Merge branch 'master' into rocm3

docs/GPU-Targets.rst

@@ -171,4 +171,4 @@ Known issues:
 
 .. _GPUCapsViewer: https://www.ozone3d.net/gpu_caps_viewer/
 
-.. _PoCL: http://portablecl.org/
+.. _PoCL: https://portablecl.org/

docs/GPU-Tutorial.rst

@@ -183,7 +183,7 @@ Huan Zhang, Si Si and Cho-Jui Hsieh. "`GPU Acceleration for Large-scale Tree Boo
 
 .. _Microsoft Azure cloud computing platform: https://azure.microsoft.com/
 
-.. _AMDGPU-Pro: https://www.amd.com/en/support
+.. _AMDGPU-Pro: https://www.amd.com/en/support.html
 
 .. _Python-package Examples: https://github.com/microsoft/LightGBM/tree/master/examples/python-guide
 

docs/Parameters.rst

@@ -162,7 +162,7 @@ Core Parameters
 
    -  ranking application
 
-      -  ``lambdarank``, `lambdarank <https://proceedings.neurips.cc/paper_files/paper/2006/file/af44c4c56f385c43f2529f9b1b018f6a-Paper.pdf>`__ objective. `label_gain <#label_gain>`__ can be used to set the gain (weight) of ``int`` label and all values in ``label`` must be smaller than number of elements in ``label_gain``
+      -  ``lambdarank``, `lambdarank <https://proceedings.neurips.cc/paper/2006/hash/af44c4c56f385c43f2529f9b1b018f6a-Abstract.html>`__ objective. `label_gain <#label_gain>`__ can be used to set the gain (weight) of ``int`` label and all values in ``label`` must be smaller than number of elements in ``label_gain``
 
       -  ``rank_xendcg``, `XE_NDCG_MART <https://arxiv.org/abs/1911.09798>`__ ranking objective function, aliases: ``xendcg``, ``xe_ndcg``, ``xe_ndcg_mart``, ``xendcg_mart``
 
@@ -491,7 +491,7 @@ Learning Control Parameters
 
 -  ``linear_lambda`` :raw-html:`<a id="linear_lambda" title="Permalink to this parameter" href="#linear_lambda">&#x1F517;&#xFE0E;</a>`, default = ``0.0``, type = double, constraints: ``linear_lambda >= 0.0``
 
-   -  linear tree regularization, corresponds to the parameter ``lambda`` in Eq. 3 of `Gradient Boosting with Piece-Wise Linear Regression Trees <https://arxiv.org/pdf/1802.05640.pdf>`__
+   -  linear tree regularization, corresponds to the parameter ``lambda`` in Eq. 3 of `Gradient Boosting with Piece-Wise Linear Regression Trees <https://arxiv.org/abs/1802.05640>`__
 
 -  ``min_gain_to_split`` :raw-html:`<a id="min_gain_to_split" title="Permalink to this parameter" href="#min_gain_to_split">&#x1F517;&#xFE0E;</a>`, default = ``0.0``, type = double, aliases: ``min_split_gain``, constraints: ``min_gain_to_split >= 0.0``
 
@@ -845,7 +845,7 @@ Dataset Parameters
 
 -  ``enable_bundle`` :raw-html:`<a id="enable_bundle" title="Permalink to this parameter" href="#enable_bundle">&#x1F517;&#xFE0E;</a>`, default = ``true``, type = bool, aliases: ``is_enable_bundle``, ``bundle``
 
-   -  set this to ``false`` to disable Exclusive Feature Bundling (EFB), which is described in `LightGBM: A Highly Efficient Gradient Boosting Decision Tree <https://papers.nips.cc/paper_files/paper/2017/hash/6449f44a102fde848669bdd9eb6b76fa-Abstract.html>`__
+   -  set this to ``false`` to disable Exclusive Feature Bundling (EFB), which is described in `LightGBM: A Highly Efficient Gradient Boosting Decision Tree <https://proceedings.neurips.cc/paper/2017/hash/6449f44a102fde848669bdd9eb6b76fa-Abstract.html>`__
 
    -  **Note**: disabling this may cause the slow training speed for sparse datasets
 
@@ -1192,7 +1192,7 @@ Objective Parameters
 
    -  used only in ``lambdarank`` application
 
-   -  controls the number of top-results to focus on during training, refer to "truncation level" in the Sec. 3 of `LambdaMART paper <https://www.microsoft.com/en-us/research/wp-content/uploads/2016/02/MSR-TR-2010-82.pdf>`__
+   -  controls the number of top-results to focus on during training, refer to "truncation level" in the Sec. 3 of `LambdaMART paper <https://www.microsoft.com/en-us/research/publication/from-ranknet-to-lambdarank-to-lambdamart-an-overview/>`__
 
    -  this parameter is closely related to the desirable cutoff ``k`` in the metric **NDCG@k** that we aim at optimizing the ranker for. The optimal setting for this parameter is likely to be slightly higher than ``k`` (e.g., ``k + 3``) to include more pairs of documents to train on, but perhaps not too high to avoid deviating too much from the desired target metric **NDCG@k**
 
@@ -1261,11 +1261,13 @@ Metric Parameters
 
       -  ``average_precision``, `average precision score <https://scikit-learn.org/stable/modules/generated/sklearn.metrics.average_precision_score.html>`__
 
+      -  ``r2``, `R-squared <https://scikit-learn.org/stable/modules/generated/sklearn.metrics.r2_score.html>`__
+
       -  ``binary_logloss``, `log loss <https://en.wikipedia.org/wiki/Cross_entropy>`__, aliases: ``binary``
 
       -  ``binary_error``, for one sample: ``0`` for correct classification, ``1`` for error classification
 
-      -  ``auc_mu``, `AUC-mu <http://proceedings.mlr.press/v97/kleiman19a/kleiman19a.pdf>`__
+      -  ``auc_mu``, `AUC-mu <https://proceedings.mlr.press/v97/kleiman19a.html>`__
 
       -  ``multi_logloss``, log loss for multi-class classification, aliases: ``multiclass``, ``softmax``, ``multiclassova``, ``multiclass_ova``, ``ova``, ``ovr``
 

include/LightGBM/application.h

@@ -2,8 +2,8 @@
  * Copyright (c) 2016 Microsoft Corporation. All rights reserved.
  * Licensed under the MIT License. See LICENSE file in the project root for license information.
  */
-#ifndef LIGHTGBM_APPLICATION_H_
-#define LIGHTGBM_APPLICATION_H_
+#ifndef LIGHTGBM_INCLUDE_LIGHTGBM_APPLICATION_H_
+#define LIGHTGBM_INCLUDE_LIGHTGBM_APPLICATION_H_
 
 #include <LightGBM/config.h>
 #include <LightGBM/meta.h>
@@ -89,4 +89,4 @@ inline void Application::Run() {
 
 }  // namespace LightGBM
 
-#endif   // LightGBM_APPLICATION_H_
+#endif   // LIGHTGBM_INCLUDE_LIGHTGBM_APPLICATION_H_

include/LightGBM/arrow.h

@@ -5,8 +5,8 @@
  * Author: Oliver Borchert
  */
 
-#ifndef LIGHTGBM_ARROW_H_
-#define LIGHTGBM_ARROW_H_
+#ifndef LIGHTGBM_INCLUDE_LIGHTGBM_ARROW_H_
+#define LIGHTGBM_INCLUDE_LIGHTGBM_ARROW_H_
 
 #include <algorithm>
 #include <cstdint>
@@ -296,4 +296,4 @@ class ArrowTable {
 
 #include "arrow.tpp"
 
-#endif /* LIGHTGBM_ARROW_H_ */
+#endif  // LIGHTGBM_INCLUDE_LIGHTGBM_ARROW_H_

include/LightGBM/bin.h

@@ -2,8 +2,8 @@
  * Copyright (c) 2016 Microsoft Corporation. All rights reserved.
  * Licensed under the MIT License. See LICENSE file in the project root for license information.
  */
-#ifndef LIGHTGBM_BIN_H_
-#define LIGHTGBM_BIN_H_
+#ifndef LIGHTGBM_INCLUDE_LIGHTGBM_BIN_H_
+#define LIGHTGBM_INCLUDE_LIGHTGBM_BIN_H_
 
 #include <LightGBM/meta.h>
 #include <LightGBM/utils/common.h>
@@ -651,4 +651,4 @@ inline uint32_t BinMapper::ValueToBin(double value) const {
 
 }  // namespace LightGBM
 
-#endif   // LightGBM_BIN_H_
+#endif   // LIGHTGBM_INCLUDE_LIGHTGBM_BIN_H_

include/LightGBM/boosting.h

@@ -2,8 +2,8 @@
  * Copyright (c) 2016 Microsoft Corporation. All rights reserved.
  * Licensed under the MIT License. See LICENSE file in the project root for license information.
  */
-#ifndef LIGHTGBM_BOOSTING_H_
-#define LIGHTGBM_BOOSTING_H_
+#ifndef LIGHTGBM_INCLUDE_LIGHTGBM_BOOSTING_H_
+#define LIGHTGBM_INCLUDE_LIGHTGBM_BOOSTING_H_
 
 #include <LightGBM/config.h>
 #include <LightGBM/meta.h>
@@ -328,4 +328,4 @@ class GBDTBase : public Boosting {
 
 }  // namespace LightGBM
 
-#endif   // LightGBM_BOOSTING_H_
+#endif   // LIGHTGBM_INCLUDE_LIGHTGBM_BOOSTING_H_

include/LightGBM/c_api.h

@@ -10,8 +10,8 @@
  * .
  * The reason is that they are called frequently, and the type conversion on them may be time-cost.
  */
-#ifndef LIGHTGBM_C_API_H_
-#define LIGHTGBM_C_API_H_
+#ifndef LIGHTGBM_INCLUDE_LIGHTGBM_C_API_H_
+#define LIGHTGBM_INCLUDE_LIGHTGBM_C_API_H_
 
 #include <LightGBM/arrow.h>
 #include <LightGBM/export.h>
@@ -1663,4 +1663,4 @@ INLINE_FUNCTION void LGBM_SetLastError(const char* msg) {
 #endif
 }
 
-#endif  /* LIGHTGBM_C_API_H_ */
+#endif  /* LIGHTGBM_INCLUDE_LIGHTGBM_C_API_H_ */

include/LightGBM/config.h

@@ -13,8 +13,8 @@
  *           - param is only used by the CLI (especially the "predict" and "convert_model" tasks)
  *           - param is related to LightGBM writing files (e.g. "output_model", "save_binary")
  */
-#ifndef LIGHTGBM_CONFIG_H_
-#define LIGHTGBM_CONFIG_H_
+#ifndef LIGHTGBM_INCLUDE_LIGHTGBM_CONFIG_H_
+#define LIGHTGBM_INCLUDE_LIGHTGBM_CONFIG_H_
 
 #include <LightGBM/export.h>
 #include <LightGBM/meta.h>
@@ -154,7 +154,7 @@ struct Config {
   // descl2 = ``cross_entropy_lambda``, alternative parameterization of cross-entropy, aliases: ``xentlambda``
   // descl2 = label is anything in interval [0, 1]
   // desc = ranking application
-  // descl2 = ``lambdarank``, `lambdarank <https://proceedings.neurips.cc/paper_files/paper/2006/file/af44c4c56f385c43f2529f9b1b018f6a-Paper.pdf>`__ objective. `label_gain <#label_gain>`__ can be used to set the gain (weight) of ``int`` label and all values in ``label`` must be smaller than number of elements in ``label_gain``
+  // descl2 = ``lambdarank``, `lambdarank <https://proceedings.neurips.cc/paper/2006/hash/af44c4c56f385c43f2529f9b1b018f6a-Abstract.html>`__ objective. `label_gain <#label_gain>`__ can be used to set the gain (weight) of ``int`` label and all values in ``label`` must be smaller than number of elements in ``label_gain``
   // descl2 = ``rank_xendcg``, `XE_NDCG_MART <https://arxiv.org/abs/1911.09798>`__ ranking objective function, aliases: ``xendcg``, ``xe_ndcg``, ``xe_ndcg_mart``, ``xendcg_mart``
   // descl2 = ``rank_xendcg`` is faster than and achieves the similar performance as ``lambdarank``
   // descl2 = label should be ``int`` type, and larger number represents the higher relevance (e.g. 0:bad, 1:fair, 2:good, 3:perfect)
@@ -423,7 +423,7 @@ struct Config {
   double lambda_l2 = 0.0;
 
   // check = >=0.0
-  // desc = linear tree regularization, corresponds to the parameter ``lambda`` in Eq. 3 of `Gradient Boosting with Piece-Wise Linear Regression Trees <https://arxiv.org/pdf/1802.05640.pdf>`__
+  // desc = linear tree regularization, corresponds to the parameter ``lambda`` in Eq. 3 of `Gradient Boosting with Piece-Wise Linear Regression Trees <https://arxiv.org/abs/1802.05640>`__
   double linear_lambda = 0.0;
 
   // alias = min_split_gain
@@ -706,7 +706,7 @@ struct Config {
   bool is_enable_sparse = true;
 
   // alias = is_enable_bundle, bundle
-  // desc = set this to ``false`` to disable Exclusive Feature Bundling (EFB), which is described in `LightGBM: A Highly Efficient Gradient Boosting Decision Tree <https://papers.nips.cc/paper_files/paper/2017/hash/6449f44a102fde848669bdd9eb6b76fa-Abstract.html>`__
+  // desc = set this to ``false`` to disable Exclusive Feature Bundling (EFB), which is described in `LightGBM: A Highly Efficient Gradient Boosting Decision Tree <https://proceedings.neurips.cc/paper/2017/hash/6449f44a102fde848669bdd9eb6b76fa-Abstract.html>`__
   // desc = **Note**: disabling this may cause the slow training speed for sparse datasets
   bool enable_bundle = true;
 
@@ -977,7 +977,7 @@ struct Config {
 
   // check = >0
   // desc = used only in ``lambdarank`` application
-  // desc = controls the number of top-results to focus on during training, refer to "truncation level" in the Sec. 3 of `LambdaMART paper <https://www.microsoft.com/en-us/research/wp-content/uploads/2016/02/MSR-TR-2010-82.pdf>`__
+  // desc = controls the number of top-results to focus on during training, refer to "truncation level" in the Sec. 3 of `LambdaMART paper <https://www.microsoft.com/en-us/research/publication/from-ranknet-to-lambdarank-to-lambdamart-an-overview/>`__
   // desc = this parameter is closely related to the desirable cutoff ``k`` in the metric **NDCG@k** that we aim at optimizing the ranker for. The optimal setting for this parameter is likely to be slightly higher than ``k`` (e.g., ``k + 3``) to include more pairs of documents to train on, but perhaps not too high to avoid deviating too much from the desired target metric **NDCG@k**
   int lambdarank_truncation_level = 30;
 
@@ -1028,9 +1028,10 @@ struct Config {
   // descl2 = ``map``, `MAP <https://makarandtapaswi.wordpress.com/2012/07/02/intuition-behind-average-precision-and-map/>`__, aliases: ``mean_average_precision``
   // descl2 = ``auc``, `AUC <https://en.wikipedia.org/wiki/Receiver_operating_characteristic#Area_under_the_curve>`__
   // descl2 = ``average_precision``, `average precision score <https://scikit-learn.org/stable/modules/generated/sklearn.metrics.average_precision_score.html>`__
+  // descl2 = ``r2``, `R-squared <https://scikit-learn.org/stable/modules/generated/sklearn.metrics.r2_score.html>`__
   // descl2 = ``binary_logloss``, `log loss <https://en.wikipedia.org/wiki/Cross_entropy>`__, aliases: ``binary``
   // descl2 = ``binary_error``, for one sample: ``0`` for correct classification, ``1`` for error classification
-  // descl2 = ``auc_mu``, `AUC-mu <http://proceedings.mlr.press/v97/kleiman19a/kleiman19a.pdf>`__
+  // descl2 = ``auc_mu``, `AUC-mu <https://proceedings.mlr.press/v97/kleiman19a.html>`__
   // descl2 = ``multi_logloss``, log loss for multi-class classification, aliases: ``multiclass``, ``softmax``, ``multiclassova``, ``multiclass_ova``, ``ova``, ``ovr``
   // descl2 = ``multi_error``, error rate for multi-class classification
   // descl2 = ``cross_entropy``, cross-entropy (with optional linear weights), aliases: ``xentropy``
@@ -1319,4 +1320,4 @@ inline std::string ParseMetricAlias(const std::string& type) {
 
 }   // namespace LightGBM
 
-#endif   // LightGBM_CONFIG_H_
+#endif   // LIGHTGBM_INCLUDE_LIGHTGBM_CONFIG_H_

include/LightGBM/cuda/cuda_algorithms.hpp

@@ -4,8 +4,8 @@
  * Modifications Copyright(C) 2023 Advanced Micro Devices, Inc. All rights reserved.
  */
 
-#ifndef LIGHTGBM_CUDA_CUDA_ALGORITHMS_HPP_
-#define LIGHTGBM_CUDA_CUDA_ALGORITHMS_HPP_
+#ifndef LIGHTGBM_INCLUDE_LIGHTGBM_CUDA_CUDA_ALGORITHMS_HPP_
+#define LIGHTGBM_INCLUDE_LIGHTGBM_CUDA_CUDA_ALGORITHMS_HPP_
 
 #ifdef USE_CUDA
 
@@ -622,4 +622,4 @@ __device__ VAL_T PercentileDevice(const VAL_T* values,
 }  // namespace LightGBM
 
 #endif  // USE_CUDA
-#endif  // LIGHTGBM_CUDA_CUDA_ALGORITHMS_HPP_
+#endif  // LIGHTGBM_INCLUDE_LIGHTGBM_CUDA_CUDA_ALGORITHMS_HPP_

include/LightGBM/cuda/cuda_column_data.hpp

@@ -3,10 +3,10 @@
  * Licensed under the MIT License. See LICENSE file in the project root for license information.
  */
 
-#ifdef USE_CUDA
+#ifndef LIGHTGBM_INCLUDE_LIGHTGBM_CUDA_CUDA_COLUMN_DATA_HPP_
+#define LIGHTGBM_INCLUDE_LIGHTGBM_CUDA_CUDA_COLUMN_DATA_HPP_
 
-#ifndef LIGHTGBM_CUDA_CUDA_COLUMN_DATA_HPP_
-#define LIGHTGBM_CUDA_CUDA_COLUMN_DATA_HPP_
+#ifdef USE_CUDA
 
 #include <LightGBM/config.h>
 #include <LightGBM/cuda/cuda_utils.hu>
@@ -137,6 +137,6 @@ class CUDAColumnData {
 
 }  // namespace LightGBM
 
-#endif  // LIGHTGBM_CUDA_CUDA_COLUMN_DATA_HPP_
-
 #endif  // USE_CUDA
+
+#endif  // LIGHTGBM_INCLUDE_LIGHTGBM_CUDA_CUDA_COLUMN_DATA_HPP_

include/LightGBM/cuda/cuda_metadata.hpp

@@ -3,10 +3,10 @@
  * Licensed under the MIT License. See LICENSE file in the project root for license information.
  */
 
-#ifdef USE_CUDA
+#ifndef LIGHTGBM_INCLUDE_LIGHTGBM_CUDA_CUDA_METADATA_HPP_
+#define LIGHTGBM_INCLUDE_LIGHTGBM_CUDA_CUDA_METADATA_HPP_
 
-#ifndef LIGHTGBM_CUDA_CUDA_METADATA_HPP_
-#define LIGHTGBM_CUDA_CUDA_METADATA_HPP_
+#ifdef USE_CUDA
 
 #include <LightGBM/cuda/cuda_utils.hu>
 #include <LightGBM/meta.h>
@@ -53,6 +53,6 @@ class CUDAMetadata {
 
 }  // namespace LightGBM
 
-#endif  // LIGHTGBM_CUDA_CUDA_METADATA_HPP_
-
 #endif  // USE_CUDA
+
+#endif  // LIGHTGBM_INCLUDE_LIGHTGBM_CUDA_CUDA_METADATA_HPP_

include/LightGBM/cuda/cuda_metric.hpp

@@ -4,8 +4,8 @@
  * license information.
  */
 
-#ifndef LIGHTGBM_CUDA_CUDA_METRIC_HPP_
-#define LIGHTGBM_CUDA_CUDA_METRIC_HPP_
+#ifndef LIGHTGBM_INCLUDE_LIGHTGBM_CUDA_CUDA_METRIC_HPP_
+#define LIGHTGBM_INCLUDE_LIGHTGBM_CUDA_CUDA_METRIC_HPP_
 
 #ifdef USE_CUDA
 
@@ -41,4 +41,4 @@ class CUDAMetricInterface: public HOST_METRIC {
 
 #endif  // USE_CUDA
 
-#endif  // LIGHTGBM_CUDA_CUDA_METRIC_HPP_
+#endif  // LIGHTGBM_INCLUDE_LIGHTGBM_CUDA_CUDA_METRIC_HPP_

include/LightGBM/cuda/cuda_objective_function.hpp

@@ -4,8 +4,8 @@
  * license information.
  */
 
-#ifndef LIGHTGBM_CUDA_CUDA_OBJECTIVE_FUNCTION_HPP_
-#define LIGHTGBM_CUDA_CUDA_OBJECTIVE_FUNCTION_HPP_
+#ifndef LIGHTGBM_INCLUDE_LIGHTGBM_CUDA_CUDA_OBJECTIVE_FUNCTION_HPP_
+#define LIGHTGBM_INCLUDE_LIGHTGBM_CUDA_CUDA_OBJECTIVE_FUNCTION_HPP_
 
 #ifdef USE_CUDA
 
@@ -83,4 +83,4 @@ class CUDAObjectiveInterface: public HOST_OBJECTIVE {
 
 #endif  // USE_CUDA
 
-#endif  // LIGHTGBM_CUDA_CUDA_OBJECTIVE_FUNCTION_HPP_
+#endif  // LIGHTGBM_INCLUDE_LIGHTGBM_CUDA_CUDA_OBJECTIVE_FUNCTION_HPP_

include/LightGBM/cuda/cuda_random.hpp

@@ -2,8 +2,8 @@
  * Copyright (c) 2021 Microsoft Corporation. All rights reserved.
  * Licensed under the MIT License. See LICENSE file in the project root for license information.
  */
-#ifndef LIGHTGBM_CUDA_CUDA_RANDOM_HPP_
-#define LIGHTGBM_CUDA_CUDA_RANDOM_HPP_
+#ifndef LIGHTGBM_INCLUDE_LIGHTGBM_CUDA_CUDA_RANDOM_HPP_
+#define LIGHTGBM_INCLUDE_LIGHTGBM_CUDA_CUDA_RANDOM_HPP_
 
 #ifdef USE_CUDA
 
@@ -73,4 +73,4 @@ class CUDARandom {
 
 #endif  // USE_CUDA
 
-#endif  // LIGHTGBM_CUDA_CUDA_RANDOM_HPP_
+#endif  // LIGHTGBM_INCLUDE_LIGHTGBM_CUDA_CUDA_RANDOM_HPP_

include/LightGBM/cuda/cuda_rocm_interop.h

 /*!
  * Copyright(C) 2023 Advanced Micro Devices, Inc. All rights reserved.
  */
-#ifndef LIGHTGBM_CUDA_CUDA_ROCM_INTEROP_H_
-#define LIGHTGBM_CUDA_CUDA_ROCM_INTEROP_H_
+
+#ifndef LIGHTGBM_INCLUDE_LIGHTGBM_CUDA_CUDA_ROCM_INTEROP_H_
+#define LIGHTGBM_INCLUDE_LIGHTGBM_CUDA_CUDA_ROCM_INTEROP_H_
 
 #ifdef USE_CUDA
 
@@ -61,8 +62,8 @@ static inline constexpr int WARP_SIZE_INTERNAL() {
 #else  // __HIP_PLATFORM_AMD__
 // CUDA warpSize is not a constexpr, but always 32
 #define WARPSIZE 32
-#endif
+#endif  // defined(__HIP_PLATFORM_AMD__) || defined(__HIP__)
 
 #endif  // USE_CUDA
 
-#endif  // LIGHTGBM_CUDA_CUDA_ROCM_INTEROP_H_
+#endif  // LIGHTGBM_INCLUDE_LIGHTGBM_CUDA_CUDA_ROCM_INTEROP_H_

include/LightGBM/cuda/cuda_row_data.hpp

@@ -3,10 +3,10 @@
  * Licensed under the MIT License. See LICENSE file in the project root for license information.
  */
 
-#ifdef USE_CUDA
+#ifndef LIGHTGBM_INCLUDE_LIGHTGBM_CUDA_CUDA_ROW_DATA_HPP_
+#define LIGHTGBM_INCLUDE_LIGHTGBM_CUDA_CUDA_ROW_DATA_HPP_
 
-#ifndef LIGHTGBM_CUDA_CUDA_ROW_DATA_HPP_
-#define LIGHTGBM_CUDA_CUDA_ROW_DATA_HPP_
+#ifdef USE_CUDA
 
 #include <LightGBM/bin.h>
 #include <LightGBM/config.h>
@@ -175,6 +175,7 @@ class CUDARowData {
 };
 
 }  // namespace LightGBM
-#endif  // LIGHTGBM_CUDA_CUDA_ROW_DATA_HPP_
 
 #endif  // USE_CUDA
+
+#endif  // LIGHTGBM_INCLUDE_LIGHTGBM_CUDA_CUDA_ROW_DATA_HPP_

include/LightGBM/cuda/cuda_split_info.hpp

@@ -5,10 +5,10 @@
  * Modifications Copyright(C) 2023 Advanced Micro Devices, Inc. All rights reserved.
  */
 
-#ifdef USE_CUDA
+#ifndef LIGHTGBM_INCLUDE_LIGHTGBM_CUDA_CUDA_SPLIT_INFO_HPP_
+#define LIGHTGBM_INCLUDE_LIGHTGBM_CUDA_CUDA_SPLIT_INFO_HPP_
 
-#ifndef LIGHTGBM_CUDA_CUDA_SPLIT_INFO_HPP_
-#define LIGHTGBM_CUDA_CUDA_SPLIT_INFO_HPP_
+#ifdef USE_CUDA
 
 #include <LightGBM/meta.h>
 
@@ -103,6 +103,6 @@ class CUDASplitInfo {
 
 }  // namespace LightGBM
 
-#endif  // LIGHTGBM_CUDA_CUDA_SPLIT_INFO_HPP_
-
 #endif  // USE_CUDA
+
+#endif  // LIGHTGBM_INCLUDE_LIGHTGBM_CUDA_CUDA_SPLIT_INFO_HPP_

include/LightGBM/cuda/cuda_tree.hpp

@@ -3,10 +3,10 @@
  * Licensed under the MIT License. See LICENSE file in the project root for license information.
  */
 
-#ifdef USE_CUDA
+#ifndef LIGHTGBM_INCLUDE_LIGHTGBM_CUDA_CUDA_TREE_HPP_
+#define LIGHTGBM_INCLUDE_LIGHTGBM_CUDA_CUDA_TREE_HPP_
 
-#ifndef LIGHTGBM_CUDA_CUDA_TREE_HPP_
-#define LIGHTGBM_CUDA_CUDA_TREE_HPP_
+#ifdef USE_CUDA
 
 #include <LightGBM/cuda/cuda_column_data.hpp>
 #include <LightGBM/cuda/cuda_split_info.hpp>
@@ -168,6 +168,6 @@ class CUDATree : public Tree {
 
 }  // namespace LightGBM
 
-#endif  // LIGHTGBM_CUDA_CUDA_TREE_HPP_
-
 #endif  // USE_CUDA
+
+#endif  // LIGHTGBM_INCLUDE_LIGHTGBM_CUDA_CUDA_TREE_HPP_