Absolute include path (#281)

* ad gelu and fast_gelu

* added GeLU and fast GeLU

* clean up

* add gemm+fastgelu example

* add gemm+gelu instances

* update profiler

* clean up

* clean up

* adding gemm+bias+activation

* clean

* adding bias

* clean

* adding gemm multiple d

* debugging

* add gemm bias add fastgelu

* rename, clean

* refactoring; add readme

* refactor

* refactor

* refactor

* refactor

* refactor

* refactor

* fix

* fix

* update example

* update example

* rename

* update example

* add ckProfiler

* clean

* clean

* clean

* clean

* add client app example

* update readme

* delete obselete files

* remove old client app

* delete old file

* cleaning

* clean

* remove half

* fix header path

* fix header path

* fix header path

* fix header path

* fix header path

* fix header path for all examples

* fix header path

* fix header path

* fix header path

* fix header path

* fix header path

* fix header path

* fix header path

* fix header path

* fix header path

* revert client app example

* clean build

* fix build

* temporary disable client test on Jenkins

* clean

* clean

* clean

library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_b16_f32_b16.hpp

-#ifndef DEVICE_REDUCE_INSTANCE_BLOCKWISE_B16_F32_B16_HPP
-#define DEVICE_REDUCE_INSTANCE_BLOCKWISE_B16_F32_B16_HPP
+#pragma once
 
-#include "data_type.hpp"
-#include "device_reduce_instance_blockwise.hpp"
+#include "ck/utility/data_type.hpp"
+
+#include "ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise.hpp"
 
 namespace ck {
 namespace tensor_operation {
@@ -53,7 +53,4 @@ ADD_BLOCKWISE_INST_REF_BY_ID(bhalf_t, float, bhalf_t, 4, 0, 1, 2, 1);
 } // namespace device_reduce_instance
 } // namespace device
 } // namespace tensor_operation
-
 } // namespace ck
-
-#endif

library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f16_f16.hpp

-#ifndef DEVICE_REDUCE_INSTANCE_BLOCKWISE_F16_F16_F16_HPP
-#define DEVICE_REDUCE_INSTANCE_BLOCKWISE_F16_F16_F16_HPP
+#pragma once
 
-#include "data_type.hpp"
-#include "device_reduce_instance_blockwise.hpp"
+#include "ck/utility/data_type.hpp"
+
+#include "ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise.hpp"
 
 namespace ck {
 namespace tensor_operation {
@@ -40,7 +40,4 @@ ADD_BLOCKWISE_INST_REF_BY_ID(half_t, half_t, half_t, 4, 0, 1, 2, 1);
 } // namespace device_reduce_instance
 } // namespace device
 } // namespace tensor_operation
-
 } // namespace ck
-
-#endif

library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f16_f32_f16.hpp

-#ifndef DEVICE_REDUCE_INSTANCE_BLOCKWISE_F16_F32_F16_HPP
-#define DEVICE_REDUCE_INSTANCE_BLOCKWISE_F16_F32_F16_HPP
+#pragma once
 
-#include "data_type.hpp"
-#include "device_reduce_instance_blockwise.hpp"
+#include "ck/utility/data_type.hpp"
+
+#include "ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise.hpp"
 
 namespace ck {
 namespace tensor_operation {
@@ -28,7 +28,4 @@ ADD_BLOCKWISE_INST_REF_BY_ID(half_t, float, half_t, 7, 0, 0, 2, 1);
 } // namespace device_reduce_instance
 } // namespace device
 } // namespace tensor_operation
-
 } // namespace ck
-
-#endif

library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f32_f32.hpp

-#ifndef DEVICE_REDUCE_INSTANCE_BLOCKWISE_F32_F32_F32_HPP
-#define DEVICE_REDUCE_INSTANCE_BLOCKWISE_F32_F32_F32_HPP
+#pragma once
 
-#include "device_reduce_instance_blockwise.hpp"
+#include "ck/utility/data_type.hpp"
+
+#include "ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise.hpp"
 
 namespace ck {
 namespace tensor_operation {
@@ -51,7 +52,4 @@ ADD_BLOCKWISE_INST_REF_BY_ID(float, float, float, 4, 0, 1, 2, 1);
 } // namespace device_reduce_instance
 } // namespace device
 } // namespace tensor_operation
-
 } // namespace ck
-
-#endif

library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f32_f64_f32.hpp

-#ifndef DEVICE_REDUCE_INSTANCE_BLOCKWISE_F32_F64_F32_HPP
-#define DEVICE_REDUCE_INSTANCE_BLOCKWISE_F32_F64_F32_HPP
+#pragma once
 
-#include "device_reduce_instance_blockwise.hpp"
+#include "ck/utility/data_type.hpp"
+
+#include "ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise.hpp"
 
 namespace ck {
 namespace tensor_operation {
@@ -27,7 +28,4 @@ ADD_BLOCKWISE_INST_REF_BY_ID(float, double, float, 7, 0, 0, 2, 1);
 } // namespace device_reduce_instance
 } // namespace device
 } // namespace tensor_operation
-
 } // namespace ck
-
-#endif

library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_f64_f64_f64.hpp

-#ifndef DEVICE_REDUCE_INSTANCE_BLOCKWISE_F64_F64_F64_HPP
-#define DEVICE_REDUCE_INSTANCE_BLOCKWISE_F64_F64_F64_HPP
+#pragma once
 
-#include "device_reduce_instance_blockwise.hpp"
+#include "ck/utility/data_type.hpp"
+
+#include "ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise.hpp"
 
 namespace ck {
 namespace tensor_operation {
@@ -51,7 +52,4 @@ ADD_BLOCKWISE_INST_REF_BY_ID(double, double, double, 4, 0, 1, 2, 1);
 } // namespace device_reduce_instance
 } // namespace device
 } // namespace tensor_operation
-
 } // namespace ck
-
-#endif

library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i32_i8.hpp

-#ifndef DEVICE_REDUCE_INSTANCE_BLOCKWISE_I8_I32_I8_HPP
-#define DEVICE_REDUCE_INSTANCE_BLOCKWISE_I8_I32_I8_HPP
+#pragma once
 
-#include "device_reduce_instance_blockwise.hpp"
+#include "ck/utility/data_type.hpp"
+
+#include "ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise.hpp"
 
 namespace ck {
 namespace tensor_operation {
@@ -23,7 +24,4 @@ ADD_BLOCKWISE_INST_REF_BY_ID(int8_t, int32_t, int8_t, 5, 0, 0, 2, 1);
 } // namespace device_reduce_instance
 } // namespace device
 } // namespace tensor_operation
-
 } // namespace ck
-
-#endif

library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise_i8_i8_i8.hpp

-#ifndef DEVICE_REDUCE_INSTANCE_BLOCKWISE_I8_I8_I8_HPP
-#define DEVICE_REDUCE_INSTANCE_BLOCKWISE_I8_I8_I8_HPP
+#pragma once
 
-#include "device_reduce_instance_blockwise.hpp"
+#include "ck/utility/data_type.hpp"
+
+#include "ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_blockwise.hpp"
 
 namespace ck {
 namespace tensor_operation {
@@ -39,7 +40,4 @@ ADD_BLOCKWISE_INST_REF_BY_ID(int8_t, int8_t, int8_t, 4, 0, 1, 2, 1);
 } // namespace device_reduce_instance
 } // namespace device
 } // namespace tensor_operation
-
 } // namespace ck
-
-#endif

library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_impl_common.hpp

-#ifndef DEVICE_REDUCE_INSTANCE_IMPL_COMMON_HPP
-#define DEVICE_REDUCE_INSTANCE_IMPL_COMMON_HPP
+#pragma once
 
 namespace ck {
 namespace tensor_operation {
@@ -35,7 +34,4 @@ struct ReductionConfiguration_2
 } // namespace device_reduce_instance
 } // namespace device
 } // namespace tensor_operation
-
 } // namespace ck
-
-#endif

library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add.hpp

-#ifndef DEVICE_REDUCE_INSTANCE_MULTIBLOCK_ATOMIC_ADD_HPP
-#define DEVICE_REDUCE_INSTANCE_MULTIBLOCK_ATOMIC_ADD_HPP
+#pragma once
 
-#include "reduction_operator_mapping.hpp"
-#include "device_reduce_instance_impl_common.hpp"
-#include "device_reduce_multiblock.hpp"
+#include "ck/tensor_operation/gpu/device/reduction_operator_mapping.hpp"
+#include "ck/tensor_operation/gpu/device/device_reduce_multiblock.hpp"
+
+#include "ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_impl_common.hpp"
 
 namespace ck {
 namespace tensor_operation {
@@ -193,7 +193,4 @@ void add_device_reduce_instance_multiblock_atomic_add(
 } // namespace device_reduce_instance
 } // namespace device
 } // namespace tensor_operation
-
 } // namespace ck
-
-#endif

library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_b16_f32_f32.hpp

-#ifndef DEVICE_REDUCE_INSTANCE_MULTIBLOCK_ATOMIC_ADD_B16_F32_F32_HPP
-#define DEVICE_REDUCE_INSTANCE_MULTIBLOCK_ATOMIC_ADD_B16_F32_F32_HPP
+#pragma once
 
-#include "data_type.hpp"
-#include "device_reduce_instance_multiblock_atomic_add.hpp"
+#include "ck/utility/data_type.hpp"
+
+#include "ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add.hpp"
 
 namespace ck {
 namespace tensor_operation {
@@ -24,7 +24,4 @@ ADD_MULTIBLOCK_ATOMIC_ADD_INST_REF_BY_ID(bhalf_t, float, float, 5, 0, 0, 2, 1);
 } // namespace device_reduce_instance
 } // namespace device
 } // namespace tensor_operation
-
 } // namespace ck
-
-#endif

library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f16_f32_f32.hpp

-#ifndef DEVICE_REDUCE_INSTANCE_MULTIBLOCK_ATOMIC_ADD_F16_F32_F32_HPP
-#define DEVICE_REDUCE_INSTANCE_MULTIBLOCK_ATOMIC_ADD_F16_F32_F32_HPP
+#pragma once
 
-#include "data_type.hpp"
-#include "device_reduce_instance_multiblock_atomic_add.hpp"
+#include "ck/utility/data_type.hpp"
+
+#include "ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add.hpp"
 
 namespace ck {
 namespace tensor_operation {
@@ -24,7 +24,4 @@ ADD_MULTIBLOCK_ATOMIC_ADD_INST_REF_BY_ID(half_t, float, float, 5, 0, 0, 2, 1);
 } // namespace device_reduce_instance
 } // namespace device
 } // namespace tensor_operation
-
 } // namespace ck
-
-#endif

library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f32_f32_f32.hpp

-#ifndef DEVICE_REDUCE_INSTANCE_MULTIBLOCK_ATOMIC_ADD_F32_F32_F32_HPP
-#define DEVICE_REDUCE_INSTANCE_MULTIBLOCK_ATOMIC_ADD_F32_F32_F32_HPP
+#pragma once
 
-#include "device_reduce_instance_multiblock_atomic_add.hpp"
+#include "ck/utility/data_type.hpp"
+
+#include "ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add.hpp"
 
 namespace ck {
 namespace tensor_operation {
@@ -23,7 +24,4 @@ ADD_MULTIBLOCK_ATOMIC_ADD_INST_REF_BY_ID(float, float, float, 5, 0, 0, 2, 1);
 } // namespace device_reduce_instance
 } // namespace device
 } // namespace tensor_operation
-
 } // namespace ck
-
-#endif

library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f32_f64_f32.hpp

-#ifndef DEVICE_REDUCE_INSTANCE_MULTIBLOCK_ATOMIC_ADD_F32_F64_F32_HPP
-#define DEVICE_REDUCE_INSTANCE_MULTIBLOCK_ATOMIC_ADD_F32_F64_F32_HPP
+#pragma once
 
-#include "device_reduce_instance_multiblock_atomic_add.hpp"
+#include "ck/utility/data_type.hpp"
+
+#include "ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add.hpp"
 
 namespace ck {
 namespace tensor_operation {
@@ -23,7 +24,4 @@ ADD_MULTIBLOCK_ATOMIC_ADD_INST_REF_BY_ID(float, double, float, 5, 0, 0, 2, 1);
 } // namespace device_reduce_instance
 } // namespace device
 } // namespace tensor_operation
-
 } // namespace ck
-
-#endif

library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f64_f64_f64.hpp

-#ifndef DEVICE_REDUCE_INSTANCE_MULTIBLOCK_ATOMIC_ADD_F64_F64_F64_HPP
-#define DEVICE_REDUCE_INSTANCE_MULTIBLOCK_ATOMIC_ADD_F64_F64_F64_HPP
+#pragma once
 
-#include "device_reduce_instance_multiblock_atomic_add.hpp"
+#include "ck/utility/data_type.hpp"
+
+#include "ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add.hpp"
 
 namespace ck {
 namespace tensor_operation {
@@ -23,7 +24,4 @@ ADD_MULTIBLOCK_ATOMIC_ADD_INST_REF_BY_ID(double, double, double, 5, 0, 0, 2, 1);
 } // namespace device_reduce_instance
 } // namespace device
 } // namespace tensor_operation
-
 } // namespace ck
-
-#endif

library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise.hpp

-#ifndef DEVICE_REDUCE_INSTANCE_THREADWISE_HPP
-#define DEVICE_REDUCE_INSTANCE_THREADWISE_HPP
+#pragma once
 
-#include "reduction_operator_mapping.hpp"
-#include "device_reduce_instance_impl_common.hpp"
-#include "device_reduce_threadwise.hpp"
+#include "ck/tensor_operation/gpu/device/reduction_operator_mapping.hpp"
+#include "ck/tensor_operation/gpu/device/device_reduce_threadwise.hpp"
+#include "ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_impl_common.hpp"
 
 namespace ck {
 namespace tensor_operation {
@@ -152,7 +151,4 @@ void add_device_reduce_instance_threadwise(
 } // namespace device_reduce_instance
 } // namespace device
 } // namespace tensor_operation
-
 } // namespace ck
-
-#endif

library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16.hpp

-#ifndef DEVICE_REDUCE_INSTANCE_THREADWISE_B16_F32_B16_HPP
-#define DEVICE_REDUCE_INSTANCE_THREADWISE_B16_F32_B16_HPP
+#pragma once
 
-#include "data_type.hpp"
-#include "device_reduce_instance_threadwise.hpp"
+#include "ck/utility/data_type.hpp"
+
+#include "ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise.hpp"
 
 namespace ck {
 namespace tensor_operation {
@@ -53,7 +53,4 @@ ADD_THREADWISE_INST_REF_BY_ID(bhalf_t, float, bhalf_t, 4, 0, 1, 2, 1);
 } // namespace device_reduce_instance
 } // namespace device
 } // namespace tensor_operation
-
 } // namespace ck
-
-#endif

library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f16_f16.hpp

-#ifndef DEVICE_REDUCE_INSTANCE_THREADWISE_F16_F16_F16_HPP
-#define DEVICE_REDUCE_INSTANCE_THREADWISE_F16_F16_F16_HPP
+#pragma once
 
-#include "data_type.hpp"
-#include "device_reduce_instance_threadwise.hpp"
+#include "ck/utility/data_type.hpp"
+
+#include "ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise.hpp"
 
 namespace ck {
 namespace tensor_operation {
@@ -40,7 +40,4 @@ ADD_THREADWISE_INST_REF_BY_ID(half_t, half_t, half_t, 4, 0, 1, 2, 1);
 } // namespace device_reduce_instance
 } // namespace device
 } // namespace tensor_operation
-
 } // namespace ck
-
-#endif

library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f32_f16.hpp

-#ifndef DEVICE_REDUCE_INSTANCE_THREADWISE_F16_F32_F16_HPP
-#define DEVICE_REDUCE_INSTANCE_THREADWISE_F16_F32_F16_HPP
+#pragma once
 
-#include "data_type.hpp"
-#include "device_reduce_instance_threadwise.hpp"
+#include "ck/utility/data_type.hpp"
+
+#include "ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise.hpp"
 
 namespace ck {
 namespace tensor_operation {
@@ -28,7 +28,4 @@ ADD_THREADWISE_INST_REF_BY_ID(half_t, float, half_t, 7, 0, 0, 2, 1);
 } // namespace device_reduce_instance
 } // namespace device
 } // namespace tensor_operation
-
 } // namespace ck
-
-#endif

library/include/ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32.hpp

-#ifndef DEVICE_REDUCE_INSTANCE_THREADWISE_F32_F32_F32_HPP
-#define DEVICE_REDUCE_INSTANCE_THREADWISE_F32_F32_F32_HPP
+#pragma once
 
-#include "device_reduce_instance_threadwise.hpp"
+#include "ck/utility/data_type.hpp"
+
+#include "ck/library/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise.hpp"
 
 namespace ck {
 namespace tensor_operation {
@@ -51,7 +52,4 @@ ADD_THREADWISE_INST_REF_BY_ID(float, float, float, 4, 0, 1, 2, 1);
 } // namespace device_reduce_instance
 } // namespace device
 } // namespace tensor_operation
-
 } // namespace ck
-
-#endif