get_HDF5_rowMins

C++ Function Reference

1 Signature

Eigen::VectorXd BigDataStatMeth::get_HDF5_rowMins(BigDataStatMeth::hdf5Dataset *dsA, bool bparal, Rcpp::Nullable< int > wsize, Rcpp::Nullable< int > threads)

2 Description

Row minimums of an HDF5 matrix (block-wise, parallel).

3 Parameters

  • dsA (BigDataStatMeth::hdf5Dataset *): Open HDF5 dataset.
  • bparal (bool): Enable OpenMP parallelism.
  • wsize (Rcpp::Nullable< int >): Block size (NULL = auto).
  • threads (Rcpp::Nullable< int >): Thread count (NULL = auto).

4 Returns

Vector of length nrows_R.

5 Details

Equivalent to apply(X, 1, min).

6 Call Graph

Function dependencies

7 Source Code

File: inst/include/hdf5Algebra/matrixAggregations.hpp • Lines 645-704

inline Eigen::VectorXd get_HDF5_rowMins(BigDataStatMeth::hdf5Dataset* dsA,
                                         bool bparal,
                                         Rcpp::Nullable<int> wsize,
                                         Rcpp::Nullable<int> threads)
{
    try {
        const hsize_t nHDF5rows = dsA->nrows();
        const hsize_t nHDF5cols = dsA->ncols();

        const hsize_t bs = agg_block_size(wsize, nHDF5cols, nHDF5rows);

        std::vector<hsize_t> starts, sizes;
        agg_make_blocks(nHDF5cols, bs, starts, sizes);

        const std::vector<hsize_t> stride = {1, 1}, blk = {1, 1};
        const int nthreads = static_cast<int>(
            BigDataStatMeth::get_threads(bparal, threads));

        Eigen::VectorXd result =
            Eigen::VectorXd::Constant(nHDF5cols,
                                      std::numeric_limits<double>::infinity());

        #pragma omp parallel for schedule(dynamic) num_threads(nthreads) \
                shared(dsA, starts, sizes, result)
        for (hsize_t bi = 0; bi < starts.size(); bi++) {
            std::vector<double> vd(nHDF5rows * sizes[bi]);
            //.. 20260325 - remove critical ..// #pragma omp critical(accessFile)
            //.. 20260325 - remove critical ..// { 
            dsA->readDatasetBlock({0, starts[bi]}, {nHDF5rows, sizes[bi]}, stride, blk, vd.data()); 
            //.. 20260325 - remove critical ..// }

            Eigen::Map<const RMMatd> X(vd.data(),
                static_cast<Eigen::Index>(nHDF5rows),
                static_cast<Eigen::Index>(sizes[bi]));

            // colwise min: compares across ncols_R (HDF5 rows), one min per R-row
            Eigen::RowVectorXd block_mins = X.colwise().minCoeff();
            // Take element-wise min with running result to handle multi-block case
            // (This case only occurs when ncols_R > 1 block, which shouldn't
            //  happen for row-wise iteration where ncols_R is the fixed dim.
            //  But defensive code here for correctness.)
            for (hsize_t k = 0; k < sizes[bi]; k++) {
                result[starts[bi] + k] = std::min(result[starts[bi] + k],
                                                   block_mins[k]);
            }
        }

        return result;

    } catch (H5::FileIException& e) {
        throw std::runtime_error("c++ exception get_HDF5_rowMins (File IException): "
                                 + std::string(e.getDetailMsg()));
    } catch (H5::DataSetIException& e) {
        throw std::runtime_error("c++ exception get_HDF5_rowMins (DataSet IException): "
                                 + std::string(e.getDetailMsg()));
    } catch (std::exception& e) {
        throw std::runtime_error(std::string("c++ exception get_HDF5_rowMins: ")
                                 + e.what());
    }
}

8 Usage Example

#include "BigDataStatMeth.hpp"

// Example usage
auto result = get_HDF5_rowMins(...);