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

Reduce thread contention in column split tests. (#10658)

Browse Source 
---------

Co-authored-by: Philip Hyunsu Cho <chohyu01@cs.washington.edu>
This commit is contained in:
Jiaming Yuan
2024-08-01 18:36:46 +08:00
committed by GitHub
parent 778751a1bb
commit 77c844cef7
8 changed files with 101 additions and 61 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
tests/cpp/tree/test_approx.cc
View File

@@ -2,6 +2,11 @@
* Copyright 2021-2024, XGBoost contributors.
*/
#include <gtest/gtest.h>
#include <xgboost/tree_updater.h> // for TreeUpdater
#include <algorithm> // for transform
#include <memory> // for unique_ptr
#include <vector> // for vector
#include "../../../src/tree/common_row_partitioner.h"
#include "../../../src/tree/param.h" // for TrainParam

67
tests/cpp/tree/test_column_split.cc Normal file
View File

@@ -0,0 +1,67 @@
/**
* Copyright 2024, XGBoost Contributors
*/
#include "test_column_split.h"
#include <gtest/gtest.h>
#include <xgboost/tree_model.h> // for RegTree
#include <xgboost/tree_updater.h> // for TreeUpdater
#include <thread> // for hardware_concurrency
#include <vector> // for vector
#include "../../../src/tree/param.h" // for TrainParam
#include "../collective/test_worker.h" // for TestDistributedGlobal
namespace xgboost::tree {
void TestColumnSplit(bst_target_t n_targets, bool categorical, std::string name, float sparsity) {
auto constexpr kRows = 32;
auto constexpr kCols = 16;
RegTree expected_tree{n_targets, static_cast<bst_feature_t>(kCols)};
ObjInfo task{ObjInfo::kRegression};
Context ctx;
{
auto p_dmat = GenerateCatDMatrix(kRows, kCols, sparsity, categorical);
auto gpair = GenerateRandomGradients(&ctx, kRows, n_targets);
std::unique_ptr<TreeUpdater> updater{TreeUpdater::Create(name, &ctx, &task)};
std::vector<HostDeviceVector<bst_node_t>> position(1);
TrainParam param;
param.Init(Args{});
updater->Configure(Args{});
updater->Update(&param, &gpair, p_dmat.get(), position, {&expected_tree});
}
auto constexpr kWorldSize = 2;
auto verify = [&] {
Context ctx;
ctx.UpdateAllowUnknown(
Args{{"nthread", std::to_string(collective::GetWorkerLocalThreads(kWorldSize))}});
auto p_dmat = GenerateCatDMatrix(kRows, kCols, sparsity, categorical);
auto gpair = GenerateRandomGradients(&ctx, kRows, n_targets);
ObjInfo task{ObjInfo::kRegression};
std::unique_ptr<TreeUpdater> updater{TreeUpdater::Create(name, &ctx, &task)};
std::vector<HostDeviceVector<bst_node_t>> position(1);
std::unique_ptr<DMatrix> sliced{
p_dmat->SliceCol(collective::GetWorldSize(), collective::GetRank())};
RegTree tree{n_targets, static_cast<bst_feature_t>(kCols)};
TrainParam param;
param.Init(Args{});
updater->Configure(Args{});
updater->Update(&param, &gpair, sliced.get(), position, {&tree});
Json json{Object{}};
tree.SaveModel(&json);
Json expected_json{Object{}};
expected_tree.SaveModel(&expected_json);
ASSERT_EQ(json, expected_json);
};
collective::TestDistributedGlobal(kWorldSize, [&] { verify(); });
}
} // namespace xgboost::tree

52
tests/cpp/tree/test_column_split.h
View File

@@ -4,15 +4,11 @@
#pragma once
#include <xgboost/data.h> // for FeatureType, DMatrix
#include <xgboost/tree_model.h> // for RegTree
#include <xgboost/tree_updater.h> // for TreeUpdater
#include <cstddef> // for size_t
#include <memory> // for shared_ptr
#include <vector> // for vector
#include "../../../src/tree/param.h" // for TrainParam
#include "../collective/test_worker.h" // for TestDistributedGlobal
#include "../helpers.h" // for RandomDataGenerator
namespace xgboost::tree {
@@ -33,51 +29,5 @@ inline std::shared_ptr<DMatrix> GenerateCatDMatrix(std::size_t rows, std::size_t
}
}
inline void TestColumnSplit(bst_target_t n_targets, bool categorical, std::string name,
float sparsity) {
auto constexpr kRows = 32;
auto constexpr kCols = 16;
RegTree expected_tree{n_targets, static_cast<bst_feature_t>(kCols)};
ObjInfo task{ObjInfo::kRegression};
Context ctx;
{
auto p_dmat = GenerateCatDMatrix(kRows, kCols, sparsity, categorical);
auto gpair = GenerateRandomGradients(&ctx, kRows, n_targets);
std::unique_ptr<TreeUpdater> updater{TreeUpdater::Create(name, &ctx, &task)};
std::vector<HostDeviceVector<bst_node_t>> position(1);
TrainParam param;
param.Init(Args{});
updater->Configure(Args{});
updater->Update(&param, &gpair, p_dmat.get(), position, {&expected_tree});
}
auto verify = [&] {
Context ctx;
auto p_dmat = GenerateCatDMatrix(kRows, kCols, sparsity, categorical);
auto gpair = GenerateRandomGradients(&ctx, kRows, n_targets);
ObjInfo task{ObjInfo::kRegression};
std::unique_ptr<TreeUpdater> updater{TreeUpdater::Create(name, &ctx, &task)};
std::vector<HostDeviceVector<bst_node_t>> position(1);
std::unique_ptr<DMatrix> sliced{
p_dmat->SliceCol(collective::GetWorldSize(), collective::GetRank())};
RegTree tree{n_targets, static_cast<bst_feature_t>(kCols)};
TrainParam param;
param.Init(Args{});
updater->Configure(Args{});
updater->Update(&param, &gpair, sliced.get(), position, {&tree});
Json json{Object{}};
tree.SaveModel(&json);
Json expected_json{Object{}};
expected_tree.SaveModel(&expected_json);
ASSERT_EQ(json, expected_json);
};
auto constexpr kWorldSize = 2;
collective::TestDistributedGlobal(kWorldSize, [&] { verify(); });
}
void TestColumnSplit(bst_target_t n_targets, bool categorical, std::string name, float sparsity);
} // namespace xgboost::tree