pvec

Parallelization of a vectorized function call

system.time(pvec(1:1e7, sqrt, mc.cores = 1))

##    user  system elapsed 
##   0.208   0.028   0.236

system.time(pvec(1:1e7, sqrt, mc.cores = 4))

##    user  system elapsed 
##   0.472   0.186   0.542

system.time(pvec(1:1e7, sqrt, mc.cores = 8))

##    user  system elapsed 
##   0.350   0.225   0.335

mclapply

Parallelized version of lapply

system.time(rnorm(1e6))

##    user  system elapsed 
##   0.106   0.000   0.105

system.time(unlist(mclapply(1:10, function(x) rnorm(1e5), mc.cores = 2)))

##    user  system elapsed 
##   0.214   0.160   0.078

system.time(unlist(mclapply(1:10, function(x) rnorm(1e5), mc.cores = 4)))

##    user  system elapsed 
##   0.205   0.042   0.053

system.time(unlist(mclapply(1:10, function(x) rnorm(1e5), mc.cores = 4)))

##    user  system elapsed 
##   0.128   0.036   0.054

system.time(unlist(mclapply(1:10, function(x) rnorm(1e5), mc.cores = 8)))

##    user  system elapsed 
##   0.118   0.050   0.039

system.time(unlist(mclapply(1:10, function(x) rnorm(1e5), mc.cores = 10)))

##    user  system elapsed 
##   0.092   0.046   0.036

system.time(unlist(mclapply(1:10, function(x) rnorm(1e5), mc.cores = 12)))

##    user  system elapsed 
##   0.137   0.062   0.035

mcparallel

Asynchronously evaluation of an R expression in a separate process

m = mcparallel(rnorm(1e6))
n = mcparallel(rbeta(1e6,1,1))
o = mcparallel(rgamma(1e6,1,1))

str(m)

## List of 2
##  $ pid: int 28580
##  $ fd : int [1:2] 4 7
##  - attr(*, "class")= chr [1:3] "parallelJob" "childProcess" "process"

str(n)

## List of 2
##  $ pid: int 28581
##  $ fd : int [1:2] 5 9
##  - attr(*, "class")= chr [1:3] "parallelJob" "childProcess" "process"

mccollect - waiting

p = mcparallel(mean(rnorm(1e5)))
mccollect(p, wait = FALSE, 10) # will retrieve the result (since it's fast)

## [[1]]
## [1] 0.00217601

mccollect(p, wait = FALSE)     # will signal the job as terminating

## [[1]]
## NULL

mccollect(p, wait = FALSE)     # there is no longer such a job

## NULL

registerDoMC

Primarily used to set the number of cores used by foreach, by default uses options("cores") or half the number of cores found by detectCores from the parallel package.

options("cores")

## $cores
## NULL

detectCores()

## [1] 24

getDoParWorkers()

## [1] 1

registerDoMC(4)
getDoParWorkers()

## [1] 4

foreach

A slightly more powerful version of base for loops (think for with an lapply flavor). Combined with %do% or %dopar% for single or multicore execution.

for(i in 1:10) sqrt(i)

foreach(i = 1:5) %do% sqrt(i)   

## [[1]]
## [1] 1
## 
## [[2]]
## [1] 1.414214
## 
## [[3]]
## [1] 1.732051
## 
## [[4]]
## [1] 2
## 
## [[5]]
## [1] 2.236068

foreach - iterators

foreach can iterate across more than one value

foreach(i = 1:5, j = 1:5) %do% sqrt(i^2+j^2)   

## [[1]]
## [1] 1.414214
## 
## [[2]]
## [1] 2.828427
## 
## [[3]]
## [1] 4.242641
## 
## [[4]]
## [1] 5.656854
## 
## [[5]]
## [1] 7.071068

foreach(i = 1:5, j = 1:2) %do% sqrt(i^2+j^2)   

## [[1]]
## [1] 1.414214
## 
## [[2]]
## [1] 2.828427

foreach - combining results

foreach(i = 1:5, .combine='c') %do% sqrt(i)   

## [1] 1.000000 1.414214 1.732051 2.000000 2.236068

foreach(i = 1:5, .combine='cbind') %do% sqrt(i)   

##      result.1 result.2 result.3 result.4 result.5
## [1,]        1 1.414214 1.732051        2 2.236068

foreach(i = 1:5, .combine='+') %do% sqrt(i)   

## [1] 8.382332

foreach - parallelization

Swapping out %do% for %dopar% will use the parallel backend.

registerDoMC(4)
system.time(foreach(i = 1:10) %dopar% mean(rnorm(1e6)))

##    user  system elapsed 
##   0.472   0.023   0.356

registerDoMC(8)
system.time(foreach(i = 1:10) %dopar% mean(rnorm(1e6)))

##    user  system elapsed 
##   1.363   0.063   0.242

registerDoMC(12)
system.time(foreach(i = 1:10) %dopar% mean(rnorm(1e6)))

##    user  system elapsed 
##   1.251   0.063   0.136