bd1f3a38f0
- Reduce dependency on dmlc parsers and provide an interface for users to load data by themselves. - Remove use of threaded iterator and IO queue. - Remove `page_size`. - Make sure the number of pages in memory is bounded. - Make sure the cache can not be violated. - Provide an interface for internal algorithms to process data asynchronously.
42 lines
1.3 KiB
Plaintext
42 lines
1.3 KiB
Plaintext
#include <xgboost/c_api.h>
|
|
|
|
#include "helpers.h"
|
|
#include "../../src/data/device_adapter.cuh"
|
|
#include "../../src/data/iterative_device_dmatrix.h"
|
|
|
|
namespace xgboost {
|
|
|
|
CudaArrayIterForTest::CudaArrayIterForTest(float sparsity, size_t rows,
|
|
size_t cols, size_t batches)
|
|
: ArrayIterForTest{sparsity, rows, cols, batches} {
|
|
rng_->Device(0);
|
|
std::tie(batches_, interface_) =
|
|
rng_->GenerateArrayInterfaceBatch(&data_, n_batches_);
|
|
this->Reset();
|
|
}
|
|
|
|
size_t constexpr CudaArrayIterForTest::kRows;
|
|
size_t constexpr CudaArrayIterForTest::kCols;
|
|
size_t constexpr CudaArrayIterForTest::kBatches;
|
|
|
|
int CudaArrayIterForTest::Next() {
|
|
if (iter_ == n_batches_) {
|
|
return 0;
|
|
}
|
|
XGProxyDMatrixSetDataCudaArrayInterface(proxy_, batches_[iter_].c_str());
|
|
iter_++;
|
|
return 1;
|
|
}
|
|
|
|
|
|
std::shared_ptr<DMatrix> RandomDataGenerator::GenerateDeviceDMatrix(bool with_label,
|
|
bool float_label,
|
|
size_t classes) {
|
|
CudaArrayIterForTest iter{this->sparsity_, this->rows_, this->cols_, 1};
|
|
auto m = std::make_shared<data::IterativeDeviceDMatrix>(
|
|
&iter, iter.Proxy(), Reset, Next, std::numeric_limits<float>::quiet_NaN(),
|
|
0, bins_);
|
|
return m;
|
|
}
|
|
} // namespace xgboost
|