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

Support cpu quantile sketch with column-wise data split (#8742)

Browse Source
This commit is contained in:
Rong Ou
2023-02-04 22:26:24 -08:00
committed by GitHub
parent c1786849e3
commit 66191e9926
15 changed files with 250 additions and 118 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
src/common/hist_util.cc
View File

@@ -45,14 +45,16 @@ HistogramCuts SketchOnDMatrix(DMatrix *m, int32_t max_bins, int32_t n_threads, b
if (!use_sorted) {
HostSketchContainer container(max_bins, m->Info().feature_types.ConstHostSpan(), reduced,
HostSketchContainer::UseGroup(info), n_threads);
HostSketchContainer::UseGroup(info),
m->Info().data_split_mode == DataSplitMode::kCol, n_threads);
for (auto const& page : m->GetBatches<SparsePage>()) {
container.PushRowPage(page, info, hessian);
}
container.MakeCuts(&out);
} else {
SortedSketchContainer container{max_bins, m->Info().feature_types.ConstHostSpan(), reduced,
HostSketchContainer::UseGroup(info), n_threads};
HostSketchContainer::UseGroup(info),
m->Info().data_split_mode == DataSplitMode::kCol, n_threads};
for (auto const& page : m->GetBatches<SortedCSCPage>()) {
container.PushColPage(page, info, hessian);
}