قياس الأداء باستخدام microbenchmark

لماذا microbenchmark؟

الاستخدام الأساسي لـ microbenchmark

# library(microbenchmark)
# x <- 1:10000
#
# microbenchmark(
#   loop = {
#     s <- 0
#     for (v in x) s <- s + v
#   },
#   vectorized = sum(x),
#   times = 200L
# )

اختيار الوسيطة times

# library(microbenchmark)
# microbenchmark(
#   fast_op = sqrt(2),
#   times = 10000L   # many reps for a nanosecond-scale operation
# )
# microbenchmark(
#   slow_op = sort(rnorm(1e6)),
#   times = 10L      # fewer reps for second-scale operation
# )

تحديد الوسيطة unit

# library(microbenchmark)
# x <- runif(1000)
#
# microbenchmark(
#   sapply_sqrt = sapply(x, sqrt),
#   vectorized  = sqrt(x),
#   times = 500L,
#   unit = 'us'   # display in microseconds
# )

تفسير ناتج الملخص

# Example summary output (unit: microseconds):
#
#         expr    min     lq   mean  median    uq    max neval
#         loop 1203.1 1245.3 1301.7  1262.4 1310.1 2100.8   100
#   vectorized    2.1    2.3    2.9     2.4    2.6   18.3   100
#
# => vectorized is ~525x faster at median
cat('Always compare medians, not means, for microbenchmark results
')

الدالة summary() على كائن microbenchmark

# library(microbenchmark)
# x <- rnorm(5000)
# mb <- microbenchmark(
#   vapply_abs  = vapply(x, abs, numeric(1)),
#   base_abs    = abs(x),
#   times = 200L
# )
# s <- summary(mb, unit = 'ms')
# print(s[, c('expr', 'min', 'median', 'max')])

استخدام autoplot() للمقارنة المرئية

# library(microbenchmark)
# library(ggplot2)
#
# x <- 1:50000
# mb <- microbenchmark(
#   loop   = { s <- 0; for (v in x) s <- s + v },
#   vapply = vapply(x, identity, numeric(1)),
#   vec    = sum(x),
#   times  = 100L
# )
# autoplot(mb)  # opens ggplot2 violin chart

مقارنة for loop بـ vapply وsapply

# library(microbenchmark)
# x <- runif(5000, 1, 100)
#
# mb <- microbenchmark(
#   for_loop = {
#     r <- numeric(length(x))
#     for (i in seq_along(x)) r[i] <- log(x[i])
#   },
#   sapply_log  = sapply(x, log),
#   vapply_log  = vapply(x, log, numeric(1)),
#   vec_log     = log(x),
#   times = 200L, unit = 'us'
# )
# print(mb)

التحقق من الصحة أولًا

# x <- runif(1000)
# r1 <- sapply(x, sqrt)
# r2 <- sqrt(x)
# r3 <- vapply(x, sqrt, numeric(1))
#
# stopifnot(isTRUE(all.equal(r1, r2)))
# stopifnot(isTRUE(all.equal(r1, r3)))
# cat('All three produce identical results -- safe to benchmark
')
cat('Always verify correctness before comparing speed
')

إجراء الاختبار المعياري باستخدام setup

# library(microbenchmark)
#
# microbenchmark(
#   sort_base  = sort(x),
#   sort_order = x[order(x)],
#   setup = { x <- rnorm(10000) },
#   times = 100L
# )
# Each iteration refreshes x via setup, then times sort_base and sort_order

الإبلاغ عن الاختبارات المعيارية في التحليل

cat('R version    :', R.version$version.string, '
')
cat('Platform     :', R.version$platform, '
')
cat('Logical cores:', parallel::detectCores(), '
')

اختبار سريع: مقياس microbenchmark

مراجعة microbenchmark