speed up for const hessian (#2857)

* speed up for const hessian * rename template * fix clang build * template init * add comment
microsoft · Mar 3, 2020 · bc7d2f0 · bc7d2f0
1 parent f7037fd
commit bc7d2f0
Show file tree

Hide file tree

Showing 8 changed files with 272 additions and 265 deletions.
diff --git a/include/LightGBM/bin.h b/include/LightGBM/bin.h
@@ -30,6 +30,9 @@ enum MissingType {
 };
 
 typedef double hist_t;
+typedef uint64_t hist_cnt_t;
+// check at compile time
+static_assert(sizeof(hist_t) == sizeof(hist_cnt_t), "Histogram entry size is not correct");
 
 const size_t kHistEntrySize = 2 * sizeof(hist_t);
 const int kHistOffset = 2;
@@ -482,20 +485,24 @@ class MultiValBin {
       const std::vector<uint32_t>& lower, const std::vector<uint32_t>& upper,
       const std::vector<uint32_t>& delta) = 0;
 
-  virtual void ConstructHistogram(
-    const data_size_t* data_indices, data_size_t start, data_size_t end,
-    const score_t* gradients, const score_t* hessians,
-    hist_t* out) const = 0;
+  virtual void ConstructHistogram(const data_size_t* data_indices,
+                                  data_size_t start, data_size_t end,
+                                  const score_t* gradients,
+                                  const score_t* hessians,
+                                  hist_t* out) const = 0;
 
   virtual void ConstructHistogram(data_size_t start, data_size_t end,
-    const score_t* gradients, const score_t* hessians,
-    hist_t* out) const = 0;
+                                  const score_t* gradients,
+                                  const score_t* hessians,
+                                  hist_t* out) const = 0;
 
-  virtual void ConstructHistogram(const data_size_t* data_indices, data_size_t start, data_size_t end,
-    const score_t* ordered_gradients, hist_t* out) const = 0;
 
-  virtual void ConstructHistogram(data_size_t start, data_size_t end,
-    const score_t* ordered_gradients, hist_t* out) const = 0;
+  virtual void ConstructHistogramOrdered(const data_size_t* data_indices,
+                                         data_size_t start, data_size_t end,
+                                         const score_t* ordered_gradients,
+                                         const score_t* ordered_hessians,
+                                         hist_t* out) const = 0;
+
 
   virtual void FinishLoad() = 0;
 

diff --git a/include/LightGBM/dataset.h b/include/LightGBM/dataset.h
@@ -482,20 +482,56 @@ class Dataset {
   void InitTrain(const std::vector<int8_t>& is_feature_used,
                  TrainingShareStates* share_state) const;
 
-  void ConstructHistograms(const std::vector<int8_t>& is_feature_used,
-                           const data_size_t* data_indices,
-                           data_size_t num_data, const score_t* gradients,
-                           const score_t* hessians, score_t* ordered_gradients,
-                           score_t* ordered_hessians,
-                           TrainingShareStates* share_state,
-                           hist_t* histogram_data) const;
-
+  template <bool USE_INDICES, bool USE_HESSIAN>
+  void ConstructHistogramsInner(const std::vector<int8_t>& is_feature_used,
+                                const data_size_t* data_indices,
+                                data_size_t num_data, const score_t* gradients,
+                                const score_t* hessians,
+                                score_t* ordered_gradients,
+                                score_t* ordered_hessians,
+                                TrainingShareStates* share_state,
+                                hist_t* hist_data) const;
+
+  template <bool USE_INDICES, bool ORDERED>
   void ConstructHistogramsMultiVal(const data_size_t* data_indices,
                                    data_size_t num_data,
                                    const score_t* gradients,
                                    const score_t* hessians,
                                    TrainingShareStates* share_state,
-                                   hist_t* histogram_data) const;
+                                   hist_t* hist_data) const;
+
+  inline void ConstructHistograms(
+      const std::vector<int8_t>& is_feature_used,
+      const data_size_t* data_indices, data_size_t num_data,
+      const score_t* gradients, const score_t* hessians,
+      score_t* ordered_gradients, score_t* ordered_hessians,
+      TrainingShareStates* share_state, hist_t* hist_data) const {
+    if (num_data <= 0) {
+      return;
+    }
+    bool use_indices = data_indices != nullptr && (num_data < num_data_);
+    if (share_state->is_constant_hessian) {
+      if (use_indices) {
+        ConstructHistogramsInner<true, false>(
+            is_feature_used, data_indices, num_data, gradients, hessians,
+            ordered_gradients, ordered_hessians, share_state, hist_data);
+      } else {
+        ConstructHistogramsInner<false, false>(
+            is_feature_used, data_indices, num_data, gradients, hessians,
+            ordered_gradients, ordered_hessians, share_state, hist_data);
+      }
+    } else {
+      if (use_indices) {
+        ConstructHistogramsInner<true, true>(
+            is_feature_used, data_indices, num_data, gradients, hessians,
+            ordered_gradients, ordered_hessians, share_state, hist_data);
+      } else {
+        ConstructHistogramsInner<false, true>(
+            is_feature_used, data_indices, num_data, gradients, hessians,
+            ordered_gradients, ordered_hessians, share_state, hist_data);
+      }
+    }
+  }
 
   void FixHistogram(int feature_idx, double sum_gradient, double sum_hessian, hist_t* data) const;