clang format

example/32_batched_gemm_scale_softmax_gemm/batched_multihead_attention_backward_pt1_fp16.cpp

@@ -160,7 +160,7 @@ using DeviceGemmInstance =
         8,              // CShuffleBlockTransferScalarPerVector_NPerBlock
         MaskingSpec>;   // MaskingSpecialization
 #else
-//2nd template
+// 2nd template
 using DeviceGemmInstance =
     ck::tensor_operation::device::DeviceBatchedMultiheadAttentionBackward_Xdl_CShuffle_PT1<
         NumDimG,

include/ck/tensor_operation/gpu/grid/gridwise_batched_multihead_attention_backward_xdl_cshuffle_pt1.hpp

@@ -1564,8 +1564,8 @@ struct GridwiseBatchedMultiheadAttentionBackward_Xdl_CShuffle_PT1
                      n3, // NInputNum
                      n4>,
             Sequence<0, 1, 2, 3, 4, 5, 6, 7, 8, 9>,
-            9,  // DstVectorDim
-            1,  // DstScalarPerVector
+            9, // DstVectorDim
+            1, // DstScalarPerVector
             InMemoryDataOperationEnum::Set,
             1, // DstScalarStrideInVector
             true>{z_grid_desc_m0_n0_m1_n1_m2_n2_m3_n3_n4_n5,
@@ -1938,7 +1938,6 @@ struct GridwiseBatchedMultiheadAttentionBackward_Xdl_CShuffle_PT1
                     else
                     {
                         s_element_op(s_slash_p_thread_buf(i), s_slash_p_thread_buf[i]);
-
                     }
                 });
             }