck/utility/data_type.hpp"
-#include "profiler/include/profile_softmax_impl.hpp"
+#include "profiler/profile_softmax_impl.hpp"
 
 namespace ck {