qqnormGpu {clrng}

qqnormGpu

Description

Calculate quantiles on a GPU and produce a Q-Q plot in R.

Usage

qqnormGpu(
  y,
  ylim,
  mu = 0,
  sigma = 1,
  lower.tail = 1,
  main = "Normal Q-Q Plot",
  xlab = "Theoretical Quantiles",
  ylab = "Sample Quantiles",
  Nglobal = getOption("clrng.Nglobal"),
  Nlocal = c(2, 2),
  type = getOption("clrng.type"),
  verbose = FALSE,
  ...
)

Arguments

y

data sample.

ylim

limits on the plot region.

mu

mean of Normal distribution, default is 0.

sigma

variance of Normal distribution, default is 1.

lower.tail

a logical value specifying whether use lower tail probability, default is TRUE.

main

plot label.

xlab

plot label.

ylab

plot label.

Nglobal

a (non-empty) integer vector specifying size of work items for use, with default value from global option 'clrng.Nglobal'.

Nlocal

a (non-empty) integer vector specifying size of local group size of the index space, default is c(2,2).

type

a character string specifying "double" or "float" of random numbers, with default value from global option 'clrng.type'.

verbose

a logical value, if TRUE, print extra information, default is FALSE.

...

other graphical parameters.

Value

a Normal Q-Q plot.

Examples

library(clrng)
if (detectGPUs() >= 1) {
setContext(grep("gpu", listContexts()$device_type)[1])
y <- stats::rt(256, df = 5)  # generates 256 random numbers from a Student's t-distribution
clrng::qqnormGpu(y, ylim=c(-4,5), mu=0, sigma=1, Nglobal=c(16,4))
x<-stats::rnorm(256)
clrng::qqnormGpu(x, Nglobal=c(8,6)) } else {
  message("No GPU context available")
}