commit 94c7471e3a29e44681cb40d8a0406026867fe299
author Yongfeng Gu <yongfengg@nvidia.com> Fri Aug 02 14:11:25 2019 -0400
committer Yongfeng Gu <yongfengg@nvidia.com> Fri Aug 02 14:11:25 2019 -0400
tree 3134ba9cd2ac49bcf20e9b41e81f1c8f285fdb89
parent dab29eebfa2f80fe7739ca34cdfdbc64ef24a31c

Minor change to one comment.

tensorflow/compiler/xla/service/gpu/ir_emission_utils.cc

diff --git a/tensorflow/compiler/xla/service/gpu/ir_emission_utils.cc b/tensorflow/compiler/xla/service/gpu/ir_emission_utils.cc
index b5c197f..78f8e22 100644
--- a/tensorflow/compiler/xla/service/gpu/ir_emission_utils.cc
+++ b/tensorflow/compiler/xla/service/gpu/ir_emission_utils.cc
@@ -220,7 +220,7 @@
   }
 
   // For column reduction, the tile block is tize_size_y x tile_size_x, and we
-  // are reducing along tile_size_y. tile_size_y needs to be
+  // are reducing along tile_size_y. Only tile_size_y needs to be
   // large enough to make the tiling implementation efficient.
   return dims_in_elem[1] >= kWarpSize;
 }