Merge pull request NVIDIA#1471 from lilohuang/main

Reduce scan_by_key memory consumption

Author: alliepiper

thrust/system/detail/generic/scan_by_key.inl

@@ -108,7 +108,7 @@ __host__ __device__
                                        AssociativeOperator binary_op)
 {
   using OutputType = typename thrust::iterator_traits<InputIterator2>::value_type;
-  using HeadFlagType = thrust::detail::uint32_t;
+  using HeadFlagType = thrust::detail::uint8_t;
 
   const size_t n = last1 - first1;
 
@@ -204,7 +204,7 @@ __host__ __device__
                                        AssociativeOperator binary_op)
 {
   using OutputType = T;
-  using HeadFlagType = thrust::detail::uint32_t;
+  using HeadFlagType = thrust::detail::uint8_t;
 
   const size_t n = last1 - first1;