Hendrik/xgboost
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Bound the size of the histogram cache. (#9440)

Browse Source 
- A new histogram collection with a limit in size.
- Unify histogram building logic between hist, multi-hist, and approx.
This commit is contained in:
Jiaming Yuan
2023-08-08 03:21:26 +08:00
committed by GitHub
parent 5bd163aa25
commit 54029a59af
27 changed files with 994 additions and 565 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
tests/cpp/tree/test_evaluate_splits.h
View File

@@ -2,22 +2,24 @@
* Copyright 2022-2023 by XGBoost Contributors
*/
#include <gtest/gtest.h>
#include <xgboost/base.h> // for GradientPairInternal, GradientPairPrecise
#include <xgboost/data.h> // for MetaInfo
#include <xgboost/host_device_vector.h> // for HostDeviceVector
#include <xgboost/span.h> // for operator!=, Span, SpanIterator
#include <xgboost/base.h> // for GradientPairInternal, GradientPairPrecise
#include <xgboost/data.h> // for MetaInfo
#include <xgboost/host_device_vector.h> // for HostDeviceVector
#include <xgboost/span.h> // for operator!=, Span, SpanIterator
#include <algorithm> // for max, max_element, next_permutation, copy
#include <cmath> // for isnan
#include <cstddef> // for size_t
#include <cstdint> // for int32_t, uint64_t, uint32_t
#include <limits> // for numeric_limits
#include <numeric> // for iota
#include <tuple> // for make_tuple, tie, tuple
#include <utility> // for pair
#include <vector> // for vector
#include <algorithm> // for max, max_element, next_permutation, copy
#include <cmath> // for isnan
#include <cstddef> // for size_t
#include <cstdint> // for int32_t, uint64_t, uint32_t
#include <limits> // for numeric_limits
#include <numeric> // for iota
#include <tuple> // for make_tuple, tie, tuple
#include <utility> // for pair
#include <vector> // for vector
#include "../../../src/common/hist_util.h" // for HistogramCuts, HistCollection, GHistRow
#include "../../../src/tree/hist/hist_cache.h" // for HistogramCollection
#include "../../../src/tree/hist/param.h" // for HistMakerTrainParam
#include "../../../src/tree/param.h" // for TrainParam, GradStats
#include "../../../src/tree/split_evaluator.h" // for TreeEvaluator
#include "../helpers.h" // for SimpleLCG, SimpleRealUniformDistribution
@@ -35,7 +37,7 @@ class TestPartitionBasedSplit : public ::testing::Test {
MetaInfo info_;
float best_score_{-std::numeric_limits<float>::infinity()};
common::HistogramCuts cuts_;
common::HistCollection hist_;
BoundedHistCollection hist_;
GradientPairPrecise total_gpair_;
void SetUp() override {
@@ -56,9 +58,9 @@ class TestPartitionBasedSplit : public ::testing::Test {
cuts_.min_vals_.Resize(1);
hist_.Init(cuts_.TotalBins());
hist_.AddHistRow(0);
hist_.AllocateAllData();
HistMakerTrainParam hist_param;
hist_.Reset(cuts_.TotalBins(), hist_param.internal_max_cached_hist_node);
hist_.AllocateHistograms({0});
auto node_hist = hist_[0];
SimpleLCG lcg;