1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383
|
<!DOCTYPE html>
<html xmlns="http://www.w3.org/1999/xhtml">
<head>
<meta charset="utf-8" />
<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
<meta name="generator" content="pandoc" />
<meta name="viewport" content="width=device-width, initial-scale=1">
<meta name="author" content="Michel Lang" />
<meta name="date" content="2018-05-14" />
<title>Benchmark</title>
<style type="text/css">code{white-space: pre;}</style>
<style type="text/css">
a.sourceLine { display: inline-block; line-height: 1.25; }
a.sourceLine { pointer-events: none; color: inherit; text-decoration: inherit; }
a.sourceLine:empty { height: 1.2em; position: absolute; }
.sourceCode { overflow: visible; }
code.sourceCode { white-space: pre; position: relative; }
div.sourceCode { margin: 1em 0; }
pre.sourceCode { margin: 0; }
@media screen {
div.sourceCode { overflow: auto; }
}
@media print {
code.sourceCode { white-space: pre-wrap; }
a.sourceLine { text-indent: -1em; padding-left: 1em; }
}
pre.numberSource a.sourceLine
{ position: relative; }
pre.numberSource a.sourceLine:empty
{ position: absolute; }
pre.numberSource a.sourceLine::before
{ content: attr(data-line-number);
position: absolute; left: -5em; text-align: right; vertical-align: baseline;
border: none; pointer-events: all;
-webkit-touch-callout: none; -webkit-user-select: none;
-khtml-user-select: none; -moz-user-select: none;
-ms-user-select: none; user-select: none;
padding: 0 4px; width: 4em;
color: #aaaaaa;
}
pre.numberSource { margin-left: 3em; border-left: 1px solid #aaaaaa; padding-left: 4px; }
div.sourceCode
{ }
@media screen {
a.sourceLine::before { text-decoration: underline; }
}
code span.al { color: #ff0000; font-weight: bold; } /* Alert */
code span.an { color: #60a0b0; font-weight: bold; font-style: italic; } /* Annotation */
code span.at { color: #7d9029; } /* Attribute */
code span.bn { color: #40a070; } /* BaseN */
code span.bu { } /* BuiltIn */
code span.cf { color: #007020; font-weight: bold; } /* ControlFlow */
code span.ch { color: #4070a0; } /* Char */
code span.cn { color: #880000; } /* Constant */
code span.co { color: #60a0b0; font-style: italic; } /* Comment */
code span.cv { color: #60a0b0; font-weight: bold; font-style: italic; } /* CommentVar */
code span.do { color: #ba2121; font-style: italic; } /* Documentation */
code span.dt { color: #902000; } /* DataType */
code span.dv { color: #40a070; } /* DecVal */
code span.er { color: #ff0000; font-weight: bold; } /* Error */
code span.ex { } /* Extension */
code span.fl { color: #40a070; } /* Float */
code span.fu { color: #06287e; } /* Function */
code span.im { } /* Import */
code span.in { color: #60a0b0; font-weight: bold; font-style: italic; } /* Information */
code span.kw { color: #007020; font-weight: bold; } /* Keyword */
code span.op { color: #666666; } /* Operator */
code span.ot { color: #007020; } /* Other */
code span.pp { color: #bc7a00; } /* Preprocessor */
code span.sc { color: #4070a0; } /* SpecialChar */
code span.ss { color: #bb6688; } /* SpecialString */
code span.st { color: #4070a0; } /* String */
code span.va { color: #19177c; } /* Variable */
code span.vs { color: #4070a0; } /* VerbatimString */
code span.wa { color: #60a0b0; font-weight: bold; font-style: italic; } /* Warning */
</style>
<style type="text/css">body {
background-color: #fff;
margin: 1em auto;
max-width: 700px;
overflow: visible;
padding-left: 2em;
padding-right: 2em;
font-family: "Open Sans", "Helvetica Neue", Helvetica, Arial, sans-serif;
font-size: 14px;
line-height: 1.35;
}
#header {
text-align: center;
}
#TOC {
clear: both;
margin: 0 0 10px 10px;
padding: 4px;
width: 400px;
border: 1px solid #CCCCCC;
border-radius: 5px;
background-color: #f6f6f6;
font-size: 13px;
line-height: 1.3;
}
#TOC .toctitle {
font-weight: bold;
font-size: 15px;
margin-left: 5px;
}
#TOC ul {
padding-left: 40px;
margin-left: -1.5em;
margin-top: 5px;
margin-bottom: 5px;
}
#TOC ul ul {
margin-left: -2em;
}
#TOC li {
line-height: 16px;
}
table {
margin: 1em auto;
border-width: 1px;
border-color: #DDDDDD;
border-style: outset;
border-collapse: collapse;
}
table th {
border-width: 2px;
padding: 5px;
border-style: inset;
}
table td {
border-width: 1px;
border-style: inset;
line-height: 18px;
padding: 5px 5px;
}
table, table th, table td {
border-left-style: none;
border-right-style: none;
}
table thead, table tr.even {
background-color: #f7f7f7;
}
p {
margin: 0.5em 0;
}
blockquote {
background-color: #f6f6f6;
padding: 0.25em 0.75em;
}
hr {
border-style: solid;
border: none;
border-top: 1px solid #777;
margin: 28px 0;
}
dl {
margin-left: 0;
}
dl dd {
margin-bottom: 13px;
margin-left: 13px;
}
dl dt {
font-weight: bold;
}
ul {
margin-top: 0;
}
ul li {
list-style: circle outside;
}
ul ul {
margin-bottom: 0;
}
pre, code {
background-color: #f7f7f7;
border-radius: 3px;
color: #333;
white-space: pre-wrap;
}
pre {
border-radius: 3px;
margin: 5px 0px 10px 0px;
padding: 10px;
}
pre:not([class]) {
background-color: #f7f7f7;
}
code {
font-family: Consolas, Monaco, 'Courier New', monospace;
font-size: 85%;
}
p > code, li > code {
padding: 2px 0px;
}
div.figure {
text-align: center;
}
img {
background-color: #FFFFFF;
padding: 2px;
border: 1px solid #DDDDDD;
border-radius: 3px;
border: 1px solid #CCCCCC;
margin: 0 5px;
}
h1 {
margin-top: 0;
font-size: 35px;
line-height: 40px;
}
h2 {
border-bottom: 4px solid #f7f7f7;
padding-top: 10px;
padding-bottom: 2px;
font-size: 145%;
}
h3 {
border-bottom: 2px solid #f7f7f7;
padding-top: 10px;
font-size: 120%;
}
h4 {
border-bottom: 1px solid #f7f7f7;
margin-left: 8px;
font-size: 105%;
}
h5, h6 {
border-bottom: 1px solid #ccc;
font-size: 105%;
}
a {
color: #0033dd;
text-decoration: none;
}
a:hover {
color: #6666ff; }
a:visited {
color: #800080; }
a:visited:hover {
color: #BB00BB; }
a[href^="http:"] {
text-decoration: underline; }
a[href^="https:"] {
text-decoration: underline; }
code > span.kw { color: #555; font-weight: bold; }
code > span.dt { color: #902000; }
code > span.dv { color: #40a070; }
code > span.bn { color: #d14; }
code > span.fl { color: #d14; }
code > span.ch { color: #d14; }
code > span.st { color: #d14; }
code > span.co { color: #888888; font-style: italic; }
code > span.ot { color: #007020; }
code > span.al { color: #ff0000; font-weight: bold; }
code > span.fu { color: #900; font-weight: bold; } code > span.er { color: #a61717; background-color: #e3d2d2; }
</style>
</head>
<body>
<h1 class="title toc-ignore">Benchmark</h1>
<h4 class="author"><em>Michel Lang</em></h4>
<h4 class="date"><em>2018-05-14</em></h4>
<p>This small benchmark compares the performance of the base64 encoding/decoding in package <code>base64url</code> with the implementations in the packages <a href="https://cran.r-project.org/package=base64enc"><code>base64enc</code></a> and <a href="https://cran.r-project.org/package=openssl"><code>openssl</code></a>.</p>
<div id="encoding-of-a-single-string" class="section level2">
<h2>Encoding of a single string</h2>
<div class="sourceCode" id="cb1"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb1-1" data-line-number="1"><span class="kw">library</span>(base64url)</a>
<a class="sourceLine" id="cb1-2" data-line-number="2"><span class="kw">library</span>(base64enc)</a>
<a class="sourceLine" id="cb1-3" data-line-number="3"><span class="kw">library</span>(openssl)</a>
<a class="sourceLine" id="cb1-4" data-line-number="4"><span class="kw">library</span>(microbenchmark)</a>
<a class="sourceLine" id="cb1-5" data-line-number="5"></a>
<a class="sourceLine" id="cb1-6" data-line-number="6">x =<span class="st"> "plain text"</span></a>
<a class="sourceLine" id="cb1-7" data-line-number="7"><span class="kw">microbenchmark</span>(</a>
<a class="sourceLine" id="cb1-8" data-line-number="8"> <span class="dt">base64url =</span> <span class="kw">base64_urlencode</span>(x),</a>
<a class="sourceLine" id="cb1-9" data-line-number="9"> <span class="dt">base64enc =</span> <span class="kw">base64encode</span>(<span class="kw">charToRaw</span>(x)),</a>
<a class="sourceLine" id="cb1-10" data-line-number="10"> <span class="dt">openssl =</span> <span class="kw">base64_encode</span>(x)</a>
<a class="sourceLine" id="cb1-11" data-line-number="11">)</a></code></pre></div>
<pre><code>## Unit: nanoseconds
## expr min lq mean median uq max neval
## base64url 408 461.5 853.52 698.0 782.5 20430 100
## base64enc 1199 1367.0 3114.89 1865.0 1983.5 139937 100
## openssl 13188 13536.0 15256.11 13749.5 14081.5 135871 100</code></pre>
</div>
<div id="decoding-of-a-single-string" class="section level2">
<h2>Decoding of a single string</h2>
<div class="sourceCode" id="cb3"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb3-1" data-line-number="1">x =<span class="st"> "N0JBLlRaUTp1bi5KOW4xWStNWEJoLHRQaDZ3"</span></a>
<a class="sourceLine" id="cb3-2" data-line-number="2"><span class="kw">microbenchmark</span>(</a>
<a class="sourceLine" id="cb3-3" data-line-number="3"> <span class="dt">base64url =</span> <span class="kw">base64_urldecode</span>(x),</a>
<a class="sourceLine" id="cb3-4" data-line-number="4"> <span class="dt">base64enc =</span> <span class="kw">rawToChar</span>(<span class="kw">base64decode</span>(x)),</a>
<a class="sourceLine" id="cb3-5" data-line-number="5"> <span class="dt">openssl =</span> <span class="kw">rawToChar</span>(<span class="kw">base64_decode</span>(x))</a>
<a class="sourceLine" id="cb3-6" data-line-number="6">)</a></code></pre></div>
<pre><code>## Unit: nanoseconds
## expr min lq mean median uq max neval
## base64url 423 485.0 1104.57 655.5 923 40442 100
## base64enc 1504 1681.5 2879.92 2225.5 2546 76432 100
## openssl 19066 19643.0 21264.27 19915.5 20281 119636 100</code></pre>
</div>
<div id="encoding-and-decoding-of-character-vectors" class="section level2">
<h2>Encoding and decoding of character vectors</h2>
<p>Here, the task has changed from encoding/decoding a single string to processing multiple strings stored inside a character vector. First, we create a small utility function which returns <code>n</code> random strings with a random number of characters (between 1 and 32) each.</p>
<div class="sourceCode" id="cb5"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb5-1" data-line-number="1">rand =<span class="st"> </span><span class="cf">function</span>(n, <span class="dt">min =</span> <span class="dv">1</span>, <span class="dt">max =</span> <span class="dv">32</span>) {</a>
<a class="sourceLine" id="cb5-2" data-line-number="2"> chars =<span class="st"> </span><span class="kw">c</span>(letters, LETTERS, <span class="kw">as.character</span>(<span class="dv">0</span><span class="op">:</span><span class="dv">9</span>), <span class="kw">c</span>(<span class="st">"."</span>, <span class="st">":"</span>, <span class="st">","</span>, <span class="st">"+"</span>, <span class="st">"-"</span>, <span class="st">"*"</span>, <span class="st">"/"</span>))</a>
<a class="sourceLine" id="cb5-3" data-line-number="3"> <span class="kw">replicate</span>(n, <span class="kw">paste0</span>(<span class="kw">sample</span>(chars, <span class="kw">sample</span>(min<span class="op">:</span>max, <span class="dv">1</span>), <span class="dt">replace =</span> <span class="ot">TRUE</span>), <span class="dt">collapse =</span> <span class="st">""</span>))</a>
<a class="sourceLine" id="cb5-4" data-line-number="4">}</a>
<a class="sourceLine" id="cb5-5" data-line-number="5"><span class="kw">set.seed</span>(<span class="dv">1</span>)</a>
<a class="sourceLine" id="cb5-6" data-line-number="6"><span class="kw">rand</span>(<span class="dv">10</span>)</a></code></pre></div>
<pre><code>## [1] "zN.n9+TRe" "mVA1IX/"
## [3] "1,oSisAaA8xHP" "m5U2hXC4S2MK2bGY"
## [5] "G7EqegvJTC.uFwSrH0f8x5x" "G97A1-DXBw0"
## [7] "XiqjqeS" "13FC3PTys/RoiG:P*YyDkaXhES/IH"
## [9] "0FJopP" "fcS,PMK*JVPqrYFmZh7"</code></pre>
<p>Only <code>base64url</code> is vectorized for string input, the alternative implementations need wrappers to process character vectors:</p>
<div class="sourceCode" id="cb7"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb7-1" data-line-number="1">base64enc_encode =<span class="st"> </span><span class="cf">function</span>(x) {</a>
<a class="sourceLine" id="cb7-2" data-line-number="2"> <span class="kw">vapply</span>(x, <span class="cf">function</span>(x) <span class="kw">base64encode</span>(<span class="kw">charToRaw</span>(x)), <span class="ot">NA_character_</span>, <span class="dt">USE.NAMES =</span> <span class="ot">FALSE</span>)</a>
<a class="sourceLine" id="cb7-3" data-line-number="3">}</a>
<a class="sourceLine" id="cb7-4" data-line-number="4"></a>
<a class="sourceLine" id="cb7-5" data-line-number="5">openssl_encode =<span class="st"> </span><span class="cf">function</span>(x) {</a>
<a class="sourceLine" id="cb7-6" data-line-number="6"> <span class="kw">vapply</span>(x, <span class="cf">function</span>(x) <span class="kw">base64_encode</span>(x), <span class="ot">NA_character_</span>, <span class="dt">USE.NAMES =</span> <span class="ot">FALSE</span>)</a>
<a class="sourceLine" id="cb7-7" data-line-number="7">}</a>
<a class="sourceLine" id="cb7-8" data-line-number="8"></a>
<a class="sourceLine" id="cb7-9" data-line-number="9">base64enc_decode =<span class="st"> </span><span class="cf">function</span>(x) {</a>
<a class="sourceLine" id="cb7-10" data-line-number="10"> <span class="kw">vapply</span>(x, <span class="cf">function</span>(x) <span class="kw">rawToChar</span>(<span class="kw">base64decode</span>(x)), <span class="ot">NA_character_</span>, <span class="dt">USE.NAMES =</span> <span class="ot">FALSE</span>)</a>
<a class="sourceLine" id="cb7-11" data-line-number="11">}</a>
<a class="sourceLine" id="cb7-12" data-line-number="12"></a>
<a class="sourceLine" id="cb7-13" data-line-number="13">openssl_decode =<span class="st"> </span><span class="cf">function</span>(x) {</a>
<a class="sourceLine" id="cb7-14" data-line-number="14"> <span class="kw">vapply</span>(x, <span class="cf">function</span>(x) <span class="kw">rawToChar</span>(<span class="kw">base64_decode</span>(x)), <span class="ot">NA_character_</span>, <span class="dt">USE.NAMES =</span> <span class="ot">FALSE</span>)</a>
<a class="sourceLine" id="cb7-15" data-line-number="15">}</a></code></pre></div>
<p>The following benchmark measures the runtime to encode 1000 random strings and then decode them again:</p>
<div class="sourceCode" id="cb8"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb8-1" data-line-number="1"><span class="kw">set.seed</span>(<span class="dv">1</span>)</a>
<a class="sourceLine" id="cb8-2" data-line-number="2">x =<span class="st"> </span><span class="kw">rand</span>(<span class="dv">1000</span>)</a>
<a class="sourceLine" id="cb8-3" data-line-number="3"><span class="kw">microbenchmark</span>(</a>
<a class="sourceLine" id="cb8-4" data-line-number="4"> <span class="dt">base64url =</span> <span class="kw">base64_urldecode</span>(<span class="kw">base64_urlencode</span>(x)),</a>
<a class="sourceLine" id="cb8-5" data-line-number="5"> <span class="dt">base64enc =</span> <span class="kw">base64enc_decode</span>(<span class="kw">base64enc_encode</span>(x)),</a>
<a class="sourceLine" id="cb8-6" data-line-number="6"> <span class="dt">openssl =</span> <span class="kw">openssl_decode</span>(<span class="kw">openssl_encode</span>(x))</a>
<a class="sourceLine" id="cb8-7" data-line-number="7">)</a></code></pre></div>
<pre><code>## Unit: microseconds
## expr min lq mean median uq max
## base64url 214.031 222.0655 270.415 260.3725 311.967 441.127
## base64enc 3613.444 3974.8940 4228.395 4058.2495 4157.485 11094.540
## openssl 34166.572 35453.3810 36002.175 35794.9835 36349.533 42507.878
## neval
## 100
## 100
## 100</code></pre>
</div>
<!-- dynamically load mathjax for compatibility with self-contained -->
<script>
(function () {
var script = document.createElement("script");
script.type = "text/javascript";
script.src = "https://mathjax.rstudio.com/latest/MathJax.js?config=TeX-AMS-MML_HTMLorMML";
document.getElementsByTagName("head")[0].appendChild(script);
})();
</script>
</body>
</html>
|