<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd"> <html xmlns="http://www.w3.org/1999/xhtml"> <head> <meta http-equiv="Content-Type" content="text/xhtml;charset=UTF-8"/> <meta http-equiv="X-UA-Compatible" content="IE=9"/> <meta name="generator" content="Doxygen 1.8.14"/> <meta name="viewport" content="width=device-width, initial-scale=1"/> <title>Crypto++: simon-simd.cpp Source File</title> <link href="tabs.css" rel="stylesheet" type="text/css"/> <script type="text/javascript" src="jquery.js"></script> <script type="text/javascript" src="dynsections.js"></script> <link href="doxygen.css" rel="stylesheet" type="text/css" /> </head> <body> <div id="top"><!-- do not remove this div, it is closed by doxygen! --> <div id="titlearea"> <table cellspacing="0" cellpadding="0"> <tbody> <tr style="height: 56px;"> <td id="projectalign" style="padding-left: 0.5em;"> <div id="projectname">Crypto++  <span id="projectnumber">7.0</span> </div> <div id="projectbrief">Free C++ class library of cryptographic schemes</div> </td> </tr> </tbody> </table> </div> <!-- end header part --> <!-- Generated by Doxygen 1.8.14 --> <script type="text/javascript" src="menudata.js"></script> <script type="text/javascript" src="menu.js"></script> <script type="text/javascript"> /* @license magnet:?xt=urn:btih:cf05388f2679ee054f2beb29a391d25f4e673ac3&dn=gpl-2.0.txt GPL-v2 */ $(function() { initMenu('',false,false,'search.php','Search'); }); /* @license-end */</script> <div id="main-nav"></div> </div><!-- top --> <div class="header"> <div class="headertitle"> <div class="title">simon-simd.cpp</div> </div> </div><!--header--> <div class="contents"> <div class="fragment"><div class="line"><a name="l00001"></a><span class="lineno"> 1</span> <span class="comment">// simon-simd.cpp - written and placed in the public domain by Jeffrey Walton</span></div><div class="line"><a name="l00002"></a><span class="lineno"> 2</span> <span class="comment">//</span></div><div class="line"><a name="l00003"></a><span class="lineno"> 3</span> <span class="comment">// This source file uses intrinsics and built-ins to gain access to</span></div><div class="line"><a name="l00004"></a><span class="lineno"> 4</span> <span class="comment">// SSSE3, ARM NEON and ARMv8a, and Power7 Altivec instructions. A separate</span></div><div class="line"><a name="l00005"></a><span class="lineno"> 5</span> <span class="comment">// source file is needed because additional CXXFLAGS are required to enable</span></div><div class="line"><a name="l00006"></a><span class="lineno"> 6</span> <span class="comment">// the appropriate instructions sets in some build configurations.</span></div><div class="line"><a name="l00007"></a><span class="lineno"> 7</span> </div><div class="line"><a name="l00008"></a><span class="lineno"> 8</span> <span class="preprocessor">#include "<a class="code" href="pch_8h.html">pch.h</a>"</span></div><div class="line"><a name="l00009"></a><span class="lineno"> 9</span> <span class="preprocessor">#include "<a class="code" href="config_8h.html">config.h</a>"</span></div><div class="line"><a name="l00010"></a><span class="lineno"> 10</span> </div><div class="line"><a name="l00011"></a><span class="lineno"> 11</span> <span class="preprocessor">#include "<a class="code" href="simon_8h.html">simon.h</a>"</span></div><div class="line"><a name="l00012"></a><span class="lineno"> 12</span> <span class="preprocessor">#include "<a class="code" href="misc_8h.html">misc.h</a>"</span></div><div class="line"><a name="l00013"></a><span class="lineno"> 13</span> <span class="preprocessor">#include "adv-simd.h"</span></div><div class="line"><a name="l00014"></a><span class="lineno"> 14</span> </div><div class="line"><a name="l00015"></a><span class="lineno"> 15</span> <span class="comment">// Uncomment for benchmarking C++ against SSE or NEON.</span></div><div class="line"><a name="l00016"></a><span class="lineno"> 16</span> <span class="comment">// Do so in both simon.cpp and simon-simd.cpp.</span></div><div class="line"><a name="l00017"></a><span class="lineno"> 17</span> <span class="comment">// #undef CRYPTOPP_SSSE3_AVAILABLE</span></div><div class="line"><a name="l00018"></a><span class="lineno"> 18</span> <span class="comment">// #undef CRYPTOPP_SSE41_AVAILABLE</span></div><div class="line"><a name="l00019"></a><span class="lineno"> 19</span> <span class="comment">// #undef CRYPTOPP_ARM_NEON_AVAILABLE</span></div><div class="line"><a name="l00020"></a><span class="lineno"> 20</span> </div><div class="line"><a name="l00021"></a><span class="lineno"> 21</span> <span class="preprocessor">#if (CRYPTOPP_SSSE3_AVAILABLE)</span></div><div class="line"><a name="l00022"></a><span class="lineno"> 22</span> <span class="preprocessor"># include <pmmintrin.h></span></div><div class="line"><a name="l00023"></a><span class="lineno"> 23</span> <span class="preprocessor"># include <tmmintrin.h></span></div><div class="line"><a name="l00024"></a><span class="lineno"> 24</span> <span class="preprocessor">#endif</span></div><div class="line"><a name="l00025"></a><span class="lineno"> 25</span> </div><div class="line"><a name="l00026"></a><span class="lineno"> 26</span> <span class="preprocessor">#if (CRYPTOPP_SSE41_AVAILABLE)</span></div><div class="line"><a name="l00027"></a><span class="lineno"> 27</span> <span class="preprocessor"># include <smmintrin.h></span></div><div class="line"><a name="l00028"></a><span class="lineno"> 28</span> <span class="preprocessor">#endif</span></div><div class="line"><a name="l00029"></a><span class="lineno"> 29</span> </div><div class="line"><a name="l00030"></a><span class="lineno"> 30</span> <span class="preprocessor">#if defined(__AVX512F__) && defined(__AVX512VL__)</span></div><div class="line"><a name="l00031"></a><span class="lineno"> 31</span> <span class="preprocessor"># define CRYPTOPP_AVX512_ROTATE 1</span></div><div class="line"><a name="l00032"></a><span class="lineno"> 32</span> <span class="preprocessor"># include <immintrin.h></span></div><div class="line"><a name="l00033"></a><span class="lineno"> 33</span> <span class="preprocessor">#endif</span></div><div class="line"><a name="l00034"></a><span class="lineno"> 34</span> </div><div class="line"><a name="l00035"></a><span class="lineno"> 35</span> <span class="preprocessor">#if (CRYPTOPP_ARM_NEON_AVAILABLE)</span></div><div class="line"><a name="l00036"></a><span class="lineno"> 36</span> <span class="preprocessor"># include <arm_neon.h></span></div><div class="line"><a name="l00037"></a><span class="lineno"> 37</span> <span class="preprocessor">#endif</span></div><div class="line"><a name="l00038"></a><span class="lineno"> 38</span> </div><div class="line"><a name="l00039"></a><span class="lineno"> 39</span> <span class="comment">// Can't use CRYPTOPP_ARM_XXX_AVAILABLE because too many</span></div><div class="line"><a name="l00040"></a><span class="lineno"> 40</span> <span class="comment">// compilers don't follow ACLE conventions for the include.</span></div><div class="line"><a name="l00041"></a><span class="lineno"> 41</span> <span class="preprocessor">#if defined(CRYPTOPP_ARM_ACLE_AVAILABLE)</span></div><div class="line"><a name="l00042"></a><span class="lineno"> 42</span> <span class="preprocessor"># include <stdint.h></span></div><div class="line"><a name="l00043"></a><span class="lineno"> 43</span> <span class="preprocessor"># include <arm_acle.h></span></div><div class="line"><a name="l00044"></a><span class="lineno"> 44</span> <span class="preprocessor">#endif</span></div><div class="line"><a name="l00045"></a><span class="lineno"> 45</span> </div><div class="line"><a name="l00046"></a><span class="lineno"> 46</span> <span class="comment">// https://www.spinics.net/lists/gcchelp/msg47735.html and</span></div><div class="line"><a name="l00047"></a><span class="lineno"> 47</span> <span class="comment">// https://www.spinics.net/lists/gcchelp/msg47749.html</span></div><div class="line"><a name="l00048"></a><span class="lineno"> 48</span> <span class="preprocessor">#if (CRYPTOPP_GCC_VERSION >= 40900)</span></div><div class="line"><a name="l00049"></a><span class="lineno"> 49</span> <span class="preprocessor"># define GCC_NO_UBSAN __attribute__ ((no_sanitize_undefined))</span></div><div class="line"><a name="l00050"></a><span class="lineno"> 50</span> <span class="preprocessor">#else</span></div><div class="line"><a name="l00051"></a><span class="lineno"> 51</span> <span class="preprocessor"># define GCC_NO_UBSAN</span></div><div class="line"><a name="l00052"></a><span class="lineno"> 52</span> <span class="preprocessor">#endif</span></div><div class="line"><a name="l00053"></a><span class="lineno"> 53</span> </div><div class="line"><a name="l00054"></a><span class="lineno"> 54</span> ANONYMOUS_NAMESPACE_BEGIN</div><div class="line"><a name="l00055"></a><span class="lineno"> 55</span> </div><div class="line"><a name="l00056"></a><span class="lineno"> 56</span> <span class="keyword">using</span> CryptoPP::byte;</div><div class="line"><a name="l00057"></a><span class="lineno"> 57</span> <span class="keyword">using</span> CryptoPP::word32;</div><div class="line"><a name="l00058"></a><span class="lineno"> 58</span> <span class="keyword">using</span> CryptoPP::word64;</div><div class="line"><a name="l00059"></a><span class="lineno"> 59</span> <span class="keyword">using</span> <a class="code" href="misc_8h.html#aaf7b80a08d25ab9d62693c9e4798ef98">CryptoPP::rotlFixed</a>;</div><div class="line"><a name="l00060"></a><span class="lineno"> 60</span> <span class="keyword">using</span> <a class="code" href="misc_8h.html#abf88e95400925b89c94641916535b6da">CryptoPP::rotrFixed</a>;</div><div class="line"><a name="l00061"></a><span class="lineno"> 61</span> <span class="keyword">using</span> <a class="code" href="misc_8h.html#a810542d642def73fd278c08092417e11">CryptoPP::vec_swap</a>; <span class="comment">// SunCC</span></div><div class="line"><a name="l00062"></a><span class="lineno"> 62</span> </div><div class="line"><a name="l00063"></a><span class="lineno"> 63</span> <span class="comment">// *************************** ARM NEON ************************** //</span></div><div class="line"><a name="l00064"></a><span class="lineno"> 64</span> </div><div class="line"><a name="l00065"></a><span class="lineno"> 65</span> <span class="preprocessor">#if (CRYPTOPP_ARM_NEON_AVAILABLE)</span></div><div class="line"><a name="l00066"></a><span class="lineno"> 66</span> </div><div class="line"><a name="l00067"></a><span class="lineno"> 67</span> <span class="keyword">template</span> <<span class="keyword">class</span> T></div><div class="line"><a name="l00068"></a><span class="lineno"> 68</span> <span class="keyword">inline</span> T UnpackHigh32(<span class="keyword">const</span> T& a, <span class="keyword">const</span> T& b)</div><div class="line"><a name="l00069"></a><span class="lineno"> 69</span> {</div><div class="line"><a name="l00070"></a><span class="lineno"> 70</span>  <span class="keyword">const</span> uint32x2_t x(vget_high_u32((uint32x4_t)a));</div><div class="line"><a name="l00071"></a><span class="lineno"> 71</span>  <span class="keyword">const</span> uint32x2_t y(vget_high_u32((uint32x4_t)b));</div><div class="line"><a name="l00072"></a><span class="lineno"> 72</span>  <span class="keyword">const</span> uint32x2x2_t r = vzip_u32(x, y);</div><div class="line"><a name="l00073"></a><span class="lineno"> 73</span>  <span class="keywordflow">return</span> (T)vcombine_u32(r.val[0], r.val[1]);</div><div class="line"><a name="l00074"></a><span class="lineno"> 74</span> }</div><div class="line"><a name="l00075"></a><span class="lineno"> 75</span> </div><div class="line"><a name="l00076"></a><span class="lineno"> 76</span> <span class="keyword">template</span> <<span class="keyword">class</span> T></div><div class="line"><a name="l00077"></a><span class="lineno"> 77</span> <span class="keyword">inline</span> T UnpackLow32(<span class="keyword">const</span> T& a, <span class="keyword">const</span> T& b)</div><div class="line"><a name="l00078"></a><span class="lineno"> 78</span> {</div><div class="line"><a name="l00079"></a><span class="lineno"> 79</span>  <span class="keyword">const</span> uint32x2_t x(vget_low_u32((uint32x4_t)a));</div><div class="line"><a name="l00080"></a><span class="lineno"> 80</span>  <span class="keyword">const</span> uint32x2_t y(vget_low_u32((uint32x4_t)b));</div><div class="line"><a name="l00081"></a><span class="lineno"> 81</span>  <span class="keyword">const</span> uint32x2x2_t r = vzip_u32(x, y);</div><div class="line"><a name="l00082"></a><span class="lineno"> 82</span>  <span class="keywordflow">return</span> (T)vcombine_u32(r.val[0], r.val[1]);</div><div class="line"><a name="l00083"></a><span class="lineno"> 83</span> }</div><div class="line"><a name="l00084"></a><span class="lineno"> 84</span> </div><div class="line"><a name="l00085"></a><span class="lineno"> 85</span> <span class="keyword">template</span> <<span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> R></div><div class="line"><a name="l00086"></a><span class="lineno"> 86</span> <span class="keyword">inline</span> uint32x4_t RotateLeft32(<span class="keyword">const</span> uint32x4_t& val)</div><div class="line"><a name="l00087"></a><span class="lineno"> 87</span> {</div><div class="line"><a name="l00088"></a><span class="lineno"> 88</span>  <span class="keyword">const</span> uint32x4_t a(vshlq_n_u32(val, R));</div><div class="line"><a name="l00089"></a><span class="lineno"> 89</span>  <span class="keyword">const</span> uint32x4_t b(vshrq_n_u32(val, 32 - R));</div><div class="line"><a name="l00090"></a><span class="lineno"> 90</span>  <span class="keywordflow">return</span> vorrq_u32(a, b);</div><div class="line"><a name="l00091"></a><span class="lineno"> 91</span> }</div><div class="line"><a name="l00092"></a><span class="lineno"> 92</span> </div><div class="line"><a name="l00093"></a><span class="lineno"> 93</span> <span class="keyword">template</span> <<span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> R></div><div class="line"><a name="l00094"></a><span class="lineno"> 94</span> <span class="keyword">inline</span> uint32x4_t RotateRight32(<span class="keyword">const</span> uint32x4_t& val)</div><div class="line"><a name="l00095"></a><span class="lineno"> 95</span> {</div><div class="line"><a name="l00096"></a><span class="lineno"> 96</span>  <span class="keyword">const</span> uint32x4_t a(vshlq_n_u32(val, 32 - R));</div><div class="line"><a name="l00097"></a><span class="lineno"> 97</span>  <span class="keyword">const</span> uint32x4_t b(vshrq_n_u32(val, R));</div><div class="line"><a name="l00098"></a><span class="lineno"> 98</span>  <span class="keywordflow">return</span> vorrq_u32(a, b);</div><div class="line"><a name="l00099"></a><span class="lineno"> 99</span> }</div><div class="line"><a name="l00100"></a><span class="lineno"> 100</span> </div><div class="line"><a name="l00101"></a><span class="lineno"> 101</span> <span class="preprocessor">#if defined(__aarch32__) || defined(__aarch64__)</span></div><div class="line"><a name="l00102"></a><span class="lineno"> 102</span> <span class="comment">// Faster than two Shifts and an Or. Thanks to Louis Wingers and Bryan Weeks.</span></div><div class="line"><a name="l00103"></a><span class="lineno"> 103</span> <span class="keyword">template</span> <></div><div class="line"><a name="l00104"></a><span class="lineno"> 104</span> <span class="keyword">inline</span> uint32x4_t RotateLeft32<8>(<span class="keyword">const</span> uint32x4_t& val)</div><div class="line"><a name="l00105"></a><span class="lineno"> 105</span> {</div><div class="line"><a name="l00106"></a><span class="lineno"> 106</span> <span class="preprocessor">#if defined(CRYPTOPP_BIG_ENDIAN)</span></div><div class="line"><a name="l00107"></a><span class="lineno"> 107</span>  <span class="keyword">const</span> uint8_t maskb[16] = { 14,13,12,15, 10,9,8,11, 6,5,4,7, 2,1,0,3 };</div><div class="line"><a name="l00108"></a><span class="lineno"> 108</span>  <span class="keyword">const</span> uint8x16_t mask = vld1q_u8(maskb);</div><div class="line"><a name="l00109"></a><span class="lineno"> 109</span> <span class="preprocessor">#else</span></div><div class="line"><a name="l00110"></a><span class="lineno"> 110</span>  <span class="keyword">const</span> uint8_t maskb[16] = { 3,0,1,2, 7,4,5,6, 11,8,9,10, 15,12,13,14 };</div><div class="line"><a name="l00111"></a><span class="lineno"> 111</span>  <span class="keyword">const</span> uint8x16_t mask = vld1q_u8(maskb);</div><div class="line"><a name="l00112"></a><span class="lineno"> 112</span> <span class="preprocessor">#endif</span></div><div class="line"><a name="l00113"></a><span class="lineno"> 113</span> </div><div class="line"><a name="l00114"></a><span class="lineno"> 114</span>  <span class="keywordflow">return</span> vreinterpretq_u32_u8(</div><div class="line"><a name="l00115"></a><span class="lineno"> 115</span>  vqtbl1q_u8(vreinterpretq_u8_u32(val), mask));</div><div class="line"><a name="l00116"></a><span class="lineno"> 116</span> }</div><div class="line"><a name="l00117"></a><span class="lineno"> 117</span> </div><div class="line"><a name="l00118"></a><span class="lineno"> 118</span> <span class="comment">// Faster than two Shifts and an Or. Thanks to Louis Wingers and Bryan Weeks.</span></div><div class="line"><a name="l00119"></a><span class="lineno"> 119</span> <span class="keyword">template</span> <></div><div class="line"><a name="l00120"></a><span class="lineno"> 120</span> <span class="keyword">inline</span> uint32x4_t RotateRight32<8>(<span class="keyword">const</span> uint32x4_t& val)</div><div class="line"><a name="l00121"></a><span class="lineno"> 121</span> {</div><div class="line"><a name="l00122"></a><span class="lineno"> 122</span> <span class="preprocessor">#if defined(CRYPTOPP_BIG_ENDIAN)</span></div><div class="line"><a name="l00123"></a><span class="lineno"> 123</span>  <span class="keyword">const</span> uint8_t maskb[16] = { 12,15,14,13, 8,11,10,9, 4,7,6,5, 0,3,2,1 };</div><div class="line"><a name="l00124"></a><span class="lineno"> 124</span>  <span class="keyword">const</span> uint8x16_t mask = vld1q_u8(maskb);</div><div class="line"><a name="l00125"></a><span class="lineno"> 125</span> <span class="preprocessor">#else</span></div><div class="line"><a name="l00126"></a><span class="lineno"> 126</span>  <span class="keyword">const</span> uint8_t maskb[16] = { 1,2,3,0, 5,6,7,4, 9,10,11,8, 13,14,14,12 };</div><div class="line"><a name="l00127"></a><span class="lineno"> 127</span>  <span class="keyword">const</span> uint8x16_t mask = vld1q_u8(maskb);</div><div class="line"><a name="l00128"></a><span class="lineno"> 128</span> <span class="preprocessor">#endif</span></div><div class="line"><a name="l00129"></a><span class="lineno"> 129</span> </div><div class="line"><a name="l00130"></a><span class="lineno"> 130</span>  <span class="keywordflow">return</span> vreinterpretq_u32_u8(</div><div class="line"><a name="l00131"></a><span class="lineno"> 131</span>  vqtbl1q_u8(vreinterpretq_u8_u32(val), mask));</div><div class="line"><a name="l00132"></a><span class="lineno"> 132</span> }</div><div class="line"><a name="l00133"></a><span class="lineno"> 133</span> <span class="preprocessor">#endif</span></div><div class="line"><a name="l00134"></a><span class="lineno"> 134</span> </div><div class="line"><a name="l00135"></a><span class="lineno"> 135</span> <span class="keyword">inline</span> uint32x4_t SIMON64_f(<span class="keyword">const</span> uint32x4_t& val)</div><div class="line"><a name="l00136"></a><span class="lineno"> 136</span> {</div><div class="line"><a name="l00137"></a><span class="lineno"> 137</span>  <span class="keywordflow">return</span> veorq_u32(RotateLeft32<2>(val),</div><div class="line"><a name="l00138"></a><span class="lineno"> 138</span>  vandq_u32(RotateLeft32<1>(val), RotateLeft32<8>(val)));</div><div class="line"><a name="l00139"></a><span class="lineno"> 139</span> }</div><div class="line"><a name="l00140"></a><span class="lineno"> 140</span> </div><div class="line"><a name="l00141"></a><span class="lineno"> 141</span> <span class="keyword">inline</span> <span class="keywordtype">void</span> SIMON64_Enc_Block(uint32x4_t &block1, uint32x4_t &block0,</div><div class="line"><a name="l00142"></a><span class="lineno"> 142</span>  <span class="keyword">const</span> word32 *subkeys, <span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> rounds)</div><div class="line"><a name="l00143"></a><span class="lineno"> 143</span> {</div><div class="line"><a name="l00144"></a><span class="lineno"> 144</span>  <span class="comment">// Rearrange the data for vectorization. The incoming data was read into</span></div><div class="line"><a name="l00145"></a><span class="lineno"> 145</span>  <span class="comment">// a little-endian word array. Depending on the number of blocks it needs to</span></div><div class="line"><a name="l00146"></a><span class="lineno"> 146</span>  <span class="comment">// be permuted to the following. If only a single block is available then</span></div><div class="line"><a name="l00147"></a><span class="lineno"> 147</span>  <span class="comment">// a Zero block is provided to promote vectorizations.</span></div><div class="line"><a name="l00148"></a><span class="lineno"> 148</span>  <span class="comment">// [A1 A2 A3 A4][B1 B2 B3 B4] ... => [A1 A3 B1 B3][A2 A4 B2 B4] ...</span></div><div class="line"><a name="l00149"></a><span class="lineno"> 149</span>  uint32x4_t x1 = vuzpq_u32(block0, block1).val[1];</div><div class="line"><a name="l00150"></a><span class="lineno"> 150</span>  uint32x4_t y1 = vuzpq_u32(block0, block1).val[0];</div><div class="line"><a name="l00151"></a><span class="lineno"> 151</span> </div><div class="line"><a name="l00152"></a><span class="lineno"> 152</span>  <span class="keywordflow">for</span> (<span class="keywordtype">int</span> i = 0; i < static_cast<int>(rounds & ~1)-1; i += 2)</div><div class="line"><a name="l00153"></a><span class="lineno"> 153</span>  {</div><div class="line"><a name="l00154"></a><span class="lineno"> 154</span>  <span class="keyword">const</span> uint32x4_t rk1 = vld1q_dup_u32(subkeys+i);</div><div class="line"><a name="l00155"></a><span class="lineno"> 155</span>  y1 = veorq_u32(veorq_u32(y1, SIMON64_f(x1)), rk1);</div><div class="line"><a name="l00156"></a><span class="lineno"> 156</span> </div><div class="line"><a name="l00157"></a><span class="lineno"> 157</span>  <span class="keyword">const</span> uint32x4_t rk2 = vld1q_dup_u32(subkeys+i+1);</div><div class="line"><a name="l00158"></a><span class="lineno"> 158</span>  x1 = veorq_u32(veorq_u32(x1, SIMON64_f(y1)), rk2);</div><div class="line"><a name="l00159"></a><span class="lineno"> 159</span>  }</div><div class="line"><a name="l00160"></a><span class="lineno"> 160</span> </div><div class="line"><a name="l00161"></a><span class="lineno"> 161</span>  <span class="keywordflow">if</span> (rounds & 1)</div><div class="line"><a name="l00162"></a><span class="lineno"> 162</span>  {</div><div class="line"><a name="l00163"></a><span class="lineno"> 163</span>  <span class="keyword">const</span> uint32x4_t rk = vld1q_dup_u32(subkeys+rounds-1);</div><div class="line"><a name="l00164"></a><span class="lineno"> 164</span> </div><div class="line"><a name="l00165"></a><span class="lineno"> 165</span>  y1 = veorq_u32(veorq_u32(y1, SIMON64_f(x1)), rk);</div><div class="line"><a name="l00166"></a><span class="lineno"> 166</span>  std::swap(x1, y1);</div><div class="line"><a name="l00167"></a><span class="lineno"> 167</span>  }</div><div class="line"><a name="l00168"></a><span class="lineno"> 168</span> </div><div class="line"><a name="l00169"></a><span class="lineno"> 169</span>  <span class="comment">// [A1 A3 B1 B3][A2 A4 B2 B4] => [A1 A2 A3 A4][B1 B2 B3 B4]</span></div><div class="line"><a name="l00170"></a><span class="lineno"> 170</span>  block0 = UnpackLow32(y1, x1);</div><div class="line"><a name="l00171"></a><span class="lineno"> 171</span>  block1 = UnpackHigh32(y1, x1);</div><div class="line"><a name="l00172"></a><span class="lineno"> 172</span> }</div><div class="line"><a name="l00173"></a><span class="lineno"> 173</span> </div><div class="line"><a name="l00174"></a><span class="lineno"> 174</span> <span class="keyword">inline</span> <span class="keywordtype">void</span> SIMON64_Dec_Block(uint32x4_t &block0, uint32x4_t &block1,</div><div class="line"><a name="l00175"></a><span class="lineno"> 175</span>  <span class="keyword">const</span> word32 *subkeys, <span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> rounds)</div><div class="line"><a name="l00176"></a><span class="lineno"> 176</span> {</div><div class="line"><a name="l00177"></a><span class="lineno"> 177</span>  <span class="comment">// Rearrange the data for vectorization. The incoming data was read into</span></div><div class="line"><a name="l00178"></a><span class="lineno"> 178</span>  <span class="comment">// a little-endian word array. Depending on the number of blocks it needs to</span></div><div class="line"><a name="l00179"></a><span class="lineno"> 179</span>  <span class="comment">// be permuted to the following. If only a single block is available then</span></div><div class="line"><a name="l00180"></a><span class="lineno"> 180</span>  <span class="comment">// a Zero block is provided to promote vectorizations.</span></div><div class="line"><a name="l00181"></a><span class="lineno"> 181</span>  <span class="comment">// [A1 A2 A3 A4][B1 B2 B3 B4] ... => [A1 A3 B1 B3][A2 A4 B2 B4] ...</span></div><div class="line"><a name="l00182"></a><span class="lineno"> 182</span>  uint32x4_t x1 = vuzpq_u32(block0, block1).val[1];</div><div class="line"><a name="l00183"></a><span class="lineno"> 183</span>  uint32x4_t y1 = vuzpq_u32(block0, block1).val[0];</div><div class="line"><a name="l00184"></a><span class="lineno"> 184</span> </div><div class="line"><a name="l00185"></a><span class="lineno"> 185</span>  <span class="keywordflow">if</span> (rounds & 1)</div><div class="line"><a name="l00186"></a><span class="lineno"> 186</span>  {</div><div class="line"><a name="l00187"></a><span class="lineno"> 187</span>  std::swap(x1, y1);</div><div class="line"><a name="l00188"></a><span class="lineno"> 188</span>  <span class="keyword">const</span> uint32x4_t rk = vld1q_dup_u32(subkeys + rounds - 1);</div><div class="line"><a name="l00189"></a><span class="lineno"> 189</span> </div><div class="line"><a name="l00190"></a><span class="lineno"> 190</span>  y1 = veorq_u32(veorq_u32(y1, rk), SIMON64_f(x1));</div><div class="line"><a name="l00191"></a><span class="lineno"> 191</span>  rounds--;</div><div class="line"><a name="l00192"></a><span class="lineno"> 192</span>  }</div><div class="line"><a name="l00193"></a><span class="lineno"> 193</span> </div><div class="line"><a name="l00194"></a><span class="lineno"> 194</span>  <span class="keywordflow">for</span> (<span class="keywordtype">int</span> i = static_cast<int>(rounds-2); i >= 0; i -= 2)</div><div class="line"><a name="l00195"></a><span class="lineno"> 195</span>  {</div><div class="line"><a name="l00196"></a><span class="lineno"> 196</span>  <span class="keyword">const</span> uint32x4_t rk1 = vld1q_dup_u32(subkeys+i+1);</div><div class="line"><a name="l00197"></a><span class="lineno"> 197</span>  x1 = veorq_u32(veorq_u32(x1, SIMON64_f(y1)), rk1);</div><div class="line"><a name="l00198"></a><span class="lineno"> 198</span> </div><div class="line"><a name="l00199"></a><span class="lineno"> 199</span>  <span class="keyword">const</span> uint32x4_t rk2 = vld1q_dup_u32(subkeys+i);</div><div class="line"><a name="l00200"></a><span class="lineno"> 200</span>  y1 = veorq_u32(veorq_u32(y1, SIMON64_f(x1)), rk2);</div><div class="line"><a name="l00201"></a><span class="lineno"> 201</span>  }</div><div class="line"><a name="l00202"></a><span class="lineno"> 202</span> </div><div class="line"><a name="l00203"></a><span class="lineno"> 203</span>  <span class="comment">// [A1 A3 B1 B3][A2 A4 B2 B4] => [A1 A2 A3 A4][B1 B2 B3 B4]</span></div><div class="line"><a name="l00204"></a><span class="lineno"> 204</span>  block0 = UnpackLow32(y1, x1);</div><div class="line"><a name="l00205"></a><span class="lineno"> 205</span>  block1 = UnpackHigh32(y1, x1);</div><div class="line"><a name="l00206"></a><span class="lineno"> 206</span> }</div><div class="line"><a name="l00207"></a><span class="lineno"> 207</span> </div><div class="line"><a name="l00208"></a><span class="lineno"> 208</span> <span class="keyword">inline</span> <span class="keywordtype">void</span> SIMON64_Enc_6_Blocks(uint32x4_t &block0, uint32x4_t &block1,</div><div class="line"><a name="l00209"></a><span class="lineno"> 209</span>  uint32x4_t &block2, uint32x4_t &block3, uint32x4_t &block4, uint32x4_t &block5,</div><div class="line"><a name="l00210"></a><span class="lineno"> 210</span>  <span class="keyword">const</span> word32 *subkeys, <span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> rounds)</div><div class="line"><a name="l00211"></a><span class="lineno"> 211</span> {</div><div class="line"><a name="l00212"></a><span class="lineno"> 212</span>  <span class="comment">// Rearrange the data for vectorization. The incoming data was read into</span></div><div class="line"><a name="l00213"></a><span class="lineno"> 213</span>  <span class="comment">// a little-endian word array. Depending on the number of blocks it needs to</span></div><div class="line"><a name="l00214"></a><span class="lineno"> 214</span>  <span class="comment">// be permuted to the following. If only a single block is available then</span></div><div class="line"><a name="l00215"></a><span class="lineno"> 215</span>  <span class="comment">// a Zero block is provided to promote vectorizations.</span></div><div class="line"><a name="l00216"></a><span class="lineno"> 216</span>  <span class="comment">// [A1 A2 A3 A4][B1 B2 B3 B4] ... => [A1 A3 B1 B3][A2 A4 B2 B4] ...</span></div><div class="line"><a name="l00217"></a><span class="lineno"> 217</span>  uint32x4_t x1 = vuzpq_u32(block0, block1).val[1];</div><div class="line"><a name="l00218"></a><span class="lineno"> 218</span>  uint32x4_t y1 = vuzpq_u32(block0, block1).val[0];</div><div class="line"><a name="l00219"></a><span class="lineno"> 219</span>  uint32x4_t x2 = vuzpq_u32(block2, block3).val[1];</div><div class="line"><a name="l00220"></a><span class="lineno"> 220</span>  uint32x4_t y2 = vuzpq_u32(block2, block3).val[0];</div><div class="line"><a name="l00221"></a><span class="lineno"> 221</span>  uint32x4_t x3 = vuzpq_u32(block4, block5).val[1];</div><div class="line"><a name="l00222"></a><span class="lineno"> 222</span>  uint32x4_t y3 = vuzpq_u32(block4, block5).val[0];</div><div class="line"><a name="l00223"></a><span class="lineno"> 223</span> </div><div class="line"><a name="l00224"></a><span class="lineno"> 224</span>  <span class="keywordflow">for</span> (<span class="keywordtype">int</span> i = 0; i < static_cast<int>(rounds & ~1) - 1; i += 2)</div><div class="line"><a name="l00225"></a><span class="lineno"> 225</span>  {</div><div class="line"><a name="l00226"></a><span class="lineno"> 226</span>  <span class="keyword">const</span> uint32x4_t rk1 = vld1q_dup_u32(subkeys+i);</div><div class="line"><a name="l00227"></a><span class="lineno"> 227</span>  y1 = veorq_u32(veorq_u32(y1, SIMON64_f(x1)), rk1);</div><div class="line"><a name="l00228"></a><span class="lineno"> 228</span>  y2 = veorq_u32(veorq_u32(y2, SIMON64_f(x2)), rk1);</div><div class="line"><a name="l00229"></a><span class="lineno"> 229</span>  y3 = veorq_u32(veorq_u32(y3, SIMON64_f(x3)), rk1);</div><div class="line"><a name="l00230"></a><span class="lineno"> 230</span> </div><div class="line"><a name="l00231"></a><span class="lineno"> 231</span>  <span class="keyword">const</span> uint32x4_t rk2 = vld1q_dup_u32(subkeys+i+1);</div><div class="line"><a name="l00232"></a><span class="lineno"> 232</span>  x1 = veorq_u32(veorq_u32(x1, SIMON64_f(y1)), rk2);</div><div class="line"><a name="l00233"></a><span class="lineno"> 233</span>  x2 = veorq_u32(veorq_u32(x2, SIMON64_f(y2)), rk2);</div><div class="line"><a name="l00234"></a><span class="lineno"> 234</span>  x3 = veorq_u32(veorq_u32(x3, SIMON64_f(y3)), rk2);</div><div class="line"><a name="l00235"></a><span class="lineno"> 235</span>  }</div><div class="line"><a name="l00236"></a><span class="lineno"> 236</span> </div><div class="line"><a name="l00237"></a><span class="lineno"> 237</span>  <span class="keywordflow">if</span> (rounds & 1)</div><div class="line"><a name="l00238"></a><span class="lineno"> 238</span>  {</div><div class="line"><a name="l00239"></a><span class="lineno"> 239</span>  <span class="keyword">const</span> uint32x4_t rk = vld1q_dup_u32(subkeys + rounds - 1);</div><div class="line"><a name="l00240"></a><span class="lineno"> 240</span> </div><div class="line"><a name="l00241"></a><span class="lineno"> 241</span>  y1 = veorq_u32(veorq_u32(y1, SIMON64_f(x1)), rk);</div><div class="line"><a name="l00242"></a><span class="lineno"> 242</span>  y2 = veorq_u32(veorq_u32(y2, SIMON64_f(x2)), rk);</div><div class="line"><a name="l00243"></a><span class="lineno"> 243</span>  y3 = veorq_u32(veorq_u32(y3, SIMON64_f(x3)), rk);</div><div class="line"><a name="l00244"></a><span class="lineno"> 244</span>  std::swap(x1, y1); std::swap(x2, y2); std::swap(x3, y3);</div><div class="line"><a name="l00245"></a><span class="lineno"> 245</span>  }</div><div class="line"><a name="l00246"></a><span class="lineno"> 246</span> </div><div class="line"><a name="l00247"></a><span class="lineno"> 247</span>  <span class="comment">// [A1 A3 B1 B3][A2 A4 B2 B4] => [A1 A2 A3 A4][B1 B2 B3 B4]</span></div><div class="line"><a name="l00248"></a><span class="lineno"> 248</span>  block0 = UnpackLow32(y1, x1);</div><div class="line"><a name="l00249"></a><span class="lineno"> 249</span>  block1 = UnpackHigh32(y1, x1);</div><div class="line"><a name="l00250"></a><span class="lineno"> 250</span>  block2 = UnpackLow32(y2, x2);</div><div class="line"><a name="l00251"></a><span class="lineno"> 251</span>  block3 = UnpackHigh32(y2, x2);</div><div class="line"><a name="l00252"></a><span class="lineno"> 252</span>  block4 = UnpackLow32(y3, x3);</div><div class="line"><a name="l00253"></a><span class="lineno"> 253</span>  block5 = UnpackHigh32(y3, x3);</div><div class="line"><a name="l00254"></a><span class="lineno"> 254</span> }</div><div class="line"><a name="l00255"></a><span class="lineno"> 255</span> </div><div class="line"><a name="l00256"></a><span class="lineno"> 256</span> <span class="keyword">inline</span> <span class="keywordtype">void</span> SIMON64_Dec_6_Blocks(uint32x4_t &block0, uint32x4_t &block1,</div><div class="line"><a name="l00257"></a><span class="lineno"> 257</span>  uint32x4_t &block2, uint32x4_t &block3, uint32x4_t &block4, uint32x4_t &block5,</div><div class="line"><a name="l00258"></a><span class="lineno"> 258</span>  <span class="keyword">const</span> word32 *subkeys, <span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> rounds)</div><div class="line"><a name="l00259"></a><span class="lineno"> 259</span> {</div><div class="line"><a name="l00260"></a><span class="lineno"> 260</span>  <span class="comment">// Rearrange the data for vectorization. The incoming data was read into</span></div><div class="line"><a name="l00261"></a><span class="lineno"> 261</span>  <span class="comment">// a little-endian word array. Depending on the number of blocks it needs to</span></div><div class="line"><a name="l00262"></a><span class="lineno"> 262</span>  <span class="comment">// be permuted to the following. If only a single block is available then</span></div><div class="line"><a name="l00263"></a><span class="lineno"> 263</span>  <span class="comment">// a Zero block is provided to promote vectorizations.</span></div><div class="line"><a name="l00264"></a><span class="lineno"> 264</span>  <span class="comment">// [A1 A2 A3 A4][B1 B2 B3 B4] ... => [A1 A3 B1 B3][A2 A4 B2 B4] ...</span></div><div class="line"><a name="l00265"></a><span class="lineno"> 265</span>  uint32x4_t x1 = vuzpq_u32(block0, block1).val[1];</div><div class="line"><a name="l00266"></a><span class="lineno"> 266</span>  uint32x4_t y1 = vuzpq_u32(block0, block1).val[0];</div><div class="line"><a name="l00267"></a><span class="lineno"> 267</span>  uint32x4_t x2 = vuzpq_u32(block2, block3).val[1];</div><div class="line"><a name="l00268"></a><span class="lineno"> 268</span>  uint32x4_t y2 = vuzpq_u32(block2, block3).val[0];</div><div class="line"><a name="l00269"></a><span class="lineno"> 269</span>  uint32x4_t x3 = vuzpq_u32(block4, block5).val[1];</div><div class="line"><a name="l00270"></a><span class="lineno"> 270</span>  uint32x4_t y3 = vuzpq_u32(block4, block5).val[0];</div><div class="line"><a name="l00271"></a><span class="lineno"> 271</span> </div><div class="line"><a name="l00272"></a><span class="lineno"> 272</span>  <span class="keywordflow">if</span> (rounds & 1)</div><div class="line"><a name="l00273"></a><span class="lineno"> 273</span>  {</div><div class="line"><a name="l00274"></a><span class="lineno"> 274</span>  std::swap(x1, y1); std::swap(x2, y2); std::swap(x3, y3);</div><div class="line"><a name="l00275"></a><span class="lineno"> 275</span>  <span class="keyword">const</span> uint32x4_t rk = vld1q_dup_u32(subkeys + rounds - 1);</div><div class="line"><a name="l00276"></a><span class="lineno"> 276</span> </div><div class="line"><a name="l00277"></a><span class="lineno"> 277</span>  y1 = veorq_u32(veorq_u32(y1, rk), SIMON64_f(x1));</div><div class="line"><a name="l00278"></a><span class="lineno"> 278</span>  y2 = veorq_u32(veorq_u32(y2, rk), SIMON64_f(x2));</div><div class="line"><a name="l00279"></a><span class="lineno"> 279</span>  y3 = veorq_u32(veorq_u32(y3, rk), SIMON64_f(x3));</div><div class="line"><a name="l00280"></a><span class="lineno"> 280</span>  rounds--;</div><div class="line"><a name="l00281"></a><span class="lineno"> 281</span>  }</div><div class="line"><a name="l00282"></a><span class="lineno"> 282</span> </div><div class="line"><a name="l00283"></a><span class="lineno"> 283</span>  <span class="keywordflow">for</span> (<span class="keywordtype">int</span> i = static_cast<int>(rounds-2); i >= 0; i -= 2)</div><div class="line"><a name="l00284"></a><span class="lineno"> 284</span>  {</div><div class="line"><a name="l00285"></a><span class="lineno"> 285</span>  <span class="keyword">const</span> uint32x4_t rk1 = vld1q_dup_u32(subkeys + i + 1);</div><div class="line"><a name="l00286"></a><span class="lineno"> 286</span>  x1 = veorq_u32(veorq_u32(x1, SIMON64_f(y1)), rk1);</div><div class="line"><a name="l00287"></a><span class="lineno"> 287</span>  x2 = veorq_u32(veorq_u32(x2, SIMON64_f(y2)), rk1);</div><div class="line"><a name="l00288"></a><span class="lineno"> 288</span>  x3 = veorq_u32(veorq_u32(x3, SIMON64_f(y3)), rk1);</div><div class="line"><a name="l00289"></a><span class="lineno"> 289</span> </div><div class="line"><a name="l00290"></a><span class="lineno"> 290</span>  <span class="keyword">const</span> uint32x4_t rk2 = vld1q_dup_u32(subkeys + i);</div><div class="line"><a name="l00291"></a><span class="lineno"> 291</span>  y1 = veorq_u32(veorq_u32(y1, SIMON64_f(x1)), rk2);</div><div class="line"><a name="l00292"></a><span class="lineno"> 292</span>  y2 = veorq_u32(veorq_u32(y2, SIMON64_f(x2)), rk2);</div><div class="line"><a name="l00293"></a><span class="lineno"> 293</span>  y3 = veorq_u32(veorq_u32(y3, SIMON64_f(x3)), rk2);</div><div class="line"><a name="l00294"></a><span class="lineno"> 294</span>  }</div><div class="line"><a name="l00295"></a><span class="lineno"> 295</span> </div><div class="line"><a name="l00296"></a><span class="lineno"> 296</span>  <span class="comment">// [A1 A3 B1 B3][A2 A4 B2 B4] => [A1 A2 A3 A4][B1 B2 B3 B4]</span></div><div class="line"><a name="l00297"></a><span class="lineno"> 297</span>  block0 = UnpackLow32(y1, x1);</div><div class="line"><a name="l00298"></a><span class="lineno"> 298</span>  block1 = UnpackHigh32(y1, x1);</div><div class="line"><a name="l00299"></a><span class="lineno"> 299</span>  block2 = UnpackLow32(y2, x2);</div><div class="line"><a name="l00300"></a><span class="lineno"> 300</span>  block3 = UnpackHigh32(y2, x2);</div><div class="line"><a name="l00301"></a><span class="lineno"> 301</span>  block4 = UnpackLow32(y3, x3);</div><div class="line"><a name="l00302"></a><span class="lineno"> 302</span>  block5 = UnpackHigh32(y3, x3);</div><div class="line"><a name="l00303"></a><span class="lineno"> 303</span> }</div><div class="line"><a name="l00304"></a><span class="lineno"> 304</span> </div><div class="line"><a name="l00305"></a><span class="lineno"> 305</span> <span class="preprocessor">#endif // CRYPTOPP_ARM_NEON_AVAILABLE</span></div><div class="line"><a name="l00306"></a><span class="lineno"> 306</span> </div><div class="line"><a name="l00307"></a><span class="lineno"> 307</span> <span class="preprocessor">#if (CRYPTOPP_ARM_NEON_AVAILABLE)</span></div><div class="line"><a name="l00308"></a><span class="lineno"> 308</span> </div><div class="line"><a name="l00309"></a><span class="lineno"> 309</span> <span class="keyword">template</span> <<span class="keyword">class</span> T></div><div class="line"><a name="l00310"></a><span class="lineno"> 310</span> <span class="keyword">inline</span> T UnpackHigh64(<span class="keyword">const</span> T& a, <span class="keyword">const</span> T& b)</div><div class="line"><a name="l00311"></a><span class="lineno"> 311</span> {</div><div class="line"><a name="l00312"></a><span class="lineno"> 312</span>  <span class="keyword">const</span> uint64x1_t x(vget_high_u64((uint64x2_t)a));</div><div class="line"><a name="l00313"></a><span class="lineno"> 313</span>  <span class="keyword">const</span> uint64x1_t y(vget_high_u64((uint64x2_t)b));</div><div class="line"><a name="l00314"></a><span class="lineno"> 314</span>  <span class="keywordflow">return</span> (T)vcombine_u64(x, y);</div><div class="line"><a name="l00315"></a><span class="lineno"> 315</span> }</div><div class="line"><a name="l00316"></a><span class="lineno"> 316</span> </div><div class="line"><a name="l00317"></a><span class="lineno"> 317</span> <span class="keyword">template</span> <<span class="keyword">class</span> T></div><div class="line"><a name="l00318"></a><span class="lineno"> 318</span> <span class="keyword">inline</span> T UnpackLow64(<span class="keyword">const</span> T& a, <span class="keyword">const</span> T& b)</div><div class="line"><a name="l00319"></a><span class="lineno"> 319</span> {</div><div class="line"><a name="l00320"></a><span class="lineno"> 320</span>  <span class="keyword">const</span> uint64x1_t x(vget_low_u64((uint64x2_t)a));</div><div class="line"><a name="l00321"></a><span class="lineno"> 321</span>  <span class="keyword">const</span> uint64x1_t y(vget_low_u64((uint64x2_t)b));</div><div class="line"><a name="l00322"></a><span class="lineno"> 322</span>  <span class="keywordflow">return</span> (T)vcombine_u64(x, y);</div><div class="line"><a name="l00323"></a><span class="lineno"> 323</span> }</div><div class="line"><a name="l00324"></a><span class="lineno"> 324</span> </div><div class="line"><a name="l00325"></a><span class="lineno"> 325</span> <span class="keyword">template</span> <<span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> R></div><div class="line"><a name="l00326"></a><span class="lineno"> 326</span> <span class="keyword">inline</span> uint64x2_t RotateLeft64(<span class="keyword">const</span> uint64x2_t& val)</div><div class="line"><a name="l00327"></a><span class="lineno"> 327</span> {</div><div class="line"><a name="l00328"></a><span class="lineno"> 328</span>  <span class="keyword">const</span> uint64x2_t a(vshlq_n_u64(val, R));</div><div class="line"><a name="l00329"></a><span class="lineno"> 329</span>  <span class="keyword">const</span> uint64x2_t b(vshrq_n_u64(val, 64 - R));</div><div class="line"><a name="l00330"></a><span class="lineno"> 330</span>  <span class="keywordflow">return</span> vorrq_u64(a, b);</div><div class="line"><a name="l00331"></a><span class="lineno"> 331</span> }</div><div class="line"><a name="l00332"></a><span class="lineno"> 332</span> </div><div class="line"><a name="l00333"></a><span class="lineno"> 333</span> <span class="keyword">template</span> <<span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> R></div><div class="line"><a name="l00334"></a><span class="lineno"> 334</span> <span class="keyword">inline</span> uint64x2_t RotateRight64(<span class="keyword">const</span> uint64x2_t& val)</div><div class="line"><a name="l00335"></a><span class="lineno"> 335</span> {</div><div class="line"><a name="l00336"></a><span class="lineno"> 336</span>  <span class="keyword">const</span> uint64x2_t a(vshlq_n_u64(val, 64 - R));</div><div class="line"><a name="l00337"></a><span class="lineno"> 337</span>  <span class="keyword">const</span> uint64x2_t b(vshrq_n_u64(val, R));</div><div class="line"><a name="l00338"></a><span class="lineno"> 338</span>  <span class="keywordflow">return</span> vorrq_u64(a, b);</div><div class="line"><a name="l00339"></a><span class="lineno"> 339</span> }</div><div class="line"><a name="l00340"></a><span class="lineno"> 340</span> </div><div class="line"><a name="l00341"></a><span class="lineno"> 341</span> <span class="preprocessor">#if defined(__aarch32__) || defined(__aarch64__)</span></div><div class="line"><a name="l00342"></a><span class="lineno"> 342</span> <span class="comment">// Faster than two Shifts and an Or. Thanks to Louis Wingers and Bryan Weeks.</span></div><div class="line"><a name="l00343"></a><span class="lineno"> 343</span> <span class="keyword">template</span> <></div><div class="line"><a name="l00344"></a><span class="lineno"> 344</span> <span class="keyword">inline</span> uint64x2_t RotateLeft64<8>(<span class="keyword">const</span> uint64x2_t& val)</div><div class="line"><a name="l00345"></a><span class="lineno"> 345</span> {</div><div class="line"><a name="l00346"></a><span class="lineno"> 346</span> <span class="preprocessor">#if defined(CRYPTOPP_BIG_ENDIAN)</span></div><div class="line"><a name="l00347"></a><span class="lineno"> 347</span>  <span class="keyword">const</span> uint8_t maskb[16] = { 14,13,12,11, 10,9,8,15, 6,5,4,3, 2,1,0,7 };</div><div class="line"><a name="l00348"></a><span class="lineno"> 348</span>  <span class="keyword">const</span> uint8x16_t mask = vld1q_u8(maskb);</div><div class="line"><a name="l00349"></a><span class="lineno"> 349</span> <span class="preprocessor">#else</span></div><div class="line"><a name="l00350"></a><span class="lineno"> 350</span>  <span class="keyword">const</span> uint8_t maskb[16] = { 7,0,1,2, 3,4,5,6, 15,8,9,10, 11,12,13,14 };</div><div class="line"><a name="l00351"></a><span class="lineno"> 351</span>  <span class="keyword">const</span> uint8x16_t mask = vld1q_u8(maskb);</div><div class="line"><a name="l00352"></a><span class="lineno"> 352</span> <span class="preprocessor">#endif</span></div><div class="line"><a name="l00353"></a><span class="lineno"> 353</span> </div><div class="line"><a name="l00354"></a><span class="lineno"> 354</span>  <span class="keywordflow">return</span> vreinterpretq_u64_u8(</div><div class="line"><a name="l00355"></a><span class="lineno"> 355</span>  vqtbl1q_u8(vreinterpretq_u8_u64(val), mask));</div><div class="line"><a name="l00356"></a><span class="lineno"> 356</span> }</div><div class="line"><a name="l00357"></a><span class="lineno"> 357</span> </div><div class="line"><a name="l00358"></a><span class="lineno"> 358</span> <span class="comment">// Faster than two Shifts and an Or. Thanks to Louis Wingers and Bryan Weeks.</span></div><div class="line"><a name="l00359"></a><span class="lineno"> 359</span> <span class="keyword">template</span> <></div><div class="line"><a name="l00360"></a><span class="lineno"> 360</span> <span class="keyword">inline</span> uint64x2_t RotateRight64<8>(<span class="keyword">const</span> uint64x2_t& val)</div><div class="line"><a name="l00361"></a><span class="lineno"> 361</span> {</div><div class="line"><a name="l00362"></a><span class="lineno"> 362</span> <span class="preprocessor">#if defined(CRYPTOPP_BIG_ENDIAN)</span></div><div class="line"><a name="l00363"></a><span class="lineno"> 363</span>  <span class="keyword">const</span> uint8_t maskb[16] = { 8,15,14,13, 12,11,10,9, 0,7,6,5, 4,3,2,1 };</div><div class="line"><a name="l00364"></a><span class="lineno"> 364</span>  <span class="keyword">const</span> uint8x16_t mask = vld1q_u8(maskb);</div><div class="line"><a name="l00365"></a><span class="lineno"> 365</span> <span class="preprocessor">#else</span></div><div class="line"><a name="l00366"></a><span class="lineno"> 366</span>  <span class="keyword">const</span> uint8_t maskb[16] = { 1,2,3,4, 5,6,7,0, 9,10,11,12, 13,14,15,8 };</div><div class="line"><a name="l00367"></a><span class="lineno"> 367</span>  <span class="keyword">const</span> uint8x16_t mask = vld1q_u8(maskb);</div><div class="line"><a name="l00368"></a><span class="lineno"> 368</span> <span class="preprocessor">#endif</span></div><div class="line"><a name="l00369"></a><span class="lineno"> 369</span> </div><div class="line"><a name="l00370"></a><span class="lineno"> 370</span>  <span class="keywordflow">return</span> vreinterpretq_u64_u8(</div><div class="line"><a name="l00371"></a><span class="lineno"> 371</span>  vqtbl1q_u8(vreinterpretq_u8_u64(val), mask));</div><div class="line"><a name="l00372"></a><span class="lineno"> 372</span> }</div><div class="line"><a name="l00373"></a><span class="lineno"> 373</span> <span class="preprocessor">#endif</span></div><div class="line"><a name="l00374"></a><span class="lineno"> 374</span> </div><div class="line"><a name="l00375"></a><span class="lineno"> 375</span> <span class="keyword">inline</span> uint64x2_t SIMON128_f(<span class="keyword">const</span> uint64x2_t& val)</div><div class="line"><a name="l00376"></a><span class="lineno"> 376</span> {</div><div class="line"><a name="l00377"></a><span class="lineno"> 377</span>  <span class="keywordflow">return</span> veorq_u64(RotateLeft64<2>(val),</div><div class="line"><a name="l00378"></a><span class="lineno"> 378</span>  vandq_u64(RotateLeft64<1>(val), RotateLeft64<8>(val)));</div><div class="line"><a name="l00379"></a><span class="lineno"> 379</span> }</div><div class="line"><a name="l00380"></a><span class="lineno"> 380</span> </div><div class="line"><a name="l00381"></a><span class="lineno"> 381</span> <span class="keyword">inline</span> <span class="keywordtype">void</span> SIMON128_Enc_Block(uint64x2_t &block0, uint64x2_t &block1,</div><div class="line"><a name="l00382"></a><span class="lineno"> 382</span>  <span class="keyword">const</span> word64 *subkeys, <span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> rounds)</div><div class="line"><a name="l00383"></a><span class="lineno"> 383</span> {</div><div class="line"><a name="l00384"></a><span class="lineno"> 384</span>  <span class="comment">// Rearrange the data for vectorization. The incoming data was read into</span></div><div class="line"><a name="l00385"></a><span class="lineno"> 385</span>  <span class="comment">// a little-endian word array. Depending on the number of blocks it needs to</span></div><div class="line"><a name="l00386"></a><span class="lineno"> 386</span>  <span class="comment">// be permuted to the following.</span></div><div class="line"><a name="l00387"></a><span class="lineno"> 387</span>  <span class="comment">// [A1 A2][B1 B2] ... => [A1 B1][A2 B2] ...</span></div><div class="line"><a name="l00388"></a><span class="lineno"> 388</span>  uint64x2_t x1 = UnpackHigh64(block0, block1);</div><div class="line"><a name="l00389"></a><span class="lineno"> 389</span>  uint64x2_t y1 = UnpackLow64(block0, block1);</div><div class="line"><a name="l00390"></a><span class="lineno"> 390</span> </div><div class="line"><a name="l00391"></a><span class="lineno"> 391</span>  <span class="keywordflow">for</span> (<span class="keywordtype">int</span> i = 0; i < static_cast<int>(rounds & ~1)-1; i += 2)</div><div class="line"><a name="l00392"></a><span class="lineno"> 392</span>  {</div><div class="line"><a name="l00393"></a><span class="lineno"> 393</span>  <span class="keyword">const</span> uint64x2_t rk1 = vld1q_dup_u64(subkeys+i);</div><div class="line"><a name="l00394"></a><span class="lineno"> 394</span>  y1 = veorq_u64(veorq_u64(y1, SIMON128_f(x1)), rk1);</div><div class="line"><a name="l00395"></a><span class="lineno"> 395</span> </div><div class="line"><a name="l00396"></a><span class="lineno"> 396</span>  <span class="keyword">const</span> uint64x2_t rk2 = vld1q_dup_u64(subkeys+i+1);</div><div class="line"><a name="l00397"></a><span class="lineno"> 397</span>  x1 = veorq_u64(veorq_u64(x1, SIMON128_f(y1)), rk2);</div><div class="line"><a name="l00398"></a><span class="lineno"> 398</span>  }</div><div class="line"><a name="l00399"></a><span class="lineno"> 399</span> </div><div class="line"><a name="l00400"></a><span class="lineno"> 400</span>  <span class="keywordflow">if</span> (rounds & 1)</div><div class="line"><a name="l00401"></a><span class="lineno"> 401</span>  {</div><div class="line"><a name="l00402"></a><span class="lineno"> 402</span>  <span class="keyword">const</span> uint64x2_t rk = vld1q_dup_u64(subkeys+rounds-1);</div><div class="line"><a name="l00403"></a><span class="lineno"> 403</span> </div><div class="line"><a name="l00404"></a><span class="lineno"> 404</span>  y1 = veorq_u64(veorq_u64(y1, SIMON128_f(x1)), rk);</div><div class="line"><a name="l00405"></a><span class="lineno"> 405</span>  std::swap(x1, y1);</div><div class="line"><a name="l00406"></a><span class="lineno"> 406</span>  }</div><div class="line"><a name="l00407"></a><span class="lineno"> 407</span> </div><div class="line"><a name="l00408"></a><span class="lineno"> 408</span>  <span class="comment">// [A1 B1][A2 B2] ... => [A1 A2][B1 B2] ...</span></div><div class="line"><a name="l00409"></a><span class="lineno"> 409</span>  block0 = UnpackLow64(y1, x1);</div><div class="line"><a name="l00410"></a><span class="lineno"> 410</span>  block1 = UnpackHigh64(y1, x1);</div><div class="line"><a name="l00411"></a><span class="lineno"> 411</span> }</div><div class="line"><a name="l00412"></a><span class="lineno"> 412</span> </div><div class="line"><a name="l00413"></a><span class="lineno"> 413</span> <span class="keyword">inline</span> <span class="keywordtype">void</span> SIMON128_Enc_6_Blocks(uint64x2_t &block0, uint64x2_t &block1,</div><div class="line"><a name="l00414"></a><span class="lineno"> 414</span>  uint64x2_t &block2, uint64x2_t &block3, uint64x2_t &block4, uint64x2_t &block5,</div><div class="line"><a name="l00415"></a><span class="lineno"> 415</span>  <span class="keyword">const</span> word64 *subkeys, <span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> rounds)</div><div class="line"><a name="l00416"></a><span class="lineno"> 416</span> {</div><div class="line"><a name="l00417"></a><span class="lineno"> 417</span>  <span class="comment">// Rearrange the data for vectorization. The incoming data was read into</span></div><div class="line"><a name="l00418"></a><span class="lineno"> 418</span>  <span class="comment">// a little-endian word array. Depending on the number of blocks it needs to</span></div><div class="line"><a name="l00419"></a><span class="lineno"> 419</span>  <span class="comment">// be permuted to the following.</span></div><div class="line"><a name="l00420"></a><span class="lineno"> 420</span>  <span class="comment">// [A1 A2][B1 B2] ... => [A1 B1][A2 B2] ...</span></div><div class="line"><a name="l00421"></a><span class="lineno"> 421</span>  uint64x2_t x1 = UnpackHigh64(block0, block1);</div><div class="line"><a name="l00422"></a><span class="lineno"> 422</span>  uint64x2_t y1 = UnpackLow64(block0, block1);</div><div class="line"><a name="l00423"></a><span class="lineno"> 423</span>  uint64x2_t x2 = UnpackHigh64(block2, block3);</div><div class="line"><a name="l00424"></a><span class="lineno"> 424</span>  uint64x2_t y2 = UnpackLow64(block2, block3);</div><div class="line"><a name="l00425"></a><span class="lineno"> 425</span>  uint64x2_t x3 = UnpackHigh64(block4, block5);</div><div class="line"><a name="l00426"></a><span class="lineno"> 426</span>  uint64x2_t y3 = UnpackLow64(block4, block5);</div><div class="line"><a name="l00427"></a><span class="lineno"> 427</span> </div><div class="line"><a name="l00428"></a><span class="lineno"> 428</span>  <span class="keywordflow">for</span> (<span class="keywordtype">int</span> i = 0; i < static_cast<int>(rounds & ~1) - 1; i += 2)</div><div class="line"><a name="l00429"></a><span class="lineno"> 429</span>  {</div><div class="line"><a name="l00430"></a><span class="lineno"> 430</span>  <span class="keyword">const</span> uint64x2_t rk1 = vld1q_dup_u64(subkeys+i);</div><div class="line"><a name="l00431"></a><span class="lineno"> 431</span>  y1 = veorq_u64(veorq_u64(y1, SIMON128_f(x1)), rk1);</div><div class="line"><a name="l00432"></a><span class="lineno"> 432</span>  y2 = veorq_u64(veorq_u64(y2, SIMON128_f(x2)), rk1);</div><div class="line"><a name="l00433"></a><span class="lineno"> 433</span>  y3 = veorq_u64(veorq_u64(y3, SIMON128_f(x3)), rk1);</div><div class="line"><a name="l00434"></a><span class="lineno"> 434</span> </div><div class="line"><a name="l00435"></a><span class="lineno"> 435</span>  <span class="keyword">const</span> uint64x2_t rk2 = vld1q_dup_u64(subkeys+i+1);</div><div class="line"><a name="l00436"></a><span class="lineno"> 436</span>  x1 = veorq_u64(veorq_u64(x1, SIMON128_f(y1)), rk2);</div><div class="line"><a name="l00437"></a><span class="lineno"> 437</span>  x2 = veorq_u64(veorq_u64(x2, SIMON128_f(y2)), rk2);</div><div class="line"><a name="l00438"></a><span class="lineno"> 438</span>  x3 = veorq_u64(veorq_u64(x3, SIMON128_f(y3)), rk2);</div><div class="line"><a name="l00439"></a><span class="lineno"> 439</span>  }</div><div class="line"><a name="l00440"></a><span class="lineno"> 440</span> </div><div class="line"><a name="l00441"></a><span class="lineno"> 441</span>  <span class="keywordflow">if</span> (rounds & 1)</div><div class="line"><a name="l00442"></a><span class="lineno"> 442</span>  {</div><div class="line"><a name="l00443"></a><span class="lineno"> 443</span>  <span class="keyword">const</span> uint64x2_t rk = vld1q_dup_u64(subkeys + rounds - 1);</div><div class="line"><a name="l00444"></a><span class="lineno"> 444</span> </div><div class="line"><a name="l00445"></a><span class="lineno"> 445</span>  y1 = veorq_u64(veorq_u64(y1, SIMON128_f(x1)), rk);</div><div class="line"><a name="l00446"></a><span class="lineno"> 446</span>  y2 = veorq_u64(veorq_u64(y2, SIMON128_f(x2)), rk);</div><div class="line"><a name="l00447"></a><span class="lineno"> 447</span>  y3 = veorq_u64(veorq_u64(y3, SIMON128_f(x3)), rk);</div><div class="line"><a name="l00448"></a><span class="lineno"> 448</span>  std::swap(x1, y1); std::swap(x2, y2); std::swap(x3, y3);</div><div class="line"><a name="l00449"></a><span class="lineno"> 449</span>  }</div><div class="line"><a name="l00450"></a><span class="lineno"> 450</span> </div><div class="line"><a name="l00451"></a><span class="lineno"> 451</span>  <span class="comment">// [A1 B1][A2 B2] ... => [A1 A2][B1 B2] ...</span></div><div class="line"><a name="l00452"></a><span class="lineno"> 452</span>  block0 = UnpackLow64(y1, x1);</div><div class="line"><a name="l00453"></a><span class="lineno"> 453</span>  block1 = UnpackHigh64(y1, x1);</div><div class="line"><a name="l00454"></a><span class="lineno"> 454</span>  block2 = UnpackLow64(y2, x2);</div><div class="line"><a name="l00455"></a><span class="lineno"> 455</span>  block3 = UnpackHigh64(y2, x2);</div><div class="line"><a name="l00456"></a><span class="lineno"> 456</span>  block4 = UnpackLow64(y3, x3);</div><div class="line"><a name="l00457"></a><span class="lineno"> 457</span>  block5 = UnpackHigh64(y3, x3);</div><div class="line"><a name="l00458"></a><span class="lineno"> 458</span> }</div><div class="line"><a name="l00459"></a><span class="lineno"> 459</span> </div><div class="line"><a name="l00460"></a><span class="lineno"> 460</span> <span class="keyword">inline</span> <span class="keywordtype">void</span> SIMON128_Dec_Block(uint64x2_t &block0, uint64x2_t &block1,</div><div class="line"><a name="l00461"></a><span class="lineno"> 461</span>  <span class="keyword">const</span> word64 *subkeys, <span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> rounds)</div><div class="line"><a name="l00462"></a><span class="lineno"> 462</span> {</div><div class="line"><a name="l00463"></a><span class="lineno"> 463</span>  <span class="comment">// Rearrange the data for vectorization. The incoming data was read into</span></div><div class="line"><a name="l00464"></a><span class="lineno"> 464</span>  <span class="comment">// a little-endian word array. Depending on the number of blocks it needs to</span></div><div class="line"><a name="l00465"></a><span class="lineno"> 465</span>  <span class="comment">// be permuted to the following.</span></div><div class="line"><a name="l00466"></a><span class="lineno"> 466</span>  <span class="comment">// [A1 A2][B1 B2] ... => [A1 B1][A2 B2] ...</span></div><div class="line"><a name="l00467"></a><span class="lineno"> 467</span>  uint64x2_t x1 = UnpackHigh64(block0, block1);</div><div class="line"><a name="l00468"></a><span class="lineno"> 468</span>  uint64x2_t y1 = UnpackLow64(block0, block1);</div><div class="line"><a name="l00469"></a><span class="lineno"> 469</span> </div><div class="line"><a name="l00470"></a><span class="lineno"> 470</span>  <span class="keywordflow">if</span> (rounds & 1)</div><div class="line"><a name="l00471"></a><span class="lineno"> 471</span>  {</div><div class="line"><a name="l00472"></a><span class="lineno"> 472</span>  std::swap(x1, y1);</div><div class="line"><a name="l00473"></a><span class="lineno"> 473</span>  <span class="keyword">const</span> uint64x2_t rk = vld1q_dup_u64(subkeys + rounds - 1);</div><div class="line"><a name="l00474"></a><span class="lineno"> 474</span> </div><div class="line"><a name="l00475"></a><span class="lineno"> 475</span>  y1 = veorq_u64(veorq_u64(y1, rk), SIMON128_f(x1));</div><div class="line"><a name="l00476"></a><span class="lineno"> 476</span>  rounds--;</div><div class="line"><a name="l00477"></a><span class="lineno"> 477</span>  }</div><div class="line"><a name="l00478"></a><span class="lineno"> 478</span> </div><div class="line"><a name="l00479"></a><span class="lineno"> 479</span>  <span class="keywordflow">for</span> (<span class="keywordtype">int</span> i = static_cast<int>(rounds-2); i >= 0; i -= 2)</div><div class="line"><a name="l00480"></a><span class="lineno"> 480</span>  {</div><div class="line"><a name="l00481"></a><span class="lineno"> 481</span>  <span class="keyword">const</span> uint64x2_t rk1 = vld1q_dup_u64(subkeys+i+1);</div><div class="line"><a name="l00482"></a><span class="lineno"> 482</span>  x1 = veorq_u64(veorq_u64(x1, SIMON128_f(y1)), rk1);</div><div class="line"><a name="l00483"></a><span class="lineno"> 483</span> </div><div class="line"><a name="l00484"></a><span class="lineno"> 484</span>  <span class="keyword">const</span> uint64x2_t rk2 = vld1q_dup_u64(subkeys+i);</div><div class="line"><a name="l00485"></a><span class="lineno"> 485</span>  y1 = veorq_u64(veorq_u64(y1, SIMON128_f(x1)), rk2);</div><div class="line"><a name="l00486"></a><span class="lineno"> 486</span>  }</div><div class="line"><a name="l00487"></a><span class="lineno"> 487</span> </div><div class="line"><a name="l00488"></a><span class="lineno"> 488</span>  <span class="comment">// [A1 B1][A2 B2] ... => [A1 A2][B1 B2] ...</span></div><div class="line"><a name="l00489"></a><span class="lineno"> 489</span>  block0 = UnpackLow64(y1, x1);</div><div class="line"><a name="l00490"></a><span class="lineno"> 490</span>  block1 = UnpackHigh64(y1, x1);</div><div class="line"><a name="l00491"></a><span class="lineno"> 491</span> }</div><div class="line"><a name="l00492"></a><span class="lineno"> 492</span> </div><div class="line"><a name="l00493"></a><span class="lineno"> 493</span> <span class="keyword">inline</span> <span class="keywordtype">void</span> SIMON128_Dec_6_Blocks(uint64x2_t &block0, uint64x2_t &block1,</div><div class="line"><a name="l00494"></a><span class="lineno"> 494</span>  uint64x2_t &block2, uint64x2_t &block3, uint64x2_t &block4, uint64x2_t &block5,</div><div class="line"><a name="l00495"></a><span class="lineno"> 495</span>  <span class="keyword">const</span> word64 *subkeys, <span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> rounds)</div><div class="line"><a name="l00496"></a><span class="lineno"> 496</span> {</div><div class="line"><a name="l00497"></a><span class="lineno"> 497</span>  <span class="comment">// Rearrange the data for vectorization. The incoming data was read into</span></div><div class="line"><a name="l00498"></a><span class="lineno"> 498</span>  <span class="comment">// a little-endian word array. Depending on the number of blocks it needs to</span></div><div class="line"><a name="l00499"></a><span class="lineno"> 499</span>  <span class="comment">// be permuted to the following.</span></div><div class="line"><a name="l00500"></a><span class="lineno"> 500</span>  <span class="comment">// [A1 A2][B1 B2] ... => [A1 B1][A2 B2] ...</span></div><div class="line"><a name="l00501"></a><span class="lineno"> 501</span>  uint64x2_t x1 = UnpackHigh64(block0, block1);</div><div class="line"><a name="l00502"></a><span class="lineno"> 502</span>  uint64x2_t y1 = UnpackLow64(block0, block1);</div><div class="line"><a name="l00503"></a><span class="lineno"> 503</span>  uint64x2_t x2 = UnpackHigh64(block2, block3);</div><div class="line"><a name="l00504"></a><span class="lineno"> 504</span>  uint64x2_t y2 = UnpackLow64(block2, block3);</div><div class="line"><a name="l00505"></a><span class="lineno"> 505</span>  uint64x2_t x3 = UnpackHigh64(block4, block5);</div><div class="line"><a name="l00506"></a><span class="lineno"> 506</span>  uint64x2_t y3 = UnpackLow64(block4, block5);</div><div class="line"><a name="l00507"></a><span class="lineno"> 507</span> </div><div class="line"><a name="l00508"></a><span class="lineno"> 508</span>  <span class="keywordflow">if</span> (rounds & 1)</div><div class="line"><a name="l00509"></a><span class="lineno"> 509</span>  {</div><div class="line"><a name="l00510"></a><span class="lineno"> 510</span>  std::swap(x1, y1); std::swap(x2, y2); std::swap(x3, y3);</div><div class="line"><a name="l00511"></a><span class="lineno"> 511</span>  <span class="keyword">const</span> uint64x2_t rk = vld1q_dup_u64(subkeys + rounds - 1);</div><div class="line"><a name="l00512"></a><span class="lineno"> 512</span> </div><div class="line"><a name="l00513"></a><span class="lineno"> 513</span>  y1 = veorq_u64(veorq_u64(y1, rk), SIMON128_f(x1));</div><div class="line"><a name="l00514"></a><span class="lineno"> 514</span>  y2 = veorq_u64(veorq_u64(y2, rk), SIMON128_f(x2));</div><div class="line"><a name="l00515"></a><span class="lineno"> 515</span>  y3 = veorq_u64(veorq_u64(y3, rk), SIMON128_f(x3));</div><div class="line"><a name="l00516"></a><span class="lineno"> 516</span>  rounds--;</div><div class="line"><a name="l00517"></a><span class="lineno"> 517</span>  }</div><div class="line"><a name="l00518"></a><span class="lineno"> 518</span> </div><div class="line"><a name="l00519"></a><span class="lineno"> 519</span>  <span class="keywordflow">for</span> (<span class="keywordtype">int</span> i = static_cast<int>(rounds-2); i >= 0; i -= 2)</div><div class="line"><a name="l00520"></a><span class="lineno"> 520</span>  {</div><div class="line"><a name="l00521"></a><span class="lineno"> 521</span>  <span class="keyword">const</span> uint64x2_t rk1 = vld1q_dup_u64(subkeys + i + 1);</div><div class="line"><a name="l00522"></a><span class="lineno"> 522</span>  x1 = veorq_u64(veorq_u64(x1, SIMON128_f(y1)), rk1);</div><div class="line"><a name="l00523"></a><span class="lineno"> 523</span>  x2 = veorq_u64(veorq_u64(x2, SIMON128_f(y2)), rk1);</div><div class="line"><a name="l00524"></a><span class="lineno"> 524</span>  x3 = veorq_u64(veorq_u64(x3, SIMON128_f(y3)), rk1);</div><div class="line"><a name="l00525"></a><span class="lineno"> 525</span> </div><div class="line"><a name="l00526"></a><span class="lineno"> 526</span>  <span class="keyword">const</span> uint64x2_t rk2 = vld1q_dup_u64(subkeys + i);</div><div class="line"><a name="l00527"></a><span class="lineno"> 527</span>  y1 = veorq_u64(veorq_u64(y1, SIMON128_f(x1)), rk2);</div><div class="line"><a name="l00528"></a><span class="lineno"> 528</span>  y2 = veorq_u64(veorq_u64(y2, SIMON128_f(x2)), rk2);</div><div class="line"><a name="l00529"></a><span class="lineno"> 529</span>  y3 = veorq_u64(veorq_u64(y3, SIMON128_f(x3)), rk2);</div><div class="line"><a name="l00530"></a><span class="lineno"> 530</span>  }</div><div class="line"><a name="l00531"></a><span class="lineno"> 531</span> </div><div class="line"><a name="l00532"></a><span class="lineno"> 532</span>  <span class="comment">// [A1 B1][A2 B2] ... => [A1 A2][B1 B2] ...</span></div><div class="line"><a name="l00533"></a><span class="lineno"> 533</span>  block0 = UnpackLow64(y1, x1);</div><div class="line"><a name="l00534"></a><span class="lineno"> 534</span>  block1 = UnpackHigh64(y1, x1);</div><div class="line"><a name="l00535"></a><span class="lineno"> 535</span>  block2 = UnpackLow64(y2, x2);</div><div class="line"><a name="l00536"></a><span class="lineno"> 536</span>  block3 = UnpackHigh64(y2, x2);</div><div class="line"><a name="l00537"></a><span class="lineno"> 537</span>  block4 = UnpackLow64(y3, x3);</div><div class="line"><a name="l00538"></a><span class="lineno"> 538</span>  block5 = UnpackHigh64(y3, x3);</div><div class="line"><a name="l00539"></a><span class="lineno"> 539</span> }</div><div class="line"><a name="l00540"></a><span class="lineno"> 540</span> </div><div class="line"><a name="l00541"></a><span class="lineno"> 541</span> <span class="preprocessor">#endif // CRYPTOPP_ARM_NEON_AVAILABLE</span></div><div class="line"><a name="l00542"></a><span class="lineno"> 542</span> </div><div class="line"><a name="l00543"></a><span class="lineno"> 543</span> <span class="comment">// ***************************** IA-32 ***************************** //</span></div><div class="line"><a name="l00544"></a><span class="lineno"> 544</span> </div><div class="line"><a name="l00545"></a><span class="lineno"> 545</span> <span class="preprocessor">#if defined(CRYPTOPP_SSSE3_AVAILABLE)</span></div><div class="line"><a name="l00546"></a><span class="lineno"> 546</span> </div><div class="line"><a name="l00547"></a><span class="lineno"> 547</span> <span class="comment">// Clang __m128i casts, http://bugs.llvm.org/show_bug.cgi?id=20670</span></div><div class="line"><a name="l00548"></a><span class="lineno"> 548</span> <span class="preprocessor">#ifndef M128_CAST</span></div><div class="line"><a name="l00549"></a><span class="lineno"> 549</span> <span class="preprocessor"># define M128_CAST(x) ((__m128i *)(void *)(x))</span></div><div class="line"><a name="l00550"></a><span class="lineno"> 550</span> <span class="preprocessor">#endif</span></div><div class="line"><a name="l00551"></a><span class="lineno"> 551</span> <span class="preprocessor">#ifndef CONST_M128_CAST</span></div><div class="line"><a name="l00552"></a><span class="lineno"> 552</span> <span class="preprocessor"># define CONST_M128_CAST(x) ((const __m128i *)(const void *)(x))</span></div><div class="line"><a name="l00553"></a><span class="lineno"> 553</span> <span class="preprocessor">#endif</span></div><div class="line"><a name="l00554"></a><span class="lineno"> 554</span> </div><div class="line"><a name="l00555"></a><span class="lineno"> 555</span> <span class="comment">// GCC double casts, https://www.spinics.net/lists/gcchelp/msg47735.html</span></div><div class="line"><a name="l00556"></a><span class="lineno"> 556</span> <span class="preprocessor">#ifndef DOUBLE_CAST</span></div><div class="line"><a name="l00557"></a><span class="lineno"> 557</span> <span class="preprocessor"># define DOUBLE_CAST(x) ((double *)(void *)(x))</span></div><div class="line"><a name="l00558"></a><span class="lineno"> 558</span> <span class="preprocessor">#endif</span></div><div class="line"><a name="l00559"></a><span class="lineno"> 559</span> <span class="preprocessor">#ifndef CONST_DOUBLE_CAST</span></div><div class="line"><a name="l00560"></a><span class="lineno"> 560</span> <span class="preprocessor"># define CONST_DOUBLE_CAST(x) ((const double *)(const void *)(x))</span></div><div class="line"><a name="l00561"></a><span class="lineno"> 561</span> <span class="preprocessor">#endif</span></div><div class="line"><a name="l00562"></a><span class="lineno"> 562</span> </div><div class="line"><a name="l00563"></a><span class="lineno"> 563</span> <span class="keyword">inline</span> <span class="keywordtype">void</span> Swap128(__m128i& a,__m128i& b)</div><div class="line"><a name="l00564"></a><span class="lineno"> 564</span> {</div><div class="line"><a name="l00565"></a><span class="lineno"> 565</span> <span class="preprocessor">#if defined(__SUNPRO_CC) && (__SUNPRO_CC <= 0x5120)</span></div><div class="line"><a name="l00566"></a><span class="lineno"> 566</span>  <span class="comment">// __m128i is an unsigned long long[2], and support for swapping it was not added until C++11.</span></div><div class="line"><a name="l00567"></a><span class="lineno"> 567</span>  <span class="comment">// SunCC 12.1 - 12.3 fail to consume the swap; while SunCC 12.4 consumes it without -std=c++11.</span></div><div class="line"><a name="l00568"></a><span class="lineno"> 568</span>  <a class="code" href="misc_8h.html#a810542d642def73fd278c08092417e11">vec_swap</a>(a, b);</div><div class="line"><a name="l00569"></a><span class="lineno"> 569</span> <span class="preprocessor">#else</span></div><div class="line"><a name="l00570"></a><span class="lineno"> 570</span>  std::swap(a, b);</div><div class="line"><a name="l00571"></a><span class="lineno"> 571</span> <span class="preprocessor">#endif</span></div><div class="line"><a name="l00572"></a><span class="lineno"> 572</span> }</div><div class="line"><a name="l00573"></a><span class="lineno"> 573</span> </div><div class="line"><a name="l00574"></a><span class="lineno"> 574</span> <span class="preprocessor">#if defined(CRYPTOPP_AVX512_ROTATE)</span></div><div class="line"><a name="l00575"></a><span class="lineno"> 575</span> <span class="keyword">template</span> <<span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> R></div><div class="line"><a name="l00576"></a><span class="lineno"> 576</span> <span class="keyword">inline</span> __m128i RotateLeft64(<span class="keyword">const</span> __m128i& val)</div><div class="line"><a name="l00577"></a><span class="lineno"> 577</span> {</div><div class="line"><a name="l00578"></a><span class="lineno"> 578</span>  <span class="keywordflow">return</span> _mm_rol_epi64(val, R);</div><div class="line"><a name="l00579"></a><span class="lineno"> 579</span> }</div><div class="line"><a name="l00580"></a><span class="lineno"> 580</span> </div><div class="line"><a name="l00581"></a><span class="lineno"> 581</span> <span class="keyword">template</span> <<span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> R></div><div class="line"><a name="l00582"></a><span class="lineno"> 582</span> <span class="keyword">inline</span> __m128i RotateRight64(<span class="keyword">const</span> __m128i& val)</div><div class="line"><a name="l00583"></a><span class="lineno"> 583</span> {</div><div class="line"><a name="l00584"></a><span class="lineno"> 584</span>  <span class="keywordflow">return</span> _mm_ror_epi64(val, R);</div><div class="line"><a name="l00585"></a><span class="lineno"> 585</span> }</div><div class="line"><a name="l00586"></a><span class="lineno"> 586</span> <span class="preprocessor">#else</span></div><div class="line"><a name="l00587"></a><span class="lineno"> 587</span> <span class="keyword">template</span> <<span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> R></div><div class="line"><a name="l00588"></a><span class="lineno"> 588</span> <span class="keyword">inline</span> __m128i RotateLeft64(<span class="keyword">const</span> __m128i& val)</div><div class="line"><a name="l00589"></a><span class="lineno"> 589</span> {</div><div class="line"><a name="l00590"></a><span class="lineno"> 590</span>  <span class="keywordflow">return</span> _mm_or_si128(</div><div class="line"><a name="l00591"></a><span class="lineno"> 591</span>  _mm_slli_epi64(val, R), _mm_srli_epi64(val, 64-R));</div><div class="line"><a name="l00592"></a><span class="lineno"> 592</span> }</div><div class="line"><a name="l00593"></a><span class="lineno"> 593</span> </div><div class="line"><a name="l00594"></a><span class="lineno"> 594</span> <span class="keyword">template</span> <<span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> R></div><div class="line"><a name="l00595"></a><span class="lineno"> 595</span> <span class="keyword">inline</span> __m128i RotateRight64(<span class="keyword">const</span> __m128i& val)</div><div class="line"><a name="l00596"></a><span class="lineno"> 596</span> {</div><div class="line"><a name="l00597"></a><span class="lineno"> 597</span>  <span class="keywordflow">return</span> _mm_or_si128(</div><div class="line"><a name="l00598"></a><span class="lineno"> 598</span>  _mm_slli_epi64(val, 64-R), _mm_srli_epi64(val, R));</div><div class="line"><a name="l00599"></a><span class="lineno"> 599</span> }</div><div class="line"><a name="l00600"></a><span class="lineno"> 600</span> </div><div class="line"><a name="l00601"></a><span class="lineno"> 601</span> <span class="comment">// Faster than two Shifts and an Or. Thanks to Louis Wingers and Bryan Weeks.</span></div><div class="line"><a name="l00602"></a><span class="lineno"> 602</span> <span class="keyword">template</span> <></div><div class="line"><a name="l00603"></a><span class="lineno"> 603</span> <span class="keyword">inline</span> __m128i RotateLeft64<8>(<span class="keyword">const</span> __m128i& val)</div><div class="line"><a name="l00604"></a><span class="lineno"> 604</span> {</div><div class="line"><a name="l00605"></a><span class="lineno"> 605</span>  <span class="keyword">const</span> __m128i mask = _mm_set_epi8(14,13,12,11, 10,9,8,15, 6,5,4,3, 2,1,0,7);</div><div class="line"><a name="l00606"></a><span class="lineno"> 606</span>  <span class="keywordflow">return</span> _mm_shuffle_epi8(val, mask);</div><div class="line"><a name="l00607"></a><span class="lineno"> 607</span> }</div><div class="line"><a name="l00608"></a><span class="lineno"> 608</span> </div><div class="line"><a name="l00609"></a><span class="lineno"> 609</span> <span class="comment">// Faster than two Shifts and an Or. Thanks to Louis Wingers and Bryan Weeks.</span></div><div class="line"><a name="l00610"></a><span class="lineno"> 610</span> <span class="keyword">template</span> <></div><div class="line"><a name="l00611"></a><span class="lineno"> 611</span> <span class="keyword">inline</span> __m128i RotateRight64<8>(<span class="keyword">const</span> __m128i& val)</div><div class="line"><a name="l00612"></a><span class="lineno"> 612</span> {</div><div class="line"><a name="l00613"></a><span class="lineno"> 613</span>  <span class="keyword">const</span> __m128i mask = _mm_set_epi8(8,15,14,13, 12,11,10,9, 0,7,6,5, 4,3,2,1);</div><div class="line"><a name="l00614"></a><span class="lineno"> 614</span>  <span class="keywordflow">return</span> _mm_shuffle_epi8(val, mask);</div><div class="line"><a name="l00615"></a><span class="lineno"> 615</span> }</div><div class="line"><a name="l00616"></a><span class="lineno"> 616</span> <span class="preprocessor">#endif // CRYPTOPP_AVX512_ROTATE</span></div><div class="line"><a name="l00617"></a><span class="lineno"> 617</span> </div><div class="line"><a name="l00618"></a><span class="lineno"> 618</span> <span class="keyword">inline</span> __m128i SIMON128_f(<span class="keyword">const</span> __m128i& v)</div><div class="line"><a name="l00619"></a><span class="lineno"> 619</span> {</div><div class="line"><a name="l00620"></a><span class="lineno"> 620</span>  <span class="keywordflow">return</span> _mm_xor_si128(RotateLeft64<2>(v),</div><div class="line"><a name="l00621"></a><span class="lineno"> 621</span>  _mm_and_si128(RotateLeft64<1>(v), RotateLeft64<8>(v)));</div><div class="line"><a name="l00622"></a><span class="lineno"> 622</span> }</div><div class="line"><a name="l00623"></a><span class="lineno"> 623</span> </div><div class="line"><a name="l00624"></a><span class="lineno"> 624</span> <span class="keyword">inline</span> <span class="keywordtype">void</span> GCC_NO_UBSAN SIMON128_Enc_Block(__m128i &block0, __m128i &block1,</div><div class="line"><a name="l00625"></a><span class="lineno"> 625</span>  <span class="keyword">const</span> word64 *subkeys, <span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> rounds)</div><div class="line"><a name="l00626"></a><span class="lineno"> 626</span> {</div><div class="line"><a name="l00627"></a><span class="lineno"> 627</span>  <span class="comment">// Rearrange the data for vectorization. The incoming data was read into</span></div><div class="line"><a name="l00628"></a><span class="lineno"> 628</span>  <span class="comment">// a little-endian word array. Depending on the number of blocks it needs to</span></div><div class="line"><a name="l00629"></a><span class="lineno"> 629</span>  <span class="comment">// be permuted to the following.</span></div><div class="line"><a name="l00630"></a><span class="lineno"> 630</span>  <span class="comment">// [A1 A2][B1 B2] ... => [A1 B1][A2 B2] ...</span></div><div class="line"><a name="l00631"></a><span class="lineno"> 631</span>  __m128i x1 = _mm_unpackhi_epi64(block0, block1);</div><div class="line"><a name="l00632"></a><span class="lineno"> 632</span>  __m128i y1 = _mm_unpacklo_epi64(block0, block1);</div><div class="line"><a name="l00633"></a><span class="lineno"> 633</span> </div><div class="line"><a name="l00634"></a><span class="lineno"> 634</span>  <span class="keywordflow">for</span> (<span class="keywordtype">int</span> i = 0; i < static_cast<int>(rounds & ~1)-1; i += 2)</div><div class="line"><a name="l00635"></a><span class="lineno"> 635</span>  {</div><div class="line"><a name="l00636"></a><span class="lineno"> 636</span>  <span class="keyword">const</span> __m128i rk1 = _mm_castpd_si128(</div><div class="line"><a name="l00637"></a><span class="lineno"> 637</span>  _mm_loaddup_pd(CONST_DOUBLE_CAST(subkeys+i)));</div><div class="line"><a name="l00638"></a><span class="lineno"> 638</span>  y1 = _mm_xor_si128(_mm_xor_si128(y1, SIMON128_f(x1)), rk1);</div><div class="line"><a name="l00639"></a><span class="lineno"> 639</span> </div><div class="line"><a name="l00640"></a><span class="lineno"> 640</span>  <span class="keyword">const</span> __m128i rk2 = _mm_castpd_si128(</div><div class="line"><a name="l00641"></a><span class="lineno"> 641</span>  _mm_loaddup_pd(CONST_DOUBLE_CAST(subkeys+i+1)));</div><div class="line"><a name="l00642"></a><span class="lineno"> 642</span>  x1 = _mm_xor_si128(_mm_xor_si128(x1, SIMON128_f(y1)), rk2);</div><div class="line"><a name="l00643"></a><span class="lineno"> 643</span>  }</div><div class="line"><a name="l00644"></a><span class="lineno"> 644</span> </div><div class="line"><a name="l00645"></a><span class="lineno"> 645</span>  <span class="keywordflow">if</span> (rounds & 1)</div><div class="line"><a name="l00646"></a><span class="lineno"> 646</span>  {</div><div class="line"><a name="l00647"></a><span class="lineno"> 647</span>  <span class="keyword">const</span> __m128i rk = _mm_castpd_si128(</div><div class="line"><a name="l00648"></a><span class="lineno"> 648</span>  _mm_loaddup_pd(CONST_DOUBLE_CAST(subkeys+rounds-1)));</div><div class="line"><a name="l00649"></a><span class="lineno"> 649</span> </div><div class="line"><a name="l00650"></a><span class="lineno"> 650</span>  y1 = _mm_xor_si128(_mm_xor_si128(y1, SIMON128_f(x1)), rk);</div><div class="line"><a name="l00651"></a><span class="lineno"> 651</span>  Swap128(x1, y1);</div><div class="line"><a name="l00652"></a><span class="lineno"> 652</span>  }</div><div class="line"><a name="l00653"></a><span class="lineno"> 653</span> </div><div class="line"><a name="l00654"></a><span class="lineno"> 654</span>  <span class="comment">// [A1 B1][A2 B2] ... => [A1 A2][B1 B2] ...</span></div><div class="line"><a name="l00655"></a><span class="lineno"> 655</span>  block0 = _mm_unpacklo_epi64(y1, x1);</div><div class="line"><a name="l00656"></a><span class="lineno"> 656</span>  block1 = _mm_unpackhi_epi64(y1, x1);</div><div class="line"><a name="l00657"></a><span class="lineno"> 657</span> }</div><div class="line"><a name="l00658"></a><span class="lineno"> 658</span> </div><div class="line"><a name="l00659"></a><span class="lineno"> 659</span> <span class="keyword">inline</span> <span class="keywordtype">void</span> GCC_NO_UBSAN SIMON128_Enc_6_Blocks(__m128i &block0, __m128i &block1,</div><div class="line"><a name="l00660"></a><span class="lineno"> 660</span>  __m128i &block2, __m128i &block3, __m128i &block4, __m128i &block5,</div><div class="line"><a name="l00661"></a><span class="lineno"> 661</span>  <span class="keyword">const</span> word64 *subkeys, <span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> rounds)</div><div class="line"><a name="l00662"></a><span class="lineno"> 662</span> {</div><div class="line"><a name="l00663"></a><span class="lineno"> 663</span>  <span class="comment">// Rearrange the data for vectorization. The incoming data was read into</span></div><div class="line"><a name="l00664"></a><span class="lineno"> 664</span>  <span class="comment">// a little-endian word array. Depending on the number of blocks it needs to</span></div><div class="line"><a name="l00665"></a><span class="lineno"> 665</span>  <span class="comment">// be permuted to the following.</span></div><div class="line"><a name="l00666"></a><span class="lineno"> 666</span>  <span class="comment">// [A1 A2][B1 B2] ... => [A1 B1][A2 B2] ...</span></div><div class="line"><a name="l00667"></a><span class="lineno"> 667</span>  __m128i x1 = _mm_unpackhi_epi64(block0, block1);</div><div class="line"><a name="l00668"></a><span class="lineno"> 668</span>  __m128i y1 = _mm_unpacklo_epi64(block0, block1);</div><div class="line"><a name="l00669"></a><span class="lineno"> 669</span>  __m128i x2 = _mm_unpackhi_epi64(block2, block3);</div><div class="line"><a name="l00670"></a><span class="lineno"> 670</span>  __m128i y2 = _mm_unpacklo_epi64(block2, block3);</div><div class="line"><a name="l00671"></a><span class="lineno"> 671</span>  __m128i x3 = _mm_unpackhi_epi64(block4, block5);</div><div class="line"><a name="l00672"></a><span class="lineno"> 672</span>  __m128i y3 = _mm_unpacklo_epi64(block4, block5);</div><div class="line"><a name="l00673"></a><span class="lineno"> 673</span> </div><div class="line"><a name="l00674"></a><span class="lineno"> 674</span>  <span class="keywordflow">for</span> (<span class="keywordtype">int</span> i = 0; i < static_cast<int>(rounds & ~1) - 1; i += 2)</div><div class="line"><a name="l00675"></a><span class="lineno"> 675</span>  {</div><div class="line"><a name="l00676"></a><span class="lineno"> 676</span>  <span class="keyword">const</span> __m128i rk1 = _mm_castpd_si128(</div><div class="line"><a name="l00677"></a><span class="lineno"> 677</span>  _mm_loaddup_pd(CONST_DOUBLE_CAST(subkeys + i)));</div><div class="line"><a name="l00678"></a><span class="lineno"> 678</span>  y1 = _mm_xor_si128(_mm_xor_si128(y1, SIMON128_f(x1)), rk1);</div><div class="line"><a name="l00679"></a><span class="lineno"> 679</span>  y2 = _mm_xor_si128(_mm_xor_si128(y2, SIMON128_f(x2)), rk1);</div><div class="line"><a name="l00680"></a><span class="lineno"> 680</span>  y3 = _mm_xor_si128(_mm_xor_si128(y3, SIMON128_f(x3)), rk1);</div><div class="line"><a name="l00681"></a><span class="lineno"> 681</span> </div><div class="line"><a name="l00682"></a><span class="lineno"> 682</span>  <span class="keyword">const</span> __m128i rk2 = _mm_castpd_si128(</div><div class="line"><a name="l00683"></a><span class="lineno"> 683</span>  _mm_loaddup_pd(CONST_DOUBLE_CAST(subkeys + i + 1)));</div><div class="line"><a name="l00684"></a><span class="lineno"> 684</span>  x1 = _mm_xor_si128(_mm_xor_si128(x1, SIMON128_f(y1)), rk2);</div><div class="line"><a name="l00685"></a><span class="lineno"> 685</span>  x2 = _mm_xor_si128(_mm_xor_si128(x2, SIMON128_f(y2)), rk2);</div><div class="line"><a name="l00686"></a><span class="lineno"> 686</span>  x3 = _mm_xor_si128(_mm_xor_si128(x3, SIMON128_f(y3)), rk2);</div><div class="line"><a name="l00687"></a><span class="lineno"> 687</span>  }</div><div class="line"><a name="l00688"></a><span class="lineno"> 688</span> </div><div class="line"><a name="l00689"></a><span class="lineno"> 689</span>  <span class="keywordflow">if</span> (rounds & 1)</div><div class="line"><a name="l00690"></a><span class="lineno"> 690</span>  {</div><div class="line"><a name="l00691"></a><span class="lineno"> 691</span>  <span class="keyword">const</span> __m128i rk = _mm_castpd_si128(</div><div class="line"><a name="l00692"></a><span class="lineno"> 692</span>  _mm_loaddup_pd(CONST_DOUBLE_CAST(subkeys + rounds - 1)));</div><div class="line"><a name="l00693"></a><span class="lineno"> 693</span>  y1 = _mm_xor_si128(_mm_xor_si128(y1, SIMON128_f(x1)), rk);</div><div class="line"><a name="l00694"></a><span class="lineno"> 694</span>  y2 = _mm_xor_si128(_mm_xor_si128(y2, SIMON128_f(x2)), rk);</div><div class="line"><a name="l00695"></a><span class="lineno"> 695</span>  y3 = _mm_xor_si128(_mm_xor_si128(y3, SIMON128_f(x3)), rk);</div><div class="line"><a name="l00696"></a><span class="lineno"> 696</span>  Swap128(x1, y1); Swap128(x2, y2); Swap128(x3, y3);</div><div class="line"><a name="l00697"></a><span class="lineno"> 697</span>  }</div><div class="line"><a name="l00698"></a><span class="lineno"> 698</span> </div><div class="line"><a name="l00699"></a><span class="lineno"> 699</span>  <span class="comment">// [A1 B1][A2 B2] ... => [A1 A2][B1 B2] ...</span></div><div class="line"><a name="l00700"></a><span class="lineno"> 700</span>  block0 = _mm_unpacklo_epi64(y1, x1);</div><div class="line"><a name="l00701"></a><span class="lineno"> 701</span>  block1 = _mm_unpackhi_epi64(y1, x1);</div><div class="line"><a name="l00702"></a><span class="lineno"> 702</span>  block2 = _mm_unpacklo_epi64(y2, x2);</div><div class="line"><a name="l00703"></a><span class="lineno"> 703</span>  block3 = _mm_unpackhi_epi64(y2, x2);</div><div class="line"><a name="l00704"></a><span class="lineno"> 704</span>  block4 = _mm_unpacklo_epi64(y3, x3);</div><div class="line"><a name="l00705"></a><span class="lineno"> 705</span>  block5 = _mm_unpackhi_epi64(y3, x3);</div><div class="line"><a name="l00706"></a><span class="lineno"> 706</span> }</div><div class="line"><a name="l00707"></a><span class="lineno"> 707</span> </div><div class="line"><a name="l00708"></a><span class="lineno"> 708</span> <span class="keyword">inline</span> <span class="keywordtype">void</span> GCC_NO_UBSAN SIMON128_Dec_Block(__m128i &block0, __m128i &block1,</div><div class="line"><a name="l00709"></a><span class="lineno"> 709</span>  <span class="keyword">const</span> word64 *subkeys, <span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> rounds)</div><div class="line"><a name="l00710"></a><span class="lineno"> 710</span> {</div><div class="line"><a name="l00711"></a><span class="lineno"> 711</span>  <span class="comment">// Rearrange the data for vectorization. The incoming data was read into</span></div><div class="line"><a name="l00712"></a><span class="lineno"> 712</span>  <span class="comment">// a little-endian word array. Depending on the number of blocks it needs to</span></div><div class="line"><a name="l00713"></a><span class="lineno"> 713</span>  <span class="comment">// be permuted to the following.</span></div><div class="line"><a name="l00714"></a><span class="lineno"> 714</span>  <span class="comment">// [A1 A2][B1 B2] ... => [A1 B1][A2 B2] ...</span></div><div class="line"><a name="l00715"></a><span class="lineno"> 715</span>  __m128i x1 = _mm_unpackhi_epi64(block0, block1);</div><div class="line"><a name="l00716"></a><span class="lineno"> 716</span>  __m128i y1 = _mm_unpacklo_epi64(block0, block1);</div><div class="line"><a name="l00717"></a><span class="lineno"> 717</span> </div><div class="line"><a name="l00718"></a><span class="lineno"> 718</span>  <span class="keywordflow">if</span> (rounds & 1)</div><div class="line"><a name="l00719"></a><span class="lineno"> 719</span>  {</div><div class="line"><a name="l00720"></a><span class="lineno"> 720</span>  <span class="keyword">const</span> __m128i rk = _mm_castpd_si128(</div><div class="line"><a name="l00721"></a><span class="lineno"> 721</span>  _mm_loaddup_pd(CONST_DOUBLE_CAST(subkeys + rounds - 1)));</div><div class="line"><a name="l00722"></a><span class="lineno"> 722</span> </div><div class="line"><a name="l00723"></a><span class="lineno"> 723</span>  Swap128(x1, y1);</div><div class="line"><a name="l00724"></a><span class="lineno"> 724</span>  y1 = _mm_xor_si128(_mm_xor_si128(y1, rk), SIMON128_f(x1));</div><div class="line"><a name="l00725"></a><span class="lineno"> 725</span>  rounds--;</div><div class="line"><a name="l00726"></a><span class="lineno"> 726</span>  }</div><div class="line"><a name="l00727"></a><span class="lineno"> 727</span> </div><div class="line"><a name="l00728"></a><span class="lineno"> 728</span>  <span class="keywordflow">for</span> (<span class="keywordtype">int</span> i = static_cast<int>(rounds-2); i >= 0; i -= 2)</div><div class="line"><a name="l00729"></a><span class="lineno"> 729</span>  {</div><div class="line"><a name="l00730"></a><span class="lineno"> 730</span>  <span class="keyword">const</span> __m128i rk1 = _mm_castpd_si128(</div><div class="line"><a name="l00731"></a><span class="lineno"> 731</span>  _mm_loaddup_pd(CONST_DOUBLE_CAST(subkeys+i+1)));</div><div class="line"><a name="l00732"></a><span class="lineno"> 732</span>  x1 = _mm_xor_si128(_mm_xor_si128(x1, SIMON128_f(y1)), rk1);</div><div class="line"><a name="l00733"></a><span class="lineno"> 733</span> </div><div class="line"><a name="l00734"></a><span class="lineno"> 734</span>  <span class="keyword">const</span> __m128i rk2 = _mm_castpd_si128(</div><div class="line"><a name="l00735"></a><span class="lineno"> 735</span>  _mm_loaddup_pd(CONST_DOUBLE_CAST(subkeys+i)));</div><div class="line"><a name="l00736"></a><span class="lineno"> 736</span>  y1 = _mm_xor_si128(_mm_xor_si128(y1, SIMON128_f(x1)), rk2);</div><div class="line"><a name="l00737"></a><span class="lineno"> 737</span>  }</div><div class="line"><a name="l00738"></a><span class="lineno"> 738</span> </div><div class="line"><a name="l00739"></a><span class="lineno"> 739</span>  <span class="comment">// [A1 B1][A2 B2] ... => [A1 A2][B1 B2] ...</span></div><div class="line"><a name="l00740"></a><span class="lineno"> 740</span>  block0 = _mm_unpacklo_epi64(y1, x1);</div><div class="line"><a name="l00741"></a><span class="lineno"> 741</span>  block1 = _mm_unpackhi_epi64(y1, x1);</div><div class="line"><a name="l00742"></a><span class="lineno"> 742</span> }</div><div class="line"><a name="l00743"></a><span class="lineno"> 743</span> </div><div class="line"><a name="l00744"></a><span class="lineno"> 744</span> <span class="keyword">inline</span> <span class="keywordtype">void</span> GCC_NO_UBSAN SIMON128_Dec_6_Blocks(__m128i &block0, __m128i &block1,</div><div class="line"><a name="l00745"></a><span class="lineno"> 745</span>  __m128i &block2, __m128i &block3, __m128i &block4, __m128i &block5,</div><div class="line"><a name="l00746"></a><span class="lineno"> 746</span>  <span class="keyword">const</span> word64 *subkeys, <span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> rounds)</div><div class="line"><a name="l00747"></a><span class="lineno"> 747</span> {</div><div class="line"><a name="l00748"></a><span class="lineno"> 748</span>  <span class="comment">// Rearrange the data for vectorization. The incoming data was read into</span></div><div class="line"><a name="l00749"></a><span class="lineno"> 749</span>  <span class="comment">// a little-endian word array. Depending on the number of blocks it needs to</span></div><div class="line"><a name="l00750"></a><span class="lineno"> 750</span>  <span class="comment">// be permuted to the following.</span></div><div class="line"><a name="l00751"></a><span class="lineno"> 751</span>  <span class="comment">// [A1 A2][B1 B2] ... => [A1 B1][A2 B2] ...</span></div><div class="line"><a name="l00752"></a><span class="lineno"> 752</span>  __m128i x1 = _mm_unpackhi_epi64(block0, block1);</div><div class="line"><a name="l00753"></a><span class="lineno"> 753</span>  __m128i y1 = _mm_unpacklo_epi64(block0, block1);</div><div class="line"><a name="l00754"></a><span class="lineno"> 754</span>  __m128i x2 = _mm_unpackhi_epi64(block2, block3);</div><div class="line"><a name="l00755"></a><span class="lineno"> 755</span>  __m128i y2 = _mm_unpacklo_epi64(block2, block3);</div><div class="line"><a name="l00756"></a><span class="lineno"> 756</span>  __m128i x3 = _mm_unpackhi_epi64(block4, block5);</div><div class="line"><a name="l00757"></a><span class="lineno"> 757</span>  __m128i y3 = _mm_unpacklo_epi64(block4, block5);</div><div class="line"><a name="l00758"></a><span class="lineno"> 758</span> </div><div class="line"><a name="l00759"></a><span class="lineno"> 759</span>  <span class="keywordflow">if</span> (rounds & 1)</div><div class="line"><a name="l00760"></a><span class="lineno"> 760</span>  {</div><div class="line"><a name="l00761"></a><span class="lineno"> 761</span>  <span class="keyword">const</span> __m128i rk = _mm_castpd_si128(</div><div class="line"><a name="l00762"></a><span class="lineno"> 762</span>  _mm_loaddup_pd(CONST_DOUBLE_CAST(subkeys + rounds - 1)));</div><div class="line"><a name="l00763"></a><span class="lineno"> 763</span> </div><div class="line"><a name="l00764"></a><span class="lineno"> 764</span>  Swap128(x1, y1); Swap128(x2, y2); Swap128(x3, y3);</div><div class="line"><a name="l00765"></a><span class="lineno"> 765</span>  y1 = _mm_xor_si128(_mm_xor_si128(y1, rk), SIMON128_f(x1));</div><div class="line"><a name="l00766"></a><span class="lineno"> 766</span>  y2 = _mm_xor_si128(_mm_xor_si128(y2, rk), SIMON128_f(x2));</div><div class="line"><a name="l00767"></a><span class="lineno"> 767</span>  y3 = _mm_xor_si128(_mm_xor_si128(y3, rk), SIMON128_f(x3));</div><div class="line"><a name="l00768"></a><span class="lineno"> 768</span>  rounds--;</div><div class="line"><a name="l00769"></a><span class="lineno"> 769</span>  }</div><div class="line"><a name="l00770"></a><span class="lineno"> 770</span> </div><div class="line"><a name="l00771"></a><span class="lineno"> 771</span>  <span class="keywordflow">for</span> (<span class="keywordtype">int</span> i = static_cast<int>(rounds-2); i >= 0; i -= 2)</div><div class="line"><a name="l00772"></a><span class="lineno"> 772</span>  {</div><div class="line"><a name="l00773"></a><span class="lineno"> 773</span>  <span class="keyword">const</span> __m128i rk1 = _mm_castpd_si128(</div><div class="line"><a name="l00774"></a><span class="lineno"> 774</span>  _mm_loaddup_pd(CONST_DOUBLE_CAST(subkeys + i + 1)));</div><div class="line"><a name="l00775"></a><span class="lineno"> 775</span>  x1 = _mm_xor_si128(_mm_xor_si128(x1, SIMON128_f(y1)), rk1);</div><div class="line"><a name="l00776"></a><span class="lineno"> 776</span>  x2 = _mm_xor_si128(_mm_xor_si128(x2, SIMON128_f(y2)), rk1);</div><div class="line"><a name="l00777"></a><span class="lineno"> 777</span>  x3 = _mm_xor_si128(_mm_xor_si128(x3, SIMON128_f(y3)), rk1);</div><div class="line"><a name="l00778"></a><span class="lineno"> 778</span> </div><div class="line"><a name="l00779"></a><span class="lineno"> 779</span>  <span class="keyword">const</span> __m128i rk2 = _mm_castpd_si128(</div><div class="line"><a name="l00780"></a><span class="lineno"> 780</span>  _mm_loaddup_pd(CONST_DOUBLE_CAST(subkeys + i)));</div><div class="line"><a name="l00781"></a><span class="lineno"> 781</span>  y1 = _mm_xor_si128(_mm_xor_si128(y1, SIMON128_f(x1)), rk2);</div><div class="line"><a name="l00782"></a><span class="lineno"> 782</span>  y2 = _mm_xor_si128(_mm_xor_si128(y2, SIMON128_f(x2)), rk2);</div><div class="line"><a name="l00783"></a><span class="lineno"> 783</span>  y3 = _mm_xor_si128(_mm_xor_si128(y3, SIMON128_f(x3)), rk2);</div><div class="line"><a name="l00784"></a><span class="lineno"> 784</span>  }</div><div class="line"><a name="l00785"></a><span class="lineno"> 785</span> </div><div class="line"><a name="l00786"></a><span class="lineno"> 786</span>  <span class="comment">// [A1 B1][A2 B2] ... => [A1 A2][B1 B2] ...</span></div><div class="line"><a name="l00787"></a><span class="lineno"> 787</span>  block0 = _mm_unpacklo_epi64(y1, x1);</div><div class="line"><a name="l00788"></a><span class="lineno"> 788</span>  block1 = _mm_unpackhi_epi64(y1, x1);</div><div class="line"><a name="l00789"></a><span class="lineno"> 789</span>  block2 = _mm_unpacklo_epi64(y2, x2);</div><div class="line"><a name="l00790"></a><span class="lineno"> 790</span>  block3 = _mm_unpackhi_epi64(y2, x2);</div><div class="line"><a name="l00791"></a><span class="lineno"> 791</span>  block4 = _mm_unpacklo_epi64(y3, x3);</div><div class="line"><a name="l00792"></a><span class="lineno"> 792</span>  block5 = _mm_unpackhi_epi64(y3, x3);</div><div class="line"><a name="l00793"></a><span class="lineno"> 793</span> }</div><div class="line"><a name="l00794"></a><span class="lineno"> 794</span> </div><div class="line"><a name="l00795"></a><span class="lineno"> 795</span> <span class="preprocessor">#endif // CRYPTOPP_SSSE3_AVAILABLE</span></div><div class="line"><a name="l00796"></a><span class="lineno"> 796</span> </div><div class="line"><a name="l00797"></a><span class="lineno"> 797</span> <span class="preprocessor">#if defined(CRYPTOPP_SSE41_AVAILABLE)</span></div><div class="line"><a name="l00798"></a><span class="lineno"> 798</span> </div><div class="line"><a name="l00799"></a><span class="lineno"> 799</span> <span class="keyword">template</span> <<span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> R></div><div class="line"><a name="l00800"></a><span class="lineno"> 800</span> <span class="keyword">inline</span> __m128i RotateLeft32(<span class="keyword">const</span> __m128i& val)</div><div class="line"><a name="l00801"></a><span class="lineno"> 801</span> {</div><div class="line"><a name="l00802"></a><span class="lineno"> 802</span>  <span class="keywordflow">return</span> _mm_or_si128(</div><div class="line"><a name="l00803"></a><span class="lineno"> 803</span>  _mm_slli_epi32(val, R), _mm_srli_epi32(val, 32-R));</div><div class="line"><a name="l00804"></a><span class="lineno"> 804</span> }</div><div class="line"><a name="l00805"></a><span class="lineno"> 805</span> </div><div class="line"><a name="l00806"></a><span class="lineno"> 806</span> <span class="keyword">template</span> <<span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> R></div><div class="line"><a name="l00807"></a><span class="lineno"> 807</span> <span class="keyword">inline</span> __m128i RotateRight32(<span class="keyword">const</span> __m128i& val)</div><div class="line"><a name="l00808"></a><span class="lineno"> 808</span> {</div><div class="line"><a name="l00809"></a><span class="lineno"> 809</span>  <span class="keywordflow">return</span> _mm_or_si128(</div><div class="line"><a name="l00810"></a><span class="lineno"> 810</span>  _mm_slli_epi32(val, 32-R), _mm_srli_epi32(val, R));</div><div class="line"><a name="l00811"></a><span class="lineno"> 811</span> }</div><div class="line"><a name="l00812"></a><span class="lineno"> 812</span> </div><div class="line"><a name="l00813"></a><span class="lineno"> 813</span> <span class="comment">// Faster than two Shifts and an Or. Thanks to Louis Wingers and Bryan Weeks.</span></div><div class="line"><a name="l00814"></a><span class="lineno"> 814</span> <span class="keyword">template</span> <></div><div class="line"><a name="l00815"></a><span class="lineno"> 815</span> <span class="keyword">inline</span> __m128i RotateLeft32<8>(<span class="keyword">const</span> __m128i& val)</div><div class="line"><a name="l00816"></a><span class="lineno"> 816</span> {</div><div class="line"><a name="l00817"></a><span class="lineno"> 817</span>  <span class="keyword">const</span> __m128i mask = _mm_set_epi8(14,13,12,15, 10,9,8,11, 6,5,4,7, 2,1,0,3);</div><div class="line"><a name="l00818"></a><span class="lineno"> 818</span>  <span class="keywordflow">return</span> _mm_shuffle_epi8(val, mask);</div><div class="line"><a name="l00819"></a><span class="lineno"> 819</span> }</div><div class="line"><a name="l00820"></a><span class="lineno"> 820</span> </div><div class="line"><a name="l00821"></a><span class="lineno"> 821</span> <span class="comment">// Faster than two Shifts and an Or. Thanks to Louis Wingers and Bryan Weeks.</span></div><div class="line"><a name="l00822"></a><span class="lineno"> 822</span> <span class="keyword">template</span> <></div><div class="line"><a name="l00823"></a><span class="lineno"> 823</span> <span class="keyword">inline</span> __m128i RotateRight32<8>(<span class="keyword">const</span> __m128i& val)</div><div class="line"><a name="l00824"></a><span class="lineno"> 824</span> {</div><div class="line"><a name="l00825"></a><span class="lineno"> 825</span>  <span class="keyword">const</span> __m128i mask = _mm_set_epi8(12,15,14,13, 8,11,10,9, 4,7,6,5, 0,3,2,1);</div><div class="line"><a name="l00826"></a><span class="lineno"> 826</span>  <span class="keywordflow">return</span> _mm_shuffle_epi8(val, mask);</div><div class="line"><a name="l00827"></a><span class="lineno"> 827</span> }</div><div class="line"><a name="l00828"></a><span class="lineno"> 828</span> </div><div class="line"><a name="l00829"></a><span class="lineno"> 829</span> <span class="keyword">inline</span> __m128i SIMON64_f(<span class="keyword">const</span> __m128i& v)</div><div class="line"><a name="l00830"></a><span class="lineno"> 830</span> {</div><div class="line"><a name="l00831"></a><span class="lineno"> 831</span>  <span class="keywordflow">return</span> _mm_xor_si128(RotateLeft32<2>(v),</div><div class="line"><a name="l00832"></a><span class="lineno"> 832</span>  _mm_and_si128(RotateLeft32<1>(v), RotateLeft32<8>(v)));</div><div class="line"><a name="l00833"></a><span class="lineno"> 833</span> }</div><div class="line"><a name="l00834"></a><span class="lineno"> 834</span> </div><div class="line"><a name="l00835"></a><span class="lineno"> 835</span> <span class="keyword">inline</span> <span class="keywordtype">void</span> GCC_NO_UBSAN SIMON64_Enc_Block(__m128i &block0, __m128i &block1,</div><div class="line"><a name="l00836"></a><span class="lineno"> 836</span>  <span class="keyword">const</span> word32 *subkeys, <span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> rounds)</div><div class="line"><a name="l00837"></a><span class="lineno"> 837</span> {</div><div class="line"><a name="l00838"></a><span class="lineno"> 838</span>  <span class="comment">// Rearrange the data for vectorization. The incoming data was read into</span></div><div class="line"><a name="l00839"></a><span class="lineno"> 839</span>  <span class="comment">// a little-endian word array. Depending on the number of blocks it needs to</span></div><div class="line"><a name="l00840"></a><span class="lineno"> 840</span>  <span class="comment">// be permuted to the following. Thanks to Peter Cordes for help with the</span></div><div class="line"><a name="l00841"></a><span class="lineno"> 841</span>  <span class="comment">// SSE permutes below.</span></div><div class="line"><a name="l00842"></a><span class="lineno"> 842</span>  <span class="comment">// [A1 A2 A3 A4][B1 B2 B3 B4] ... => [A1 A3 B1 B3][A2 A4 B2 B4] ...</span></div><div class="line"><a name="l00843"></a><span class="lineno"> 843</span>  <span class="keyword">const</span> __m128 t0 = _mm_castsi128_ps(block0);</div><div class="line"><a name="l00844"></a><span class="lineno"> 844</span>  <span class="keyword">const</span> __m128 t1 = _mm_castsi128_ps(block1);</div><div class="line"><a name="l00845"></a><span class="lineno"> 845</span>  __m128i x1 = _mm_castps_si128(_mm_shuffle_ps(t0, t1, _MM_SHUFFLE(3,1,3,1)));</div><div class="line"><a name="l00846"></a><span class="lineno"> 846</span>  __m128i y1 = _mm_castps_si128(_mm_shuffle_ps(t0, t1, _MM_SHUFFLE(2,0,2,0)));</div><div class="line"><a name="l00847"></a><span class="lineno"> 847</span> </div><div class="line"><a name="l00848"></a><span class="lineno"> 848</span>  <span class="keywordflow">for</span> (<span class="keywordtype">int</span> i = 0; i < static_cast<int>(rounds & ~1)-1; i += 2)</div><div class="line"><a name="l00849"></a><span class="lineno"> 849</span>  {</div><div class="line"><a name="l00850"></a><span class="lineno"> 850</span>  <span class="keyword">const</span> __m128i rk1 = _mm_set1_epi32(subkeys[i]);</div><div class="line"><a name="l00851"></a><span class="lineno"> 851</span>  y1 = _mm_xor_si128(_mm_xor_si128(y1, SIMON64_f(x1)), rk1);</div><div class="line"><a name="l00852"></a><span class="lineno"> 852</span> </div><div class="line"><a name="l00853"></a><span class="lineno"> 853</span>  <span class="keyword">const</span> __m128i rk2 = _mm_set1_epi32(subkeys[i+1]);</div><div class="line"><a name="l00854"></a><span class="lineno"> 854</span>  x1 = _mm_xor_si128(_mm_xor_si128(x1, SIMON64_f(y1)), rk2);</div><div class="line"><a name="l00855"></a><span class="lineno"> 855</span>  }</div><div class="line"><a name="l00856"></a><span class="lineno"> 856</span> </div><div class="line"><a name="l00857"></a><span class="lineno"> 857</span>  <span class="keywordflow">if</span> (rounds & 1)</div><div class="line"><a name="l00858"></a><span class="lineno"> 858</span>  {</div><div class="line"><a name="l00859"></a><span class="lineno"> 859</span>  <span class="keyword">const</span> __m128i rk = _mm_set1_epi32(subkeys[rounds-1]);</div><div class="line"><a name="l00860"></a><span class="lineno"> 860</span>  y1 = _mm_xor_si128(_mm_xor_si128(y1, SIMON64_f(x1)), rk);</div><div class="line"><a name="l00861"></a><span class="lineno"> 861</span>  Swap128(x1, y1);</div><div class="line"><a name="l00862"></a><span class="lineno"> 862</span>  }</div><div class="line"><a name="l00863"></a><span class="lineno"> 863</span> </div><div class="line"><a name="l00864"></a><span class="lineno"> 864</span>  <span class="comment">// The is roughly the SSE equivalent to ARM vzp32</span></div><div class="line"><a name="l00865"></a><span class="lineno"> 865</span>  <span class="comment">// [A1 A3 B1 B3][A2 A4 B2 B4] => [A1 A2 A3 A4][B1 B2 B3 B4]</span></div><div class="line"><a name="l00866"></a><span class="lineno"> 866</span>  block0 = _mm_unpacklo_epi32(y1, x1);</div><div class="line"><a name="l00867"></a><span class="lineno"> 867</span>  block1 = _mm_unpackhi_epi32(y1, x1);</div><div class="line"><a name="l00868"></a><span class="lineno"> 868</span> }</div><div class="line"><a name="l00869"></a><span class="lineno"> 869</span> </div><div class="line"><a name="l00870"></a><span class="lineno"> 870</span> <span class="keyword">inline</span> <span class="keywordtype">void</span> GCC_NO_UBSAN SIMON64_Dec_Block(__m128i &block0, __m128i &block1,</div><div class="line"><a name="l00871"></a><span class="lineno"> 871</span>  <span class="keyword">const</span> word32 *subkeys, <span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> rounds)</div><div class="line"><a name="l00872"></a><span class="lineno"> 872</span> {</div><div class="line"><a name="l00873"></a><span class="lineno"> 873</span>  <span class="comment">// Rearrange the data for vectorization. The incoming data was read into</span></div><div class="line"><a name="l00874"></a><span class="lineno"> 874</span>  <span class="comment">// a little-endian word array. Depending on the number of blocks it needs to</span></div><div class="line"><a name="l00875"></a><span class="lineno"> 875</span>  <span class="comment">// be permuted to the following. Thanks to Peter Cordes for help with the</span></div><div class="line"><a name="l00876"></a><span class="lineno"> 876</span>  <span class="comment">// SSE permutes below.</span></div><div class="line"><a name="l00877"></a><span class="lineno"> 877</span>  <span class="comment">// [A1 A2 A3 A4][B1 B2 B3 B4] ... => [A1 A3 B1 B3][A2 A4 B2 B4] ...</span></div><div class="line"><a name="l00878"></a><span class="lineno"> 878</span>  <span class="keyword">const</span> __m128 t0 = _mm_castsi128_ps(block0);</div><div class="line"><a name="l00879"></a><span class="lineno"> 879</span>  <span class="keyword">const</span> __m128 t1 = _mm_castsi128_ps(block1);</div><div class="line"><a name="l00880"></a><span class="lineno"> 880</span>  __m128i x1 = _mm_castps_si128(_mm_shuffle_ps(t0, t1, _MM_SHUFFLE(3,1,3,1)));</div><div class="line"><a name="l00881"></a><span class="lineno"> 881</span>  __m128i y1 = _mm_castps_si128(_mm_shuffle_ps(t0, t1, _MM_SHUFFLE(2,0,2,0)));</div><div class="line"><a name="l00882"></a><span class="lineno"> 882</span> </div><div class="line"><a name="l00883"></a><span class="lineno"> 883</span>  <span class="keywordflow">if</span> (rounds & 1)</div><div class="line"><a name="l00884"></a><span class="lineno"> 884</span>  {</div><div class="line"><a name="l00885"></a><span class="lineno"> 885</span>  Swap128(x1, y1);</div><div class="line"><a name="l00886"></a><span class="lineno"> 886</span>  <span class="keyword">const</span> __m128i rk = _mm_set1_epi32(subkeys[rounds-1]);</div><div class="line"><a name="l00887"></a><span class="lineno"> 887</span>  y1 = _mm_xor_si128(_mm_xor_si128(y1, rk), SIMON64_f(x1));</div><div class="line"><a name="l00888"></a><span class="lineno"> 888</span>  rounds--;</div><div class="line"><a name="l00889"></a><span class="lineno"> 889</span>  }</div><div class="line"><a name="l00890"></a><span class="lineno"> 890</span> </div><div class="line"><a name="l00891"></a><span class="lineno"> 891</span>  <span class="keywordflow">for</span> (<span class="keywordtype">int</span> i = static_cast<int>(rounds-2); i >= 0; i -= 2)</div><div class="line"><a name="l00892"></a><span class="lineno"> 892</span>  {</div><div class="line"><a name="l00893"></a><span class="lineno"> 893</span>  <span class="keyword">const</span> __m128i rk1 = _mm_set1_epi32(subkeys[i+1]);</div><div class="line"><a name="l00894"></a><span class="lineno"> 894</span>  x1 = _mm_xor_si128(_mm_xor_si128(x1, SIMON64_f(y1)), rk1);</div><div class="line"><a name="l00895"></a><span class="lineno"> 895</span> </div><div class="line"><a name="l00896"></a><span class="lineno"> 896</span>  <span class="keyword">const</span> __m128i rk2 = _mm_set1_epi32(subkeys[i]);</div><div class="line"><a name="l00897"></a><span class="lineno"> 897</span>  y1 = _mm_xor_si128(_mm_xor_si128(y1, SIMON64_f(x1)), rk2);</div><div class="line"><a name="l00898"></a><span class="lineno"> 898</span>  }</div><div class="line"><a name="l00899"></a><span class="lineno"> 899</span> </div><div class="line"><a name="l00900"></a><span class="lineno"> 900</span>  <span class="comment">// The is roughly the SSE equivalent to ARM vzp32</span></div><div class="line"><a name="l00901"></a><span class="lineno"> 901</span>  <span class="comment">// [A1 A3 B1 B3][A2 A4 B2 B4] => [A1 A2 A3 A4][B1 B2 B3 B4]</span></div><div class="line"><a name="l00902"></a><span class="lineno"> 902</span>  block0 = _mm_unpacklo_epi32(y1, x1);</div><div class="line"><a name="l00903"></a><span class="lineno"> 903</span>  block1 = _mm_unpackhi_epi32(y1, x1);</div><div class="line"><a name="l00904"></a><span class="lineno"> 904</span> }</div><div class="line"><a name="l00905"></a><span class="lineno"> 905</span> </div><div class="line"><a name="l00906"></a><span class="lineno"> 906</span> <span class="keyword">inline</span> <span class="keywordtype">void</span> GCC_NO_UBSAN SIMON64_Enc_6_Blocks(__m128i &block0, __m128i &block1,</div><div class="line"><a name="l00907"></a><span class="lineno"> 907</span>  __m128i &block2, __m128i &block3, __m128i &block4, __m128i &block5,</div><div class="line"><a name="l00908"></a><span class="lineno"> 908</span>  <span class="keyword">const</span> word32 *subkeys, <span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> rounds)</div><div class="line"><a name="l00909"></a><span class="lineno"> 909</span> {</div><div class="line"><a name="l00910"></a><span class="lineno"> 910</span>  <span class="comment">// Rearrange the data for vectorization. The incoming data was read into</span></div><div class="line"><a name="l00911"></a><span class="lineno"> 911</span>  <span class="comment">// a little-endian word array. Depending on the number of blocks it needs to</span></div><div class="line"><a name="l00912"></a><span class="lineno"> 912</span>  <span class="comment">// be permuted to the following. Thanks to Peter Cordes for help with the</span></div><div class="line"><a name="l00913"></a><span class="lineno"> 913</span>  <span class="comment">// SSE permutes below.</span></div><div class="line"><a name="l00914"></a><span class="lineno"> 914</span>  <span class="comment">// [A1 A2 A3 A4][B1 B2 B3 B4] ... => [A1 A3 B1 B3][A2 A4 B2 B4] ...</span></div><div class="line"><a name="l00915"></a><span class="lineno"> 915</span>  <span class="keyword">const</span> __m128 t0 = _mm_castsi128_ps(block0);</div><div class="line"><a name="l00916"></a><span class="lineno"> 916</span>  <span class="keyword">const</span> __m128 t1 = _mm_castsi128_ps(block1);</div><div class="line"><a name="l00917"></a><span class="lineno"> 917</span>  __m128i x1 = _mm_castps_si128(_mm_shuffle_ps(t0, t1, _MM_SHUFFLE(3,1,3,1)));</div><div class="line"><a name="l00918"></a><span class="lineno"> 918</span>  __m128i y1 = _mm_castps_si128(_mm_shuffle_ps(t0, t1, _MM_SHUFFLE(2,0,2,0)));</div><div class="line"><a name="l00919"></a><span class="lineno"> 919</span> </div><div class="line"><a name="l00920"></a><span class="lineno"> 920</span>  <span class="keyword">const</span> __m128 t2 = _mm_castsi128_ps(block2);</div><div class="line"><a name="l00921"></a><span class="lineno"> 921</span>  <span class="keyword">const</span> __m128 t3 = _mm_castsi128_ps(block3);</div><div class="line"><a name="l00922"></a><span class="lineno"> 922</span>  __m128i x2 = _mm_castps_si128(_mm_shuffle_ps(t2, t3, _MM_SHUFFLE(3,1,3,1)));</div><div class="line"><a name="l00923"></a><span class="lineno"> 923</span>  __m128i y2 = _mm_castps_si128(_mm_shuffle_ps(t2, t3, _MM_SHUFFLE(2,0,2,0)));</div><div class="line"><a name="l00924"></a><span class="lineno"> 924</span> </div><div class="line"><a name="l00925"></a><span class="lineno"> 925</span>  <span class="keyword">const</span> __m128 t4 = _mm_castsi128_ps(block4);</div><div class="line"><a name="l00926"></a><span class="lineno"> 926</span>  <span class="keyword">const</span> __m128 t5 = _mm_castsi128_ps(block5);</div><div class="line"><a name="l00927"></a><span class="lineno"> 927</span>  __m128i x3 = _mm_castps_si128(_mm_shuffle_ps(t4, t5, _MM_SHUFFLE(3,1,3,1)));</div><div class="line"><a name="l00928"></a><span class="lineno"> 928</span>  __m128i y3 = _mm_castps_si128(_mm_shuffle_ps(t4, t5, _MM_SHUFFLE(2,0,2,0)));</div><div class="line"><a name="l00929"></a><span class="lineno"> 929</span> </div><div class="line"><a name="l00930"></a><span class="lineno"> 930</span>  <span class="keywordflow">for</span> (<span class="keywordtype">int</span> i = 0; i < static_cast<int>(rounds & ~1)-1; i += 2)</div><div class="line"><a name="l00931"></a><span class="lineno"> 931</span>  {</div><div class="line"><a name="l00932"></a><span class="lineno"> 932</span>  <span class="keyword">const</span> __m128i rk1 = _mm_set1_epi32(subkeys[i]);</div><div class="line"><a name="l00933"></a><span class="lineno"> 933</span>  y1 = _mm_xor_si128(_mm_xor_si128(y1, SIMON64_f(x1)), rk1);</div><div class="line"><a name="l00934"></a><span class="lineno"> 934</span>  y2 = _mm_xor_si128(_mm_xor_si128(y2, SIMON64_f(x2)), rk1);</div><div class="line"><a name="l00935"></a><span class="lineno"> 935</span>  y3 = _mm_xor_si128(_mm_xor_si128(y3, SIMON64_f(x3)), rk1);</div><div class="line"><a name="l00936"></a><span class="lineno"> 936</span> </div><div class="line"><a name="l00937"></a><span class="lineno"> 937</span>  <span class="keyword">const</span> __m128i rk2 = _mm_set1_epi32(subkeys[i+1]);</div><div class="line"><a name="l00938"></a><span class="lineno"> 938</span>  x1 = _mm_xor_si128(_mm_xor_si128(x1, SIMON64_f(y1)), rk2);</div><div class="line"><a name="l00939"></a><span class="lineno"> 939</span>  x2 = _mm_xor_si128(_mm_xor_si128(x2, SIMON64_f(y2)), rk2);</div><div class="line"><a name="l00940"></a><span class="lineno"> 940</span>  x3 = _mm_xor_si128(_mm_xor_si128(x3, SIMON64_f(y3)), rk2);</div><div class="line"><a name="l00941"></a><span class="lineno"> 941</span>  }</div><div class="line"><a name="l00942"></a><span class="lineno"> 942</span> </div><div class="line"><a name="l00943"></a><span class="lineno"> 943</span>  <span class="keywordflow">if</span> (rounds & 1)</div><div class="line"><a name="l00944"></a><span class="lineno"> 944</span>  {</div><div class="line"><a name="l00945"></a><span class="lineno"> 945</span>  <span class="keyword">const</span> __m128i rk = _mm_set1_epi32(subkeys[rounds-1]);</div><div class="line"><a name="l00946"></a><span class="lineno"> 946</span>  y1 = _mm_xor_si128(_mm_xor_si128(y1, SIMON64_f(x1)), rk);</div><div class="line"><a name="l00947"></a><span class="lineno"> 947</span>  y2 = _mm_xor_si128(_mm_xor_si128(y2, SIMON64_f(x2)), rk);</div><div class="line"><a name="l00948"></a><span class="lineno"> 948</span>  y3 = _mm_xor_si128(_mm_xor_si128(y3, SIMON64_f(x3)), rk);</div><div class="line"><a name="l00949"></a><span class="lineno"> 949</span>  Swap128(x1, y1); Swap128(x2, y2); Swap128(x3, y3);</div><div class="line"><a name="l00950"></a><span class="lineno"> 950</span>  }</div><div class="line"><a name="l00951"></a><span class="lineno"> 951</span> </div><div class="line"><a name="l00952"></a><span class="lineno"> 952</span>  <span class="comment">// The is roughly the SSE equivalent to ARM vzp32</span></div><div class="line"><a name="l00953"></a><span class="lineno"> 953</span>  <span class="comment">// [A1 A3 B1 B3][A2 A4 B2 B4] => [A1 A2 A3 A4][B1 B2 B3 B4]</span></div><div class="line"><a name="l00954"></a><span class="lineno"> 954</span>  block0 = _mm_unpacklo_epi32(y1, x1);</div><div class="line"><a name="l00955"></a><span class="lineno"> 955</span>  block1 = _mm_unpackhi_epi32(y1, x1);</div><div class="line"><a name="l00956"></a><span class="lineno"> 956</span>  block2 = _mm_unpacklo_epi32(y2, x2);</div><div class="line"><a name="l00957"></a><span class="lineno"> 957</span>  block3 = _mm_unpackhi_epi32(y2, x2);</div><div class="line"><a name="l00958"></a><span class="lineno"> 958</span>  block4 = _mm_unpacklo_epi32(y3, x3);</div><div class="line"><a name="l00959"></a><span class="lineno"> 959</span>  block5 = _mm_unpackhi_epi32(y3, x3);</div><div class="line"><a name="l00960"></a><span class="lineno"> 960</span> }</div><div class="line"><a name="l00961"></a><span class="lineno"> 961</span> </div><div class="line"><a name="l00962"></a><span class="lineno"> 962</span> <span class="keyword">inline</span> <span class="keywordtype">void</span> GCC_NO_UBSAN SIMON64_Dec_6_Blocks(__m128i &block0, __m128i &block1,</div><div class="line"><a name="l00963"></a><span class="lineno"> 963</span>  __m128i &block2, __m128i &block3, __m128i &block4, __m128i &block5,</div><div class="line"><a name="l00964"></a><span class="lineno"> 964</span>  <span class="keyword">const</span> word32 *subkeys, <span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> rounds)</div><div class="line"><a name="l00965"></a><span class="lineno"> 965</span> {</div><div class="line"><a name="l00966"></a><span class="lineno"> 966</span>  <span class="comment">// Rearrange the data for vectorization. The incoming data was read into</span></div><div class="line"><a name="l00967"></a><span class="lineno"> 967</span>  <span class="comment">// a little-endian word array. Depending on the number of blocks it needs to</span></div><div class="line"><a name="l00968"></a><span class="lineno"> 968</span>  <span class="comment">// be permuted to the following. Thanks to Peter Cordes for help with the</span></div><div class="line"><a name="l00969"></a><span class="lineno"> 969</span>  <span class="comment">// SSE permutes below.</span></div><div class="line"><a name="l00970"></a><span class="lineno"> 970</span>  <span class="comment">// [A1 A2 A3 A4][B1 B2 B3 B4] ... => [A1 A3 B1 B3][A2 A4 B2 B4] ...</span></div><div class="line"><a name="l00971"></a><span class="lineno"> 971</span>  <span class="keyword">const</span> __m128 t0 = _mm_castsi128_ps(block0);</div><div class="line"><a name="l00972"></a><span class="lineno"> 972</span>  <span class="keyword">const</span> __m128 t1 = _mm_castsi128_ps(block1);</div><div class="line"><a name="l00973"></a><span class="lineno"> 973</span>  __m128i x1 = _mm_castps_si128(_mm_shuffle_ps(t0, t1, _MM_SHUFFLE(3,1,3,1)));</div><div class="line"><a name="l00974"></a><span class="lineno"> 974</span>  __m128i y1 = _mm_castps_si128(_mm_shuffle_ps(t0, t1, _MM_SHUFFLE(2,0,2,0)));</div><div class="line"><a name="l00975"></a><span class="lineno"> 975</span> </div><div class="line"><a name="l00976"></a><span class="lineno"> 976</span>  <span class="keyword">const</span> __m128 t2 = _mm_castsi128_ps(block2);</div><div class="line"><a name="l00977"></a><span class="lineno"> 977</span>  <span class="keyword">const</span> __m128 t3 = _mm_castsi128_ps(block3);</div><div class="line"><a name="l00978"></a><span class="lineno"> 978</span>  __m128i x2 = _mm_castps_si128(_mm_shuffle_ps(t2, t3, _MM_SHUFFLE(3,1,3,1)));</div><div class="line"><a name="l00979"></a><span class="lineno"> 979</span>  __m128i y2 = _mm_castps_si128(_mm_shuffle_ps(t2, t3, _MM_SHUFFLE(2,0,2,0)));</div><div class="line"><a name="l00980"></a><span class="lineno"> 980</span> </div><div class="line"><a name="l00981"></a><span class="lineno"> 981</span>  <span class="keyword">const</span> __m128 t4 = _mm_castsi128_ps(block4);</div><div class="line"><a name="l00982"></a><span class="lineno"> 982</span>  <span class="keyword">const</span> __m128 t5 = _mm_castsi128_ps(block5);</div><div class="line"><a name="l00983"></a><span class="lineno"> 983</span>  __m128i x3 = _mm_castps_si128(_mm_shuffle_ps(t4, t5, _MM_SHUFFLE(3,1,3,1)));</div><div class="line"><a name="l00984"></a><span class="lineno"> 984</span>  __m128i y3 = _mm_castps_si128(_mm_shuffle_ps(t4, t5, _MM_SHUFFLE(2,0,2,0)));</div><div class="line"><a name="l00985"></a><span class="lineno"> 985</span> </div><div class="line"><a name="l00986"></a><span class="lineno"> 986</span>  <span class="keywordflow">if</span> (rounds & 1)</div><div class="line"><a name="l00987"></a><span class="lineno"> 987</span>  {</div><div class="line"><a name="l00988"></a><span class="lineno"> 988</span>  Swap128(x1, y1); Swap128(x2, y2); Swap128(x3, y3);</div><div class="line"><a name="l00989"></a><span class="lineno"> 989</span>  <span class="keyword">const</span> __m128i rk = _mm_set1_epi32(subkeys[rounds-1]);</div><div class="line"><a name="l00990"></a><span class="lineno"> 990</span>  y1 = _mm_xor_si128(_mm_xor_si128(y1, rk), SIMON64_f(x1));</div><div class="line"><a name="l00991"></a><span class="lineno"> 991</span>  y2 = _mm_xor_si128(_mm_xor_si128(y2, rk), SIMON64_f(x2));</div><div class="line"><a name="l00992"></a><span class="lineno"> 992</span>  y3 = _mm_xor_si128(_mm_xor_si128(y3, rk), SIMON64_f(x3));</div><div class="line"><a name="l00993"></a><span class="lineno"> 993</span>  rounds--;</div><div class="line"><a name="l00994"></a><span class="lineno"> 994</span>  }</div><div class="line"><a name="l00995"></a><span class="lineno"> 995</span> </div><div class="line"><a name="l00996"></a><span class="lineno"> 996</span>  <span class="keywordflow">for</span> (<span class="keywordtype">int</span> i = static_cast<int>(rounds-2); i >= 0; i -= 2)</div><div class="line"><a name="l00997"></a><span class="lineno"> 997</span>  {</div><div class="line"><a name="l00998"></a><span class="lineno"> 998</span>  <span class="keyword">const</span> __m128i rk1 = _mm_set1_epi32(subkeys[i+1]);</div><div class="line"><a name="l00999"></a><span class="lineno"> 999</span>  x1 = _mm_xor_si128(_mm_xor_si128(x1, SIMON64_f(y1)), rk1);</div><div class="line"><a name="l01000"></a><span class="lineno"> 1000</span>  x2 = _mm_xor_si128(_mm_xor_si128(x2, SIMON64_f(y2)), rk1);</div><div class="line"><a name="l01001"></a><span class="lineno"> 1001</span>  x3 = _mm_xor_si128(_mm_xor_si128(x3, SIMON64_f(y3)), rk1);</div><div class="line"><a name="l01002"></a><span class="lineno"> 1002</span> </div><div class="line"><a name="l01003"></a><span class="lineno"> 1003</span>  <span class="keyword">const</span> __m128i rk2 = _mm_set1_epi32(subkeys[i]);</div><div class="line"><a name="l01004"></a><span class="lineno"> 1004</span>  y1 = _mm_xor_si128(_mm_xor_si128(y1, SIMON64_f(x1)), rk2);</div><div class="line"><a name="l01005"></a><span class="lineno"> 1005</span>  y2 = _mm_xor_si128(_mm_xor_si128(y2, SIMON64_f(x2)), rk2);</div><div class="line"><a name="l01006"></a><span class="lineno"> 1006</span>  y3 = _mm_xor_si128(_mm_xor_si128(y3, SIMON64_f(x3)), rk2);</div><div class="line"><a name="l01007"></a><span class="lineno"> 1007</span>  }</div><div class="line"><a name="l01008"></a><span class="lineno"> 1008</span> </div><div class="line"><a name="l01009"></a><span class="lineno"> 1009</span>  <span class="comment">// The is roughly the SSE equivalent to ARM vzp32</span></div><div class="line"><a name="l01010"></a><span class="lineno"> 1010</span>  <span class="comment">// [A1 A3 B1 B3][A2 A4 B2 B4] => [A1 A2 A3 A4][B1 B2 B3 B4]</span></div><div class="line"><a name="l01011"></a><span class="lineno"> 1011</span>  block0 = _mm_unpacklo_epi32(y1, x1);</div><div class="line"><a name="l01012"></a><span class="lineno"> 1012</span>  block1 = _mm_unpackhi_epi32(y1, x1);</div><div class="line"><a name="l01013"></a><span class="lineno"> 1013</span>  block2 = _mm_unpacklo_epi32(y2, x2);</div><div class="line"><a name="l01014"></a><span class="lineno"> 1014</span>  block3 = _mm_unpackhi_epi32(y2, x2);</div><div class="line"><a name="l01015"></a><span class="lineno"> 1015</span>  block4 = _mm_unpacklo_epi32(y3, x3);</div><div class="line"><a name="l01016"></a><span class="lineno"> 1016</span>  block5 = _mm_unpackhi_epi32(y3, x3);</div><div class="line"><a name="l01017"></a><span class="lineno"> 1017</span> }</div><div class="line"><a name="l01018"></a><span class="lineno"> 1018</span> </div><div class="line"><a name="l01019"></a><span class="lineno"> 1019</span> <span class="preprocessor">#endif // CRYPTOPP_SSE41_AVAILABLE</span></div><div class="line"><a name="l01020"></a><span class="lineno"> 1020</span> </div><div class="line"><a name="l01021"></a><span class="lineno"> 1021</span> ANONYMOUS_NAMESPACE_END</div><div class="line"><a name="l01022"></a><span class="lineno"> 1022</span> <span class="comment"></span></div><div class="line"><a name="l01023"></a><span class="lineno"> 1023</span> <span class="comment">///////////////////////////////////////////////////////////////////////</span></div><div class="line"><a name="l01024"></a><span class="lineno"> 1024</span> <span class="comment"></span></div><div class="line"><a name="l01025"></a><span class="lineno"> 1025</span> NAMESPACE_BEGIN(<a class="code" href="namespace_crypto_p_p.html">CryptoPP</a>)</div><div class="line"><a name="l01026"></a><span class="lineno"> 1026</span> </div><div class="line"><a name="l01027"></a><span class="lineno"> 1027</span> <span class="comment">// *************************** ARM NEON **************************** //</span></div><div class="line"><a name="l01028"></a><span class="lineno"> 1028</span> </div><div class="line"><a name="l01029"></a><span class="lineno"> 1029</span> <span class="preprocessor">#if (CRYPTOPP_ARM_NEON_AVAILABLE)</span></div><div class="line"><a name="l01030"></a><span class="lineno"> 1030</span> <span class="keywordtype">size_t</span> SIMON64_Enc_AdvancedProcessBlocks_NEON(<span class="keyword">const</span> word32* subKeys, <span class="keywordtype">size_t</span> rounds,</div><div class="line"><a name="l01031"></a><span class="lineno"> 1031</span>  <span class="keyword">const</span> byte *inBlocks, <span class="keyword">const</span> byte *xorBlocks, byte *outBlocks, <span class="keywordtype">size_t</span> length, word32 flags)</div><div class="line"><a name="l01032"></a><span class="lineno"> 1032</span> {</div><div class="line"><a name="l01033"></a><span class="lineno"> 1033</span>  <span class="keywordflow">return</span> AdvancedProcessBlocks64_6x2_NEON(SIMON64_Enc_Block, SIMON64_Enc_6_Blocks,</div><div class="line"><a name="l01034"></a><span class="lineno"> 1034</span>  subKeys, rounds, inBlocks, xorBlocks, outBlocks, length, flags);</div><div class="line"><a name="l01035"></a><span class="lineno"> 1035</span> }</div><div class="line"><a name="l01036"></a><span class="lineno"> 1036</span> </div><div class="line"><a name="l01037"></a><span class="lineno"> 1037</span> <span class="keywordtype">size_t</span> SIMON64_Dec_AdvancedProcessBlocks_NEON(<span class="keyword">const</span> word32* subKeys, <span class="keywordtype">size_t</span> rounds,</div><div class="line"><a name="l01038"></a><span class="lineno"> 1038</span>  <span class="keyword">const</span> byte *inBlocks, <span class="keyword">const</span> byte *xorBlocks, byte *outBlocks, <span class="keywordtype">size_t</span> length, word32 flags)</div><div class="line"><a name="l01039"></a><span class="lineno"> 1039</span> {</div><div class="line"><a name="l01040"></a><span class="lineno"> 1040</span>  <span class="keywordflow">return</span> AdvancedProcessBlocks64_6x2_NEON(SIMON64_Dec_Block, SIMON64_Dec_6_Blocks,</div><div class="line"><a name="l01041"></a><span class="lineno"> 1041</span>  subKeys, rounds, inBlocks, xorBlocks, outBlocks, length, flags);</div><div class="line"><a name="l01042"></a><span class="lineno"> 1042</span> }</div><div class="line"><a name="l01043"></a><span class="lineno"> 1043</span> <span class="preprocessor">#endif // CRYPTOPP_ARM_NEON_AVAILABLE</span></div><div class="line"><a name="l01044"></a><span class="lineno"> 1044</span> </div><div class="line"><a name="l01045"></a><span class="lineno"> 1045</span> <span class="preprocessor">#if (CRYPTOPP_ARM_NEON_AVAILABLE)</span></div><div class="line"><a name="l01046"></a><span class="lineno"> 1046</span> <span class="keywordtype">size_t</span> SIMON128_Enc_AdvancedProcessBlocks_NEON(<span class="keyword">const</span> word64* subKeys, <span class="keywordtype">size_t</span> rounds,</div><div class="line"><a name="l01047"></a><span class="lineno"> 1047</span>  <span class="keyword">const</span> byte *inBlocks, <span class="keyword">const</span> byte *xorBlocks, byte *outBlocks, <span class="keywordtype">size_t</span> length, word32 flags)</div><div class="line"><a name="l01048"></a><span class="lineno"> 1048</span> {</div><div class="line"><a name="l01049"></a><span class="lineno"> 1049</span>  <span class="keywordflow">return</span> AdvancedProcessBlocks128_6x2_NEON(SIMON128_Enc_Block, SIMON128_Enc_6_Blocks,</div><div class="line"><a name="l01050"></a><span class="lineno"> 1050</span>  subKeys, rounds, inBlocks, xorBlocks, outBlocks, length, flags);</div><div class="line"><a name="l01051"></a><span class="lineno"> 1051</span> }</div><div class="line"><a name="l01052"></a><span class="lineno"> 1052</span> </div><div class="line"><a name="l01053"></a><span class="lineno"> 1053</span> <span class="keywordtype">size_t</span> SIMON128_Dec_AdvancedProcessBlocks_NEON(<span class="keyword">const</span> word64* subKeys, <span class="keywordtype">size_t</span> rounds,</div><div class="line"><a name="l01054"></a><span class="lineno"> 1054</span>  <span class="keyword">const</span> byte *inBlocks, <span class="keyword">const</span> byte *xorBlocks, byte *outBlocks, <span class="keywordtype">size_t</span> length, word32 flags)</div><div class="line"><a name="l01055"></a><span class="lineno"> 1055</span> {</div><div class="line"><a name="l01056"></a><span class="lineno"> 1056</span>  <span class="keywordflow">return</span> AdvancedProcessBlocks128_6x2_NEON(SIMON128_Dec_Block, SIMON128_Dec_6_Blocks,</div><div class="line"><a name="l01057"></a><span class="lineno"> 1057</span>  subKeys, rounds, inBlocks, xorBlocks, outBlocks, length, flags);</div><div class="line"><a name="l01058"></a><span class="lineno"> 1058</span> }</div><div class="line"><a name="l01059"></a><span class="lineno"> 1059</span> <span class="preprocessor">#endif // CRYPTOPP_ARM_NEON_AVAILABLE</span></div><div class="line"><a name="l01060"></a><span class="lineno"> 1060</span> </div><div class="line"><a name="l01061"></a><span class="lineno"> 1061</span> <span class="comment">// ***************************** IA-32 ***************************** //</span></div><div class="line"><a name="l01062"></a><span class="lineno"> 1062</span> </div><div class="line"><a name="l01063"></a><span class="lineno"> 1063</span> <span class="preprocessor">#if defined(CRYPTOPP_SSE41_AVAILABLE)</span></div><div class="line"><a name="l01064"></a><span class="lineno"> 1064</span> <span class="keywordtype">size_t</span> SIMON64_Enc_AdvancedProcessBlocks_SSE41(<span class="keyword">const</span> word32* subKeys, <span class="keywordtype">size_t</span> rounds,</div><div class="line"><a name="l01065"></a><span class="lineno"> 1065</span>  <span class="keyword">const</span> byte *inBlocks, <span class="keyword">const</span> byte *xorBlocks, byte *outBlocks, <span class="keywordtype">size_t</span> length, word32 flags)</div><div class="line"><a name="l01066"></a><span class="lineno"> 1066</span> {</div><div class="line"><a name="l01067"></a><span class="lineno"> 1067</span>  <span class="keywordflow">return</span> AdvancedProcessBlocks64_6x2_SSE(SIMON64_Enc_Block, SIMON64_Enc_6_Blocks,</div><div class="line"><a name="l01068"></a><span class="lineno"> 1068</span>  subKeys, rounds, inBlocks, xorBlocks, outBlocks, length, flags);</div><div class="line"><a name="l01069"></a><span class="lineno"> 1069</span> }</div><div class="line"><a name="l01070"></a><span class="lineno"> 1070</span> </div><div class="line"><a name="l01071"></a><span class="lineno"> 1071</span> <span class="keywordtype">size_t</span> SIMON64_Dec_AdvancedProcessBlocks_SSE41(<span class="keyword">const</span> word32* subKeys, <span class="keywordtype">size_t</span> rounds,</div><div class="line"><a name="l01072"></a><span class="lineno"> 1072</span>  <span class="keyword">const</span> byte *inBlocks, <span class="keyword">const</span> byte *xorBlocks, byte *outBlocks, <span class="keywordtype">size_t</span> length, word32 flags)</div><div class="line"><a name="l01073"></a><span class="lineno"> 1073</span> {</div><div class="line"><a name="l01074"></a><span class="lineno"> 1074</span>  <span class="keywordflow">return</span> AdvancedProcessBlocks64_6x2_SSE(SIMON64_Dec_Block, SIMON64_Dec_6_Blocks,</div><div class="line"><a name="l01075"></a><span class="lineno"> 1075</span>  subKeys, rounds, inBlocks, xorBlocks, outBlocks, length, flags);</div><div class="line"><a name="l01076"></a><span class="lineno"> 1076</span> }</div><div class="line"><a name="l01077"></a><span class="lineno"> 1077</span> <span class="preprocessor">#endif</span></div><div class="line"><a name="l01078"></a><span class="lineno"> 1078</span> </div><div class="line"><a name="l01079"></a><span class="lineno"> 1079</span> <span class="preprocessor">#if defined(CRYPTOPP_SSSE3_AVAILABLE)</span></div><div class="line"><a name="l01080"></a><span class="lineno"> 1080</span> <span class="keywordtype">size_t</span> SIMON128_Enc_AdvancedProcessBlocks_SSSE3(<span class="keyword">const</span> word64* subKeys, <span class="keywordtype">size_t</span> rounds,</div><div class="line"><a name="l01081"></a><span class="lineno"> 1081</span>  <span class="keyword">const</span> byte *inBlocks, <span class="keyword">const</span> byte *xorBlocks, byte *outBlocks, <span class="keywordtype">size_t</span> length, word32 flags)</div><div class="line"><a name="l01082"></a><span class="lineno"> 1082</span> {</div><div class="line"><a name="l01083"></a><span class="lineno"> 1083</span>  <span class="keywordflow">return</span> AdvancedProcessBlocks128_6x2_SSE(SIMON128_Enc_Block, SIMON128_Enc_6_Blocks,</div><div class="line"><a name="l01084"></a><span class="lineno"> 1084</span>  subKeys, rounds, inBlocks, xorBlocks, outBlocks, length, flags);</div><div class="line"><a name="l01085"></a><span class="lineno"> 1085</span> }</div><div class="line"><a name="l01086"></a><span class="lineno"> 1086</span> </div><div class="line"><a name="l01087"></a><span class="lineno"> 1087</span> <span class="keywordtype">size_t</span> SIMON128_Dec_AdvancedProcessBlocks_SSSE3(<span class="keyword">const</span> word64* subKeys, <span class="keywordtype">size_t</span> rounds,</div><div class="line"><a name="l01088"></a><span class="lineno"> 1088</span>  <span class="keyword">const</span> byte *inBlocks, <span class="keyword">const</span> byte *xorBlocks, byte *outBlocks, <span class="keywordtype">size_t</span> length, word32 flags)</div><div class="line"><a name="l01089"></a><span class="lineno"> 1089</span> {</div><div class="line"><a name="l01090"></a><span class="lineno"> 1090</span>  <span class="keywordflow">return</span> AdvancedProcessBlocks128_6x2_SSE(SIMON128_Dec_Block, SIMON128_Dec_6_Blocks,</div><div class="line"><a name="l01091"></a><span class="lineno"> 1091</span>  subKeys, rounds, inBlocks, xorBlocks, outBlocks, length, flags);</div><div class="line"><a name="l01092"></a><span class="lineno"> 1092</span> }</div><div class="line"><a name="l01093"></a><span class="lineno"> 1093</span> <span class="preprocessor">#endif // CRYPTOPP_SSSE3_AVAILABLE</span></div><div class="line"><a name="l01094"></a><span class="lineno"> 1094</span> </div><div class="line"><a name="l01095"></a><span class="lineno"> 1095</span> NAMESPACE_END</div><div class="ttc" id="misc_8h_html"><div class="ttname"><a href="misc_8h.html">misc.h</a></div><div class="ttdoc">Utility functions for the Crypto++ library. </div></div> <div class="ttc" id="misc_8h_html_aaf7b80a08d25ab9d62693c9e4798ef98"><div class="ttname"><a href="misc_8h.html#aaf7b80a08d25ab9d62693c9e4798ef98">rotlFixed</a></div><div class="ttdeci">T rotlFixed(T x, unsigned int y)</div><div class="ttdoc">Performs a left rotate. </div><div class="ttdef"><b>Definition:</b> <a href="misc_8h_source.html#l01416">misc.h:1416</a></div></div> <div class="ttc" id="config_8h_html"><div class="ttname"><a href="config_8h.html">config.h</a></div><div class="ttdoc">Library configuration file. </div></div> <div class="ttc" id="pch_8h_html"><div class="ttname"><a href="pch_8h.html">pch.h</a></div><div class="ttdoc">Precompiled header file. </div></div> <div class="ttc" id="simon_8h_html"><div class="ttname"><a href="simon_8h.html">simon.h</a></div><div class="ttdoc">Classes for the Simon block cipher. </div></div> <div class="ttc" id="namespace_crypto_p_p_html"><div class="ttname"><a href="namespace_crypto_p_p.html">CryptoPP</a></div><div class="ttdoc">Crypto++ library namespace. </div></div> <div class="ttc" id="misc_8h_html_abf88e95400925b89c94641916535b6da"><div class="ttname"><a href="misc_8h.html#abf88e95400925b89c94641916535b6da">rotrFixed</a></div><div class="ttdeci">T rotrFixed(T x, unsigned int y)</div><div class="ttdoc">Performs a right rotate. </div><div class="ttdef"><b>Definition:</b> <a href="misc_8h_source.html#l01441">misc.h:1441</a></div></div> <div class="ttc" id="misc_8h_html_a810542d642def73fd278c08092417e11"><div class="ttname"><a href="misc_8h.html#a810542d642def73fd278c08092417e11">vec_swap</a></div><div class="ttdeci">void vec_swap(T &a, T &b)</div><div class="ttdoc">Swaps two variables which are arrays. </div><div class="ttdef"><b>Definition:</b> <a href="misc_8h_source.html#l00471">misc.h:471</a></div></div> </div><!-- fragment --></div><!-- contents --> <!-- start footer part --> <hr class="footer"/><address class="footer"><small> Generated on Sun Sep 16 2018 07:58:05 for Crypto++ by  <a href="http://www.doxygen.org/index.html"> <img class="footer" src="doxygen.png" alt="doxygen"/> </a> 1.8.14 </small></address> </body> </html>