Unify CPU hist sketching (#5880)

dmlc · Aug 11, 2020 · ee70a23 · ee70a23
1 parent bd6b7f4
commit ee70a23
Show file tree

Hide file tree

Showing 18 changed files with 647 additions and 676 deletions.
diff --git a/amalgamation/xgboost-all0.cc b/amalgamation/xgboost-all0.cc
@@ -70,6 +70,7 @@
 #include "../src/common/common.cc"
 #include "../src/common/charconv.cc"
 #include "../src/common/timer.cc"
+#include "../src/common/quantile.cc"
 #include "../src/common/host_device_vector.cc"
 #include "../src/common/hist_util.cc"
 #include "../src/common/json.cc"

diff --git a/include/xgboost/data.h b/include/xgboost/data.h
@@ -239,6 +239,21 @@ struct BatchParam {
   }
 };
 
+struct HostSparsePageView {
+  using Inst = common::Span<Entry const>;
+
+  common::Span<bst_row_t const> offset;
+  common::Span<Entry const> data;
+
+  Inst operator[](size_t i) const {
+    auto size = *(offset.data() + i + 1) - *(offset.data() + i);
+    return {data.data() + *(offset.data() + i),
+            static_cast<Inst::index_type>(size)};
+  }
+
+  size_t Size() const { return offset.size() == 0 ? 0 : offset.size() - 1; }
+};
+
 /*!
  * \brief In-memory storage unit of sparse batch, stored in CSR format.
  */
@@ -270,6 +285,11 @@ class SparsePage {
             static_cast<Inst::index_type>(size)};
   }
 
+  HostSparsePageView GetView() const {
+    return {offset.ConstHostSpan(), data.ConstHostSpan()};
+  }
+
+
   /*! \brief constructor */
   SparsePage() {
     this->Clear();