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

[backport] Fix scope of feature set pointers (#8850) (#8972)

Browse Source 
---------

Co-authored-by: Rory Mitchell <r.a.mitchell.nz@gmail.com>
This commit is contained in:
Jiaming Yuan 2023-03-27 00:33:08 +08:00 committed by GitHub
parent ba50e6eb62
commit 4be75d852c
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 35 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
src/tree/updater_gpu_hist.cu
View File

@ -306,6 +306,8 @@ struct GPUHistMakerDevice {
matrix.is_dense matrix.is_dense
}; };
dh::TemporaryArray<GPUExpandEntry> entries(2 * candidates.size()); dh::TemporaryArray<GPUExpandEntry> entries(2 * candidates.size());
// Store the feature set ptrs so they dont go out of scope before the kernel is called
std::vector<std::shared_ptr<HostDeviceVector<bst_feature_t>>> feature_sets;
for (size_t i = 0; i < candidates.size(); i++) { for (size_t i = 0; i < candidates.size(); i++) {
auto candidate = candidates.at(i); auto candidate = candidates.at(i);
int left_nidx = tree[candidate.nid].LeftChild(); int left_nidx = tree[candidate.nid].LeftChild();
@ -314,10 +316,12 @@ struct GPUHistMakerDevice {
nidx[i * 2 + 1] = right_nidx; nidx[i * 2 + 1] = right_nidx;
auto left_sampled_features = column_sampler.GetFeatureSet(tree.GetDepth(left_nidx)); auto left_sampled_features = column_sampler.GetFeatureSet(tree.GetDepth(left_nidx));
left_sampled_features->SetDevice(ctx_->gpu_id); left_sampled_features->SetDevice(ctx_->gpu_id);
feature_sets.emplace_back(left_sampled_features);
common::Span<bst_feature_t> left_feature_set = common::Span<bst_feature_t> left_feature_set =
interaction_constraints.Query(left_sampled_features->DeviceSpan(), left_nidx); interaction_constraints.Query(left_sampled_features->DeviceSpan(), left_nidx);
auto right_sampled_features = column_sampler.GetFeatureSet(tree.GetDepth(right_nidx)); auto right_sampled_features = column_sampler.GetFeatureSet(tree.GetDepth(right_nidx));
right_sampled_features->SetDevice(ctx_->gpu_id); right_sampled_features->SetDevice(ctx_->gpu_id);
feature_sets.emplace_back(right_sampled_features);
common::Span<bst_feature_t> right_feature_set = common::Span<bst_feature_t> right_feature_set =
interaction_constraints.Query(right_sampled_features->DeviceSpan(), interaction_constraints.Query(right_sampled_features->DeviceSpan(),
right_nidx); right_nidx);

31
tests/python-gpu/test_gpu_updaters.py
View File

@ -215,3 +215,34 @@ class TestGPUUpdaters:
@pytest.mark.parametrize("weighted", [True, False]) @pytest.mark.parametrize("weighted", [True, False])
def test_adaptive(self, weighted) -> None: def test_adaptive(self, weighted) -> None:
self.cputest.run_adaptive("gpu_hist", weighted) self.cputest.run_adaptive("gpu_hist", weighted)
@pytest.mark.skipif(**tm.no_pandas())
def test_issue8824(self):
# column sampling by node crashes because shared pointers go out of scope
import pandas as pd
data = pd.DataFrame(np.random.rand(1024, 8))
data.columns = "x" + data.columns.astype(str)
features = data.columns
data["y"] = data.sum(axis=1) < 4
dtrain = xgb.DMatrix(data[features], label=data["y"])
model = xgb.train(
dtrain=dtrain,
params={
"max_depth": 5,
"learning_rate": 0.05,
"objective": "binary:logistic",
"tree_method": "gpu_hist",
"colsample_bytree": 0.5,
"colsample_bylevel": 0.5,
"colsample_bynode": 0.5, # Causes issues
"reg_alpha": 0.05,
"reg_lambda": 0.005,
"seed": 66,
"subsample": 0.5,
"gamma": 0.2,
"predictor": "auto",
"eval_metric": "auc",
},
num_boost_round=150,
)