Comparing methods of checking whether a value is NA

output.txt

## my results
Unit: milliseconds
                expr      min       lq   median       uq      max neval
           R_IsNA(x) 39.21518 40.16967 40.84210 42.75894 63.77600   100
 R_IsNA_alternate(x) 22.69085 23.66232 24.26383 25.78633 49.38843   100
 
## sessionInfo
R Under development (unstable) (2014-02-01 r64910)
Platform: x86_64-apple-darwin13.0.0 (64-bit)

locale:
[1] en_CA.UTF-8/en_CA.UTF-8/en_CA.UTF-8/C/en_CA.UTF-8/en_CA.UTF-8

attached base packages:
[1] stats     graphics  grDevices utils     datasets  methods   base     

other attached packages:
[1] microbenchmark_1.3-0 knitr_1.5.15         devtools_1.4.1.99    BiocInstaller_1.13.3

loaded via a namespace (and not attached):
 [1] compiler_3.1.0 digest_0.6.4   evaluate_0.5.1 formatR_0.10   httr_0.2       memoise_0.1    parallel_3.1.0
 [8] Rcpp_0.11.0.2  RCurl_1.95-4.1 stringr_0.6.2  tools_3.1.0    whisker_0.3-2
 
## compiler info
kevinushey@Kevin-MBP:~$ clang -v
Apple LLVM version 5.0 (clang-500.2.79) (based on LLVM 3.3svn)
Target: x86_64-apple-darwin13.0.0
Thread model: posix

## compiled with -g -O3 -march=native -std=c++11

R_IsNA.cpp

// run me by installing Rcpp and calling sourceCpp on this file

#include <Rcpp.h>
using namespace Rcpp;

// some initial stuff borrowed from R sources

#ifdef WORDS_BIGENDIAN
static const int hw = 0;
static const int lw = 1;
#else  /* !WORDS_BIGENDIAN */
static const int hw = 1;
static const int lw = 0;
#endif /* WORDS_BIGENDIAN */

typedef union
{
    double value;
    unsigned int word[2];
} ieee_double;

// R's detection of NA
int R_na(double x) {
  if (isnan(x)) {
    ieee_double y;
    y.value = x;
    return (y.word[lw] == 1954);
  }
  return 0;
}

// [[Rcpp::export]]
IntegerVector R_IsNA(NumericVector x) {
  return sapply(x, R_na);
}

// alternate version for detecting NA
int alternate_na(double x) {
  return memcmp(
    (char*)(&x),
    (char*)(&NA_REAL),
    sizeof(double)
  ) == 0;
}

// [[Rcpp::export]]
IntegerVector R_IsNA_alternate(NumericVector x)
{
  return sapply(x, alternate_na);
}

/*** R
library(microbenchmark)
x <- rnorm(1E7)
x[ sample(1:1E7, 1E6) ] <- NA
x[ sample(1:1E7, 1E6) ] <- NaN
microbenchmark(
  R_IsNA(x),
  R_IsNA_alternate(x)
)
*/