Refine naming

library/src/tensor_operation_instance/gpu/pool_fwd/device_avg_pool2d_fwd_nhwc_f16_instance.cpp

@@ -10,7 +10,7 @@ namespace instance {
 
 static constexpr auto ReduceOpId = ck::ReduceTensorOp::AVG;
 
-void add_device_pooling2d_fwd_nhwc_f16_instances(
+void add_device_pool2d_fwd_nhwc_f16_instances(
     std::vector<std::unique_ptr<DevicePoolFwd<4, 2, F16, F16, I32, ReduceOpId, false>>>& instances)
 {
     add_device_operation_instances(

library/src/tensor_operation_instance/gpu/pool_fwd/device_avg_pool2d_fwd_nhwc_f32_instance.cpp

@@ -10,7 +10,7 @@ namespace instance {
 
 static constexpr auto ReduceOpId = ck::ReduceTensorOp::AVG;
 
-void add_device_pooling2d_fwd_nhwc_f32_instances(
+void add_device_pool2d_fwd_nhwc_f32_instances(
     std::vector<std::unique_ptr<DevicePoolFwd<4, 2, F32, F32, I32, ReduceOpId, false>>>& instances)
 {
     add_device_operation_instances(

library/src/tensor_operation_instance/gpu/pool_fwd/device_avg_pool3d_fwd_ndhwc_f16_instance.cpp

@@ -10,7 +10,7 @@ namespace instance {
 
 static constexpr auto ReduceOpId = ck::ReduceTensorOp::AVG;
 
-void add_device_pooling3d_fwd_ndhwc_f16_instances(
+void add_device_pool3d_fwd_ndhwc_f16_instances(
     std::vector<std::unique_ptr<DevicePoolFwd<5, 3, F16, F16, I32, ReduceOpId, false>>>& instances)
 {
     add_device_operation_instances(

library/src/tensor_operation_instance/gpu/pool_fwd/device_avg_pool3d_fwd_ndhwc_f32_instance.cpp

@@ -10,7 +10,7 @@ namespace instance {
 
 static constexpr auto ReduceOpId = ck::ReduceTensorOp::AVG;
 
-void add_device_pooling3d_fwd_ndhwc_f32_instances(
+void add_device_pool3d_fwd_ndhwc_f32_instances(
     std::vector<std::unique_ptr<DevicePoolFwd<5, 3, F32, F32, I32, ReduceOpId, false>>>& instances)
 {
     add_device_operation_instances(

library/src/tensor_operation_instance/gpu/pool_fwd/device_max_pool2d_fwd_nhwc_f16_instance.cpp

@@ -10,14 +10,14 @@ namespace instance {
 
 static constexpr auto ReduceOpId = ck::ReduceTensorOp::MAX;
 
-void add_device_pooling2d_fwd_nhwc_f16_instances(
+void add_device_pool2d_fwd_nhwc_f16_instances(
     std::vector<std::unique_ptr<DevicePoolFwd<4, 2, F16, F16, I32, ReduceOpId, false>>>& instances)
 {
     add_device_operation_instances(
         instances, device_pooling2d_fwd_nhwc_instances<F16, F16, I32, F16, ReduceOpId, false>{});
 }
 
-void add_device_pooling2d_fwd_nhwc_index_f16_instances(
+void add_device_pool2d_fwd_nhwc_index_f16_instances(
     std::vector<std::unique_ptr<DevicePoolFwd<4, 2, F16, F16, I32, ReduceOpId, true>>>& instances)
 {
     add_device_operation_instances(

library/src/tensor_operation_instance/gpu/pool_fwd/device_max_pool2d_fwd_nhwc_f32_instance.cpp

@@ -10,14 +10,14 @@ namespace instance {
 
 static constexpr auto ReduceOpId = ck::ReduceTensorOp::MAX;
 
-void add_device_pooling2d_fwd_nhwc_f32_instances(
+void add_device_pool2d_fwd_nhwc_f32_instances(
     std::vector<std::unique_ptr<DevicePoolFwd<4, 2, F32, F32, I32, ReduceOpId, false>>>& instances)
 {
     add_device_operation_instances(
         instances, device_pooling2d_fwd_nhwc_instances<F32, F32, I32, F32, ReduceOpId, false>{});
 }
 
-void add_device_pooling2d_fwd_nhwc_index_f32_instances(
+void add_device_pool2d_fwd_nhwc_index_f32_instances(
     std::vector<std::unique_ptr<DevicePoolFwd<4, 2, F32, F32, I32, ReduceOpId, true>>>& instances)
 {
     add_device_operation_instances(

library/src/tensor_operation_instance/gpu/pool_fwd/device_max_pool3d_fwd_ndhwc_f16_instance.cpp

@@ -10,14 +10,14 @@ namespace instance {
 
 static constexpr auto ReduceOpId = ck::ReduceTensorOp::MAX;
 
-void add_device_pooling3d_fwd_ndhwc_f16_instances(
+void add_device_pool3d_fwd_ndhwc_f16_instances(
     std::vector<std::unique_ptr<DevicePoolFwd<5, 3, F16, F16, I32, ReduceOpId, false>>>& instances)
 {
     add_device_operation_instances(
         instances, device_pooling3d_fwd_ndhwc_instances<F16, F16, I32, F16, ReduceOpId, false>{});
 }
 
-void add_device_pooling3d_fwd_ndhwc_index_f16_instances(
+void add_device_pool3d_fwd_ndhwc_index_f16_instances(
     std::vector<std::unique_ptr<DevicePoolFwd<5, 3, F16, F16, I32, ReduceOpId, true>>>& instances)
 {
     add_device_operation_instances(

library/src/tensor_operation_instance/gpu/pool_fwd/device_max_pool3d_fwd_ndhwc_f32_instance.cpp

@@ -10,14 +10,14 @@ namespace instance {
 
 static constexpr auto ReduceOpId = ck::ReduceTensorOp::MAX;
 
-void add_device_pooling3d_fwd_ndhwc_f32_instances(
+void add_device_pool3d_fwd_ndhwc_f32_instances(
     std::vector<std::unique_ptr<DevicePoolFwd<5, 3, F32, F32, I32, ReduceOpId, false>>>& instances)
 {
     add_device_operation_instances(
         instances, device_pooling3d_fwd_ndhwc_instances<F32, F32, I32, F32, ReduceOpId, false>{});
 }
 
-void add_device_pooling3d_fwd_ndhwc_index_f32_instances(
+void add_device_pool3d_fwd_ndhwc_index_f32_instances(
     std::vector<std::unique_ptr<DevicePoolFwd<5, 3, F32, F32, I32, ReduceOpId, true>>>& instances)
 {
     add_device_operation_instances(