| <!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 `src/distributions/utils.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>utils.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" type="text/css" href="../../../normalize.css"><link rel="stylesheet" type="text/css" href="../../../rustdoc.css" id="mainThemeStyle"><link rel="stylesheet" type="text/css" href="../../../ayu.css" disabled><link rel="stylesheet" type="text/css" href="../../../dark.css" disabled><link rel="stylesheet" type="text/css" href="../../../light.css" id="themeStyle"><script id="default-settings" ></script><script src="../../../storage.js"></script><script src="../../../crates.js"></script><script defer src="../../../main.js"></script><script defer src="../../../source-script.js"></script><script defer src="../../../source-files.js"></script> |
| <noscript><link rel="stylesheet" href="../../../noscript.css"></noscript><link rel="shortcut icon" href="https://www.rust-lang.org/favicon.ico"></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"><div class="sidebar-menu" role="button">☰</div><a class="sidebar-logo" href="../../../rand/index.html"><div class="logo-container"><img src="https://www.rust-lang.org/logos/rust-logo-128x128-blk.png" alt="logo"></div> |
| </a></nav><main><div class="width-limiter"><div class="sub-container"><a class="sub-logo-container" href="../../../rand/index.html"><img src="https://www.rust-lang.org/logos/rust-logo-128x128-blk.png" alt="logo"></a><nav class="sub"><div class="theme-picker"><button id="theme-picker" aria-label="Pick another theme!" aria-haspopup="menu" title="themes"><img width="18" height="18" alt="Pick another theme!" src="../../../brush.svg"></button><div id="theme-choices" role="menu"></div></div><form class="search-form"><div class="search-container"><div> |
| <input class="search-input" name="search" autocomplete="off" spellcheck="false" placeholder="Click or press ‘S’ to search, ‘?’ for more options…" type="search"></div><button type="button" id="help-button" title="help">?</button><a id="settings-menu" href="../../../settings.html" title="settings"><img width="18" height="18" alt="Change settings" src="../../../wheel.svg"></a></div></form></nav></div><section id="main-content" class="content"><div class="example-wrap"><pre class="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> |
| <span id="191">191</span> |
| <span id="192">192</span> |
| <span id="193">193</span> |
| <span id="194">194</span> |
| <span id="195">195</span> |
| <span id="196">196</span> |
| <span id="197">197</span> |
| <span id="198">198</span> |
| <span id="199">199</span> |
| <span id="200">200</span> |
| <span id="201">201</span> |
| <span id="202">202</span> |
| <span id="203">203</span> |
| <span id="204">204</span> |
| <span id="205">205</span> |
| <span id="206">206</span> |
| <span id="207">207</span> |
| <span id="208">208</span> |
| <span id="209">209</span> |
| <span id="210">210</span> |
| <span id="211">211</span> |
| <span id="212">212</span> |
| <span id="213">213</span> |
| <span id="214">214</span> |
| <span id="215">215</span> |
| <span id="216">216</span> |
| <span id="217">217</span> |
| <span id="218">218</span> |
| <span id="219">219</span> |
| <span id="220">220</span> |
| <span id="221">221</span> |
| <span id="222">222</span> |
| <span id="223">223</span> |
| <span id="224">224</span> |
| <span id="225">225</span> |
| <span id="226">226</span> |
| <span id="227">227</span> |
| <span id="228">228</span> |
| <span id="229">229</span> |
| <span id="230">230</span> |
| <span id="231">231</span> |
| <span id="232">232</span> |
| <span id="233">233</span> |
| <span id="234">234</span> |
| <span id="235">235</span> |
| <span id="236">236</span> |
| <span id="237">237</span> |
| <span id="238">238</span> |
| <span id="239">239</span> |
| <span id="240">240</span> |
| <span id="241">241</span> |
| <span id="242">242</span> |
| <span id="243">243</span> |
| <span id="244">244</span> |
| <span id="245">245</span> |
| <span id="246">246</span> |
| <span id="247">247</span> |
| <span id="248">248</span> |
| <span id="249">249</span> |
| <span id="250">250</span> |
| <span id="251">251</span> |
| <span id="252">252</span> |
| <span id="253">253</span> |
| <span id="254">254</span> |
| <span id="255">255</span> |
| <span id="256">256</span> |
| <span id="257">257</span> |
| <span id="258">258</span> |
| <span id="259">259</span> |
| <span id="260">260</span> |
| <span id="261">261</span> |
| <span id="262">262</span> |
| <span id="263">263</span> |
| <span id="264">264</span> |
| <span id="265">265</span> |
| <span id="266">266</span> |
| <span id="267">267</span> |
| <span id="268">268</span> |
| <span id="269">269</span> |
| <span id="270">270</span> |
| <span id="271">271</span> |
| <span id="272">272</span> |
| <span id="273">273</span> |
| <span id="274">274</span> |
| <span id="275">275</span> |
| <span id="276">276</span> |
| <span id="277">277</span> |
| <span id="278">278</span> |
| <span id="279">279</span> |
| <span id="280">280</span> |
| <span id="281">281</span> |
| <span id="282">282</span> |
| <span id="283">283</span> |
| <span id="284">284</span> |
| <span id="285">285</span> |
| <span id="286">286</span> |
| <span id="287">287</span> |
| <span id="288">288</span> |
| <span id="289">289</span> |
| <span id="290">290</span> |
| <span id="291">291</span> |
| <span id="292">292</span> |
| <span id="293">293</span> |
| <span id="294">294</span> |
| <span id="295">295</span> |
| <span id="296">296</span> |
| <span id="297">297</span> |
| <span id="298">298</span> |
| <span id="299">299</span> |
| <span id="300">300</span> |
| <span id="301">301</span> |
| <span id="302">302</span> |
| <span id="303">303</span> |
| <span id="304">304</span> |
| <span id="305">305</span> |
| <span id="306">306</span> |
| <span id="307">307</span> |
| <span id="308">308</span> |
| <span id="309">309</span> |
| <span id="310">310</span> |
| <span id="311">311</span> |
| <span id="312">312</span> |
| <span id="313">313</span> |
| <span id="314">314</span> |
| <span id="315">315</span> |
| <span id="316">316</span> |
| <span id="317">317</span> |
| <span id="318">318</span> |
| <span id="319">319</span> |
| <span id="320">320</span> |
| <span id="321">321</span> |
| <span id="322">322</span> |
| <span id="323">323</span> |
| <span id="324">324</span> |
| <span id="325">325</span> |
| <span id="326">326</span> |
| <span id="327">327</span> |
| <span id="328">328</span> |
| <span id="329">329</span> |
| <span id="330">330</span> |
| <span id="331">331</span> |
| <span id="332">332</span> |
| <span id="333">333</span> |
| <span id="334">334</span> |
| <span id="335">335</span> |
| <span id="336">336</span> |
| <span id="337">337</span> |
| <span id="338">338</span> |
| <span id="339">339</span> |
| <span id="340">340</span> |
| <span id="341">341</span> |
| <span id="342">342</span> |
| <span id="343">343</span> |
| <span id="344">344</span> |
| <span id="345">345</span> |
| <span id="346">346</span> |
| <span id="347">347</span> |
| <span id="348">348</span> |
| <span id="349">349</span> |
| <span id="350">350</span> |
| <span id="351">351</span> |
| <span id="352">352</span> |
| <span id="353">353</span> |
| <span id="354">354</span> |
| <span id="355">355</span> |
| <span id="356">356</span> |
| <span id="357">357</span> |
| <span id="358">358</span> |
| <span id="359">359</span> |
| <span id="360">360</span> |
| <span id="361">361</span> |
| <span id="362">362</span> |
| <span id="363">363</span> |
| <span id="364">364</span> |
| <span id="365">365</span> |
| <span id="366">366</span> |
| <span id="367">367</span> |
| <span id="368">368</span> |
| <span id="369">369</span> |
| <span id="370">370</span> |
| <span id="371">371</span> |
| <span id="372">372</span> |
| <span id="373">373</span> |
| <span id="374">374</span> |
| <span id="375">375</span> |
| <span id="376">376</span> |
| <span id="377">377</span> |
| <span id="378">378</span> |
| <span id="379">379</span> |
| <span id="380">380</span> |
| <span id="381">381</span> |
| <span id="382">382</span> |
| <span id="383">383</span> |
| <span id="384">384</span> |
| <span id="385">385</span> |
| <span id="386">386</span> |
| <span id="387">387</span> |
| <span id="388">388</span> |
| <span id="389">389</span> |
| <span id="390">390</span> |
| <span id="391">391</span> |
| <span id="392">392</span> |
| <span id="393">393</span> |
| <span id="394">394</span> |
| <span id="395">395</span> |
| <span id="396">396</span> |
| <span id="397">397</span> |
| <span id="398">398</span> |
| <span id="399">399</span> |
| <span id="400">400</span> |
| <span id="401">401</span> |
| <span id="402">402</span> |
| <span id="403">403</span> |
| <span id="404">404</span> |
| <span id="405">405</span> |
| <span id="406">406</span> |
| <span id="407">407</span> |
| <span id="408">408</span> |
| <span id="409">409</span> |
| <span id="410">410</span> |
| <span id="411">411</span> |
| <span id="412">412</span> |
| <span id="413">413</span> |
| <span id="414">414</span> |
| <span id="415">415</span> |
| <span id="416">416</span> |
| <span id="417">417</span> |
| <span id="418">418</span> |
| <span id="419">419</span> |
| <span id="420">420</span> |
| <span id="421">421</span> |
| <span id="422">422</span> |
| <span id="423">423</span> |
| <span id="424">424</span> |
| <span id="425">425</span> |
| <span id="426">426</span> |
| <span id="427">427</span> |
| <span id="428">428</span> |
| <span id="429">429</span> |
| </pre><pre class="rust"><code><span class="comment">// Copyright 2018 Developers of the Rand project.</span> |
| <span class="comment">//</span> |
| <span class="comment">// Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or</span> |
| <span class="comment">// https://www.apache.org/licenses/LICENSE-2.0> or the MIT license</span> |
| <span class="comment">// <LICENSE-MIT or https://opensource.org/licenses/MIT>, at your</span> |
| <span class="comment">// option. This file may not be copied, modified, or distributed</span> |
| <span class="comment">// except according to those terms.</span> |
| |
| <span class="doccomment">//! Math helper functions</span> |
| |
| <span class="attribute">#[<span class="ident">cfg</span>(<span class="ident">feature</span> <span class="op">=</span> <span class="string">"simd_support"</span>)]</span> <span class="kw">use</span> <span class="ident">packed_simd</span>::<span class="kw-2">*</span>; |
| |
| |
| <span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">trait</span> <span class="ident">WideningMultiply</span><span class="op"><</span><span class="ident">RHS</span> <span class="op">=</span> <span class="self">Self</span><span class="op">></span> { |
| <span class="kw">type</span> <span class="ident">Output</span>; |
| |
| <span class="kw">fn</span> <span class="ident">wmul</span>(<span class="self">self</span>, <span class="ident">x</span>: <span class="ident">RHS</span>) -> <span class="ident"><span class="self">Self</span>::Output</span>; |
| } |
| |
| <span class="macro">macro_rules!</span> <span class="ident">wmul_impl</span> { |
| (<span class="macro-nonterminal">$</span><span class="macro-nonterminal">ty</span>:<span class="ident">ty</span>, <span class="macro-nonterminal">$</span><span class="macro-nonterminal">wide</span>:<span class="ident">ty</span>, <span class="macro-nonterminal">$</span><span class="macro-nonterminal">shift</span>:<span class="ident">expr</span>) => { |
| <span class="kw">impl</span> <span class="ident">WideningMultiply</span> <span class="kw">for</span> <span class="macro-nonterminal">$</span><span class="macro-nonterminal">ty</span> { |
| <span class="kw">type</span> <span class="ident">Output</span> <span class="op">=</span> (<span class="macro-nonterminal">$</span><span class="macro-nonterminal">ty</span>, <span class="macro-nonterminal">$</span><span class="macro-nonterminal">ty</span>); |
| |
| <span class="attribute">#[<span class="ident">inline</span>(<span class="ident">always</span>)]</span> |
| <span class="kw">fn</span> <span class="ident">wmul</span>(<span class="self">self</span>, <span class="ident">x</span>: <span class="macro-nonterminal">$</span><span class="macro-nonterminal">ty</span>) -> <span class="ident"><span class="self">Self</span>::Output</span> { |
| <span class="kw">let</span> <span class="ident">tmp</span> <span class="op">=</span> (<span class="self">self</span> <span class="kw">as</span> <span class="macro-nonterminal">$</span><span class="macro-nonterminal">wide</span>) <span class="op">*</span> (<span class="ident">x</span> <span class="kw">as</span> <span class="macro-nonterminal">$</span><span class="macro-nonterminal">wide</span>); |
| ((<span class="ident">tmp</span> <span class="op">></span><span class="op">></span> <span class="macro-nonterminal">$</span><span class="macro-nonterminal">shift</span>) <span class="kw">as</span> <span class="macro-nonterminal">$</span><span class="macro-nonterminal">ty</span>, <span class="ident">tmp</span> <span class="kw">as</span> <span class="macro-nonterminal">$</span><span class="macro-nonterminal">ty</span>) |
| } |
| } |
| }; |
| |
| <span class="comment">// simd bulk implementation</span> |
| ($((<span class="macro-nonterminal">$</span><span class="macro-nonterminal">ty</span>:<span class="ident">ident</span>, <span class="macro-nonterminal">$</span><span class="macro-nonterminal">wide</span>:<span class="ident">ident</span>),)<span class="op">+</span>, <span class="macro-nonterminal">$</span><span class="macro-nonterminal">shift</span>:<span class="ident">expr</span>) => { |
| $( |
| <span class="kw">impl</span> <span class="ident">WideningMultiply</span> <span class="kw">for</span> <span class="macro-nonterminal">$</span><span class="macro-nonterminal">ty</span> { |
| <span class="kw">type</span> <span class="ident">Output</span> <span class="op">=</span> (<span class="macro-nonterminal">$</span><span class="macro-nonterminal">ty</span>, <span class="macro-nonterminal">$</span><span class="macro-nonterminal">ty</span>); |
| |
| <span class="attribute">#[<span class="ident">inline</span>(<span class="ident">always</span>)]</span> |
| <span class="kw">fn</span> <span class="ident">wmul</span>(<span class="self">self</span>, <span class="ident">x</span>: <span class="macro-nonterminal">$</span><span class="macro-nonterminal">ty</span>) -> <span class="ident"><span class="self">Self</span>::Output</span> { |
| <span class="comment">// For supported vectors, this should compile to a couple</span> |
| <span class="comment">// supported multiply & swizzle instructions (no actual</span> |
| <span class="comment">// casting).</span> |
| <span class="comment">// TODO: optimize</span> |
| <span class="kw">let</span> <span class="ident">y</span>: <span class="macro-nonterminal">$</span><span class="macro-nonterminal">wide</span> <span class="op">=</span> <span class="self">self</span>.<span class="ident">cast</span>(); |
| <span class="kw">let</span> <span class="ident">x</span>: <span class="macro-nonterminal">$</span><span class="macro-nonterminal">wide</span> <span class="op">=</span> <span class="ident">x</span>.<span class="ident">cast</span>(); |
| <span class="kw">let</span> <span class="ident">tmp</span> <span class="op">=</span> <span class="ident">y</span> <span class="op">*</span> <span class="ident">x</span>; |
| <span class="kw">let</span> <span class="ident">hi</span>: <span class="macro-nonterminal">$</span><span class="macro-nonterminal">ty</span> <span class="op">=</span> (<span class="ident">tmp</span> <span class="op">></span><span class="op">></span> <span class="macro-nonterminal">$</span><span class="macro-nonterminal">shift</span>).<span class="ident">cast</span>(); |
| <span class="kw">let</span> <span class="ident">lo</span>: <span class="macro-nonterminal">$</span><span class="macro-nonterminal">ty</span> <span class="op">=</span> <span class="ident">tmp</span>.<span class="ident">cast</span>(); |
| (<span class="ident">hi</span>, <span class="ident">lo</span>) |
| } |
| } |
| )<span class="op">+</span> |
| }; |
| } |
| <span class="macro">wmul_impl!</span> { <span class="ident">u8</span>, <span class="ident">u16</span>, <span class="number">8</span> } |
| <span class="macro">wmul_impl!</span> { <span class="ident">u16</span>, <span class="ident">u32</span>, <span class="number">16</span> } |
| <span class="macro">wmul_impl!</span> { <span class="ident">u32</span>, <span class="ident">u64</span>, <span class="number">32</span> } |
| <span class="macro">wmul_impl!</span> { <span class="ident">u64</span>, <span class="ident">u128</span>, <span class="number">64</span> } |
| |
| <span class="comment">// This code is a translation of the __mulddi3 function in LLVM's</span> |
| <span class="comment">// compiler-rt. It is an optimised variant of the common method</span> |
| <span class="comment">// `(a + b) * (c + d) = ac + ad + bc + bd`.</span> |
| <span class="comment">//</span> |
| <span class="comment">// For some reason LLVM can optimise the C version very well, but</span> |
| <span class="comment">// keeps shuffling registers in this Rust translation.</span> |
| <span class="macro">macro_rules!</span> <span class="ident">wmul_impl_large</span> { |
| (<span class="macro-nonterminal">$</span><span class="macro-nonterminal">ty</span>:<span class="ident">ty</span>, <span class="macro-nonterminal">$</span><span class="macro-nonterminal">half</span>:<span class="ident">expr</span>) => { |
| <span class="kw">impl</span> <span class="ident">WideningMultiply</span> <span class="kw">for</span> <span class="macro-nonterminal">$</span><span class="macro-nonterminal">ty</span> { |
| <span class="kw">type</span> <span class="ident">Output</span> <span class="op">=</span> (<span class="macro-nonterminal">$</span><span class="macro-nonterminal">ty</span>, <span class="macro-nonterminal">$</span><span class="macro-nonterminal">ty</span>); |
| |
| <span class="attribute">#[<span class="ident">inline</span>(<span class="ident">always</span>)]</span> |
| <span class="kw">fn</span> <span class="ident">wmul</span>(<span class="self">self</span>, <span class="ident">b</span>: <span class="macro-nonterminal">$</span><span class="macro-nonterminal">ty</span>) -> <span class="ident"><span class="self">Self</span>::Output</span> { |
| <span class="kw">const</span> <span class="ident">LOWER_MASK</span>: <span class="macro-nonterminal">$</span><span class="macro-nonterminal">ty</span> <span class="op">=</span> <span class="op">!</span><span class="number">0</span> <span class="op">></span><span class="op">></span> <span class="macro-nonterminal">$</span><span class="macro-nonterminal">half</span>; |
| <span class="kw">let</span> <span class="kw-2">mut</span> <span class="ident">low</span> <span class="op">=</span> (<span class="self">self</span> <span class="op">&</span> <span class="ident">LOWER_MASK</span>).<span class="ident">wrapping_mul</span>(<span class="ident">b</span> <span class="op">&</span> <span class="ident">LOWER_MASK</span>); |
| <span class="kw">let</span> <span class="kw-2">mut</span> <span class="ident">t</span> <span class="op">=</span> <span class="ident">low</span> <span class="op">></span><span class="op">></span> <span class="macro-nonterminal">$</span><span class="macro-nonterminal">half</span>; |
| <span class="ident">low</span> <span class="op">&=</span> <span class="ident">LOWER_MASK</span>; |
| <span class="ident">t</span> <span class="op">+</span><span class="op">=</span> (<span class="self">self</span> <span class="op">></span><span class="op">></span> <span class="macro-nonterminal">$</span><span class="macro-nonterminal">half</span>).<span class="ident">wrapping_mul</span>(<span class="ident">b</span> <span class="op">&</span> <span class="ident">LOWER_MASK</span>); |
| <span class="ident">low</span> <span class="op">+</span><span class="op">=</span> (<span class="ident">t</span> <span class="op">&</span> <span class="ident">LOWER_MASK</span>) <span class="op"><</span><span class="op"><</span> <span class="macro-nonterminal">$</span><span class="macro-nonterminal">half</span>; |
| <span class="kw">let</span> <span class="kw-2">mut</span> <span class="ident">high</span> <span class="op">=</span> <span class="ident">t</span> <span class="op">></span><span class="op">></span> <span class="macro-nonterminal">$</span><span class="macro-nonterminal">half</span>; |
| <span class="ident">t</span> <span class="op">=</span> <span class="ident">low</span> <span class="op">></span><span class="op">></span> <span class="macro-nonterminal">$</span><span class="macro-nonterminal">half</span>; |
| <span class="ident">low</span> <span class="op">&=</span> <span class="ident">LOWER_MASK</span>; |
| <span class="ident">t</span> <span class="op">+</span><span class="op">=</span> (<span class="ident">b</span> <span class="op">></span><span class="op">></span> <span class="macro-nonterminal">$</span><span class="macro-nonterminal">half</span>).<span class="ident">wrapping_mul</span>(<span class="self">self</span> <span class="op">&</span> <span class="ident">LOWER_MASK</span>); |
| <span class="ident">low</span> <span class="op">+</span><span class="op">=</span> (<span class="ident">t</span> <span class="op">&</span> <span class="ident">LOWER_MASK</span>) <span class="op"><</span><span class="op"><</span> <span class="macro-nonterminal">$</span><span class="macro-nonterminal">half</span>; |
| <span class="ident">high</span> <span class="op">+</span><span class="op">=</span> <span class="ident">t</span> <span class="op">></span><span class="op">></span> <span class="macro-nonterminal">$</span><span class="macro-nonterminal">half</span>; |
| <span class="ident">high</span> <span class="op">+</span><span class="op">=</span> (<span class="self">self</span> <span class="op">></span><span class="op">></span> <span class="macro-nonterminal">$</span><span class="macro-nonterminal">half</span>).<span class="ident">wrapping_mul</span>(<span class="ident">b</span> <span class="op">></span><span class="op">></span> <span class="macro-nonterminal">$</span><span class="macro-nonterminal">half</span>); |
| |
| (<span class="ident">high</span>, <span class="ident">low</span>) |
| } |
| } |
| }; |
| |
| <span class="comment">// simd bulk implementation</span> |
| (($(<span class="macro-nonterminal">$</span><span class="macro-nonterminal">ty</span>:<span class="ident">ty</span>,)<span class="op">+</span>) <span class="macro-nonterminal">$</span><span class="macro-nonterminal">scalar</span>:<span class="ident">ty</span>, <span class="macro-nonterminal">$</span><span class="macro-nonterminal">half</span>:<span class="ident">expr</span>) => { |
| $( |
| <span class="kw">impl</span> <span class="ident">WideningMultiply</span> <span class="kw">for</span> <span class="macro-nonterminal">$</span><span class="macro-nonterminal">ty</span> { |
| <span class="kw">type</span> <span class="ident">Output</span> <span class="op">=</span> (<span class="macro-nonterminal">$</span><span class="macro-nonterminal">ty</span>, <span class="macro-nonterminal">$</span><span class="macro-nonterminal">ty</span>); |
| |
| <span class="attribute">#[<span class="ident">inline</span>(<span class="ident">always</span>)]</span> |
| <span class="kw">fn</span> <span class="ident">wmul</span>(<span class="self">self</span>, <span class="ident">b</span>: <span class="macro-nonterminal">$</span><span class="macro-nonterminal">ty</span>) -> <span class="ident"><span class="self">Self</span>::Output</span> { |
| <span class="comment">// needs wrapping multiplication</span> |
| <span class="kw">const</span> <span class="ident">LOWER_MASK</span>: <span class="macro-nonterminal">$</span><span class="macro-nonterminal">scalar</span> <span class="op">=</span> <span class="op">!</span><span class="number">0</span> <span class="op">></span><span class="op">></span> <span class="macro-nonterminal">$</span><span class="macro-nonterminal">half</span>; |
| <span class="kw">let</span> <span class="kw-2">mut</span> <span class="ident">low</span> <span class="op">=</span> (<span class="self">self</span> <span class="op">&</span> <span class="ident">LOWER_MASK</span>) <span class="op">*</span> (<span class="ident">b</span> <span class="op">&</span> <span class="ident">LOWER_MASK</span>); |
| <span class="kw">let</span> <span class="kw-2">mut</span> <span class="ident">t</span> <span class="op">=</span> <span class="ident">low</span> <span class="op">></span><span class="op">></span> <span class="macro-nonterminal">$</span><span class="macro-nonterminal">half</span>; |
| <span class="ident">low</span> <span class="op">&=</span> <span class="ident">LOWER_MASK</span>; |
| <span class="ident">t</span> <span class="op">+</span><span class="op">=</span> (<span class="self">self</span> <span class="op">></span><span class="op">></span> <span class="macro-nonterminal">$</span><span class="macro-nonterminal">half</span>) <span class="op">*</span> (<span class="ident">b</span> <span class="op">&</span> <span class="ident">LOWER_MASK</span>); |
| <span class="ident">low</span> <span class="op">+</span><span class="op">=</span> (<span class="ident">t</span> <span class="op">&</span> <span class="ident">LOWER_MASK</span>) <span class="op"><</span><span class="op"><</span> <span class="macro-nonterminal">$</span><span class="macro-nonterminal">half</span>; |
| <span class="kw">let</span> <span class="kw-2">mut</span> <span class="ident">high</span> <span class="op">=</span> <span class="ident">t</span> <span class="op">></span><span class="op">></span> <span class="macro-nonterminal">$</span><span class="macro-nonterminal">half</span>; |
| <span class="ident">t</span> <span class="op">=</span> <span class="ident">low</span> <span class="op">></span><span class="op">></span> <span class="macro-nonterminal">$</span><span class="macro-nonterminal">half</span>; |
| <span class="ident">low</span> <span class="op">&=</span> <span class="ident">LOWER_MASK</span>; |
| <span class="ident">t</span> <span class="op">+</span><span class="op">=</span> (<span class="ident">b</span> <span class="op">></span><span class="op">></span> <span class="macro-nonterminal">$</span><span class="macro-nonterminal">half</span>) <span class="op">*</span> (<span class="self">self</span> <span class="op">&</span> <span class="ident">LOWER_MASK</span>); |
| <span class="ident">low</span> <span class="op">+</span><span class="op">=</span> (<span class="ident">t</span> <span class="op">&</span> <span class="ident">LOWER_MASK</span>) <span class="op"><</span><span class="op"><</span> <span class="macro-nonterminal">$</span><span class="macro-nonterminal">half</span>; |
| <span class="ident">high</span> <span class="op">+</span><span class="op">=</span> <span class="ident">t</span> <span class="op">></span><span class="op">></span> <span class="macro-nonterminal">$</span><span class="macro-nonterminal">half</span>; |
| <span class="ident">high</span> <span class="op">+</span><span class="op">=</span> (<span class="self">self</span> <span class="op">></span><span class="op">></span> <span class="macro-nonterminal">$</span><span class="macro-nonterminal">half</span>) <span class="op">*</span> (<span class="ident">b</span> <span class="op">></span><span class="op">></span> <span class="macro-nonterminal">$</span><span class="macro-nonterminal">half</span>); |
| |
| (<span class="ident">high</span>, <span class="ident">low</span>) |
| } |
| } |
| )<span class="op">+</span> |
| }; |
| } |
| <span class="macro">wmul_impl_large!</span> { <span class="ident">u128</span>, <span class="number">64</span> } |
| |
| <span class="macro">macro_rules!</span> <span class="ident">wmul_impl_usize</span> { |
| (<span class="macro-nonterminal">$</span><span class="macro-nonterminal">ty</span>:<span class="ident">ty</span>) => { |
| <span class="kw">impl</span> <span class="ident">WideningMultiply</span> <span class="kw">for</span> <span class="ident">usize</span> { |
| <span class="kw">type</span> <span class="ident">Output</span> <span class="op">=</span> (<span class="ident">usize</span>, <span class="ident">usize</span>); |
| |
| <span class="attribute">#[<span class="ident">inline</span>(<span class="ident">always</span>)]</span> |
| <span class="kw">fn</span> <span class="ident">wmul</span>(<span class="self">self</span>, <span class="ident">x</span>: <span class="ident">usize</span>) -> <span class="ident"><span class="self">Self</span>::Output</span> { |
| <span class="kw">let</span> (<span class="ident">high</span>, <span class="ident">low</span>) <span class="op">=</span> (<span class="self">self</span> <span class="kw">as</span> <span class="macro-nonterminal">$</span><span class="macro-nonterminal">ty</span>).<span class="ident">wmul</span>(<span class="ident">x</span> <span class="kw">as</span> <span class="macro-nonterminal">$</span><span class="macro-nonterminal">ty</span>); |
| (<span class="ident">high</span> <span class="kw">as</span> <span class="ident">usize</span>, <span class="ident">low</span> <span class="kw">as</span> <span class="ident">usize</span>) |
| } |
| } |
| }; |
| } |
| <span class="attribute">#[<span class="ident">cfg</span>(<span class="ident">target_pointer_width</span> <span class="op">=</span> <span class="string">"16"</span>)]</span> |
| <span class="macro">wmul_impl_usize!</span> { <span class="ident">u16</span> } |
| <span class="attribute">#[<span class="ident">cfg</span>(<span class="ident">target_pointer_width</span> <span class="op">=</span> <span class="string">"32"</span>)]</span> |
| <span class="macro">wmul_impl_usize!</span> { <span class="ident">u32</span> } |
| <span class="attribute">#[<span class="ident">cfg</span>(<span class="ident">target_pointer_width</span> <span class="op">=</span> <span class="string">"64"</span>)]</span> |
| <span class="macro">wmul_impl_usize!</span> { <span class="ident">u64</span> } |
| |
| <span class="attribute">#[<span class="ident">cfg</span>(<span class="ident">feature</span> <span class="op">=</span> <span class="string">"simd_support"</span>)]</span> |
| <span class="kw">mod</span> <span class="ident">simd_wmul</span> { |
| <span class="kw">use</span> <span class="kw">super</span>::<span class="kw-2">*</span>; |
| <span class="attribute">#[<span class="ident">cfg</span>(<span class="ident">target_arch</span> <span class="op">=</span> <span class="string">"x86"</span>)]</span> <span class="kw">use</span> <span class="ident">core::arch::x86</span>::<span class="kw-2">*</span>; |
| <span class="attribute">#[<span class="ident">cfg</span>(<span class="ident">target_arch</span> <span class="op">=</span> <span class="string">"x86_64"</span>)]</span> <span class="kw">use</span> <span class="ident">core::arch::x86_64</span>::<span class="kw-2">*</span>; |
| |
| <span class="macro">wmul_impl!</span> { |
| (<span class="ident">u8x2</span>, <span class="ident">u16x2</span>), |
| (<span class="ident">u8x4</span>, <span class="ident">u16x4</span>), |
| (<span class="ident">u8x8</span>, <span class="ident">u16x8</span>), |
| (<span class="ident">u8x16</span>, <span class="ident">u16x16</span>), |
| (<span class="ident">u8x32</span>, <span class="ident">u16x32</span>),, |
| <span class="number">8</span> |
| } |
| |
| <span class="macro">wmul_impl!</span> { (<span class="ident">u16x2</span>, <span class="ident">u32x2</span>),, <span class="number">16</span> } |
| <span class="macro">wmul_impl!</span> { (<span class="ident">u16x4</span>, <span class="ident">u32x4</span>),, <span class="number">16</span> } |
| <span class="attribute">#[<span class="ident">cfg</span>(<span class="ident">not</span>(<span class="ident">target_feature</span> <span class="op">=</span> <span class="string">"sse2"</span>))]</span> |
| <span class="macro">wmul_impl!</span> { (<span class="ident">u16x8</span>, <span class="ident">u32x8</span>),, <span class="number">16</span> } |
| <span class="attribute">#[<span class="ident">cfg</span>(<span class="ident">not</span>(<span class="ident">target_feature</span> <span class="op">=</span> <span class="string">"avx2"</span>))]</span> |
| <span class="macro">wmul_impl!</span> { (<span class="ident">u16x16</span>, <span class="ident">u32x16</span>),, <span class="number">16</span> } |
| |
| <span class="comment">// 16-bit lane widths allow use of the x86 `mulhi` instructions, which</span> |
| <span class="comment">// means `wmul` can be implemented with only two instructions.</span> |
| <span class="attribute">#[<span class="ident">allow</span>(<span class="ident">unused_macros</span>)]</span> |
| <span class="macro">macro_rules!</span> <span class="ident">wmul_impl_16</span> { |
| (<span class="macro-nonterminal">$</span><span class="macro-nonterminal">ty</span>:<span class="ident">ident</span>, <span class="macro-nonterminal">$</span><span class="macro-nonterminal">intrinsic</span>:<span class="ident">ident</span>, <span class="macro-nonterminal">$</span><span class="macro-nonterminal">mulhi</span>:<span class="ident">ident</span>, <span class="macro-nonterminal">$</span><span class="macro-nonterminal">mullo</span>:<span class="ident">ident</span>) => { |
| <span class="kw">impl</span> <span class="ident">WideningMultiply</span> <span class="kw">for</span> <span class="macro-nonterminal">$</span><span class="macro-nonterminal">ty</span> { |
| <span class="kw">type</span> <span class="ident">Output</span> <span class="op">=</span> (<span class="macro-nonterminal">$</span><span class="macro-nonterminal">ty</span>, <span class="macro-nonterminal">$</span><span class="macro-nonterminal">ty</span>); |
| |
| <span class="attribute">#[<span class="ident">inline</span>(<span class="ident">always</span>)]</span> |
| <span class="kw">fn</span> <span class="ident">wmul</span>(<span class="self">self</span>, <span class="ident">x</span>: <span class="macro-nonterminal">$</span><span class="macro-nonterminal">ty</span>) -> <span class="ident"><span class="self">Self</span>::Output</span> { |
| <span class="kw">let</span> <span class="ident">b</span> <span class="op">=</span> <span class="macro-nonterminal">$</span><span class="macro-nonterminal">intrinsic::from_bits</span>(<span class="ident">x</span>); |
| <span class="kw">let</span> <span class="ident">a</span> <span class="op">=</span> <span class="macro-nonterminal">$</span><span class="macro-nonterminal">intrinsic::from_bits</span>(<span class="self">self</span>); |
| <span class="kw">let</span> <span class="ident">hi</span> <span class="op">=</span> <span class="macro-nonterminal">$</span><span class="macro-nonterminal">ty::from_bits</span>(<span class="kw">unsafe</span> { <span class="macro-nonterminal">$</span><span class="macro-nonterminal">mulhi</span>(<span class="ident">a</span>, <span class="ident">b</span>) }); |
| <span class="kw">let</span> <span class="ident">lo</span> <span class="op">=</span> <span class="macro-nonterminal">$</span><span class="macro-nonterminal">ty::from_bits</span>(<span class="kw">unsafe</span> { <span class="macro-nonterminal">$</span><span class="macro-nonterminal">mullo</span>(<span class="ident">a</span>, <span class="ident">b</span>) }); |
| (<span class="ident">hi</span>, <span class="ident">lo</span>) |
| } |
| } |
| }; |
| } |
| |
| <span class="attribute">#[<span class="ident">cfg</span>(<span class="ident">target_feature</span> <span class="op">=</span> <span class="string">"sse2"</span>)]</span> |
| <span class="macro">wmul_impl_16!</span> { <span class="ident">u16x8</span>, <span class="ident">__m128i</span>, <span class="ident">_mm_mulhi_epu16</span>, <span class="ident">_mm_mullo_epi16</span> } |
| <span class="attribute">#[<span class="ident">cfg</span>(<span class="ident">target_feature</span> <span class="op">=</span> <span class="string">"avx2"</span>)]</span> |
| <span class="macro">wmul_impl_16!</span> { <span class="ident">u16x16</span>, <span class="ident">__m256i</span>, <span class="ident">_mm256_mulhi_epu16</span>, <span class="ident">_mm256_mullo_epi16</span> } |
| <span class="comment">// FIXME: there are no `__m512i` types in stdsimd yet, so `wmul::<u16x32>`</span> |
| <span class="comment">// cannot use the same implementation.</span> |
| |
| <span class="macro">wmul_impl!</span> { |
| (<span class="ident">u32x2</span>, <span class="ident">u64x2</span>), |
| (<span class="ident">u32x4</span>, <span class="ident">u64x4</span>), |
| (<span class="ident">u32x8</span>, <span class="ident">u64x8</span>),, |
| <span class="number">32</span> |
| } |
| |
| <span class="comment">// TODO: optimize, this seems to seriously slow things down</span> |
| <span class="macro">wmul_impl_large!</span> { (<span class="ident">u8x64</span>,) <span class="ident">u8</span>, <span class="number">4</span> } |
| <span class="macro">wmul_impl_large!</span> { (<span class="ident">u16x32</span>,) <span class="ident">u16</span>, <span class="number">8</span> } |
| <span class="macro">wmul_impl_large!</span> { (<span class="ident">u32x16</span>,) <span class="ident">u32</span>, <span class="number">16</span> } |
| <span class="macro">wmul_impl_large!</span> { (<span class="ident">u64x2</span>, <span class="ident">u64x4</span>, <span class="ident">u64x8</span>,) <span class="ident">u64</span>, <span class="number">32</span> } |
| } |
| |
| <span class="doccomment">/// Helper trait when dealing with scalar and SIMD floating point types.</span> |
| <span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">trait</span> <span class="ident">FloatSIMDUtils</span> { |
| <span class="comment">// `PartialOrd` for vectors compares lexicographically. We want to compare all</span> |
| <span class="comment">// the individual SIMD lanes instead, and get the combined result over all</span> |
| <span class="comment">// lanes. This is possible using something like `a.lt(b).all()`, but we</span> |
| <span class="comment">// implement it as a trait so we can write the same code for `f32` and `f64`.</span> |
| <span class="comment">// Only the comparison functions we need are implemented.</span> |
| <span class="kw">fn</span> <span class="ident">all_lt</span>(<span class="self">self</span>, <span class="ident">other</span>: <span class="self">Self</span>) -> <span class="ident">bool</span>; |
| <span class="kw">fn</span> <span class="ident">all_le</span>(<span class="self">self</span>, <span class="ident">other</span>: <span class="self">Self</span>) -> <span class="ident">bool</span>; |
| <span class="kw">fn</span> <span class="ident">all_finite</span>(<span class="self">self</span>) -> <span class="ident">bool</span>; |
| |
| <span class="kw">type</span> <span class="ident">Mask</span>; |
| <span class="kw">fn</span> <span class="ident">finite_mask</span>(<span class="self">self</span>) -> <span class="ident"><span class="self">Self</span>::Mask</span>; |
| <span class="kw">fn</span> <span class="ident">gt_mask</span>(<span class="self">self</span>, <span class="ident">other</span>: <span class="self">Self</span>) -> <span class="ident"><span class="self">Self</span>::Mask</span>; |
| <span class="kw">fn</span> <span class="ident">ge_mask</span>(<span class="self">self</span>, <span class="ident">other</span>: <span class="self">Self</span>) -> <span class="ident"><span class="self">Self</span>::Mask</span>; |
| |
| <span class="comment">// Decrease all lanes where the mask is `true` to the next lower value</span> |
| <span class="comment">// representable by the floating-point type. At least one of the lanes</span> |
| <span class="comment">// must be set.</span> |
| <span class="kw">fn</span> <span class="ident">decrease_masked</span>(<span class="self">self</span>, <span class="ident">mask</span>: <span class="ident"><span class="self">Self</span>::Mask</span>) -> <span class="self">Self</span>; |
| |
| <span class="comment">// Convert from int value. Conversion is done while retaining the numerical</span> |
| <span class="comment">// value, not by retaining the binary representation.</span> |
| <span class="kw">type</span> <span class="ident">UInt</span>; |
| <span class="kw">fn</span> <span class="ident">cast_from_int</span>(<span class="ident">i</span>: <span class="ident"><span class="self">Self</span>::UInt</span>) -> <span class="self">Self</span>; |
| } |
| |
| <span class="doccomment">/// Implement functions available in std builds but missing from core primitives</span> |
| <span class="attribute">#[<span class="ident">cfg</span>(<span class="ident">not</span>(<span class="ident">std</span>))]</span> |
| <span class="comment">// False positive: We are following `std` here.</span> |
| <span class="attribute">#[<span class="ident">allow</span>(<span class="ident">clippy::wrong_self_convention</span>)]</span> |
| <span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">trait</span> <span class="ident">Float</span>: <span class="ident">Sized</span> { |
| <span class="kw">fn</span> <span class="ident">is_nan</span>(<span class="self">self</span>) -> <span class="ident">bool</span>; |
| <span class="kw">fn</span> <span class="ident">is_infinite</span>(<span class="self">self</span>) -> <span class="ident">bool</span>; |
| <span class="kw">fn</span> <span class="ident">is_finite</span>(<span class="self">self</span>) -> <span class="ident">bool</span>; |
| } |
| |
| <span class="doccomment">/// Implement functions on f32/f64 to give them APIs similar to SIMD types</span> |
| <span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">trait</span> <span class="ident">FloatAsSIMD</span>: <span class="ident">Sized</span> { |
| <span class="attribute">#[<span class="ident">inline</span>(<span class="ident">always</span>)]</span> |
| <span class="kw">fn</span> <span class="ident">lanes</span>() -> <span class="ident">usize</span> { |
| <span class="number">1</span> |
| } |
| <span class="attribute">#[<span class="ident">inline</span>(<span class="ident">always</span>)]</span> |
| <span class="kw">fn</span> <span class="ident">splat</span>(<span class="ident">scalar</span>: <span class="self">Self</span>) -> <span class="self">Self</span> { |
| <span class="ident">scalar</span> |
| } |
| <span class="attribute">#[<span class="ident">inline</span>(<span class="ident">always</span>)]</span> |
| <span class="kw">fn</span> <span class="ident">extract</span>(<span class="self">self</span>, <span class="ident">index</span>: <span class="ident">usize</span>) -> <span class="self">Self</span> { |
| <span class="macro">debug_assert_eq!</span>(<span class="ident">index</span>, <span class="number">0</span>); |
| <span class="self">self</span> |
| } |
| <span class="attribute">#[<span class="ident">inline</span>(<span class="ident">always</span>)]</span> |
| <span class="kw">fn</span> <span class="ident">replace</span>(<span class="self">self</span>, <span class="ident">index</span>: <span class="ident">usize</span>, <span class="ident">new_value</span>: <span class="self">Self</span>) -> <span class="self">Self</span> { |
| <span class="macro">debug_assert_eq!</span>(<span class="ident">index</span>, <span class="number">0</span>); |
| <span class="ident">new_value</span> |
| } |
| } |
| |
| <span class="kw">pub</span>(<span class="kw">crate</span>) <span class="kw">trait</span> <span class="ident">BoolAsSIMD</span>: <span class="ident">Sized</span> { |
| <span class="kw">fn</span> <span class="ident">any</span>(<span class="self">self</span>) -> <span class="ident">bool</span>; |
| <span class="kw">fn</span> <span class="ident">all</span>(<span class="self">self</span>) -> <span class="ident">bool</span>; |
| <span class="kw">fn</span> <span class="ident">none</span>(<span class="self">self</span>) -> <span class="ident">bool</span>; |
| } |
| |
| <span class="kw">impl</span> <span class="ident">BoolAsSIMD</span> <span class="kw">for</span> <span class="ident">bool</span> { |
| <span class="attribute">#[<span class="ident">inline</span>(<span class="ident">always</span>)]</span> |
| <span class="kw">fn</span> <span class="ident">any</span>(<span class="self">self</span>) -> <span class="ident">bool</span> { |
| <span class="self">self</span> |
| } |
| |
| <span class="attribute">#[<span class="ident">inline</span>(<span class="ident">always</span>)]</span> |
| <span class="kw">fn</span> <span class="ident">all</span>(<span class="self">self</span>) -> <span class="ident">bool</span> { |
| <span class="self">self</span> |
| } |
| |
| <span class="attribute">#[<span class="ident">inline</span>(<span class="ident">always</span>)]</span> |
| <span class="kw">fn</span> <span class="ident">none</span>(<span class="self">self</span>) -> <span class="ident">bool</span> { |
| <span class="op">!</span><span class="self">self</span> |
| } |
| } |
| |
| <span class="macro">macro_rules!</span> <span class="ident">scalar_float_impl</span> { |
| (<span class="macro-nonterminal">$</span><span class="macro-nonterminal">ty</span>:<span class="ident">ident</span>, <span class="macro-nonterminal">$</span><span class="macro-nonterminal">uty</span>:<span class="ident">ident</span>) => { |
| <span class="attribute">#[<span class="ident">cfg</span>(<span class="ident">not</span>(<span class="ident">std</span>))]</span> |
| <span class="kw">impl</span> <span class="ident">Float</span> <span class="kw">for</span> <span class="macro-nonterminal">$</span><span class="macro-nonterminal">ty</span> { |
| <span class="attribute">#[<span class="ident">inline</span>]</span> |
| <span class="kw">fn</span> <span class="ident">is_nan</span>(<span class="self">self</span>) -> <span class="ident">bool</span> { |
| <span class="self">self</span> <span class="op">!</span><span class="op">=</span> <span class="self">self</span> |
| } |
| |
| <span class="attribute">#[<span class="ident">inline</span>]</span> |
| <span class="kw">fn</span> <span class="ident">is_infinite</span>(<span class="self">self</span>) -> <span class="ident">bool</span> { |
| <span class="self">self</span> <span class="op">==</span> <span class="ident">::core</span>::<span class="macro-nonterminal">$</span><span class="macro-nonterminal">ty::INFINITY</span> <span class="op">|</span><span class="op">|</span> <span class="self">self</span> <span class="op">==</span> <span class="ident">::core</span>::<span class="macro-nonterminal">$</span><span class="macro-nonterminal">ty::NEG_INFINITY</span> |
| } |
| |
| <span class="attribute">#[<span class="ident">inline</span>]</span> |
| <span class="kw">fn</span> <span class="ident">is_finite</span>(<span class="self">self</span>) -> <span class="ident">bool</span> { |
| <span class="op">!</span>(<span class="self">self</span>.<span class="ident">is_nan</span>() <span class="op">|</span><span class="op">|</span> <span class="self">self</span>.<span class="ident">is_infinite</span>()) |
| } |
| } |
| |
| <span class="kw">impl</span> <span class="ident">FloatSIMDUtils</span> <span class="kw">for</span> <span class="macro-nonterminal">$</span><span class="macro-nonterminal">ty</span> { |
| <span class="kw">type</span> <span class="ident">Mask</span> <span class="op">=</span> <span class="ident">bool</span>; |
| <span class="kw">type</span> <span class="ident">UInt</span> <span class="op">=</span> <span class="macro-nonterminal">$</span><span class="macro-nonterminal">uty</span>; |
| |
| <span class="attribute">#[<span class="ident">inline</span>(<span class="ident">always</span>)]</span> |
| <span class="kw">fn</span> <span class="ident">all_lt</span>(<span class="self">self</span>, <span class="ident">other</span>: <span class="self">Self</span>) -> <span class="ident">bool</span> { |
| <span class="self">self</span> <span class="op"><</span> <span class="ident">other</span> |
| } |
| |
| <span class="attribute">#[<span class="ident">inline</span>(<span class="ident">always</span>)]</span> |
| <span class="kw">fn</span> <span class="ident">all_le</span>(<span class="self">self</span>, <span class="ident">other</span>: <span class="self">Self</span>) -> <span class="ident">bool</span> { |
| <span class="self">self</span> <span class="op"><</span><span class="op">=</span> <span class="ident">other</span> |
| } |
| |
| <span class="attribute">#[<span class="ident">inline</span>(<span class="ident">always</span>)]</span> |
| <span class="kw">fn</span> <span class="ident">all_finite</span>(<span class="self">self</span>) -> <span class="ident">bool</span> { |
| <span class="self">self</span>.<span class="ident">is_finite</span>() |
| } |
| |
| <span class="attribute">#[<span class="ident">inline</span>(<span class="ident">always</span>)]</span> |
| <span class="kw">fn</span> <span class="ident">finite_mask</span>(<span class="self">self</span>) -> <span class="ident"><span class="self">Self</span>::Mask</span> { |
| <span class="self">self</span>.<span class="ident">is_finite</span>() |
| } |
| |
| <span class="attribute">#[<span class="ident">inline</span>(<span class="ident">always</span>)]</span> |
| <span class="kw">fn</span> <span class="ident">gt_mask</span>(<span class="self">self</span>, <span class="ident">other</span>: <span class="self">Self</span>) -> <span class="ident"><span class="self">Self</span>::Mask</span> { |
| <span class="self">self</span> <span class="op">></span> <span class="ident">other</span> |
| } |
| |
| <span class="attribute">#[<span class="ident">inline</span>(<span class="ident">always</span>)]</span> |
| <span class="kw">fn</span> <span class="ident">ge_mask</span>(<span class="self">self</span>, <span class="ident">other</span>: <span class="self">Self</span>) -> <span class="ident"><span class="self">Self</span>::Mask</span> { |
| <span class="self">self</span> <span class="op">></span><span class="op">=</span> <span class="ident">other</span> |
| } |
| |
| <span class="attribute">#[<span class="ident">inline</span>(<span class="ident">always</span>)]</span> |
| <span class="kw">fn</span> <span class="ident">decrease_masked</span>(<span class="self">self</span>, <span class="ident">mask</span>: <span class="ident"><span class="self">Self</span>::Mask</span>) -> <span class="self">Self</span> { |
| <span class="macro">debug_assert!</span>(<span class="ident">mask</span>, <span class="string">"At least one lane must be set"</span>); |
| <span class="op"><</span><span class="macro-nonterminal">$</span><span class="macro-nonterminal">ty</span><span class="op">></span><span class="ident">::from_bits</span>(<span class="self">self</span>.<span class="ident">to_bits</span>() <span class="op">-</span> <span class="number">1</span>) |
| } |
| |
| <span class="attribute">#[<span class="ident">inline</span>]</span> |
| <span class="kw">fn</span> <span class="ident">cast_from_int</span>(<span class="ident">i</span>: <span class="ident"><span class="self">Self</span>::UInt</span>) -> <span class="self">Self</span> { |
| <span class="ident">i</span> <span class="kw">as</span> <span class="macro-nonterminal">$</span><span class="macro-nonterminal">ty</span> |
| } |
| } |
| |
| <span class="kw">impl</span> <span class="ident">FloatAsSIMD</span> <span class="kw">for</span> <span class="macro-nonterminal">$</span><span class="macro-nonterminal">ty</span> {} |
| }; |
| } |
| |
| <span class="macro">scalar_float_impl!</span>(<span class="ident">f32</span>, <span class="ident">u32</span>); |
| <span class="macro">scalar_float_impl!</span>(<span class="ident">f64</span>, <span class="ident">u64</span>); |
| |
| |
| <span class="attribute">#[<span class="ident">cfg</span>(<span class="ident">feature</span> <span class="op">=</span> <span class="string">"simd_support"</span>)]</span> |
| <span class="macro">macro_rules!</span> <span class="ident">simd_impl</span> { |
| (<span class="macro-nonterminal">$</span><span class="macro-nonterminal">ty</span>:<span class="ident">ident</span>, <span class="macro-nonterminal">$</span><span class="macro-nonterminal">f_scalar</span>:<span class="ident">ident</span>, <span class="macro-nonterminal">$</span><span class="macro-nonterminal">mty</span>:<span class="ident">ident</span>, <span class="macro-nonterminal">$</span><span class="macro-nonterminal">uty</span>:<span class="ident">ident</span>) => { |
| <span class="kw">impl</span> <span class="ident">FloatSIMDUtils</span> <span class="kw">for</span> <span class="macro-nonterminal">$</span><span class="macro-nonterminal">ty</span> { |
| <span class="kw">type</span> <span class="ident">Mask</span> <span class="op">=</span> <span class="macro-nonterminal">$</span><span class="macro-nonterminal">mty</span>; |
| <span class="kw">type</span> <span class="ident">UInt</span> <span class="op">=</span> <span class="macro-nonterminal">$</span><span class="macro-nonterminal">uty</span>; |
| |
| <span class="attribute">#[<span class="ident">inline</span>(<span class="ident">always</span>)]</span> |
| <span class="kw">fn</span> <span class="ident">all_lt</span>(<span class="self">self</span>, <span class="ident">other</span>: <span class="self">Self</span>) -> <span class="ident">bool</span> { |
| <span class="self">self</span>.<span class="ident">lt</span>(<span class="ident">other</span>).<span class="ident">all</span>() |
| } |
| |
| <span class="attribute">#[<span class="ident">inline</span>(<span class="ident">always</span>)]</span> |
| <span class="kw">fn</span> <span class="ident">all_le</span>(<span class="self">self</span>, <span class="ident">other</span>: <span class="self">Self</span>) -> <span class="ident">bool</span> { |
| <span class="self">self</span>.<span class="ident">le</span>(<span class="ident">other</span>).<span class="ident">all</span>() |
| } |
| |
| <span class="attribute">#[<span class="ident">inline</span>(<span class="ident">always</span>)]</span> |
| <span class="kw">fn</span> <span class="ident">all_finite</span>(<span class="self">self</span>) -> <span class="ident">bool</span> { |
| <span class="self">self</span>.<span class="ident">finite_mask</span>().<span class="ident">all</span>() |
| } |
| |
| <span class="attribute">#[<span class="ident">inline</span>(<span class="ident">always</span>)]</span> |
| <span class="kw">fn</span> <span class="ident">finite_mask</span>(<span class="self">self</span>) -> <span class="ident"><span class="self">Self</span>::Mask</span> { |
| <span class="comment">// This can possibly be done faster by checking bit patterns</span> |
| <span class="kw">let</span> <span class="ident">neg_inf</span> <span class="op">=</span> <span class="macro-nonterminal">$</span><span class="macro-nonterminal">ty::splat</span>(<span class="ident">::core</span>::<span class="macro-nonterminal">$</span><span class="macro-nonterminal">f_scalar::NEG_INFINITY</span>); |
| <span class="kw">let</span> <span class="ident">pos_inf</span> <span class="op">=</span> <span class="macro-nonterminal">$</span><span class="macro-nonterminal">ty::splat</span>(<span class="ident">::core</span>::<span class="macro-nonterminal">$</span><span class="macro-nonterminal">f_scalar::INFINITY</span>); |
| <span class="self">self</span>.<span class="ident">gt</span>(<span class="ident">neg_inf</span>) <span class="op">&</span> <span class="self">self</span>.<span class="ident">lt</span>(<span class="ident">pos_inf</span>) |
| } |
| |
| <span class="attribute">#[<span class="ident">inline</span>(<span class="ident">always</span>)]</span> |
| <span class="kw">fn</span> <span class="ident">gt_mask</span>(<span class="self">self</span>, <span class="ident">other</span>: <span class="self">Self</span>) -> <span class="ident"><span class="self">Self</span>::Mask</span> { |
| <span class="self">self</span>.<span class="ident">gt</span>(<span class="ident">other</span>) |
| } |
| |
| <span class="attribute">#[<span class="ident">inline</span>(<span class="ident">always</span>)]</span> |
| <span class="kw">fn</span> <span class="ident">ge_mask</span>(<span class="self">self</span>, <span class="ident">other</span>: <span class="self">Self</span>) -> <span class="ident"><span class="self">Self</span>::Mask</span> { |
| <span class="self">self</span>.<span class="ident">ge</span>(<span class="ident">other</span>) |
| } |
| |
| <span class="attribute">#[<span class="ident">inline</span>(<span class="ident">always</span>)]</span> |
| <span class="kw">fn</span> <span class="ident">decrease_masked</span>(<span class="self">self</span>, <span class="ident">mask</span>: <span class="ident"><span class="self">Self</span>::Mask</span>) -> <span class="self">Self</span> { |
| <span class="comment">// Casting a mask into ints will produce all bits set for</span> |
| <span class="comment">// true, and 0 for false. Adding that to the binary</span> |
| <span class="comment">// representation of a float means subtracting one from</span> |
| <span class="comment">// the binary representation, resulting in the next lower</span> |
| <span class="comment">// value representable by $ty. This works even when the</span> |
| <span class="comment">// current value is infinity.</span> |
| <span class="macro">debug_assert!</span>(<span class="ident">mask</span>.<span class="ident">any</span>(), <span class="string">"At least one lane must be set"</span>); |
| <span class="op"><</span><span class="macro-nonterminal">$</span><span class="macro-nonterminal">ty</span><span class="op">></span><span class="ident">::from_bits</span>(<span class="op"><</span><span class="macro-nonterminal">$</span><span class="macro-nonterminal">uty</span><span class="op">></span><span class="ident">::from_bits</span>(<span class="self">self</span>) <span class="op">+</span> <span class="op"><</span><span class="macro-nonterminal">$</span><span class="macro-nonterminal">uty</span><span class="op">></span><span class="ident">::from_bits</span>(<span class="ident">mask</span>)) |
| } |
| |
| <span class="attribute">#[<span class="ident">inline</span>]</span> |
| <span class="kw">fn</span> <span class="ident">cast_from_int</span>(<span class="ident">i</span>: <span class="ident"><span class="self">Self</span>::UInt</span>) -> <span class="self">Self</span> { |
| <span class="ident">i</span>.<span class="ident">cast</span>() |
| } |
| } |
| }; |
| } |
| |
| <span class="attribute">#[<span class="ident">cfg</span>(<span class="ident">feature</span><span class="op">=</span><span class="string">"simd_support"</span>)]</span> <span class="macro">simd_impl!</span> { <span class="ident">f32x2</span>, <span class="ident">f32</span>, <span class="ident">m32x2</span>, <span class="ident">u32x2</span> } |
| <span class="attribute">#[<span class="ident">cfg</span>(<span class="ident">feature</span><span class="op">=</span><span class="string">"simd_support"</span>)]</span> <span class="macro">simd_impl!</span> { <span class="ident">f32x4</span>, <span class="ident">f32</span>, <span class="ident">m32x4</span>, <span class="ident">u32x4</span> } |
| <span class="attribute">#[<span class="ident">cfg</span>(<span class="ident">feature</span><span class="op">=</span><span class="string">"simd_support"</span>)]</span> <span class="macro">simd_impl!</span> { <span class="ident">f32x8</span>, <span class="ident">f32</span>, <span class="ident">m32x8</span>, <span class="ident">u32x8</span> } |
| <span class="attribute">#[<span class="ident">cfg</span>(<span class="ident">feature</span><span class="op">=</span><span class="string">"simd_support"</span>)]</span> <span class="macro">simd_impl!</span> { <span class="ident">f32x16</span>, <span class="ident">f32</span>, <span class="ident">m32x16</span>, <span class="ident">u32x16</span> } |
| <span class="attribute">#[<span class="ident">cfg</span>(<span class="ident">feature</span><span class="op">=</span><span class="string">"simd_support"</span>)]</span> <span class="macro">simd_impl!</span> { <span class="ident">f64x2</span>, <span class="ident">f64</span>, <span class="ident">m64x2</span>, <span class="ident">u64x2</span> } |
| <span class="attribute">#[<span class="ident">cfg</span>(<span class="ident">feature</span><span class="op">=</span><span class="string">"simd_support"</span>)]</span> <span class="macro">simd_impl!</span> { <span class="ident">f64x4</span>, <span class="ident">f64</span>, <span class="ident">m64x4</span>, <span class="ident">u64x4</span> } |
| <span class="attribute">#[<span class="ident">cfg</span>(<span class="ident">feature</span><span class="op">=</span><span class="string">"simd_support"</span>)]</span> <span class="macro">simd_impl!</span> { <span class="ident">f64x8</span>, <span class="ident">f64</span>, <span class="ident">m64x8</span>, <span class="ident">u64x8</span> } |
| </code></pre></div> |
| </section><section id="search" class="content hidden"></section></div></main><div id="rustdoc-vars" data-root-path="../../../" data-current-crate="rand" data-themes="ayu,dark,light" data-resource-suffix="" data-rustdoc-version="1.60.0-nightly (1bd4fdc94 2022-01-12)" ></div> |
| </body></html> |