add interface library and refresh clang format

example/27_layernorm2d_fwd/run_layernorm_example.inc

@@ -44,9 +44,9 @@ int run_layernorm2d_fwd_example()
         {0, 1},
         std::vector<ck::index_t>{y.mDesc.GetStrides().begin(), y.mDesc.GetStrides().end()},
         std::vector<ck::index_t>{save_mean.mDesc.GetStrides().begin(),
-                                    save_mean.mDesc.GetStrides().end()},
+                                 save_mean.mDesc.GetStrides().end()},
         std::vector<ck::index_t>{save_mean.mDesc.GetStrides().begin(),
-                                    save_mean.mDesc.GetStrides().end()},
+                                 save_mean.mDesc.GetStrides().end()},
         {1},
         1e-4,
         x_dev.GetDeviceBuffer(),

example/42_groupnorm_fwd/run_groupnorm_fwd_example.inc

@@ -65,9 +65,9 @@ int run_groupnorm_fwd_example(int argc, char* argv[])
         {0, 0, 0, C, 1},
         std::vector<ck::index_t>{y.mDesc.GetStrides().begin(), y.mDesc.GetStrides().end()},
         std::vector<ck::index_t>{save_mean.mDesc.GetStrides().begin(),
-                                    save_mean.mDesc.GetStrides().end()},
+                                 save_mean.mDesc.GetStrides().end()},
         std::vector<ck::index_t>{save_mean.mDesc.GetStrides().begin(),
-                                    save_mean.mDesc.GetStrides().end()},
+                                 save_mean.mDesc.GetStrides().end()},
         {1, 2, 4}, // reduction dimension: [H, W, C]
         1e-6,
         x_dev.GetDeviceBuffer(),

example/63_layernorm4d_fwd/run_layernorm4d_fwd_example.inc

@@ -46,9 +46,9 @@ int run_layernorm4d_fwd_example()
         {0, W * C, C, 1},
         std::vector<ck::index_t>{y.mDesc.GetStrides().begin(), y.mDesc.GetStrides().end()},
         std::vector<ck::index_t>{save_mean.mDesc.GetStrides().begin(),
-                                    save_mean.mDesc.GetStrides().end()},
+                                 save_mean.mDesc.GetStrides().end()},
         std::vector<ck::index_t>{save_mean.mDesc.GetStrides().begin(),
-                                    save_mean.mDesc.GetStrides().end()},
+                                 save_mean.mDesc.GetStrides().end()},
         {1, 2, 3},
         1e-4,
         x_dev.GetDeviceBuffer(),

library/src/tensor_operation_instance/gpu/CMakeLists.txt

@@ -267,6 +267,15 @@ if(CK_DEVICE_REDUCTION_INSTANCES)
         )
 endif()
 
+add_library(device_operations INTERFACE)
+target_link_libraries(device_operations INTERFACE
+    device_contraction_operations
+    device_conv_operations
+    device_gemm_operations
+    device_other_operations
+    device_reduction_operations
+    utility)
+
 set(DEV_OPS_INC_DIRS
     ${PROJECT_SOURCE_DIR}/include/ck/
     ${PROJECT_SOURCE_DIR}/library/include/ck/

test/transpose/test_transpose_ut_cases.inc

@@ -14,7 +14,6 @@ TYPED_TEST(TestTranspose, Test1)
     this->Run();
 }
 
-
 TYPED_TEST(TestTranpose, Test2)
 {
     std::vector<int> Ms{127, 255, 312, 799, 1573};
@@ -27,4 +26,3 @@ TYPED_TEST(TestTranpose, Test2)
 
     this->Run();
 }
-