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

fix device sketch with weights in external memory mode (#5870)

Browse Source
This commit is contained in:
Rong Ou 2020-07-07 17:44:07 -07:00 committed by GitHub
parent d0a29c3135
commit 06320729d4
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 17 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
src/common/hist_util.cu
View File

@ -264,7 +264,6 @@ void ProcessWeightedBatch(int device, const SparsePage& page,
d_temp_weights[idx] = weights[group]; d_temp_weights[idx] = weights[group];
}); });
} else { } else {
CHECK_EQ(weights.size(), page.offset.Size() - 1);
dh::LaunchN(device, temp_weights.size(), [=] __device__(size_t idx) { dh::LaunchN(device, temp_weights.size(), [=] __device__(size_t idx) {
size_t element_idx = idx + begin; size_t element_idx = idx + begin;
size_t ridx = thrust::upper_bound(thrust::seq, row_ptrs.begin(), size_t ridx = thrust::upper_bound(thrust::seq, row_ptrs.begin(),

17
tests/cpp/common/test_hist_util.cu
View File

@ -209,6 +209,23 @@ TEST(HistUtil, DeviceSketchMultipleColumnsExternal) {
} }
} }
// See https://github.com/dmlc/xgboost/issues/5866.
TEST(HistUtil, DeviceSketchExternalMemoryWithWeights) {
int bin_sizes[] = {2, 16, 256, 512};
int sizes[] = {100, 1000, 1500};
int num_columns = 5;
dmlc::TemporaryDirectory temp;
for (auto num_rows : sizes) {
auto x = GenerateRandom(num_rows, num_columns);
auto dmat = GetExternalMemoryDMatrixFromData(x, num_rows, num_columns, 100, temp);
dmat->Info().weights_.HostVector() = GenerateRandomWeights(num_rows);
for (auto num_bins : bin_sizes) {
auto cuts = DeviceSketch(0, dmat.get(), num_bins);
ValidateCuts(cuts, dmat.get(), num_bins);
}
}
}
template <typename Adapter> template <typename Adapter>
void ValidateBatchedCuts(Adapter adapter, int num_bins, int num_columns, int num_rows, void ValidateBatchedCuts(Adapter adapter, int num_bins, int num_columns, int num_rows,
DMatrix* dmat) { DMatrix* dmat) {