Testing performance of H5Sselect_index in the rhdf5 package

hyperslab_selection_benchmark.R

library(rhdf5)

hslab_bm <- function(m = 10000, n = 10000) {
    ## TENxBrainData
    fid <- H5Fopen('/media/Storage/Work/ExperimentHub/1040')
    did <- H5Dopen(h5loc = fid, 'counts')
    sid <- H5Dget_space(did)

    ## select first 100 rows and a random (ordered) sample of columns
    index <- list(1:100,
                  sort(sample(x = 1:m, size = n, replace = FALSE)))
    size <- H5Sselect_index(h5space = sid, index = index)
    
    ## tidy up
    H5Sclose(sid)
    H5Dclose(did)
    H5Fclose(fid)
}

hslab2_bm <- function(m = 10000, n = 10000) {

    fid <- H5Fopen('/media/Storage/Work/ExperimentHub/1040')
    did <- H5Dopen(h5loc = fid, 'counts')
    sid <- H5Dget_space(did)
    
    x <- sort(sample(x = 1:m, size = n, replace = FALSE))
    x2 <- x %/% 100
    for(i in unique(x2)) {
        index <- list(1:100,
                      x[x2 == i])
        size = H5Sselect_index(h5space = sid, index = index)
    }
    ## tidy up
    H5Sclose(sid)
    H5Dclose(did)
    H5Fclose(fid)
}

microbenchmark::microbenchmark(
    hslab_bm(m = 10000, n = 10000),
    hslab_bm(m = 15000, n = 10000),
    hslab_bm(m = 20000, n = 10000),
    hslab2_bm(m = 10000, n = 10000),
    hslab2_bm(m = 15000, n = 10000),
    hslab2_bm(m = 20000, n = 10000),
    times = 5
)