apply reviewer suggestions

include/LightGBM/cuda/cuda_rocm_interop.h

 /*!
  * Copyright(C) 2023 Advanced Micro Devices, Inc. All rights reserved.
  */
-#pragma once
+#ifndef LIGHTGBM_CUDA_CUDA_ROCM_INTEROP_H_
+#define LIGHTGBM_CUDA_CUDA_ROCM_INTEROP_H_
 
 #ifdef USE_CUDA
 
@@ -63,3 +64,5 @@ static inline constexpr int WARP_SIZE_INTERNAL() {
 #endif
 
 #endif  // USE_CUDA
+
+#endif  // LIGHTGBM_CUDA_CUDA_ROCM_INTEROP_H_

src/treelearner/cuda/cuda_single_gpu_tree_learner.hpp

@@ -144,7 +144,7 @@ class CUDASingleGPUTreeLearner: public SerialTreeLearner {
 
 }  // namespace LightGBM
 
-#else  // USE_CUDA || USE_ROCM
+#else  // USE_CUDA
 
 // When GPU support is not compiled in, quit with an error message
 
@@ -155,7 +155,7 @@ class CUDASingleGPUTreeLearner: public SerialTreeLearner {
     #pragma warning(disable : 4702)
     explicit CUDASingleGPUTreeLearner(const Config* tree_config, const bool /*boosting_on_cuda*/) : SerialTreeLearner(tree_config) {
       Log::Fatal("CUDA Tree Learner was not enabled in this build.\n"
-                 "Please recompile with CMake option -DUSE_CUDA=1 or -DUSE_ROCM=1");
+                 "Please recompile with CMake option -DUSE_CUDA=1 (NVIDIA GPUs) or -DUSE_ROCM=1 (AMD GPUs)");
     }
 };
 

src/treelearner/serial_tree_learner.h

@@ -216,7 +216,7 @@ class SerialTreeLearner: public TreeLearner {
   std::vector<score_t, boost::alignment::aligned_allocator<score_t, 4096>> ordered_gradients_;
   /*! \brief hessians of current iteration, ordered for cache optimized, aligned to 4K page */
   std::vector<score_t, boost::alignment::aligned_allocator<score_t, 4096>> ordered_hessians_;
-#elif defined(USE_CUDA) || defined(USE_ROCM)
+#elif defined(USE_CUDA)
   /*! \brief gradients of current iteration, ordered for cache optimized */
   std::vector<score_t, CHAllocator<score_t>> ordered_gradients_;
   /*! \brief hessians of current iteration, ordered for cache optimized */