| <!DOCTYPE html><html lang="en"><head><meta charset="utf-8"><meta name="viewport" content="width=device-width, initial-scale=1.0"><meta name="generator" content="rustdoc"><meta name="description" content="Source of the Rust file `/root/.cargo/registry/src/github.com-1ecc6299db9ec823/aho-corasick-1.0.2/src/packed/vector.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>vector.rs - source</title><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../SourceSerif4-Regular.ttf.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../FiraSans-Regular.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../FiraSans-Medium.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../SourceCodePro-Regular.ttf.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../SourceSerif4-Bold.ttf.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../SourceCodePro-Semibold.ttf.woff2"><link rel="stylesheet" href="../../../normalize.css"><link rel="stylesheet" href="../../../rustdoc.css" id="mainThemeStyle"><link rel="stylesheet" href="../../../ayu.css" disabled><link rel="stylesheet" href="../../../dark.css" disabled><link rel="stylesheet" href="../../../light.css" id="themeStyle"><script id="default-settings" ></script><script src="../../../storage.js"></script><script defer src="../../../source-script.js"></script><script defer src="../../../source-files.js"></script><script defer src="../../../main.js"></script><noscript><link rel="stylesheet" href="../../../noscript.css"></noscript><link rel="alternate icon" type="image/png" href="../../../favicon-16x16.png"><link rel="alternate icon" type="image/png" href="../../../favicon-32x32.png"><link rel="icon" type="image/svg+xml" href="../../../favicon.svg"></head><body class="rustdoc source"><!--[if lte IE 11]><div class="warning">This old browser is unsupported and will most likely display funky things.</div><![endif]--><nav class="sidebar"><a class="sidebar-logo" href="../../../aho_corasick/index.html"><div class="logo-container"><img class="rust-logo" src="../../../rust-logo.svg" alt="logo"></div></a></nav><main><div class="width-limiter"><nav class="sub"><a class="sub-logo-container" href="../../../aho_corasick/index.html"><img class="rust-logo" src="../../../rust-logo.svg" alt="logo"></a><form class="search-form"><div class="search-container"><span></span><input class="search-input" name="search" autocomplete="off" spellcheck="false" placeholder="Click or press ‘S’ to search, ‘?’ for more options…" type="search"><div id="help-button" title="help" tabindex="-1"><a href="../../../help.html">?</a></div><div id="settings-menu" tabindex="-1"><a href="../../../settings.html" title="settings"><img width="22" height="22" alt="Change settings" src="../../../wheel.svg"></a></div></div></form></nav><section id="main-content" class="content"><div class="example-wrap"><pre class="src-line-numbers"><span id="1">1</span> |
| <span id="2">2</span> |
| <span id="3">3</span> |
| <span id="4">4</span> |
| <span id="5">5</span> |
| <span id="6">6</span> |
| <span id="7">7</span> |
| <span id="8">8</span> |
| <span id="9">9</span> |
| <span id="10">10</span> |
| <span id="11">11</span> |
| <span id="12">12</span> |
| <span id="13">13</span> |
| <span id="14">14</span> |
| <span id="15">15</span> |
| <span id="16">16</span> |
| <span id="17">17</span> |
| <span id="18">18</span> |
| <span id="19">19</span> |
| <span id="20">20</span> |
| <span id="21">21</span> |
| <span id="22">22</span> |
| <span id="23">23</span> |
| <span id="24">24</span> |
| <span id="25">25</span> |
| <span id="26">26</span> |
| <span id="27">27</span> |
| <span id="28">28</span> |
| <span id="29">29</span> |
| <span id="30">30</span> |
| <span id="31">31</span> |
| <span id="32">32</span> |
| <span id="33">33</span> |
| <span id="34">34</span> |
| <span id="35">35</span> |
| <span id="36">36</span> |
| <span id="37">37</span> |
| <span id="38">38</span> |
| <span id="39">39</span> |
| <span id="40">40</span> |
| <span id="41">41</span> |
| <span id="42">42</span> |
| <span id="43">43</span> |
| <span id="44">44</span> |
| <span id="45">45</span> |
| <span id="46">46</span> |
| <span id="47">47</span> |
| <span id="48">48</span> |
| <span id="49">49</span> |
| <span id="50">50</span> |
| <span id="51">51</span> |
| <span id="52">52</span> |
| <span id="53">53</span> |
| <span id="54">54</span> |
| <span id="55">55</span> |
| <span id="56">56</span> |
| <span id="57">57</span> |
| <span id="58">58</span> |
| <span id="59">59</span> |
| <span id="60">60</span> |
| <span id="61">61</span> |
| <span id="62">62</span> |
| <span id="63">63</span> |
| <span id="64">64</span> |
| <span id="65">65</span> |
| <span id="66">66</span> |
| <span id="67">67</span> |
| <span id="68">68</span> |
| <span id="69">69</span> |
| <span id="70">70</span> |
| <span id="71">71</span> |
| <span id="72">72</span> |
| <span id="73">73</span> |
| <span id="74">74</span> |
| <span id="75">75</span> |
| <span id="76">76</span> |
| <span id="77">77</span> |
| <span id="78">78</span> |
| <span id="79">79</span> |
| <span id="80">80</span> |
| <span id="81">81</span> |
| <span id="82">82</span> |
| <span id="83">83</span> |
| <span id="84">84</span> |
| <span id="85">85</span> |
| <span id="86">86</span> |
| <span id="87">87</span> |
| <span id="88">88</span> |
| <span id="89">89</span> |
| <span id="90">90</span> |
| <span id="91">91</span> |
| <span id="92">92</span> |
| <span id="93">93</span> |
| <span id="94">94</span> |
| <span id="95">95</span> |
| <span id="96">96</span> |
| <span id="97">97</span> |
| <span id="98">98</span> |
| <span id="99">99</span> |
| <span id="100">100</span> |
| <span id="101">101</span> |
| <span id="102">102</span> |
| <span id="103">103</span> |
| <span id="104">104</span> |
| <span id="105">105</span> |
| <span id="106">106</span> |
| <span id="107">107</span> |
| <span id="108">108</span> |
| <span id="109">109</span> |
| <span id="110">110</span> |
| <span id="111">111</span> |
| <span id="112">112</span> |
| <span id="113">113</span> |
| <span id="114">114</span> |
| <span id="115">115</span> |
| <span id="116">116</span> |
| <span id="117">117</span> |
| <span id="118">118</span> |
| <span id="119">119</span> |
| <span id="120">120</span> |
| <span id="121">121</span> |
| <span id="122">122</span> |
| <span id="123">123</span> |
| <span id="124">124</span> |
| <span id="125">125</span> |
| <span id="126">126</span> |
| <span id="127">127</span> |
| <span id="128">128</span> |
| <span id="129">129</span> |
| <span id="130">130</span> |
| <span id="131">131</span> |
| <span id="132">132</span> |
| <span id="133">133</span> |
| <span id="134">134</span> |
| <span id="135">135</span> |
| <span id="136">136</span> |
| <span id="137">137</span> |
| <span id="138">138</span> |
| <span id="139">139</span> |
| <span id="140">140</span> |
| <span id="141">141</span> |
| <span id="142">142</span> |
| <span id="143">143</span> |
| <span id="144">144</span> |
| <span id="145">145</span> |
| <span id="146">146</span> |
| <span id="147">147</span> |
| <span id="148">148</span> |
| <span id="149">149</span> |
| <span id="150">150</span> |
| <span id="151">151</span> |
| <span id="152">152</span> |
| <span id="153">153</span> |
| <span id="154">154</span> |
| <span id="155">155</span> |
| <span id="156">156</span> |
| <span id="157">157</span> |
| <span id="158">158</span> |
| <span id="159">159</span> |
| <span id="160">160</span> |
| <span id="161">161</span> |
| <span id="162">162</span> |
| <span id="163">163</span> |
| <span id="164">164</span> |
| <span id="165">165</span> |
| <span id="166">166</span> |
| <span id="167">167</span> |
| <span id="168">168</span> |
| <span id="169">169</span> |
| <span id="170">170</span> |
| <span id="171">171</span> |
| <span id="172">172</span> |
| <span id="173">173</span> |
| <span id="174">174</span> |
| <span id="175">175</span> |
| <span id="176">176</span> |
| <span id="177">177</span> |
| <span id="178">178</span> |
| <span id="179">179</span> |
| <span id="180">180</span> |
| <span id="181">181</span> |
| <span id="182">182</span> |
| <span id="183">183</span> |
| <span id="184">184</span> |
| <span id="185">185</span> |
| <span id="186">186</span> |
| <span id="187">187</span> |
| <span id="188">188</span> |
| <span id="189">189</span> |
| <span id="190">190</span> |
| </pre><pre class="rust"><code><span class="comment">// This file contains a set of fairly generic utility functions when working |
| // with SIMD vectors. |
| // |
| // SAFETY: All of the routines below are unsafe to call because they assume |
| // the necessary CPU target features in order to use particular vendor |
| // intrinsics. Calling these routines when the underlying CPU does not support |
| // the appropriate target features is NOT safe. Callers must ensure this |
| // themselves. |
| // |
| // Note that it may not look like this safety invariant is being upheld when |
| // these routines are called. Namely, the CPU feature check is typically pretty |
| // far away from when these routines are used. Instead, we rely on the fact |
| // that certain types serve as a guaranteed receipt that pertinent target |
| // features are enabled. For example, the only way TeddySlim3Mask256 can be |
| // constructed is if the AVX2 CPU feature is available. Thus, any code running |
| // inside of TeddySlim3Mask256 can use any of the functions below without any |
| // additional checks: its very existence *is* the check. |
| |
| </span><span class="kw">use </span>core::arch::x86_64::<span class="kw-2">*</span>; |
| |
| <span class="doccomment">/// Shift `a` to the left by two bytes (removing its two most significant |
| /// bytes), and concatenate it with the the two most significant bytes of `b`. |
| </span><span class="attribute">#[target_feature(enable = <span class="string">"avx2"</span>)] |
| </span><span class="kw">pub unsafe fn </span>alignr256_14(a: __m256i, b: __m256i) -> __m256i { |
| <span class="comment">// Credit goes to jneem for figuring this out: |
| // https://github.com/jneem/teddy/blob/9ab5e899ad6ef6911aecd3cf1033f1abe6e1f66c/src/x86/teddy_simd.rs#L145-L184 |
| // |
| // TL;DR avx2's PALIGNR instruction is actually just two 128-bit PALIGNR |
| // instructions, which is not what we want, so we need to do some extra |
| // shuffling. |
| |
| // This permute gives us the low 16 bytes of a concatenated with the high |
| // 16 bytes of b, in order of most significant to least significant. So |
| // `v = a[15:0] b[31:16]`. |
| </span><span class="kw">let </span>v = _mm256_permute2x128_si256(b, a, <span class="number">0x21</span>); |
| <span class="comment">// This effectively does this (where we deal in terms of byte-indexing |
| // and byte-shifting, and use inclusive ranges): |
| // |
| // ret[15:0] := ((a[15:0] << 16) | v[15:0]) >> 14 |
| // = ((a[15:0] << 16) | b[31:16]) >> 14 |
| // ret[31:16] := ((a[31:16] << 16) | v[31:16]) >> 14 |
| // = ((a[31:16] << 16) | a[15:0]) >> 14 |
| // |
| // Which therefore results in: |
| // |
| // ret[31:0] := a[29:16] a[15:14] a[13:0] b[31:30] |
| // |
| // The end result is that we've effectively done this: |
| // |
| // (a << 2) | (b >> 30) |
| // |
| // When `A` and `B` are strings---where the beginning of the string is in |
| // the least significant bits---we effectively result in the following |
| // semantic operation: |
| // |
| // (A >> 2) | (B << 30) |
| // |
| // The reversal being attributed to the fact that we are in little-endian. |
| </span>_mm256_alignr_epi8(a, v, <span class="number">14</span>) |
| } |
| |
| <span class="doccomment">/// Shift `a` to the left by three byte (removing its most significant byte), |
| /// and concatenate it with the the most significant byte of `b`. |
| </span><span class="attribute">#[target_feature(enable = <span class="string">"avx2"</span>)] |
| </span><span class="kw">pub unsafe fn </span>alignr256_13(a: __m256i, b: __m256i) -> __m256i { |
| <span class="comment">// For explanation, see alignr256_14. |
| </span><span class="kw">let </span>v = _mm256_permute2x128_si256(b, a, <span class="number">0x21</span>); |
| _mm256_alignr_epi8(a, v, <span class="number">13</span>) |
| } |
| |
| <span class="doccomment">/// Shift `a` to the left by one byte (removing its most significant byte), and |
| /// concatenate it with the the most significant byte of `b`. |
| </span><span class="attribute">#[target_feature(enable = <span class="string">"avx2"</span>)] |
| </span><span class="kw">pub unsafe fn </span>alignr256_15(a: __m256i, b: __m256i) -> __m256i { |
| <span class="comment">// For explanation, see alignr256_14. |
| </span><span class="kw">let </span>v = _mm256_permute2x128_si256(b, a, <span class="number">0x21</span>); |
| _mm256_alignr_epi8(a, v, <span class="number">15</span>) |
| } |
| |
| <span class="doccomment">/// Unpack the given 128-bit vector into its 64-bit components. The first |
| /// element of the array returned corresponds to the least significant 64-bit |
| /// lane in `a`. |
| </span><span class="attribute">#[target_feature(enable = <span class="string">"ssse3"</span>)] |
| </span><span class="kw">pub unsafe fn </span>unpack64x128(a: __m128i) -> [u64; <span class="number">2</span>] { |
| [ |
| _mm_cvtsi128_si64(a) <span class="kw">as </span>u64, |
| _mm_cvtsi128_si64(_mm_srli_si128(a, <span class="number">8</span>)) <span class="kw">as </span>u64, |
| ] |
| } |
| |
| <span class="doccomment">/// Unpack the given 256-bit vector into its 64-bit components. The first |
| /// element of the array returned corresponds to the least significant 64-bit |
| /// lane in `a`. |
| </span><span class="attribute">#[target_feature(enable = <span class="string">"avx2"</span>)] |
| </span><span class="kw">pub unsafe fn </span>unpack64x256(a: __m256i) -> [u64; <span class="number">4</span>] { |
| <span class="comment">// Using transmute here is precisely equivalent, but actually slower. It's |
| // not quite clear why. |
| </span><span class="kw">let </span>lo = _mm256_extracti128_si256(a, <span class="number">0</span>); |
| <span class="kw">let </span>hi = _mm256_extracti128_si256(a, <span class="number">1</span>); |
| [ |
| _mm_cvtsi128_si64(lo) <span class="kw">as </span>u64, |
| _mm_cvtsi128_si64(_mm_srli_si128(lo, <span class="number">8</span>)) <span class="kw">as </span>u64, |
| _mm_cvtsi128_si64(hi) <span class="kw">as </span>u64, |
| _mm_cvtsi128_si64(_mm_srli_si128(hi, <span class="number">8</span>)) <span class="kw">as </span>u64, |
| ] |
| } |
| |
| <span class="doccomment">/// Unpack the low 128-bits of `a` and `b`, and return them as 4 64-bit |
| /// integers. |
| /// |
| /// More precisely, if a = a4 a3 a2 a1 and b = b4 b3 b2 b1, where each element |
| /// is a 64-bit integer and a1/b1 correspond to the least significant 64 bits, |
| /// then the return value is `b2 b1 a2 a1`. |
| </span><span class="attribute">#[target_feature(enable = <span class="string">"avx2"</span>)] |
| </span><span class="kw">pub unsafe fn </span>unpacklo64x256(a: __m256i, b: __m256i) -> [u64; <span class="number">4</span>] { |
| <span class="kw">let </span>lo = _mm256_castsi256_si128(a); |
| <span class="kw">let </span>hi = _mm256_castsi256_si128(b); |
| [ |
| _mm_cvtsi128_si64(lo) <span class="kw">as </span>u64, |
| _mm_cvtsi128_si64(_mm_srli_si128(lo, <span class="number">8</span>)) <span class="kw">as </span>u64, |
| _mm_cvtsi128_si64(hi) <span class="kw">as </span>u64, |
| _mm_cvtsi128_si64(_mm_srli_si128(hi, <span class="number">8</span>)) <span class="kw">as </span>u64, |
| ] |
| } |
| |
| <span class="doccomment">/// Returns true if and only if all bits in the given 128-bit vector are 0. |
| </span><span class="attribute">#[target_feature(enable = <span class="string">"ssse3"</span>)] |
| </span><span class="kw">pub unsafe fn </span>is_all_zeroes128(a: __m128i) -> bool { |
| <span class="kw">let </span>cmp = _mm_cmpeq_epi8(a, zeroes128()); |
| _mm_movemask_epi8(cmp) <span class="kw">as </span>u32 == <span class="number">0xFFFF |
| </span>} |
| |
| <span class="doccomment">/// Returns true if and only if all bits in the given 256-bit vector are 0. |
| </span><span class="attribute">#[target_feature(enable = <span class="string">"avx2"</span>)] |
| </span><span class="kw">pub unsafe fn </span>is_all_zeroes256(a: __m256i) -> bool { |
| <span class="kw">let </span>cmp = _mm256_cmpeq_epi8(a, zeroes256()); |
| _mm256_movemask_epi8(cmp) <span class="kw">as </span>u32 == <span class="number">0xFFFFFFFF |
| </span>} |
| |
| <span class="doccomment">/// Load a 128-bit vector from slice at the given position. The slice does |
| /// not need to be unaligned. |
| /// |
| /// Since this code assumes little-endian (there is no big-endian x86), the |
| /// bytes starting in `slice[at..]` will be at the least significant bits of |
| /// the returned vector. This is important for the surrounding code, since for |
| /// example, shifting the resulting vector right is equivalent to logically |
| /// shifting the bytes in `slice` left. |
| </span><span class="attribute">#[target_feature(enable = <span class="string">"sse2"</span>)] |
| </span><span class="kw">pub unsafe fn </span>loadu128(slice: <span class="kw-2">&</span>[u8], at: usize) -> __m128i { |
| <span class="kw">let </span>ptr = slice.get_unchecked(at..).as_ptr(); |
| _mm_loadu_si128(ptr <span class="kw">as </span><span class="kw-2">*const </span>u8 <span class="kw">as </span><span class="kw-2">*const </span>__m128i) |
| } |
| |
| <span class="doccomment">/// Load a 256-bit vector from slice at the given position. The slice does |
| /// not need to be unaligned. |
| /// |
| /// Since this code assumes little-endian (there is no big-endian x86), the |
| /// bytes starting in `slice[at..]` will be at the least significant bits of |
| /// the returned vector. This is important for the surrounding code, since for |
| /// example, shifting the resulting vector right is equivalent to logically |
| /// shifting the bytes in `slice` left. |
| </span><span class="attribute">#[target_feature(enable = <span class="string">"avx2"</span>)] |
| </span><span class="kw">pub unsafe fn </span>loadu256(slice: <span class="kw-2">&</span>[u8], at: usize) -> __m256i { |
| <span class="kw">let </span>ptr = slice.get_unchecked(at..).as_ptr(); |
| _mm256_loadu_si256(ptr <span class="kw">as </span><span class="kw-2">*const </span>u8 <span class="kw">as </span><span class="kw-2">*const </span>__m256i) |
| } |
| |
| <span class="doccomment">/// Returns a 128-bit vector with all bits set to 0. |
| </span><span class="attribute">#[target_feature(enable = <span class="string">"sse2"</span>)] |
| </span><span class="kw">pub unsafe fn </span>zeroes128() -> __m128i { |
| _mm_set1_epi8(<span class="number">0</span>) |
| } |
| |
| <span class="doccomment">/// Returns a 256-bit vector with all bits set to 0. |
| </span><span class="attribute">#[target_feature(enable = <span class="string">"avx2"</span>)] |
| </span><span class="kw">pub unsafe fn </span>zeroes256() -> __m256i { |
| _mm256_set1_epi8(<span class="number">0</span>) |
| } |
| |
| <span class="doccomment">/// Returns a 128-bit vector with all bits set to 1. |
| </span><span class="attribute">#[target_feature(enable = <span class="string">"sse2"</span>)] |
| </span><span class="kw">pub unsafe fn </span>ones128() -> __m128i { |
| _mm_set1_epi8(<span class="number">0xFF </span><span class="kw">as </span>u8 <span class="kw">as </span>i8) |
| } |
| |
| <span class="doccomment">/// Returns a 256-bit vector with all bits set to 1. |
| </span><span class="attribute">#[target_feature(enable = <span class="string">"avx2"</span>)] |
| </span><span class="kw">pub unsafe fn </span>ones256() -> __m256i { |
| _mm256_set1_epi8(<span class="number">0xFF </span><span class="kw">as </span>u8 <span class="kw">as </span>i8) |
| } |
| </code></pre></div> |
| </section></div></main><div id="rustdoc-vars" data-root-path="../../../" data-current-crate="aho_corasick" data-themes="ayu,dark,light" data-resource-suffix="" data-rustdoc-version="1.66.0-nightly (5c8bff74b 2022-10-21)" ></div></body></html> |