clang format

src/targets/gpu/device/logsoftmax.cpp

@@ -40,7 +40,8 @@ void logsoftmax(hipStream_t stream, const argument& result, const argument& arg,
             auto data_idx  = batch_idx;
             // load data to lds and compute the batch max
             std::size_t remaining_item_num = batch_item_num;
-            std::size_t round_item_num     = (batch_item_num + block_size - 1) / block_size * block_size;
+            std::size_t round_item_num =
+                (batch_item_num + block_size - 1) / block_size * block_size;
             lds_data[max_block_size] = input[0];
             for(std::size_t i = thr_idx; i < round_item_num; i += block_size)
             {

src/targets/gpu/device/softmax.cpp

@@ -40,7 +40,8 @@ void softmax(hipStream_t stream, const argument& result, const argument& arg, in
             auto data_idx  = batch_idx;
             // load data to lds and compute the batch max
             std::size_t remaining_item_num = batch_item_num;
-            std::size_t round_item_num     = (batch_item_num + block_size - 1) / block_size * block_size;
+            std::size_t round_item_num =
+                (batch_item_num + block_size - 1) / block_size * block_size;
             lds_data[max_block_size] = input[0];
             for(std::size_t i = thr_idx; i < round_item_num; i += block_size)
             {

src/targets/gpu/include/migraphx/gpu/device/reduce_opers.hpp

@@ -11,8 +11,11 @@ namespace gpu {
 namespace device {
 
 template <class T>
-inline __device__ void
-reduce_max(T* data_ptr, std::size_t block_size, std::size_t thr_idx, std::size_t item_num, std::size_t max_index)
+inline __device__ void reduce_max(T* data_ptr,
+                                  std::size_t block_size,
+                                  std::size_t thr_idx,
+                                  std::size_t item_num,
+                                  std::size_t max_index)
 {
     while(true)
     {
@@ -39,8 +42,11 @@ reduce_max(T* data_ptr, std::size_t block_size, std::size_t thr_idx, std::size_t
 }
 
 template <class T>
-inline __device__ void
-reduce_min(T* data_ptr, std::size_t block_size, std::size_t thr_idx, std::size_t item_num, std::size_t min_index)
+inline __device__ void reduce_min(T* data_ptr,
+                                  std::size_t block_size,
+                                  std::size_t thr_idx,
+                                  std::size_t item_num,
+                                  std::size_t min_index)
 {
     while(true)
     {
@@ -67,8 +73,11 @@ reduce_min(T* data_ptr, std::size_t block_size, std::size_t thr_idx, std::size_t
 }
 
 template <class T>
-inline __device__ void
-reduce_sum(T* data_ptr, std::size_t block_size, std::size_t thr_idx, std::size_t item_num, std::size_t sum_index)
+inline __device__ void reduce_sum(T* data_ptr,
+                                  std::size_t block_size,
+                                  std::size_t thr_idx,
+                                  std::size_t item_num,
+                                  std::size_t sum_index)
 {
     while(true)
     {