Thanks to everyone for their help. I learned much.
#======================================================================
#include <Rcpp.h>
using namespace Rcpp;
// [[Rcpp::export]]
std::vector<double> mybar(const std::vector<double>& x, double firstelem) {
std::vector<double> tmp(x.size() + 1);
tmp[0] = firstelem;
for (int i = 1; i < (x.size()+1); i++)
tmp[i] = x[i-1];
return tmp;
}
// [[Rcpp::export]]
std::vector<double> mybar2(const std::vector<double>& x, double firstelem) {
std::vector<double> tmp(x.size() + 1);
tmp[0] = firstelem;
std::copy(x.begin(), x.end(), tmp.begin()+1);
return tmp;
}
// [[Rcpp::export]]
NumericVector mybar3(NumericVector x, double firstelem) {
NumericVector tmp(x.size() + 1);
tmp[0] = firstelem;
std::copy(x.begin(), x.end(), tmp.begin()+1);
return tmp;
}
// [[Rcpp::export]]
NumericVector mybar4(NumericVector x, double firstelem) {
NumericVector result(x.size() + 1);
result[0] = firstelem;
std::memcpy(result.begin()+1, x.begin(), x.size()*sizeof(double));
return result;
}
// [[Rcpp::export]]
NumericVector mybar5(NumericVector x, NumericVector y) {
NumericVector result(x.size() + y.size());
std::memcpy(result.begin(), x.begin(), x.size()*sizeof(double));
std::memcpy(result.begin()+x.size(), y.begin(),
y.size()*sizeof(double));
return result;
}
// [[Rcpp::export]]
NumericVector mybar6(NumericVector x, double firstelem) {
x.insert(0, firstelem);
return x;
}
// [[Rcpp::export]]
NumericVector mybar7(NumericVector x, double firstelem) {
x.push_front(firstelem);
return x;
}
// [[Rcpp::export]]
NumericVector mybar8(const NumericVector &x, const NumericVector &y) {
NumericVector result(x.size() + y.size());
std::memcpy(result.begin(), x.begin(), x.size()*sizeof(double));
std::memcpy(result.begin()+x.size(), y.begin(),
y.size()*sizeof(double));
return result;
}
/*** R
library(microbenchmark)
n=1E7
testvec = c(1,seq_len(n))
testelem <- 7
microbenchmark(c(testelem, testvec), mybar(testvec,testelem),
mybar2(testvec,testelem),
mybar3(testvec,testelem),
mybar4(testvec,testelem),
mybar5(testvec,testelem),
mybar6(testvec,testelem),
mybar7(testvec,testelem),
mybar8(testvec,testelem)
)
*/
microbenchmark(c(testelem, testvec), mybar(testvec,testelem),
+ mybar2(testvec,testelem),
+ mybar3(testvec,testelem),
+ mybar4(testvec,testelem) .... [TRUNCATED]
Unit: milliseconds
expr min lq mean
median uq max neval
c(testelem, testvec) 33.82390 37.41429 42.70048 42.48487
47.72840 81.53239 100
mybar(testvec, testelem) 93.35373 100.67106 105.30134 105.67559
109.62234 125.15337 100
mybar2(testvec, testelem) 88.00770 94.62231 98.84161 98.51031
102.49516 114.58349 100
mybar3(testvec, testelem) 27.93793 31.94207 36.76242 37.17255
41.52102 47.31534 100
mybar4(testvec, testelem) 31.37486 34.73718 39.72786 40.83917
44.21151 49.48883 100
mybar5(testvec, testelem) 30.90608 35.25496 40.24085 40.59592
44.88581 50.33709 100
mybar6(testvec, testelem) 33.24435 38.32075 43.11721 43.46578
47.93726 52.72538 100
mybar7(testvec, testelem) 30.80926 33.41609 38.45877 37.71916
43.70371 48.88513 100
mybar8(testvec, testelem) 30.88067 35.01826 40.38411 40.02501
44.49641 73.84147 100
>
On Mon, Dec 10, 2018 at 8:42 AM Serguei Sokol <serguei.so...@gmail.com
<mailto:serguei.so...@gmail.com>> wrote:
Le 10/12/2018 à 13:04, Jan van der Laan a écrit :
> Small addendum: A large part of the performance gain in my
example comes
> from using NumericVector instead of std::vector<double>. Which
avoids a
> conversion. An example using std::copy with Numeric vector runs
in the
> same time as the version using memcpy.
Yep.
Few more percents of mean cpu time can be saved by using "const &"
trick :
// [[Rcpp::export]]
NumericVector mybar5(const NumericVector &x, const NumericVector &y) {
NumericVector result(x.size() + y.size());
std::memcpy(result.begin(), x.begin(), x.size()*sizeof(double));
std::memcpy(result.begin()+x.size(), y.begin(),
y.size()*sizeof(double));
return result;
}
# output
Unit: microseconds
expr min lq mean median
uq
max
c(testelem, testvec) 258.343 338.3110 418.0047 343.4450
378.7850
3077.347
mybar(testvec, testelem) 352.699 366.8770 498.3948 374.6635
450.4420
3046.408
mybar2(testvec, testelem) 334.820 348.3685 425.0098 354.7240
366.5270
3024.128
mybar3(testvec, testelem) 233.689 244.8640 315.7256 247.5180
255.0955
2945.068
mybar4(testvec, testelem) 232.083 241.9655 340.0751 245.0035
252.8260
2934.312
mybar5(testvec, testelem) 150.787 242.7685 285.4264 245.9465
254.1880
2049.493
Serguei.
>
> Jan
>
>
>
> On 10-12-18 12:28, Jan van der Laan wrote:
>>
>> For performance memcpy is probably fastest. This gives the same
>> performance a c().
>>
>> // [[Rcpp::export]]
>> NumericVector mybar3(NumericVector x, double firstelem) {
>> NumericVector result(x.size() + 1);
>> result[0] = firstelem;
>> std::memcpy(result.begin()+1, x.begin(),
x.size()*sizeof(double));
>> return result;
>> }
>>
>>
>> Or a more general version concatenating vector of arbitrary lengths:
>>
>>
>> // [[Rcpp::export]]
>> NumericVector mybar4(NumericVector x, NumericVector y) {
>> NumericVector result(x.size() + y.size());
>> std::memcpy(result.begin(), x.begin(), x.size()*sizeof(double));
>> std::memcpy(result.begin()+x.size(), y.begin(),
>> y.size()*sizeof(double));
>> return result;
>> }
>>
>>
>>
>> > n=1E7
>> > testvec = c(1,seq_len(n))
>> > testelem <- 7
>> > microbenchmark(c(testelem, testvec), mybar(testvec,testelem),
>> + mybar2(testvec,testelem),
>> + mybar3(testvec,testelem),
>> + mybar4(testvec,testelem)
>> + )
>> Unit: milliseconds
>> expr min lq mean median
>> uq max neval
>> c(testelem, testvec) 36.48577 36.93754 41.10550 43.76742
>> 44.20709 46.09741 100
>> mybar(testvec, testelem) 102.54042 103.21756 106.88749 104.32033
>> 110.31527 119.55512 100
>> mybar2(testvec, testelem) 95.64696 96.19447 100.24691 102.61380
>> 103.58189 109.28290 100
>> mybar3(testvec, testelem) 36.45794 36.87915 40.43486 37.18063
>> 43.49643 95.49049 100
>> mybar4(testvec, testelem) 36.51334 37.05409 41.39680 43.20627
>> 43.57958 94.95482 100
>>
>>
>> Best,
>> Jan
>>
>>
>>
>> On 10-12-18 12:10, Serguei Sokol wrote:
>>> Le 09/12/2018 à 09:35, Mark Leeds a écrit :
>>>> Hi All: I wrote below and it works but I have a strong feeling
>>>> there's a better way to do it.
>>> If performance is an issue, you can save few percents of cpu
time by
>>> using std::copy() instead of explicit for loop. Yet, for this
>>> operation R's c() remains the best bet. It is more then twice
faster
>>> than both Rcpp versions below:
>>>
>>> #include <Rcpp.h>
>>> using namespace Rcpp;
>>>
>>> // [[Rcpp::export]]
>>> std::vector<double> mybar(const std::vector<double>& x, double
>>> firstelem) {
>>> std::vector<double> tmp(x.size() + 1);
>>> tmp[0] = firstelem;
>>> for (int i = 1; i < (x.size()+1); i++)
>>> tmp[i] = x[i-1];
>>> return tmp;
>>> }
>>> // [[Rcpp::export]]
>>> std::vector<double> mybar2(const std::vector<double>& x, double
>>> firstelem) {
>>> std::vector<double> tmp(x.size() + 1);
>>> tmp[0] = firstelem;
>>> std::copy(x.begin(), x.end(), tmp.begin()+1);
>>> return tmp;
>>> }
>>>
>>> /*** R
>>> library(microbenchmark)
>>> n=100000
>>> testvec = c(1,seq_len(n))
>>> testelem <- 7
>>> microbenchmark(c(testelem, testvec), mybar(testvec,testelem),
>>> mybar2(testvec,testelem))
>>> */
>>>
>>> # Ouput
>>> Unit: microseconds
>>> expr min lq mean
>>> median uq
>>> c(testelem, testvec) 247.098 248.5655 444.8657 257.3300
>>> 630.7725
>>> mybar(testvec, testelem) 594.978 622.3560 1226.5683 637.0230
>>> 1386.8385
>>> mybar2(testvec, testelem) 576.191 604.7565 1029.2124 616.1055
>>> 1351.6740
>>> max neval
>>> 7587.977 100
>>> 22149.605 100
>>> 11651.831 100
>>>
>>>
>>> Best,
>>> Serguei.
>>>
>>>> I looked on the net and found some material from back in ~2014
about
>>>> concatenating
>>>> vectors but I didn't see anything final about it. Thanks for any
>>>> insights.
>>>>
>>>> Also, the documentation for Rcpp is beyond incredible (thanks to
>>>> dirk, romain, kevin and all the other people I'm leaving out
) but
>>>> is there a general methodology for finding equivalents of R
>>>> functions. For example, if I want a cumsum function in Rcpp,
how do
>>>> I know whether to use the stl with accumulate or if there's
already
>>>> one built in so
>>>> that I just call cumsum.
>>>>
>>>> Thanks.
>>>>
>>>> #=======================================================
>>>>
>>>> #include <Rcpp.h>
>>>> using namespace Rcpp;
>>>>
>>>> // [[Rcpp::export]]
>>>> std::vector<double> mybar(const std::vector<double>& x, double
>>>> firstelem) {
>>>> std::vector<double> tmp(x.size() + 1);
>>>> tmp[0] = firstelem;
>>>> for (int i = 1; i < (x.size()+1); i++)
>>>> tmp[i] = x[i-1];
>>>> return tmp;
>>>> }
>>>>
>>>> /*** R
>>>>
>>>> testvec = c(1,2,3)
>>>> testelem <- 7
>>>> mybar(testvec,testelem)
>>>>
>>>> */
>>>>
>>>> #===============================
>>>> # OUTPUT FROM RUNNING ABOVE
>>>> #=================================
>>>> > testvec <- c(1,2,3)
>>>> > testelem <- 7
>>>> > mybar(testvec,testelem)
>>>> [1] 7 1 2 3
>>>> >
>>>>
>>>>
>>>>
>>>>
>>>>
>>>>
>>>>
>>>> _______________________________________________
>>>> Rcpp-devel mailing list
>>>> Rcpp-devel@lists.r-forge.r-project.org
<mailto:Rcpp-devel@lists.r-forge.r-project.org>
>>>>
https://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/rcpp-devel
>>>>
>>>
>>> _______________________________________________
>>> Rcpp-devel mailing list
>>> Rcpp-devel@lists.r-forge.r-project.org
<mailto:Rcpp-devel@lists.r-forge.r-project.org>
>>>
https://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/rcpp-devel
>> _______________________________________________
>> Rcpp-devel mailing list
>> Rcpp-devel@lists.r-forge.r-project.org
<mailto:Rcpp-devel@lists.r-forge.r-project.org>
>>
https://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/rcpp-devel
>
_______________________________________________
Rcpp-devel mailing list
Rcpp-devel@lists.r-forge.r-project.org
<mailto:Rcpp-devel@lists.r-forge.r-project.org>
https://lists.r-forge.r-project.org/cgi-bin/mailman/listinfo/rcpp-devel
