<!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++: sha-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">sha-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">// sha-simd.cpp - written and placed in the public domain by</span></div><div class="line"><a name="l00002"></a><span class="lineno"> 2</span> <span class="comment">// Jeffrey Walton, Uri Blumenthal and Marcel Raad.</span></div><div class="line"><a name="l00003"></a><span class="lineno"> 3</span> <span class="comment">//</span></div><div class="line"><a name="l00004"></a><span class="lineno"> 4</span> <span class="comment">// This source file uses intrinsics to gain access to SHA-NI and</span></div><div class="line"><a name="l00005"></a><span class="lineno"> 5</span> <span class="comment">// ARMv8a SHA instructions. A separate source file is needed</span></div><div class="line"><a name="l00006"></a><span class="lineno"> 6</span> <span class="comment">// because additional CXXFLAGS are required to enable the</span></div><div class="line"><a name="l00007"></a><span class="lineno"> 7</span> <span class="comment">// appropriate instructions sets in some build configurations.</span></div><div class="line"><a name="l00008"></a><span class="lineno"> 8</span> </div><div class="line"><a name="l00009"></a><span class="lineno"> 9</span> <span class="preprocessor">#include "<a class="code" href="pch_8h.html">pch.h</a>"</span></div><div class="line"><a name="l00010"></a><span class="lineno"> 10</span> <span class="preprocessor">#include "<a class="code" href="config_8h.html">config.h</a>"</span></div><div class="line"><a name="l00011"></a><span class="lineno"> 11</span> <span class="preprocessor">#include "<a class="code" href="sha_8h.html">sha.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> </div><div class="line"><a name="l00014"></a><span class="lineno"> 14</span> <span class="preprocessor">#if (CRYPTOPP_SHANI_AVAILABLE)</span></div><div class="line"><a name="l00015"></a><span class="lineno"> 15</span> <span class="preprocessor"># include <nmmintrin.h></span></div><div class="line"><a name="l00016"></a><span class="lineno"> 16</span> <span class="preprocessor"># include <immintrin.h></span></div><div class="line"><a name="l00017"></a><span class="lineno"> 17</span> <span class="preprocessor">#endif</span></div><div class="line"><a name="l00018"></a><span class="lineno"> 18</span> </div><div class="line"><a name="l00019"></a><span class="lineno"> 19</span> <span class="comment">// Use ARMv8 rather than NEON due to compiler inconsistencies</span></div><div class="line"><a name="l00020"></a><span class="lineno"> 20</span> <span class="preprocessor">#if (CRYPTOPP_ARM_SHA_AVAILABLE)</span></div><div class="line"><a name="l00021"></a><span class="lineno"> 21</span> <span class="preprocessor"># include <arm_neon.h></span></div><div class="line"><a name="l00022"></a><span class="lineno"> 22</span> <span class="preprocessor">#endif</span></div><div class="line"><a name="l00023"></a><span class="lineno"> 23</span> </div><div class="line"><a name="l00024"></a><span class="lineno"> 24</span> <span class="comment">// Can't use CRYPTOPP_ARM_XXX_AVAILABLE because too many</span></div><div class="line"><a name="l00025"></a><span class="lineno"> 25</span> <span class="comment">// compilers don't follow ACLE conventions for the include.</span></div><div class="line"><a name="l00026"></a><span class="lineno"> 26</span> <span class="preprocessor">#if defined(CRYPTOPP_ARM_ACLE_AVAILABLE)</span></div><div class="line"><a name="l00027"></a><span class="lineno"> 27</span> <span class="preprocessor"># include <stdint.h></span></div><div class="line"><a name="l00028"></a><span class="lineno"> 28</span> <span class="preprocessor"># include <arm_acle.h></span></div><div class="line"><a name="l00029"></a><span class="lineno"> 29</span> <span class="preprocessor">#endif</span></div><div class="line"><a name="l00030"></a><span class="lineno"> 30</span> </div><div class="line"><a name="l00031"></a><span class="lineno"> 31</span> <span class="preprocessor">#if CRYPTOPP_POWER8_SHA_AVAILABLE</span></div><div class="line"><a name="l00032"></a><span class="lineno"> 32</span> <span class="preprocessor"># include "<a class="code" href="ppc-simd_8h.html">ppc-simd.h</a>"</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">#ifdef CRYPTOPP_GNU_STYLE_INLINE_ASSEMBLY</span></div><div class="line"><a name="l00036"></a><span class="lineno"> 36</span> <span class="preprocessor"># include <signal.h></span></div><div class="line"><a name="l00037"></a><span class="lineno"> 37</span> <span class="preprocessor"># include <setjmp.h></span></div><div class="line"><a name="l00038"></a><span class="lineno"> 38</span> <span class="preprocessor">#endif</span></div><div class="line"><a name="l00039"></a><span class="lineno"> 39</span> </div><div class="line"><a name="l00040"></a><span class="lineno"> 40</span> <span class="preprocessor">#ifndef EXCEPTION_EXECUTE_HANDLER</span></div><div class="line"><a name="l00041"></a><span class="lineno"> 41</span> <span class="preprocessor"># define EXCEPTION_EXECUTE_HANDLER 1</span></div><div class="line"><a name="l00042"></a><span class="lineno"> 42</span> <span class="preprocessor">#endif</span></div><div class="line"><a name="l00043"></a><span class="lineno"> 43</span> </div><div class="line"><a name="l00044"></a><span class="lineno"> 44</span> <span class="comment">// Clang __m128i casts</span></div><div class="line"><a name="l00045"></a><span class="lineno"> 45</span> <span class="preprocessor">#define M128_CAST(x) ((__m128i *)(void *)(x))</span></div><div class="line"><a name="l00046"></a><span class="lineno"> 46</span> <span class="preprocessor">#define CONST_M128_CAST(x) ((const __m128i *)(const void *)(x))</span></div><div class="line"><a name="l00047"></a><span class="lineno"> 47</span> </div><div class="line"><a name="l00048"></a><span class="lineno"> 48</span> NAMESPACE_BEGIN(<a class="code" href="namespace_crypto_p_p.html">CryptoPP</a>)</div><div class="line"><a name="l00049"></a><span class="lineno"> 49</span> </div><div class="line"><a name="l00050"></a><span class="lineno"> 50</span> <span class="comment">// ***************** SIGILL probes ********************</span></div><div class="line"><a name="l00051"></a><span class="lineno"> 51</span> </div><div class="line"><a name="l00052"></a><span class="lineno"> 52</span> <span class="preprocessor">#ifdef CRYPTOPP_GNU_STYLE_INLINE_ASSEMBLY</span></div><div class="line"><a name="l00053"></a><span class="lineno"> 53</span> <span class="keyword">extern</span> <span class="stringliteral">"C"</span> {</div><div class="line"><a name="l00054"></a><span class="lineno"> 54</span>  <span class="keyword">typedef</span> void (*SigHandler)(int);</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">static</span> jmp_buf s_jmpSIGILL;</div><div class="line"><a name="l00057"></a><span class="lineno"> 57</span>  <span class="keyword">static</span> <span class="keywordtype">void</span> SigIllHandler(<span class="keywordtype">int</span>)</div><div class="line"><a name="l00058"></a><span class="lineno"> 58</span>  {</div><div class="line"><a name="l00059"></a><span class="lineno"> 59</span>  longjmp(s_jmpSIGILL, 1);</div><div class="line"><a name="l00060"></a><span class="lineno"> 60</span>  }</div><div class="line"><a name="l00061"></a><span class="lineno"> 61</span> }</div><div class="line"><a name="l00062"></a><span class="lineno"> 62</span> <span class="preprocessor">#endif // Not CRYPTOPP_MS_STYLE_INLINE_ASSEMBLY</span></div><div class="line"><a name="l00063"></a><span class="lineno"> 63</span> </div><div class="line"><a name="l00064"></a><span class="lineno"> 64</span> <span class="preprocessor">#if (CRYPTOPP_BOOL_ARM32 || CRYPTOPP_BOOL_ARM64)</span></div><div class="line"><a name="l00065"></a><span class="lineno"> 65</span> <span class="keywordtype">bool</span> CPU_ProbeSHA1()</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="preprocessor">#if defined(CRYPTOPP_NO_CPU_FEATURE_PROBES)</span></div><div class="line"><a name="l00068"></a><span class="lineno"> 68</span>  <span class="keywordflow">return</span> <span class="keyword">false</span>;</div><div class="line"><a name="l00069"></a><span class="lineno"> 69</span> <span class="preprocessor">#elif (CRYPTOPP_ARM_SHA_AVAILABLE)</span></div><div class="line"><a name="l00070"></a><span class="lineno"> 70</span> <span class="preprocessor"># if defined(CRYPTOPP_MS_STYLE_INLINE_ASSEMBLY)</span></div><div class="line"><a name="l00071"></a><span class="lineno"> 71</span>  <span class="keyword">volatile</span> <span class="keywordtype">bool</span> result = <span class="keyword">true</span>;</div><div class="line"><a name="l00072"></a><span class="lineno"> 72</span>  __try</div><div class="line"><a name="l00073"></a><span class="lineno"> 73</span>  {</div><div class="line"><a name="l00074"></a><span class="lineno"> 74</span>  uint32x4_t data1 = {1,2,3,4}, data2 = {5,6,7,8}, data3 = {9,10,11,12};</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>  uint32x4_t r1 = vsha1cq_u32 (data1, 0, data2);</div><div class="line"><a name="l00077"></a><span class="lineno"> 77</span>  uint32x4_t r2 = vsha1mq_u32 (data1, 0, data2);</div><div class="line"><a name="l00078"></a><span class="lineno"> 78</span>  uint32x4_t r3 = vsha1pq_u32 (data1, 0, data2);</div><div class="line"><a name="l00079"></a><span class="lineno"> 79</span>  uint32x4_t r4 = vsha1su0q_u32 (data1, data2, data3);</div><div class="line"><a name="l00080"></a><span class="lineno"> 80</span>  uint32x4_t r5 = vsha1su1q_u32 (data1, data2);</div><div class="line"><a name="l00081"></a><span class="lineno"> 81</span> </div><div class="line"><a name="l00082"></a><span class="lineno"> 82</span>  result = !!(vgetq_lane_u32(r1,0) | vgetq_lane_u32(r2,1) | vgetq_lane_u32(r3,2) | vgetq_lane_u32(r4,3) | vgetq_lane_u32(r5,0));</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>  __except (EXCEPTION_EXECUTE_HANDLER)</div><div class="line"><a name="l00085"></a><span class="lineno"> 85</span>  {</div><div class="line"><a name="l00086"></a><span class="lineno"> 86</span>  <span class="keywordflow">return</span> <span class="keyword">false</span>;</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="keywordflow">return</span> result;</div><div class="line"><a name="l00089"></a><span class="lineno"> 89</span> <span class="preprocessor"># else</span></div><div class="line"><a name="l00090"></a><span class="lineno"> 90</span> </div><div class="line"><a name="l00091"></a><span class="lineno"> 91</span>  <span class="comment">// longjmp and clobber warnings. Volatile is required.</span></div><div class="line"><a name="l00092"></a><span class="lineno"> 92</span>  <span class="comment">// http://github.com/weidai11/cryptopp/issues/24 and http://stackoverflow.com/q/7721854</span></div><div class="line"><a name="l00093"></a><span class="lineno"> 93</span>  <span class="keyword">volatile</span> <span class="keywordtype">bool</span> result = <span class="keyword">true</span>;</div><div class="line"><a name="l00094"></a><span class="lineno"> 94</span> </div><div class="line"><a name="l00095"></a><span class="lineno"> 95</span>  <span class="keyword">volatile</span> SigHandler oldHandler = signal(SIGILL, SigIllHandler);</div><div class="line"><a name="l00096"></a><span class="lineno"> 96</span>  <span class="keywordflow">if</span> (oldHandler == SIG_ERR)</div><div class="line"><a name="l00097"></a><span class="lineno"> 97</span>  <span class="keywordflow">return</span> <span class="keyword">false</span>;</div><div class="line"><a name="l00098"></a><span class="lineno"> 98</span> </div><div class="line"><a name="l00099"></a><span class="lineno"> 99</span>  <span class="keyword">volatile</span> sigset_t oldMask;</div><div class="line"><a name="l00100"></a><span class="lineno"> 100</span>  <span class="keywordflow">if</span> (sigprocmask(0, NULLPTR, (sigset_t*)&oldMask))</div><div class="line"><a name="l00101"></a><span class="lineno"> 101</span>  <span class="keywordflow">return</span> <span class="keyword">false</span>;</div><div class="line"><a name="l00102"></a><span class="lineno"> 102</span> </div><div class="line"><a name="l00103"></a><span class="lineno"> 103</span>  <span class="keywordflow">if</span> (setjmp(s_jmpSIGILL))</div><div class="line"><a name="l00104"></a><span class="lineno"> 104</span>  result = <span class="keyword">false</span>;</div><div class="line"><a name="l00105"></a><span class="lineno"> 105</span>  <span class="keywordflow">else</span></div><div class="line"><a name="l00106"></a><span class="lineno"> 106</span>  {</div><div class="line"><a name="l00107"></a><span class="lineno"> 107</span>  uint32x4_t data1 = {1,2,3,4}, data2 = {5,6,7,8}, data3 = {9,10,11,12};</div><div class="line"><a name="l00108"></a><span class="lineno"> 108</span> </div><div class="line"><a name="l00109"></a><span class="lineno"> 109</span>  uint32x4_t r1 = vsha1cq_u32 (data1, 0, data2);</div><div class="line"><a name="l00110"></a><span class="lineno"> 110</span>  uint32x4_t r2 = vsha1mq_u32 (data1, 0, data2);</div><div class="line"><a name="l00111"></a><span class="lineno"> 111</span>  uint32x4_t r3 = vsha1pq_u32 (data1, 0, data2);</div><div class="line"><a name="l00112"></a><span class="lineno"> 112</span>  uint32x4_t r4 = vsha1su0q_u32 (data1, data2, data3);</div><div class="line"><a name="l00113"></a><span class="lineno"> 113</span>  uint32x4_t r5 = vsha1su1q_u32 (data1, data2);</div><div class="line"><a name="l00114"></a><span class="lineno"> 114</span> </div><div class="line"><a name="l00115"></a><span class="lineno"> 115</span>  result = !!(vgetq_lane_u32(r1,0) | vgetq_lane_u32(r2,1) | vgetq_lane_u32(r3,2) | vgetq_lane_u32(r4,3) | vgetq_lane_u32(r5,0));</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>  sigprocmask(SIG_SETMASK, (sigset_t*)&oldMask, NULLPTR);</div><div class="line"><a name="l00119"></a><span class="lineno"> 119</span>  signal(SIGILL, oldHandler);</div><div class="line"><a name="l00120"></a><span class="lineno"> 120</span>  <span class="keywordflow">return</span> result;</div><div class="line"><a name="l00121"></a><span class="lineno"> 121</span> <span class="preprocessor"># endif</span></div><div class="line"><a name="l00122"></a><span class="lineno"> 122</span> <span class="preprocessor">#else</span></div><div class="line"><a name="l00123"></a><span class="lineno"> 123</span>  <span class="keywordflow">return</span> <span class="keyword">false</span>;</div><div class="line"><a name="l00124"></a><span class="lineno"> 124</span> <span class="preprocessor">#endif // CRYPTOPP_ARM_SHA_AVAILABLE</span></div><div class="line"><a name="l00125"></a><span class="lineno"> 125</span> }</div><div class="line"><a name="l00126"></a><span class="lineno"> 126</span> </div><div class="line"><a name="l00127"></a><span class="lineno"> 127</span> <span class="keywordtype">bool</span> CPU_ProbeSHA2()</div><div class="line"><a name="l00128"></a><span class="lineno"> 128</span> {</div><div class="line"><a name="l00129"></a><span class="lineno"> 129</span> <span class="preprocessor">#if defined(CRYPTOPP_NO_CPU_FEATURE_PROBES)</span></div><div class="line"><a name="l00130"></a><span class="lineno"> 130</span>  <span class="keywordflow">return</span> <span class="keyword">false</span>;</div><div class="line"><a name="l00131"></a><span class="lineno"> 131</span> <span class="preprocessor">#elif (CRYPTOPP_ARM_SHA_AVAILABLE)</span></div><div class="line"><a name="l00132"></a><span class="lineno"> 132</span> <span class="preprocessor"># if defined(CRYPTOPP_MS_STYLE_INLINE_ASSEMBLY)</span></div><div class="line"><a name="l00133"></a><span class="lineno"> 133</span>  <span class="keyword">volatile</span> <span class="keywordtype">bool</span> result = <span class="keyword">true</span>;</div><div class="line"><a name="l00134"></a><span class="lineno"> 134</span>  __try</div><div class="line"><a name="l00135"></a><span class="lineno"> 135</span>  {</div><div class="line"><a name="l00136"></a><span class="lineno"> 136</span>  uint32x4_t data1 = {1,2,3,4}, data2 = {5,6,7,8}, data3 = {9,10,11,12};</div><div class="line"><a name="l00137"></a><span class="lineno"> 137</span> </div><div class="line"><a name="l00138"></a><span class="lineno"> 138</span>  uint32x4_t r1 = vsha256hq_u32 (data1, data2, data3);</div><div class="line"><a name="l00139"></a><span class="lineno"> 139</span>  uint32x4_t r2 = vsha256h2q_u32 (data1, data2, data3);</div><div class="line"><a name="l00140"></a><span class="lineno"> 140</span>  uint32x4_t r3 = vsha256su0q_u32 (data1, data2);</div><div class="line"><a name="l00141"></a><span class="lineno"> 141</span>  uint32x4_t r4 = vsha256su1q_u32 (data1, data2, data3);</div><div class="line"><a name="l00142"></a><span class="lineno"> 142</span> </div><div class="line"><a name="l00143"></a><span class="lineno"> 143</span>  result = !!(vgetq_lane_u32(r1,0) | vgetq_lane_u32(r2,1) | vgetq_lane_u32(r3,2) | vgetq_lane_u32(r4,3));</div><div class="line"><a name="l00144"></a><span class="lineno"> 144</span>  }</div><div class="line"><a name="l00145"></a><span class="lineno"> 145</span>  __except (EXCEPTION_EXECUTE_HANDLER)</div><div class="line"><a name="l00146"></a><span class="lineno"> 146</span>  {</div><div class="line"><a name="l00147"></a><span class="lineno"> 147</span>  <span class="keywordflow">return</span> <span class="keyword">false</span>;</div><div class="line"><a name="l00148"></a><span class="lineno"> 148</span>  }</div><div class="line"><a name="l00149"></a><span class="lineno"> 149</span>  <span class="keywordflow">return</span> result;</div><div class="line"><a name="l00150"></a><span class="lineno"> 150</span> <span class="preprocessor">#else</span></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="comment">// longjmp and clobber warnings. Volatile is required.</span></div><div class="line"><a name="l00153"></a><span class="lineno"> 153</span>  <span class="comment">// http://github.com/weidai11/cryptopp/issues/24 and http://stackoverflow.com/q/7721854</span></div><div class="line"><a name="l00154"></a><span class="lineno"> 154</span>  <span class="keyword">volatile</span> <span class="keywordtype">bool</span> result = <span class="keyword">true</span>;</div><div class="line"><a name="l00155"></a><span class="lineno"> 155</span> </div><div class="line"><a name="l00156"></a><span class="lineno"> 156</span>  <span class="keyword">volatile</span> SigHandler oldHandler = signal(SIGILL, SigIllHandler);</div><div class="line"><a name="l00157"></a><span class="lineno"> 157</span>  <span class="keywordflow">if</span> (oldHandler == SIG_ERR)</div><div class="line"><a name="l00158"></a><span class="lineno"> 158</span>  <span class="keywordflow">return</span> <span class="keyword">false</span>;</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>  <span class="keyword">volatile</span> sigset_t oldMask;</div><div class="line"><a name="l00161"></a><span class="lineno"> 161</span>  <span class="keywordflow">if</span> (sigprocmask(0, NULLPTR, (sigset_t*)&oldMask))</div><div class="line"><a name="l00162"></a><span class="lineno"> 162</span>  <span class="keywordflow">return</span> <span class="keyword">false</span>;</div><div class="line"><a name="l00163"></a><span class="lineno"> 163</span> </div><div class="line"><a name="l00164"></a><span class="lineno"> 164</span>  <span class="keywordflow">if</span> (setjmp(s_jmpSIGILL))</div><div class="line"><a name="l00165"></a><span class="lineno"> 165</span>  result = <span class="keyword">false</span>;</div><div class="line"><a name="l00166"></a><span class="lineno"> 166</span>  <span class="keywordflow">else</span></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>  uint32x4_t data1 = {1,2,3,4}, data2 = {5,6,7,8}, data3 = {9,10,11,12};</div><div class="line"><a name="l00169"></a><span class="lineno"> 169</span> </div><div class="line"><a name="l00170"></a><span class="lineno"> 170</span>  uint32x4_t r1 = vsha256hq_u32 (data1, data2, data3);</div><div class="line"><a name="l00171"></a><span class="lineno"> 171</span>  uint32x4_t r2 = vsha256h2q_u32 (data1, data2, data3);</div><div class="line"><a name="l00172"></a><span class="lineno"> 172</span>  uint32x4_t r3 = vsha256su0q_u32 (data1, data2);</div><div class="line"><a name="l00173"></a><span class="lineno"> 173</span>  uint32x4_t r4 = vsha256su1q_u32 (data1, data2, data3);</div><div class="line"><a name="l00174"></a><span class="lineno"> 174</span> </div><div class="line"><a name="l00175"></a><span class="lineno"> 175</span>  result = !!(vgetq_lane_u32(r1,0) | vgetq_lane_u32(r2,1) | vgetq_lane_u32(r3,2) | vgetq_lane_u32(r4,3));</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> </div><div class="line"><a name="l00178"></a><span class="lineno"> 178</span>  sigprocmask(SIG_SETMASK, (sigset_t*)&oldMask, NULLPTR);</div><div class="line"><a name="l00179"></a><span class="lineno"> 179</span>  signal(SIGILL, oldHandler);</div><div class="line"><a name="l00180"></a><span class="lineno"> 180</span>  <span class="keywordflow">return</span> result;</div><div class="line"><a name="l00181"></a><span class="lineno"> 181</span> <span class="preprocessor"># endif</span></div><div class="line"><a name="l00182"></a><span class="lineno"> 182</span> <span class="preprocessor">#else</span></div><div class="line"><a name="l00183"></a><span class="lineno"> 183</span>  <span class="keywordflow">return</span> <span class="keyword">false</span>;</div><div class="line"><a name="l00184"></a><span class="lineno"> 184</span> <span class="preprocessor">#endif // CRYPTOPP_ARM_SHA_AVAILABLE</span></div><div class="line"><a name="l00185"></a><span class="lineno"> 185</span> }</div><div class="line"><a name="l00186"></a><span class="lineno"> 186</span> <span class="preprocessor">#endif // ARM32 or ARM64</span></div><div class="line"><a name="l00187"></a><span class="lineno"> 187</span> </div><div class="line"><a name="l00188"></a><span class="lineno"> 188</span> <span class="comment">// ***************** Intel x86 SHA ********************</span></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> <span class="comment">// provided by sha.cpp</span></div><div class="line"><a name="l00191"></a><span class="lineno"> 191</span> <span class="keyword">extern</span> <span class="keyword">const</span> word32 SHA256_K[64];</div><div class="line"><a name="l00192"></a><span class="lineno"> 192</span> <span class="keyword">extern</span> <span class="keyword">const</span> word64 SHA512_K[80];</div><div class="line"><a name="l00193"></a><span class="lineno"> 193</span> <span class="comment"></span></div><div class="line"><a name="l00194"></a><span class="lineno"> 194</span> <span class="comment">/////////////////////////////////////</span></div><div class="line"><a name="l00195"></a><span class="lineno"> 195</span> <span class="comment"></span><span class="comment">// start of Walton and Gulley code //</span><span class="comment"></span></div><div class="line"><a name="l00196"></a><span class="lineno"> 196</span> <span class="comment">/////////////////////////////////////</span></div><div class="line"><a name="l00197"></a><span class="lineno"> 197</span> <span class="comment"></span></div><div class="line"><a name="l00198"></a><span class="lineno"> 198</span> <span class="preprocessor">#if CRYPTOPP_SHANI_AVAILABLE</span></div><div class="line"><a name="l00199"></a><span class="lineno"> 199</span> <span class="comment">// Based on http://software.intel.com/en-us/articles/intel-sha-extensions and code by Sean Gulley.</span></div><div class="line"><a name="l00200"></a><span class="lineno"> 200</span> <span class="keywordtype">void</span> SHA1_HashMultipleBlocks_SHANI(word32 *state, <span class="keyword">const</span> word32 *data, <span class="keywordtype">size_t</span> length, <a class="code" href="cryptlib_8h.html#aaeb92d42f5a6e27b8ba19f18d69d142b">ByteOrder</a> order)</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>  <a class="code" href="trap_8h.html#adf3b392588bc94cbeae9f415a78c7b95">CRYPTOPP_ASSERT</a>(state);</div><div class="line"><a name="l00203"></a><span class="lineno"> 203</span>  <a class="code" href="trap_8h.html#adf3b392588bc94cbeae9f415a78c7b95">CRYPTOPP_ASSERT</a>(data);</div><div class="line"><a name="l00204"></a><span class="lineno"> 204</span>  <a class="code" href="trap_8h.html#adf3b392588bc94cbeae9f415a78c7b95">CRYPTOPP_ASSERT</a>(length >= SHA1::BLOCKSIZE);</div><div class="line"><a name="l00205"></a><span class="lineno"> 205</span> </div><div class="line"><a name="l00206"></a><span class="lineno"> 206</span>  __m128i ABCD, ABCD_SAVE, E0, E0_SAVE, E1;</div><div class="line"><a name="l00207"></a><span class="lineno"> 207</span>  __m128i MASK, MSG0, MSG1, MSG2, MSG3;</div><div class="line"><a name="l00208"></a><span class="lineno"> 208</span> </div><div class="line"><a name="l00209"></a><span class="lineno"> 209</span>  <span class="comment">// Load initial values</span></div><div class="line"><a name="l00210"></a><span class="lineno"> 210</span>  ABCD = _mm_loadu_si128(CONST_M128_CAST(state));</div><div class="line"><a name="l00211"></a><span class="lineno"> 211</span>  E0 = _mm_set_epi32(state[4], 0, 0, 0);</div><div class="line"><a name="l00212"></a><span class="lineno"> 212</span>  ABCD = _mm_shuffle_epi32(ABCD, 0x1B);</div><div class="line"><a name="l00213"></a><span class="lineno"> 213</span> </div><div class="line"><a name="l00214"></a><span class="lineno"> 214</span>  <span class="comment">// IA-32 SHA is little endian, SHA::Transform is big endian,</span></div><div class="line"><a name="l00215"></a><span class="lineno"> 215</span>  <span class="comment">// and SHA::HashMultipleBlocks can be either. ByteOrder</span></div><div class="line"><a name="l00216"></a><span class="lineno"> 216</span>  <span class="comment">// allows us to avoid extra endian reversals. It saves 1.0 cpb.</span></div><div class="line"><a name="l00217"></a><span class="lineno"> 217</span>  MASK = order == <a class="code" href="cryptlib_8h.html#aaeb92d42f5a6e27b8ba19f18d69d142baf0c3bb6c718cc7ff0bffef4e8f178c57">BIG_ENDIAN_ORDER</a> ? <span class="comment">// Data arrangement</span></div><div class="line"><a name="l00218"></a><span class="lineno"> 218</span>  _mm_set_epi8(0,1,2,3, 4,5,6,7, 8,9,10,11, 12,13,14,15) :</div><div class="line"><a name="l00219"></a><span class="lineno"> 219</span>  _mm_set_epi8(3,2,1,0, 7,6,5,4, 11,10,9,8, 15,14,13,12) ;</div><div class="line"><a name="l00220"></a><span class="lineno"> 220</span> </div><div class="line"><a name="l00221"></a><span class="lineno"> 221</span>  <span class="keywordflow">while</span> (length >= SHA1::BLOCKSIZE)</div><div class="line"><a name="l00222"></a><span class="lineno"> 222</span>  {</div><div class="line"><a name="l00223"></a><span class="lineno"> 223</span>  <span class="comment">// Save current hash</span></div><div class="line"><a name="l00224"></a><span class="lineno"> 224</span>  ABCD_SAVE = ABCD;</div><div class="line"><a name="l00225"></a><span class="lineno"> 225</span>  E0_SAVE = E0;</div><div class="line"><a name="l00226"></a><span class="lineno"> 226</span> </div><div class="line"><a name="l00227"></a><span class="lineno"> 227</span>  <span class="comment">// Rounds 0-3</span></div><div class="line"><a name="l00228"></a><span class="lineno"> 228</span>  MSG0 = _mm_loadu_si128(CONST_M128_CAST(data+0));</div><div class="line"><a name="l00229"></a><span class="lineno"> 229</span>  MSG0 = _mm_shuffle_epi8(MSG0, MASK);</div><div class="line"><a name="l00230"></a><span class="lineno"> 230</span>  E0 = _mm_add_epi32(E0, MSG0);</div><div class="line"><a name="l00231"></a><span class="lineno"> 231</span>  E1 = ABCD;</div><div class="line"><a name="l00232"></a><span class="lineno"> 232</span>  ABCD = _mm_sha1rnds4_epu32(ABCD, E0, 0);</div><div class="line"><a name="l00233"></a><span class="lineno"> 233</span> </div><div class="line"><a name="l00234"></a><span class="lineno"> 234</span>  <span class="comment">// Rounds 4-7</span></div><div class="line"><a name="l00235"></a><span class="lineno"> 235</span>  MSG1 = _mm_loadu_si128(CONST_M128_CAST(data+4));</div><div class="line"><a name="l00236"></a><span class="lineno"> 236</span>  MSG1 = _mm_shuffle_epi8(MSG1, MASK);</div><div class="line"><a name="l00237"></a><span class="lineno"> 237</span>  E1 = _mm_sha1nexte_epu32(E1, MSG1);</div><div class="line"><a name="l00238"></a><span class="lineno"> 238</span>  E0 = ABCD;</div><div class="line"><a name="l00239"></a><span class="lineno"> 239</span>  ABCD = _mm_sha1rnds4_epu32(ABCD, E1, 0);</div><div class="line"><a name="l00240"></a><span class="lineno"> 240</span>  MSG0 = _mm_sha1msg1_epu32(MSG0, MSG1);</div><div class="line"><a name="l00241"></a><span class="lineno"> 241</span> </div><div class="line"><a name="l00242"></a><span class="lineno"> 242</span>  <span class="comment">// Rounds 8-11</span></div><div class="line"><a name="l00243"></a><span class="lineno"> 243</span>  MSG2 = _mm_loadu_si128(CONST_M128_CAST(data+8));</div><div class="line"><a name="l00244"></a><span class="lineno"> 244</span>  MSG2 = _mm_shuffle_epi8(MSG2, MASK);</div><div class="line"><a name="l00245"></a><span class="lineno"> 245</span>  E0 = _mm_sha1nexte_epu32(E0, MSG2);</div><div class="line"><a name="l00246"></a><span class="lineno"> 246</span>  E1 = ABCD;</div><div class="line"><a name="l00247"></a><span class="lineno"> 247</span>  ABCD = _mm_sha1rnds4_epu32(ABCD, E0, 0);</div><div class="line"><a name="l00248"></a><span class="lineno"> 248</span>  MSG1 = _mm_sha1msg1_epu32(MSG1, MSG2);</div><div class="line"><a name="l00249"></a><span class="lineno"> 249</span>  MSG0 = _mm_xor_si128(MSG0, MSG2);</div><div class="line"><a name="l00250"></a><span class="lineno"> 250</span> </div><div class="line"><a name="l00251"></a><span class="lineno"> 251</span>  <span class="comment">// Rounds 12-15</span></div><div class="line"><a name="l00252"></a><span class="lineno"> 252</span>  MSG3 = _mm_loadu_si128(CONST_M128_CAST(data+12));</div><div class="line"><a name="l00253"></a><span class="lineno"> 253</span>  MSG3 = _mm_shuffle_epi8(MSG3, MASK);</div><div class="line"><a name="l00254"></a><span class="lineno"> 254</span>  E1 = _mm_sha1nexte_epu32(E1, MSG3);</div><div class="line"><a name="l00255"></a><span class="lineno"> 255</span>  E0 = ABCD;</div><div class="line"><a name="l00256"></a><span class="lineno"> 256</span>  MSG0 = _mm_sha1msg2_epu32(MSG0, MSG3);</div><div class="line"><a name="l00257"></a><span class="lineno"> 257</span>  ABCD = _mm_sha1rnds4_epu32(ABCD, E1, 0);</div><div class="line"><a name="l00258"></a><span class="lineno"> 258</span>  MSG2 = _mm_sha1msg1_epu32(MSG2, MSG3);</div><div class="line"><a name="l00259"></a><span class="lineno"> 259</span>  MSG1 = _mm_xor_si128(MSG1, MSG3);</div><div class="line"><a name="l00260"></a><span class="lineno"> 260</span> </div><div class="line"><a name="l00261"></a><span class="lineno"> 261</span>  <span class="comment">// Rounds 16-19</span></div><div class="line"><a name="l00262"></a><span class="lineno"> 262</span>  E0 = _mm_sha1nexte_epu32(E0, MSG0);</div><div class="line"><a name="l00263"></a><span class="lineno"> 263</span>  E1 = ABCD;</div><div class="line"><a name="l00264"></a><span class="lineno"> 264</span>  MSG1 = _mm_sha1msg2_epu32(MSG1, MSG0);</div><div class="line"><a name="l00265"></a><span class="lineno"> 265</span>  ABCD = _mm_sha1rnds4_epu32(ABCD, E0, 0);</div><div class="line"><a name="l00266"></a><span class="lineno"> 266</span>  MSG3 = _mm_sha1msg1_epu32(MSG3, MSG0);</div><div class="line"><a name="l00267"></a><span class="lineno"> 267</span>  MSG2 = _mm_xor_si128(MSG2, MSG0);</div><div class="line"><a name="l00268"></a><span class="lineno"> 268</span> </div><div class="line"><a name="l00269"></a><span class="lineno"> 269</span>  <span class="comment">// Rounds 20-23</span></div><div class="line"><a name="l00270"></a><span class="lineno"> 270</span>  E1 = _mm_sha1nexte_epu32(E1, MSG1);</div><div class="line"><a name="l00271"></a><span class="lineno"> 271</span>  E0 = ABCD;</div><div class="line"><a name="l00272"></a><span class="lineno"> 272</span>  MSG2 = _mm_sha1msg2_epu32(MSG2, MSG1);</div><div class="line"><a name="l00273"></a><span class="lineno"> 273</span>  ABCD = _mm_sha1rnds4_epu32(ABCD, E1, 1);</div><div class="line"><a name="l00274"></a><span class="lineno"> 274</span>  MSG0 = _mm_sha1msg1_epu32(MSG0, MSG1);</div><div class="line"><a name="l00275"></a><span class="lineno"> 275</span>  MSG3 = _mm_xor_si128(MSG3, MSG1);</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>  <span class="comment">// Rounds 24-27</span></div><div class="line"><a name="l00278"></a><span class="lineno"> 278</span>  E0 = _mm_sha1nexte_epu32(E0, MSG2);</div><div class="line"><a name="l00279"></a><span class="lineno"> 279</span>  E1 = ABCD;</div><div class="line"><a name="l00280"></a><span class="lineno"> 280</span>  MSG3 = _mm_sha1msg2_epu32(MSG3, MSG2);</div><div class="line"><a name="l00281"></a><span class="lineno"> 281</span>  ABCD = _mm_sha1rnds4_epu32(ABCD, E0, 1);</div><div class="line"><a name="l00282"></a><span class="lineno"> 282</span>  MSG1 = _mm_sha1msg1_epu32(MSG1, MSG2);</div><div class="line"><a name="l00283"></a><span class="lineno"> 283</span>  MSG0 = _mm_xor_si128(MSG0, MSG2);</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="comment">// Rounds 28-31</span></div><div class="line"><a name="l00286"></a><span class="lineno"> 286</span>  E1 = _mm_sha1nexte_epu32(E1, MSG3);</div><div class="line"><a name="l00287"></a><span class="lineno"> 287</span>  E0 = ABCD;</div><div class="line"><a name="l00288"></a><span class="lineno"> 288</span>  MSG0 = _mm_sha1msg2_epu32(MSG0, MSG3);</div><div class="line"><a name="l00289"></a><span class="lineno"> 289</span>  ABCD = _mm_sha1rnds4_epu32(ABCD, E1, 1);</div><div class="line"><a name="l00290"></a><span class="lineno"> 290</span>  MSG2 = _mm_sha1msg1_epu32(MSG2, MSG3);</div><div class="line"><a name="l00291"></a><span class="lineno"> 291</span>  MSG1 = _mm_xor_si128(MSG1, MSG3);</div><div class="line"><a name="l00292"></a><span class="lineno"> 292</span> </div><div class="line"><a name="l00293"></a><span class="lineno"> 293</span>  <span class="comment">// Rounds 32-35</span></div><div class="line"><a name="l00294"></a><span class="lineno"> 294</span>  E0 = _mm_sha1nexte_epu32(E0, MSG0);</div><div class="line"><a name="l00295"></a><span class="lineno"> 295</span>  E1 = ABCD;</div><div class="line"><a name="l00296"></a><span class="lineno"> 296</span>  MSG1 = _mm_sha1msg2_epu32(MSG1, MSG0);</div><div class="line"><a name="l00297"></a><span class="lineno"> 297</span>  ABCD = _mm_sha1rnds4_epu32(ABCD, E0, 1);</div><div class="line"><a name="l00298"></a><span class="lineno"> 298</span>  MSG3 = _mm_sha1msg1_epu32(MSG3, MSG0);</div><div class="line"><a name="l00299"></a><span class="lineno"> 299</span>  MSG2 = _mm_xor_si128(MSG2, MSG0);</div><div class="line"><a name="l00300"></a><span class="lineno"> 300</span> </div><div class="line"><a name="l00301"></a><span class="lineno"> 301</span>  <span class="comment">// Rounds 36-39</span></div><div class="line"><a name="l00302"></a><span class="lineno"> 302</span>  E1 = _mm_sha1nexte_epu32(E1, MSG1);</div><div class="line"><a name="l00303"></a><span class="lineno"> 303</span>  E0 = ABCD;</div><div class="line"><a name="l00304"></a><span class="lineno"> 304</span>  MSG2 = _mm_sha1msg2_epu32(MSG2, MSG1);</div><div class="line"><a name="l00305"></a><span class="lineno"> 305</span>  ABCD = _mm_sha1rnds4_epu32(ABCD, E1, 1);</div><div class="line"><a name="l00306"></a><span class="lineno"> 306</span>  MSG0 = _mm_sha1msg1_epu32(MSG0, MSG1);</div><div class="line"><a name="l00307"></a><span class="lineno"> 307</span>  MSG3 = _mm_xor_si128(MSG3, MSG1);</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="comment">// Rounds 40-43</span></div><div class="line"><a name="l00310"></a><span class="lineno"> 310</span>  E0 = _mm_sha1nexte_epu32(E0, MSG2);</div><div class="line"><a name="l00311"></a><span class="lineno"> 311</span>  E1 = ABCD;</div><div class="line"><a name="l00312"></a><span class="lineno"> 312</span>  MSG3 = _mm_sha1msg2_epu32(MSG3, MSG2);</div><div class="line"><a name="l00313"></a><span class="lineno"> 313</span>  ABCD = _mm_sha1rnds4_epu32(ABCD, E0, 2);</div><div class="line"><a name="l00314"></a><span class="lineno"> 314</span>  MSG1 = _mm_sha1msg1_epu32(MSG1, MSG2);</div><div class="line"><a name="l00315"></a><span class="lineno"> 315</span>  MSG0 = _mm_xor_si128(MSG0, MSG2);</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="comment">// Rounds 44-47</span></div><div class="line"><a name="l00318"></a><span class="lineno"> 318</span>  E1 = _mm_sha1nexte_epu32(E1, MSG3);</div><div class="line"><a name="l00319"></a><span class="lineno"> 319</span>  E0 = ABCD;</div><div class="line"><a name="l00320"></a><span class="lineno"> 320</span>  MSG0 = _mm_sha1msg2_epu32(MSG0, MSG3);</div><div class="line"><a name="l00321"></a><span class="lineno"> 321</span>  ABCD = _mm_sha1rnds4_epu32(ABCD, E1, 2);</div><div class="line"><a name="l00322"></a><span class="lineno"> 322</span>  MSG2 = _mm_sha1msg1_epu32(MSG2, MSG3);</div><div class="line"><a name="l00323"></a><span class="lineno"> 323</span>  MSG1 = _mm_xor_si128(MSG1, MSG3);</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="comment">// Rounds 48-51</span></div><div class="line"><a name="l00326"></a><span class="lineno"> 326</span>  E0 = _mm_sha1nexte_epu32(E0, MSG0);</div><div class="line"><a name="l00327"></a><span class="lineno"> 327</span>  E1 = ABCD;</div><div class="line"><a name="l00328"></a><span class="lineno"> 328</span>  MSG1 = _mm_sha1msg2_epu32(MSG1, MSG0);</div><div class="line"><a name="l00329"></a><span class="lineno"> 329</span>  ABCD = _mm_sha1rnds4_epu32(ABCD, E0, 2);</div><div class="line"><a name="l00330"></a><span class="lineno"> 330</span>  MSG3 = _mm_sha1msg1_epu32(MSG3, MSG0);</div><div class="line"><a name="l00331"></a><span class="lineno"> 331</span>  MSG2 = _mm_xor_si128(MSG2, MSG0);</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="comment">// Rounds 52-55</span></div><div class="line"><a name="l00334"></a><span class="lineno"> 334</span>  E1 = _mm_sha1nexte_epu32(E1, MSG1);</div><div class="line"><a name="l00335"></a><span class="lineno"> 335</span>  E0 = ABCD;</div><div class="line"><a name="l00336"></a><span class="lineno"> 336</span>  MSG2 = _mm_sha1msg2_epu32(MSG2, MSG1);</div><div class="line"><a name="l00337"></a><span class="lineno"> 337</span>  ABCD = _mm_sha1rnds4_epu32(ABCD, E1, 2);</div><div class="line"><a name="l00338"></a><span class="lineno"> 338</span>  MSG0 = _mm_sha1msg1_epu32(MSG0, MSG1);</div><div class="line"><a name="l00339"></a><span class="lineno"> 339</span>  MSG3 = _mm_xor_si128(MSG3, MSG1);</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="comment">// Rounds 56-59</span></div><div class="line"><a name="l00342"></a><span class="lineno"> 342</span>  E0 = _mm_sha1nexte_epu32(E0, MSG2);</div><div class="line"><a name="l00343"></a><span class="lineno"> 343</span>  E1 = ABCD;</div><div class="line"><a name="l00344"></a><span class="lineno"> 344</span>  MSG3 = _mm_sha1msg2_epu32(MSG3, MSG2);</div><div class="line"><a name="l00345"></a><span class="lineno"> 345</span>  ABCD = _mm_sha1rnds4_epu32(ABCD, E0, 2);</div><div class="line"><a name="l00346"></a><span class="lineno"> 346</span>  MSG1 = _mm_sha1msg1_epu32(MSG1, MSG2);</div><div class="line"><a name="l00347"></a><span class="lineno"> 347</span>  MSG0 = _mm_xor_si128(MSG0, MSG2);</div><div class="line"><a name="l00348"></a><span class="lineno"> 348</span> </div><div class="line"><a name="l00349"></a><span class="lineno"> 349</span>  <span class="comment">// Rounds 60-63</span></div><div class="line"><a name="l00350"></a><span class="lineno"> 350</span>  E1 = _mm_sha1nexte_epu32(E1, MSG3);</div><div class="line"><a name="l00351"></a><span class="lineno"> 351</span>  E0 = ABCD;</div><div class="line"><a name="l00352"></a><span class="lineno"> 352</span>  MSG0 = _mm_sha1msg2_epu32(MSG0, MSG3);</div><div class="line"><a name="l00353"></a><span class="lineno"> 353</span>  ABCD = _mm_sha1rnds4_epu32(ABCD, E1, 3);</div><div class="line"><a name="l00354"></a><span class="lineno"> 354</span>  MSG2 = _mm_sha1msg1_epu32(MSG2, MSG3);</div><div class="line"><a name="l00355"></a><span class="lineno"> 355</span>  MSG1 = _mm_xor_si128(MSG1, MSG3);</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>  <span class="comment">// Rounds 64-67</span></div><div class="line"><a name="l00358"></a><span class="lineno"> 358</span>  E0 = _mm_sha1nexte_epu32(E0, MSG0);</div><div class="line"><a name="l00359"></a><span class="lineno"> 359</span>  E1 = ABCD;</div><div class="line"><a name="l00360"></a><span class="lineno"> 360</span>  MSG1 = _mm_sha1msg2_epu32(MSG1, MSG0);</div><div class="line"><a name="l00361"></a><span class="lineno"> 361</span>  ABCD = _mm_sha1rnds4_epu32(ABCD, E0, 3);</div><div class="line"><a name="l00362"></a><span class="lineno"> 362</span>  MSG3 = _mm_sha1msg1_epu32(MSG3, MSG0);</div><div class="line"><a name="l00363"></a><span class="lineno"> 363</span>  MSG2 = _mm_xor_si128(MSG2, MSG0);</div><div class="line"><a name="l00364"></a><span class="lineno"> 364</span> </div><div class="line"><a name="l00365"></a><span class="lineno"> 365</span>  <span class="comment">// Rounds 68-71</span></div><div class="line"><a name="l00366"></a><span class="lineno"> 366</span>  E1 = _mm_sha1nexte_epu32(E1, MSG1);</div><div class="line"><a name="l00367"></a><span class="lineno"> 367</span>  E0 = ABCD;</div><div class="line"><a name="l00368"></a><span class="lineno"> 368</span>  MSG2 = _mm_sha1msg2_epu32(MSG2, MSG1);</div><div class="line"><a name="l00369"></a><span class="lineno"> 369</span>  ABCD = _mm_sha1rnds4_epu32(ABCD, E1, 3);</div><div class="line"><a name="l00370"></a><span class="lineno"> 370</span>  MSG3 = _mm_xor_si128(MSG3, MSG1);</div><div class="line"><a name="l00371"></a><span class="lineno"> 371</span> </div><div class="line"><a name="l00372"></a><span class="lineno"> 372</span>  <span class="comment">// Rounds 72-75</span></div><div class="line"><a name="l00373"></a><span class="lineno"> 373</span>  E0 = _mm_sha1nexte_epu32(E0, MSG2);</div><div class="line"><a name="l00374"></a><span class="lineno"> 374</span>  E1 = ABCD;</div><div class="line"><a name="l00375"></a><span class="lineno"> 375</span>  MSG3 = _mm_sha1msg2_epu32(MSG3, MSG2);</div><div class="line"><a name="l00376"></a><span class="lineno"> 376</span>  ABCD = _mm_sha1rnds4_epu32(ABCD, E0, 3);</div><div class="line"><a name="l00377"></a><span class="lineno"> 377</span> </div><div class="line"><a name="l00378"></a><span class="lineno"> 378</span>  <span class="comment">// Rounds 76-79</span></div><div class="line"><a name="l00379"></a><span class="lineno"> 379</span>  E1 = _mm_sha1nexte_epu32(E1, MSG3);</div><div class="line"><a name="l00380"></a><span class="lineno"> 380</span>  E0 = ABCD;</div><div class="line"><a name="l00381"></a><span class="lineno"> 381</span>  ABCD = _mm_sha1rnds4_epu32(ABCD, E1, 3);</div><div class="line"><a name="l00382"></a><span class="lineno"> 382</span> </div><div class="line"><a name="l00383"></a><span class="lineno"> 383</span>  <span class="comment">// Add values back to state</span></div><div class="line"><a name="l00384"></a><span class="lineno"> 384</span>  E0 = _mm_sha1nexte_epu32(E0, E0_SAVE);</div><div class="line"><a name="l00385"></a><span class="lineno"> 385</span>  ABCD = _mm_add_epi32(ABCD, ABCD_SAVE);</div><div class="line"><a name="l00386"></a><span class="lineno"> 386</span> </div><div class="line"><a name="l00387"></a><span class="lineno"> 387</span>  data += SHA1::BLOCKSIZE/<span class="keyword">sizeof</span>(word32);</div><div class="line"><a name="l00388"></a><span class="lineno"> 388</span>  length -= SHA1::BLOCKSIZE;</div><div class="line"><a name="l00389"></a><span class="lineno"> 389</span>  }</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="comment">// Save state</span></div><div class="line"><a name="l00392"></a><span class="lineno"> 392</span>  ABCD = _mm_shuffle_epi32(ABCD, 0x1B);</div><div class="line"><a name="l00393"></a><span class="lineno"> 393</span>  _mm_storeu_si128(M128_CAST(state), ABCD);</div><div class="line"><a name="l00394"></a><span class="lineno"> 394</span>  state[4] = _mm_extract_epi32(E0, 3);</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> </div><div class="line"><a name="l00397"></a><span class="lineno"> 397</span> <span class="comment">// Based on http://software.intel.com/en-us/articles/intel-sha-extensions and code by Sean Gulley.</span></div><div class="line"><a name="l00398"></a><span class="lineno"> 398</span> <span class="keywordtype">void</span> SHA256_HashMultipleBlocks_SHANI(word32 *state, <span class="keyword">const</span> word32 *data, <span class="keywordtype">size_t</span> length, <a class="code" href="cryptlib_8h.html#aaeb92d42f5a6e27b8ba19f18d69d142b">ByteOrder</a> order)</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>  <a class="code" href="trap_8h.html#adf3b392588bc94cbeae9f415a78c7b95">CRYPTOPP_ASSERT</a>(state);</div><div class="line"><a name="l00401"></a><span class="lineno"> 401</span>  <a class="code" href="trap_8h.html#adf3b392588bc94cbeae9f415a78c7b95">CRYPTOPP_ASSERT</a>(data);</div><div class="line"><a name="l00402"></a><span class="lineno"> 402</span>  <a class="code" href="trap_8h.html#adf3b392588bc94cbeae9f415a78c7b95">CRYPTOPP_ASSERT</a>(length >= SHA256::BLOCKSIZE);</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>  __m128i STATE0, STATE1;</div><div class="line"><a name="l00405"></a><span class="lineno"> 405</span>  __m128i MSG, TMP, MASK;</div><div class="line"><a name="l00406"></a><span class="lineno"> 406</span>  __m128i TMSG0, TMSG1, TMSG2, TMSG3;</div><div class="line"><a name="l00407"></a><span class="lineno"> 407</span>  __m128i ABEF_SAVE, CDGH_SAVE;</div><div class="line"><a name="l00408"></a><span class="lineno"> 408</span> </div><div class="line"><a name="l00409"></a><span class="lineno"> 409</span>  <span class="comment">// Load initial values</span></div><div class="line"><a name="l00410"></a><span class="lineno"> 410</span>  TMP = _mm_loadu_si128(M128_CAST(&state[0]));</div><div class="line"><a name="l00411"></a><span class="lineno"> 411</span>  STATE1 = _mm_loadu_si128(M128_CAST(&state[4]));</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="comment">// IA-32 SHA is little endian, SHA::Transform is big endian,</span></div><div class="line"><a name="l00414"></a><span class="lineno"> 414</span>  <span class="comment">// and SHA::HashMultipleBlocks can be either. ByteOrder</span></div><div class="line"><a name="l00415"></a><span class="lineno"> 415</span>  <span class="comment">// allows us to avoid extra endian reversals. It saves 1.0 cpb.</span></div><div class="line"><a name="l00416"></a><span class="lineno"> 416</span>  MASK = order == <a class="code" href="cryptlib_8h.html#aaeb92d42f5a6e27b8ba19f18d69d142baf0c3bb6c718cc7ff0bffef4e8f178c57">BIG_ENDIAN_ORDER</a> ? <span class="comment">// Data arrangement</span></div><div class="line"><a name="l00417"></a><span class="lineno"> 417</span>  _mm_set_epi8(12,13,14,15, 8,9,10,11, 4,5,6,7, 0,1,2,3) :</div><div class="line"><a name="l00418"></a><span class="lineno"> 418</span>  _mm_set_epi8(15,14,13,12, 11,10,9,8, 7,6,5,4, 3,2,1,0) ;</div><div class="line"><a name="l00419"></a><span class="lineno"> 419</span> </div><div class="line"><a name="l00420"></a><span class="lineno"> 420</span>  TMP = _mm_shuffle_epi32(TMP, 0xB1); <span class="comment">// CDAB</span></div><div class="line"><a name="l00421"></a><span class="lineno"> 421</span>  STATE1 = _mm_shuffle_epi32(STATE1, 0x1B); <span class="comment">// EFGH</span></div><div class="line"><a name="l00422"></a><span class="lineno"> 422</span>  STATE0 = _mm_alignr_epi8(TMP, STATE1, 8); <span class="comment">// ABEF</span></div><div class="line"><a name="l00423"></a><span class="lineno"> 423</span>  STATE1 = _mm_blend_epi16(STATE1, TMP, 0xF0); <span class="comment">// CDGH</span></div><div class="line"><a name="l00424"></a><span class="lineno"> 424</span> </div><div class="line"><a name="l00425"></a><span class="lineno"> 425</span>  <span class="keywordflow">while</span> (length >= SHA256::BLOCKSIZE)</div><div class="line"><a name="l00426"></a><span class="lineno"> 426</span>  {</div><div class="line"><a name="l00427"></a><span class="lineno"> 427</span>  <span class="comment">// Save current hash</span></div><div class="line"><a name="l00428"></a><span class="lineno"> 428</span>  ABEF_SAVE = STATE0;</div><div class="line"><a name="l00429"></a><span class="lineno"> 429</span>  CDGH_SAVE = STATE1;</div><div class="line"><a name="l00430"></a><span class="lineno"> 430</span> </div><div class="line"><a name="l00431"></a><span class="lineno"> 431</span>  <span class="comment">// Rounds 0-3</span></div><div class="line"><a name="l00432"></a><span class="lineno"> 432</span>  MSG = _mm_loadu_si128(CONST_M128_CAST(data+0));</div><div class="line"><a name="l00433"></a><span class="lineno"> 433</span>  TMSG0 = _mm_shuffle_epi8(MSG, MASK);</div><div class="line"><a name="l00434"></a><span class="lineno"> 434</span>  MSG = _mm_add_epi32(TMSG0, _mm_set_epi64x(W64LIT(0xE9B5DBA5B5C0FBCF), W64LIT(0x71374491428A2F98)));</div><div class="line"><a name="l00435"></a><span class="lineno"> 435</span>  STATE1 = _mm_sha256rnds2_epu32(STATE1, STATE0, MSG);</div><div class="line"><a name="l00436"></a><span class="lineno"> 436</span>  MSG = _mm_shuffle_epi32(MSG, 0x0E);</div><div class="line"><a name="l00437"></a><span class="lineno"> 437</span>  STATE0 = _mm_sha256rnds2_epu32(STATE0, STATE1, MSG);</div><div class="line"><a name="l00438"></a><span class="lineno"> 438</span> </div><div class="line"><a name="l00439"></a><span class="lineno"> 439</span>  <span class="comment">// Rounds 4-7</span></div><div class="line"><a name="l00440"></a><span class="lineno"> 440</span>  TMSG1 = _mm_loadu_si128(CONST_M128_CAST(data+4));</div><div class="line"><a name="l00441"></a><span class="lineno"> 441</span>  TMSG1 = _mm_shuffle_epi8(TMSG1, MASK);</div><div class="line"><a name="l00442"></a><span class="lineno"> 442</span>  MSG = _mm_add_epi32(TMSG1, _mm_set_epi64x(W64LIT(0xAB1C5ED5923F82A4), W64LIT(0x59F111F13956C25B)));</div><div class="line"><a name="l00443"></a><span class="lineno"> 443</span>  STATE1 = _mm_sha256rnds2_epu32(STATE1, STATE0, MSG);</div><div class="line"><a name="l00444"></a><span class="lineno"> 444</span>  MSG = _mm_shuffle_epi32(MSG, 0x0E);</div><div class="line"><a name="l00445"></a><span class="lineno"> 445</span>  STATE0 = _mm_sha256rnds2_epu32(STATE0, STATE1, MSG);</div><div class="line"><a name="l00446"></a><span class="lineno"> 446</span>  TMSG0 = _mm_sha256msg1_epu32(TMSG0, TMSG1);</div><div class="line"><a name="l00447"></a><span class="lineno"> 447</span> </div><div class="line"><a name="l00448"></a><span class="lineno"> 448</span>  <span class="comment">// Rounds 8-11</span></div><div class="line"><a name="l00449"></a><span class="lineno"> 449</span>  TMSG2 = _mm_loadu_si128(CONST_M128_CAST(data+8));</div><div class="line"><a name="l00450"></a><span class="lineno"> 450</span>  TMSG2 = _mm_shuffle_epi8(TMSG2, MASK);</div><div class="line"><a name="l00451"></a><span class="lineno"> 451</span>  MSG = _mm_add_epi32(TMSG2, _mm_set_epi64x(W64LIT(0x550C7DC3243185BE), W64LIT(0x12835B01D807AA98)));</div><div class="line"><a name="l00452"></a><span class="lineno"> 452</span>  STATE1 = _mm_sha256rnds2_epu32(STATE1, STATE0, MSG);</div><div class="line"><a name="l00453"></a><span class="lineno"> 453</span>  MSG = _mm_shuffle_epi32(MSG, 0x0E);</div><div class="line"><a name="l00454"></a><span class="lineno"> 454</span>  STATE0 = _mm_sha256rnds2_epu32(STATE0, STATE1, MSG);</div><div class="line"><a name="l00455"></a><span class="lineno"> 455</span>  TMSG1 = _mm_sha256msg1_epu32(TMSG1, TMSG2);</div><div class="line"><a name="l00456"></a><span class="lineno"> 456</span> </div><div class="line"><a name="l00457"></a><span class="lineno"> 457</span>  <span class="comment">// Rounds 12-15</span></div><div class="line"><a name="l00458"></a><span class="lineno"> 458</span>  TMSG3 = _mm_loadu_si128(CONST_M128_CAST(data+12));</div><div class="line"><a name="l00459"></a><span class="lineno"> 459</span>  TMSG3 = _mm_shuffle_epi8(TMSG3, MASK);</div><div class="line"><a name="l00460"></a><span class="lineno"> 460</span>  MSG = _mm_add_epi32(TMSG3, _mm_set_epi64x(W64LIT(0xC19BF1749BDC06A7), W64LIT(0x80DEB1FE72BE5D74)));</div><div class="line"><a name="l00461"></a><span class="lineno"> 461</span>  STATE1 = _mm_sha256rnds2_epu32(STATE1, STATE0, MSG);</div><div class="line"><a name="l00462"></a><span class="lineno"> 462</span>  TMP = _mm_alignr_epi8(TMSG3, TMSG2, 4);</div><div class="line"><a name="l00463"></a><span class="lineno"> 463</span>  TMSG0 = _mm_add_epi32(TMSG0, TMP);</div><div class="line"><a name="l00464"></a><span class="lineno"> 464</span>  TMSG0 = _mm_sha256msg2_epu32(TMSG0, TMSG3);</div><div class="line"><a name="l00465"></a><span class="lineno"> 465</span>  MSG = _mm_shuffle_epi32(MSG, 0x0E);</div><div class="line"><a name="l00466"></a><span class="lineno"> 466</span>  STATE0 = _mm_sha256rnds2_epu32(STATE0, STATE1, MSG);</div><div class="line"><a name="l00467"></a><span class="lineno"> 467</span>  TMSG2 = _mm_sha256msg1_epu32(TMSG2, TMSG3);</div><div class="line"><a name="l00468"></a><span class="lineno"> 468</span> </div><div class="line"><a name="l00469"></a><span class="lineno"> 469</span>  <span class="comment">// Rounds 16-19</span></div><div class="line"><a name="l00470"></a><span class="lineno"> 470</span>  MSG = _mm_add_epi32(TMSG0, _mm_set_epi64x(W64LIT(0x240CA1CC0FC19DC6), W64LIT(0xEFBE4786E49B69C1)));</div><div class="line"><a name="l00471"></a><span class="lineno"> 471</span>  STATE1 = _mm_sha256rnds2_epu32(STATE1, STATE0, MSG);</div><div class="line"><a name="l00472"></a><span class="lineno"> 472</span>  TMP = _mm_alignr_epi8(TMSG0, TMSG3, 4);</div><div class="line"><a name="l00473"></a><span class="lineno"> 473</span>  TMSG1 = _mm_add_epi32(TMSG1, TMP);</div><div class="line"><a name="l00474"></a><span class="lineno"> 474</span>  TMSG1 = _mm_sha256msg2_epu32(TMSG1, TMSG0);</div><div class="line"><a name="l00475"></a><span class="lineno"> 475</span>  MSG = _mm_shuffle_epi32(MSG, 0x0E);</div><div class="line"><a name="l00476"></a><span class="lineno"> 476</span>  STATE0 = _mm_sha256rnds2_epu32(STATE0, STATE1, MSG);</div><div class="line"><a name="l00477"></a><span class="lineno"> 477</span>  TMSG3 = _mm_sha256msg1_epu32(TMSG3, TMSG0);</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="comment">// Rounds 20-23</span></div><div class="line"><a name="l00480"></a><span class="lineno"> 480</span>  MSG = _mm_add_epi32(TMSG1, _mm_set_epi64x(W64LIT(0x76F988DA5CB0A9DC), W64LIT(0x4A7484AA2DE92C6F)));</div><div class="line"><a name="l00481"></a><span class="lineno"> 481</span>  STATE1 = _mm_sha256rnds2_epu32(STATE1, STATE0, MSG);</div><div class="line"><a name="l00482"></a><span class="lineno"> 482</span>  TMP = _mm_alignr_epi8(TMSG1, TMSG0, 4);</div><div class="line"><a name="l00483"></a><span class="lineno"> 483</span>  TMSG2 = _mm_add_epi32(TMSG2, TMP);</div><div class="line"><a name="l00484"></a><span class="lineno"> 484</span>  TMSG2 = _mm_sha256msg2_epu32(TMSG2, TMSG1);</div><div class="line"><a name="l00485"></a><span class="lineno"> 485</span>  MSG = _mm_shuffle_epi32(MSG, 0x0E);</div><div class="line"><a name="l00486"></a><span class="lineno"> 486</span>  STATE0 = _mm_sha256rnds2_epu32(STATE0, STATE1, MSG);</div><div class="line"><a name="l00487"></a><span class="lineno"> 487</span>  TMSG0 = _mm_sha256msg1_epu32(TMSG0, TMSG1);</div><div class="line"><a name="l00488"></a><span class="lineno"> 488</span> </div><div class="line"><a name="l00489"></a><span class="lineno"> 489</span>  <span class="comment">// Rounds 24-27</span></div><div class="line"><a name="l00490"></a><span class="lineno"> 490</span>  MSG = _mm_add_epi32(TMSG2, _mm_set_epi64x(W64LIT(0xBF597FC7B00327C8), W64LIT(0xA831C66D983E5152)));</div><div class="line"><a name="l00491"></a><span class="lineno"> 491</span>  STATE1 = _mm_sha256rnds2_epu32(STATE1, STATE0, MSG);</div><div class="line"><a name="l00492"></a><span class="lineno"> 492</span>  TMP = _mm_alignr_epi8(TMSG2, TMSG1, 4);</div><div class="line"><a name="l00493"></a><span class="lineno"> 493</span>  TMSG3 = _mm_add_epi32(TMSG3, TMP);</div><div class="line"><a name="l00494"></a><span class="lineno"> 494</span>  TMSG3 = _mm_sha256msg2_epu32(TMSG3, TMSG2);</div><div class="line"><a name="l00495"></a><span class="lineno"> 495</span>  MSG = _mm_shuffle_epi32(MSG, 0x0E);</div><div class="line"><a name="l00496"></a><span class="lineno"> 496</span>  STATE0 = _mm_sha256rnds2_epu32(STATE0, STATE1, MSG);</div><div class="line"><a name="l00497"></a><span class="lineno"> 497</span>  TMSG1 = _mm_sha256msg1_epu32(TMSG1, TMSG2);</div><div class="line"><a name="l00498"></a><span class="lineno"> 498</span> </div><div class="line"><a name="l00499"></a><span class="lineno"> 499</span>  <span class="comment">// Rounds 28-31</span></div><div class="line"><a name="l00500"></a><span class="lineno"> 500</span>  MSG = _mm_add_epi32(TMSG3, _mm_set_epi64x(W64LIT(0x1429296706CA6351), W64LIT(0xD5A79147C6E00BF3)));</div><div class="line"><a name="l00501"></a><span class="lineno"> 501</span>  STATE1 = _mm_sha256rnds2_epu32(STATE1, STATE0, MSG);</div><div class="line"><a name="l00502"></a><span class="lineno"> 502</span>  TMP = _mm_alignr_epi8(TMSG3, TMSG2, 4);</div><div class="line"><a name="l00503"></a><span class="lineno"> 503</span>  TMSG0 = _mm_add_epi32(TMSG0, TMP);</div><div class="line"><a name="l00504"></a><span class="lineno"> 504</span>  TMSG0 = _mm_sha256msg2_epu32(TMSG0, TMSG3);</div><div class="line"><a name="l00505"></a><span class="lineno"> 505</span>  MSG = _mm_shuffle_epi32(MSG, 0x0E);</div><div class="line"><a name="l00506"></a><span class="lineno"> 506</span>  STATE0 = _mm_sha256rnds2_epu32(STATE0, STATE1, MSG);</div><div class="line"><a name="l00507"></a><span class="lineno"> 507</span>  TMSG2 = _mm_sha256msg1_epu32(TMSG2, TMSG3);</div><div class="line"><a name="l00508"></a><span class="lineno"> 508</span> </div><div class="line"><a name="l00509"></a><span class="lineno"> 509</span>  <span class="comment">// Rounds 32-35</span></div><div class="line"><a name="l00510"></a><span class="lineno"> 510</span>  MSG = _mm_add_epi32(TMSG0, _mm_set_epi64x(W64LIT(0x53380D134D2C6DFC), W64LIT(0x2E1B213827B70A85)));</div><div class="line"><a name="l00511"></a><span class="lineno"> 511</span>  STATE1 = _mm_sha256rnds2_epu32(STATE1, STATE0, MSG);</div><div class="line"><a name="l00512"></a><span class="lineno"> 512</span>  TMP = _mm_alignr_epi8(TMSG0, TMSG3, 4);</div><div class="line"><a name="l00513"></a><span class="lineno"> 513</span>  TMSG1 = _mm_add_epi32(TMSG1, TMP);</div><div class="line"><a name="l00514"></a><span class="lineno"> 514</span>  TMSG1 = _mm_sha256msg2_epu32(TMSG1, TMSG0);</div><div class="line"><a name="l00515"></a><span class="lineno"> 515</span>  MSG = _mm_shuffle_epi32(MSG, 0x0E);</div><div class="line"><a name="l00516"></a><span class="lineno"> 516</span>  STATE0 = _mm_sha256rnds2_epu32(STATE0, STATE1, MSG);</div><div class="line"><a name="l00517"></a><span class="lineno"> 517</span>  TMSG3 = _mm_sha256msg1_epu32(TMSG3, TMSG0);</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="comment">// Rounds 36-39</span></div><div class="line"><a name="l00520"></a><span class="lineno"> 520</span>  MSG = _mm_add_epi32(TMSG1, _mm_set_epi64x(W64LIT(0x92722C8581C2C92E), W64LIT(0x766A0ABB650A7354)));</div><div class="line"><a name="l00521"></a><span class="lineno"> 521</span>  STATE1 = _mm_sha256rnds2_epu32(STATE1, STATE0, MSG);</div><div class="line"><a name="l00522"></a><span class="lineno"> 522</span>  TMP = _mm_alignr_epi8(TMSG1, TMSG0, 4);</div><div class="line"><a name="l00523"></a><span class="lineno"> 523</span>  TMSG2 = _mm_add_epi32(TMSG2, TMP);</div><div class="line"><a name="l00524"></a><span class="lineno"> 524</span>  TMSG2 = _mm_sha256msg2_epu32(TMSG2, TMSG1);</div><div class="line"><a name="l00525"></a><span class="lineno"> 525</span>  MSG = _mm_shuffle_epi32(MSG, 0x0E);</div><div class="line"><a name="l00526"></a><span class="lineno"> 526</span>  STATE0 = _mm_sha256rnds2_epu32(STATE0, STATE1, MSG);</div><div class="line"><a name="l00527"></a><span class="lineno"> 527</span>  TMSG0 = _mm_sha256msg1_epu32(TMSG0, TMSG1);</div><div class="line"><a name="l00528"></a><span class="lineno"> 528</span> </div><div class="line"><a name="l00529"></a><span class="lineno"> 529</span>  <span class="comment">// Rounds 40-43</span></div><div class="line"><a name="l00530"></a><span class="lineno"> 530</span>  MSG = _mm_add_epi32(TMSG2, _mm_set_epi64x(W64LIT(0xC76C51A3C24B8B70), W64LIT(0xA81A664BA2BFE8A1)));</div><div class="line"><a name="l00531"></a><span class="lineno"> 531</span>  STATE1 = _mm_sha256rnds2_epu32(STATE1, STATE0, MSG);</div><div class="line"><a name="l00532"></a><span class="lineno"> 532</span>  TMP = _mm_alignr_epi8(TMSG2, TMSG1, 4);</div><div class="line"><a name="l00533"></a><span class="lineno"> 533</span>  TMSG3 = _mm_add_epi32(TMSG3, TMP);</div><div class="line"><a name="l00534"></a><span class="lineno"> 534</span>  TMSG3 = _mm_sha256msg2_epu32(TMSG3, TMSG2);</div><div class="line"><a name="l00535"></a><span class="lineno"> 535</span>  MSG = _mm_shuffle_epi32(MSG, 0x0E);</div><div class="line"><a name="l00536"></a><span class="lineno"> 536</span>  STATE0 = _mm_sha256rnds2_epu32(STATE0, STATE1, MSG);</div><div class="line"><a name="l00537"></a><span class="lineno"> 537</span>  TMSG1 = _mm_sha256msg1_epu32(TMSG1, TMSG2);</div><div class="line"><a name="l00538"></a><span class="lineno"> 538</span> </div><div class="line"><a name="l00539"></a><span class="lineno"> 539</span>  <span class="comment">// Rounds 44-47</span></div><div class="line"><a name="l00540"></a><span class="lineno"> 540</span>  MSG = _mm_add_epi32(TMSG3, _mm_set_epi64x(W64LIT(0x106AA070F40E3585), W64LIT(0xD6990624D192E819)));</div><div class="line"><a name="l00541"></a><span class="lineno"> 541</span>  STATE1 = _mm_sha256rnds2_epu32(STATE1, STATE0, MSG);</div><div class="line"><a name="l00542"></a><span class="lineno"> 542</span>  TMP = _mm_alignr_epi8(TMSG3, TMSG2, 4);</div><div class="line"><a name="l00543"></a><span class="lineno"> 543</span>  TMSG0 = _mm_add_epi32(TMSG0, TMP);</div><div class="line"><a name="l00544"></a><span class="lineno"> 544</span>  TMSG0 = _mm_sha256msg2_epu32(TMSG0, TMSG3);</div><div class="line"><a name="l00545"></a><span class="lineno"> 545</span>  MSG = _mm_shuffle_epi32(MSG, 0x0E);</div><div class="line"><a name="l00546"></a><span class="lineno"> 546</span>  STATE0 = _mm_sha256rnds2_epu32(STATE0, STATE1, MSG);</div><div class="line"><a name="l00547"></a><span class="lineno"> 547</span>  TMSG2 = _mm_sha256msg1_epu32(TMSG2, TMSG3);</div><div class="line"><a name="l00548"></a><span class="lineno"> 548</span> </div><div class="line"><a name="l00549"></a><span class="lineno"> 549</span>  <span class="comment">// Rounds 48-51</span></div><div class="line"><a name="l00550"></a><span class="lineno"> 550</span>  MSG = _mm_add_epi32(TMSG0, _mm_set_epi64x(W64LIT(0x34B0BCB52748774C), W64LIT(0x1E376C0819A4C116)));</div><div class="line"><a name="l00551"></a><span class="lineno"> 551</span>  STATE1 = _mm_sha256rnds2_epu32(STATE1, STATE0, MSG);</div><div class="line"><a name="l00552"></a><span class="lineno"> 552</span>  TMP = _mm_alignr_epi8(TMSG0, TMSG3, 4);</div><div class="line"><a name="l00553"></a><span class="lineno"> 553</span>  TMSG1 = _mm_add_epi32(TMSG1, TMP);</div><div class="line"><a name="l00554"></a><span class="lineno"> 554</span>  TMSG1 = _mm_sha256msg2_epu32(TMSG1, TMSG0);</div><div class="line"><a name="l00555"></a><span class="lineno"> 555</span>  MSG = _mm_shuffle_epi32(MSG, 0x0E);</div><div class="line"><a name="l00556"></a><span class="lineno"> 556</span>  STATE0 = _mm_sha256rnds2_epu32(STATE0, STATE1, MSG);</div><div class="line"><a name="l00557"></a><span class="lineno"> 557</span>  TMSG3 = _mm_sha256msg1_epu32(TMSG3, TMSG0);</div><div class="line"><a name="l00558"></a><span class="lineno"> 558</span> </div><div class="line"><a name="l00559"></a><span class="lineno"> 559</span>  <span class="comment">// Rounds 52-55</span></div><div class="line"><a name="l00560"></a><span class="lineno"> 560</span>  MSG = _mm_add_epi32(TMSG1, _mm_set_epi64x(W64LIT(0x682E6FF35B9CCA4F), W64LIT(0x4ED8AA4A391C0CB3)));</div><div class="line"><a name="l00561"></a><span class="lineno"> 561</span>  STATE1 = _mm_sha256rnds2_epu32(STATE1, STATE0, MSG);</div><div class="line"><a name="l00562"></a><span class="lineno"> 562</span>  TMP = _mm_alignr_epi8(TMSG1, TMSG0, 4);</div><div class="line"><a name="l00563"></a><span class="lineno"> 563</span>  TMSG2 = _mm_add_epi32(TMSG2, TMP);</div><div class="line"><a name="l00564"></a><span class="lineno"> 564</span>  TMSG2 = _mm_sha256msg2_epu32(TMSG2, TMSG1);</div><div class="line"><a name="l00565"></a><span class="lineno"> 565</span>  MSG = _mm_shuffle_epi32(MSG, 0x0E);</div><div class="line"><a name="l00566"></a><span class="lineno"> 566</span>  STATE0 = _mm_sha256rnds2_epu32(STATE0, STATE1, MSG);</div><div class="line"><a name="l00567"></a><span class="lineno"> 567</span> </div><div class="line"><a name="l00568"></a><span class="lineno"> 568</span>  <span class="comment">// Rounds 56-59</span></div><div class="line"><a name="l00569"></a><span class="lineno"> 569</span>  MSG = _mm_add_epi32(TMSG2, _mm_set_epi64x(W64LIT(0x8CC7020884C87814), W64LIT(0x78A5636F748F82EE)));</div><div class="line"><a name="l00570"></a><span class="lineno"> 570</span>  STATE1 = _mm_sha256rnds2_epu32(STATE1, STATE0, MSG);</div><div class="line"><a name="l00571"></a><span class="lineno"> 571</span>  TMP = _mm_alignr_epi8(TMSG2, TMSG1, 4);</div><div class="line"><a name="l00572"></a><span class="lineno"> 572</span>  TMSG3 = _mm_add_epi32(TMSG3, TMP);</div><div class="line"><a name="l00573"></a><span class="lineno"> 573</span>  TMSG3 = _mm_sha256msg2_epu32(TMSG3, TMSG2);</div><div class="line"><a name="l00574"></a><span class="lineno"> 574</span>  MSG = _mm_shuffle_epi32(MSG, 0x0E);</div><div class="line"><a name="l00575"></a><span class="lineno"> 575</span>  STATE0 = _mm_sha256rnds2_epu32(STATE0, STATE1, MSG);</div><div class="line"><a name="l00576"></a><span class="lineno"> 576</span> </div><div class="line"><a name="l00577"></a><span class="lineno"> 577</span>  <span class="comment">// Rounds 60-63</span></div><div class="line"><a name="l00578"></a><span class="lineno"> 578</span>  MSG = _mm_add_epi32(TMSG3, _mm_set_epi64x(W64LIT(0xC67178F2BEF9A3F7), W64LIT(0xA4506CEB90BEFFFA)));</div><div class="line"><a name="l00579"></a><span class="lineno"> 579</span>  STATE1 = _mm_sha256rnds2_epu32(STATE1, STATE0, MSG);</div><div class="line"><a name="l00580"></a><span class="lineno"> 580</span>  MSG = _mm_shuffle_epi32(MSG, 0x0E);</div><div class="line"><a name="l00581"></a><span class="lineno"> 581</span>  STATE0 = _mm_sha256rnds2_epu32(STATE0, STATE1, MSG);</div><div class="line"><a name="l00582"></a><span class="lineno"> 582</span> </div><div class="line"><a name="l00583"></a><span class="lineno"> 583</span>  <span class="comment">// Add values back to state</span></div><div class="line"><a name="l00584"></a><span class="lineno"> 584</span>  STATE0 = _mm_add_epi32(STATE0, ABEF_SAVE);</div><div class="line"><a name="l00585"></a><span class="lineno"> 585</span>  STATE1 = _mm_add_epi32(STATE1, CDGH_SAVE);</div><div class="line"><a name="l00586"></a><span class="lineno"> 586</span> </div><div class="line"><a name="l00587"></a><span class="lineno"> 587</span>  data += SHA256::BLOCKSIZE/<span class="keyword">sizeof</span>(word32);</div><div class="line"><a name="l00588"></a><span class="lineno"> 588</span>  length -= SHA256::BLOCKSIZE;</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> </div><div class="line"><a name="l00591"></a><span class="lineno"> 591</span>  TMP = _mm_shuffle_epi32(STATE0, 0x1B); <span class="comment">// FEBA</span></div><div class="line"><a name="l00592"></a><span class="lineno"> 592</span>  STATE1 = _mm_shuffle_epi32(STATE1, 0xB1); <span class="comment">// DCHG</span></div><div class="line"><a name="l00593"></a><span class="lineno"> 593</span>  STATE0 = _mm_blend_epi16(TMP, STATE1, 0xF0); <span class="comment">// DCBA</span></div><div class="line"><a name="l00594"></a><span class="lineno"> 594</span>  STATE1 = _mm_alignr_epi8(STATE1, TMP, 8); <span class="comment">// ABEF</span></div><div class="line"><a name="l00595"></a><span class="lineno"> 595</span> </div><div class="line"><a name="l00596"></a><span class="lineno"> 596</span>  <span class="comment">// Save state</span></div><div class="line"><a name="l00597"></a><span class="lineno"> 597</span>  _mm_storeu_si128(M128_CAST(&state[0]), STATE0);</div><div class="line"><a name="l00598"></a><span class="lineno"> 598</span>  _mm_storeu_si128(M128_CAST(&state[4]), STATE1);</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> <span class="preprocessor">#endif // CRYPTOPP_SHANI_AVAILABLE</span></div><div class="line"><a name="l00601"></a><span class="lineno"> 601</span> <span class="comment"></span></div><div class="line"><a name="l00602"></a><span class="lineno"> 602</span> <span class="comment">///////////////////////////////////</span></div><div class="line"><a name="l00603"></a><span class="lineno"> 603</span> <span class="comment"></span><span class="comment">// end of Walton and Gulley code //</span><span class="comment"></span></div><div class="line"><a name="l00604"></a><span class="lineno"> 604</span> <span class="comment">///////////////////////////////////</span></div><div class="line"><a name="l00605"></a><span class="lineno"> 605</span> <span class="comment"></span></div><div class="line"><a name="l00606"></a><span class="lineno"> 606</span> <span class="comment">// ***************** ARMV8 SHA ********************</span></div><div class="line"><a name="l00607"></a><span class="lineno"> 607</span> <span class="comment"></span></div><div class="line"><a name="l00608"></a><span class="lineno"> 608</span> <span class="comment">/////////////////////////////////////////////////////////////</span></div><div class="line"><a name="l00609"></a><span class="lineno"> 609</span> <span class="comment"></span><span class="comment">// start of Walton, Schneiders, O'Rourke and Hovsmith code //</span><span class="comment"></span></div><div class="line"><a name="l00610"></a><span class="lineno"> 610</span> <span class="comment">/////////////////////////////////////////////////////////////</span></div><div class="line"><a name="l00611"></a><span class="lineno"> 611</span> <span class="comment"></span></div><div class="line"><a name="l00612"></a><span class="lineno"> 612</span> <span class="preprocessor">#if CRYPTOPP_ARM_SHA_AVAILABLE</span></div><div class="line"><a name="l00613"></a><span class="lineno"> 613</span> <span class="keywordtype">void</span> SHA1_HashMultipleBlocks_ARMV8(word32 *state, <span class="keyword">const</span> word32 *data, <span class="keywordtype">size_t</span> length, <a class="code" href="cryptlib_8h.html#aaeb92d42f5a6e27b8ba19f18d69d142b">ByteOrder</a> order)</div><div class="line"><a name="l00614"></a><span class="lineno"> 614</span> {</div><div class="line"><a name="l00615"></a><span class="lineno"> 615</span>  <a class="code" href="trap_8h.html#adf3b392588bc94cbeae9f415a78c7b95">CRYPTOPP_ASSERT</a>(state);</div><div class="line"><a name="l00616"></a><span class="lineno"> 616</span>  <a class="code" href="trap_8h.html#adf3b392588bc94cbeae9f415a78c7b95">CRYPTOPP_ASSERT</a>(data);</div><div class="line"><a name="l00617"></a><span class="lineno"> 617</span>  <a class="code" href="trap_8h.html#adf3b392588bc94cbeae9f415a78c7b95">CRYPTOPP_ASSERT</a>(length >= SHA1::BLOCKSIZE);</div><div class="line"><a name="l00618"></a><span class="lineno"> 618</span> </div><div class="line"><a name="l00619"></a><span class="lineno"> 619</span>  uint32x4_t C0, C1, C2, C3;</div><div class="line"><a name="l00620"></a><span class="lineno"> 620</span>  uint32x4_t ABCD, ABCD_SAVED;</div><div class="line"><a name="l00621"></a><span class="lineno"> 621</span>  uint32x4_t MSG0, MSG1, MSG2, MSG3;</div><div class="line"><a name="l00622"></a><span class="lineno"> 622</span>  uint32x4_t TMP0, TMP1;</div><div class="line"><a name="l00623"></a><span class="lineno"> 623</span>  uint32_t E0, E0_SAVED, E1;</div><div class="line"><a name="l00624"></a><span class="lineno"> 624</span> </div><div class="line"><a name="l00625"></a><span class="lineno"> 625</span>  <span class="comment">// Load initial values</span></div><div class="line"><a name="l00626"></a><span class="lineno"> 626</span>  C0 = vdupq_n_u32(0x5A827999);</div><div class="line"><a name="l00627"></a><span class="lineno"> 627</span>  C1 = vdupq_n_u32(0x6ED9EBA1);</div><div class="line"><a name="l00628"></a><span class="lineno"> 628</span>  C2 = vdupq_n_u32(0x8F1BBCDC);</div><div class="line"><a name="l00629"></a><span class="lineno"> 629</span>  C3 = vdupq_n_u32(0xCA62C1D6);</div><div class="line"><a name="l00630"></a><span class="lineno"> 630</span> </div><div class="line"><a name="l00631"></a><span class="lineno"> 631</span>  ABCD = vld1q_u32(&state[0]);</div><div class="line"><a name="l00632"></a><span class="lineno"> 632</span>  E0 = state[4];</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">while</span> (length >= SHA1::BLOCKSIZE)</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="comment">// Save current hash</span></div><div class="line"><a name="l00637"></a><span class="lineno"> 637</span>  ABCD_SAVED = ABCD;</div><div class="line"><a name="l00638"></a><span class="lineno"> 638</span>  E0_SAVED = E0;</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>  MSG0 = vld1q_u32(data + 0);</div><div class="line"><a name="l00641"></a><span class="lineno"> 641</span>  MSG1 = vld1q_u32(data + 4);</div><div class="line"><a name="l00642"></a><span class="lineno"> 642</span>  MSG2 = vld1q_u32(data + 8);</div><div class="line"><a name="l00643"></a><span class="lineno"> 643</span>  MSG3 = vld1q_u32(data + 12);</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> (order == <a class="code" href="cryptlib_8h.html#aaeb92d42f5a6e27b8ba19f18d69d142baf0c3bb6c718cc7ff0bffef4e8f178c57">BIG_ENDIAN_ORDER</a>) <span class="comment">// Data arrangement</span></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>  MSG0 = vreinterpretq_u32_u8(vrev32q_u8(vreinterpretq_u8_u32(MSG0)));</div><div class="line"><a name="l00648"></a><span class="lineno"> 648</span>  MSG1 = vreinterpretq_u32_u8(vrev32q_u8(vreinterpretq_u8_u32(MSG1)));</div><div class="line"><a name="l00649"></a><span class="lineno"> 649</span>  MSG2 = vreinterpretq_u32_u8(vrev32q_u8(vreinterpretq_u8_u32(MSG2)));</div><div class="line"><a name="l00650"></a><span class="lineno"> 650</span>  MSG3 = vreinterpretq_u32_u8(vrev32q_u8(vreinterpretq_u8_u32(MSG3)));</div><div class="line"><a name="l00651"></a><span class="lineno"> 651</span>  }</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>  TMP0 = vaddq_u32(MSG0, C0);</div><div class="line"><a name="l00654"></a><span class="lineno"> 654</span>  TMP1 = vaddq_u32(MSG1, C0);</div><div class="line"><a name="l00655"></a><span class="lineno"> 655</span> </div><div class="line"><a name="l00656"></a><span class="lineno"> 656</span>  <span class="comment">// Rounds 0-3</span></div><div class="line"><a name="l00657"></a><span class="lineno"> 657</span>  E1 = vsha1h_u32(vgetq_lane_u32(ABCD, 0));</div><div class="line"><a name="l00658"></a><span class="lineno"> 658</span>  ABCD = vsha1cq_u32(ABCD, E0, TMP0);</div><div class="line"><a name="l00659"></a><span class="lineno"> 659</span>  TMP0 = vaddq_u32(MSG2, C0);</div><div class="line"><a name="l00660"></a><span class="lineno"> 660</span>  MSG0 = vsha1su0q_u32(MSG0, MSG1, MSG2);</div><div class="line"><a name="l00661"></a><span class="lineno"> 661</span> </div><div class="line"><a name="l00662"></a><span class="lineno"> 662</span>  <span class="comment">// Rounds 4-7</span></div><div class="line"><a name="l00663"></a><span class="lineno"> 663</span>  E0 = vsha1h_u32(vgetq_lane_u32(ABCD, 0));</div><div class="line"><a name="l00664"></a><span class="lineno"> 664</span>  ABCD = vsha1cq_u32(ABCD, E1, TMP1);</div><div class="line"><a name="l00665"></a><span class="lineno"> 665</span>  TMP1 = vaddq_u32(MSG3, C0);</div><div class="line"><a name="l00666"></a><span class="lineno"> 666</span>  MSG0 = vsha1su1q_u32(MSG0, MSG3);</div><div class="line"><a name="l00667"></a><span class="lineno"> 667</span>  MSG1 = vsha1su0q_u32(MSG1, MSG2, MSG3);</div><div class="line"><a name="l00668"></a><span class="lineno"> 668</span> </div><div class="line"><a name="l00669"></a><span class="lineno"> 669</span>  <span class="comment">// Rounds 8-11</span></div><div class="line"><a name="l00670"></a><span class="lineno"> 670</span>  E1 = vsha1h_u32(vgetq_lane_u32(ABCD, 0));</div><div class="line"><a name="l00671"></a><span class="lineno"> 671</span>  ABCD = vsha1cq_u32(ABCD, E0, TMP0);</div><div class="line"><a name="l00672"></a><span class="lineno"> 672</span>  TMP0 = vaddq_u32(MSG0, C0);</div><div class="line"><a name="l00673"></a><span class="lineno"> 673</span>  MSG1 = vsha1su1q_u32(MSG1, MSG0);</div><div class="line"><a name="l00674"></a><span class="lineno"> 674</span>  MSG2 = vsha1su0q_u32(MSG2, MSG3, MSG0);</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="comment">// Rounds 12-15</span></div><div class="line"><a name="l00677"></a><span class="lineno"> 677</span>  E0 = vsha1h_u32(vgetq_lane_u32(ABCD, 0));</div><div class="line"><a name="l00678"></a><span class="lineno"> 678</span>  ABCD = vsha1cq_u32(ABCD, E1, TMP1);</div><div class="line"><a name="l00679"></a><span class="lineno"> 679</span>  TMP1 = vaddq_u32(MSG1, C1);</div><div class="line"><a name="l00680"></a><span class="lineno"> 680</span>  MSG2 = vsha1su1q_u32(MSG2, MSG1);</div><div class="line"><a name="l00681"></a><span class="lineno"> 681</span>  MSG3 = vsha1su0q_u32(MSG3, MSG0, MSG1);</div><div class="line"><a name="l00682"></a><span class="lineno"> 682</span> </div><div class="line"><a name="l00683"></a><span class="lineno"> 683</span>  <span class="comment">// Rounds 16-19</span></div><div class="line"><a name="l00684"></a><span class="lineno"> 684</span>  E1 = vsha1h_u32(vgetq_lane_u32(ABCD, 0));</div><div class="line"><a name="l00685"></a><span class="lineno"> 685</span>  ABCD = vsha1cq_u32(ABCD, E0, TMP0);</div><div class="line"><a name="l00686"></a><span class="lineno"> 686</span>  TMP0 = vaddq_u32(MSG2, C1);</div><div class="line"><a name="l00687"></a><span class="lineno"> 687</span>  MSG3 = vsha1su1q_u32(MSG3, MSG2);</div><div class="line"><a name="l00688"></a><span class="lineno"> 688</span>  MSG0 = vsha1su0q_u32(MSG0, MSG1, MSG2);</div><div class="line"><a name="l00689"></a><span class="lineno"> 689</span> </div><div class="line"><a name="l00690"></a><span class="lineno"> 690</span>  <span class="comment">// Rounds 20-23</span></div><div class="line"><a name="l00691"></a><span class="lineno"> 691</span>  E0 = vsha1h_u32(vgetq_lane_u32(ABCD, 0));</div><div class="line"><a name="l00692"></a><span class="lineno"> 692</span>  ABCD = vsha1pq_u32(ABCD, E1, TMP1);</div><div class="line"><a name="l00693"></a><span class="lineno"> 693</span>  TMP1 = vaddq_u32(MSG3, C1);</div><div class="line"><a name="l00694"></a><span class="lineno"> 694</span>  MSG0 = vsha1su1q_u32(MSG0, MSG3);</div><div class="line"><a name="l00695"></a><span class="lineno"> 695</span>  MSG1 = vsha1su0q_u32(MSG1, MSG2, MSG3);</div><div class="line"><a name="l00696"></a><span class="lineno"> 696</span> </div><div class="line"><a name="l00697"></a><span class="lineno"> 697</span>  <span class="comment">// Rounds 24-27</span></div><div class="line"><a name="l00698"></a><span class="lineno"> 698</span>  E1 = vsha1h_u32(vgetq_lane_u32(ABCD, 0));</div><div class="line"><a name="l00699"></a><span class="lineno"> 699</span>  ABCD = vsha1pq_u32(ABCD, E0, TMP0);</div><div class="line"><a name="l00700"></a><span class="lineno"> 700</span>  TMP0 = vaddq_u32(MSG0, C1);</div><div class="line"><a name="l00701"></a><span class="lineno"> 701</span>  MSG1 = vsha1su1q_u32(MSG1, MSG0);</div><div class="line"><a name="l00702"></a><span class="lineno"> 702</span>  MSG2 = vsha1su0q_u32(MSG2, MSG3, MSG0);</div><div class="line"><a name="l00703"></a><span class="lineno"> 703</span> </div><div class="line"><a name="l00704"></a><span class="lineno"> 704</span>  <span class="comment">// Rounds 28-31</span></div><div class="line"><a name="l00705"></a><span class="lineno"> 705</span>  E0 = vsha1h_u32(vgetq_lane_u32(ABCD, 0));</div><div class="line"><a name="l00706"></a><span class="lineno"> 706</span>  ABCD = vsha1pq_u32(ABCD, E1, TMP1);</div><div class="line"><a name="l00707"></a><span class="lineno"> 707</span>  TMP1 = vaddq_u32(MSG1, C1);</div><div class="line"><a name="l00708"></a><span class="lineno"> 708</span>  MSG2 = vsha1su1q_u32(MSG2, MSG1);</div><div class="line"><a name="l00709"></a><span class="lineno"> 709</span>  MSG3 = vsha1su0q_u32(MSG3, MSG0, MSG1);</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">// Rounds 32-35</span></div><div class="line"><a name="l00712"></a><span class="lineno"> 712</span>  E1 = vsha1h_u32(vgetq_lane_u32(ABCD, 0));</div><div class="line"><a name="l00713"></a><span class="lineno"> 713</span>  ABCD = vsha1pq_u32(ABCD, E0, TMP0);</div><div class="line"><a name="l00714"></a><span class="lineno"> 714</span>  TMP0 = vaddq_u32(MSG2, C2);</div><div class="line"><a name="l00715"></a><span class="lineno"> 715</span>  MSG3 = vsha1su1q_u32(MSG3, MSG2);</div><div class="line"><a name="l00716"></a><span class="lineno"> 716</span>  MSG0 = vsha1su0q_u32(MSG0, MSG1, MSG2);</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="comment">// Rounds 36-39</span></div><div class="line"><a name="l00719"></a><span class="lineno"> 719</span>  E0 = vsha1h_u32(vgetq_lane_u32(ABCD, 0));</div><div class="line"><a name="l00720"></a><span class="lineno"> 720</span>  ABCD = vsha1pq_u32(ABCD, E1, TMP1);</div><div class="line"><a name="l00721"></a><span class="lineno"> 721</span>  TMP1 = vaddq_u32(MSG3, C2);</div><div class="line"><a name="l00722"></a><span class="lineno"> 722</span>  MSG0 = vsha1su1q_u32(MSG0, MSG3);</div><div class="line"><a name="l00723"></a><span class="lineno"> 723</span>  MSG1 = vsha1su0q_u32(MSG1, MSG2, MSG3);</div><div class="line"><a name="l00724"></a><span class="lineno"> 724</span> </div><div class="line"><a name="l00725"></a><span class="lineno"> 725</span>  <span class="comment">// Rounds 40-43</span></div><div class="line"><a name="l00726"></a><span class="lineno"> 726</span>  E1 = vsha1h_u32(vgetq_lane_u32(ABCD, 0));</div><div class="line"><a name="l00727"></a><span class="lineno"> 727</span>  ABCD = vsha1mq_u32(ABCD, E0, TMP0);</div><div class="line"><a name="l00728"></a><span class="lineno"> 728</span>  TMP0 = vaddq_u32(MSG0, C2);</div><div class="line"><a name="l00729"></a><span class="lineno"> 729</span>  MSG1 = vsha1su1q_u32(MSG1, MSG0);</div><div class="line"><a name="l00730"></a><span class="lineno"> 730</span>  MSG2 = vsha1su0q_u32(MSG2, MSG3, MSG0);</div><div class="line"><a name="l00731"></a><span class="lineno"> 731</span> </div><div class="line"><a name="l00732"></a><span class="lineno"> 732</span>  <span class="comment">// Rounds 44-47</span></div><div class="line"><a name="l00733"></a><span class="lineno"> 733</span>  E0 = vsha1h_u32(vgetq_lane_u32(ABCD, 0));</div><div class="line"><a name="l00734"></a><span class="lineno"> 734</span>  ABCD = vsha1mq_u32(ABCD, E1, TMP1);</div><div class="line"><a name="l00735"></a><span class="lineno"> 735</span>  TMP1 = vaddq_u32(MSG1, C2);</div><div class="line"><a name="l00736"></a><span class="lineno"> 736</span>  MSG2 = vsha1su1q_u32(MSG2, MSG1);</div><div class="line"><a name="l00737"></a><span class="lineno"> 737</span>  MSG3 = vsha1su0q_u32(MSG3, MSG0, MSG1);</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">// Rounds 48-51</span></div><div class="line"><a name="l00740"></a><span class="lineno"> 740</span>  E1 = vsha1h_u32(vgetq_lane_u32(ABCD, 0));</div><div class="line"><a name="l00741"></a><span class="lineno"> 741</span>  ABCD = vsha1mq_u32(ABCD, E0, TMP0);</div><div class="line"><a name="l00742"></a><span class="lineno"> 742</span>  TMP0 = vaddq_u32(MSG2, C2);</div><div class="line"><a name="l00743"></a><span class="lineno"> 743</span>  MSG3 = vsha1su1q_u32(MSG3, MSG2);</div><div class="line"><a name="l00744"></a><span class="lineno"> 744</span>  MSG0 = vsha1su0q_u32(MSG0, MSG1, MSG2);</div><div class="line"><a name="l00745"></a><span class="lineno"> 745</span> </div><div class="line"><a name="l00746"></a><span class="lineno"> 746</span>  <span class="comment">// Rounds 52-55</span></div><div class="line"><a name="l00747"></a><span class="lineno"> 747</span>  E0 = vsha1h_u32(vgetq_lane_u32(ABCD, 0));</div><div class="line"><a name="l00748"></a><span class="lineno"> 748</span>  ABCD = vsha1mq_u32(ABCD, E1, TMP1);</div><div class="line"><a name="l00749"></a><span class="lineno"> 749</span>  TMP1 = vaddq_u32(MSG3, C3);</div><div class="line"><a name="l00750"></a><span class="lineno"> 750</span>  MSG0 = vsha1su1q_u32(MSG0, MSG3);</div><div class="line"><a name="l00751"></a><span class="lineno"> 751</span>  MSG1 = vsha1su0q_u32(MSG1, MSG2, MSG3);</div><div class="line"><a name="l00752"></a><span class="lineno"> 752</span> </div><div class="line"><a name="l00753"></a><span class="lineno"> 753</span>  <span class="comment">// Rounds 56-59</span></div><div class="line"><a name="l00754"></a><span class="lineno"> 754</span>  E1 = vsha1h_u32(vgetq_lane_u32(ABCD, 0));</div><div class="line"><a name="l00755"></a><span class="lineno"> 755</span>  ABCD = vsha1mq_u32(ABCD, E0, TMP0);</div><div class="line"><a name="l00756"></a><span class="lineno"> 756</span>  TMP0 = vaddq_u32(MSG0, C3);</div><div class="line"><a name="l00757"></a><span class="lineno"> 757</span>  MSG1 = vsha1su1q_u32(MSG1, MSG0);</div><div class="line"><a name="l00758"></a><span class="lineno"> 758</span>  MSG2 = vsha1su0q_u32(MSG2, MSG3, MSG0);</div><div class="line"><a name="l00759"></a><span class="lineno"> 759</span> </div><div class="line"><a name="l00760"></a><span class="lineno"> 760</span>  <span class="comment">// Rounds 60-63</span></div><div class="line"><a name="l00761"></a><span class="lineno"> 761</span>  E0 = vsha1h_u32(vgetq_lane_u32(ABCD, 0));</div><div class="line"><a name="l00762"></a><span class="lineno"> 762</span>  ABCD = vsha1pq_u32(ABCD, E1, TMP1);</div><div class="line"><a name="l00763"></a><span class="lineno"> 763</span>  TMP1 = vaddq_u32(MSG1, C3);</div><div class="line"><a name="l00764"></a><span class="lineno"> 764</span>  MSG2 = vsha1su1q_u32(MSG2, MSG1);</div><div class="line"><a name="l00765"></a><span class="lineno"> 765</span>  MSG3 = vsha1su0q_u32(MSG3, MSG0, MSG1);</div><div class="line"><a name="l00766"></a><span class="lineno"> 766</span> </div><div class="line"><a name="l00767"></a><span class="lineno"> 767</span>  <span class="comment">// Rounds 64-67</span></div><div class="line"><a name="l00768"></a><span class="lineno"> 768</span>  E1 = vsha1h_u32(vgetq_lane_u32(ABCD, 0));</div><div class="line"><a name="l00769"></a><span class="lineno"> 769</span>  ABCD = vsha1pq_u32(ABCD, E0, TMP0);</div><div class="line"><a name="l00770"></a><span class="lineno"> 770</span>  TMP0 = vaddq_u32(MSG2, C3);</div><div class="line"><a name="l00771"></a><span class="lineno"> 771</span>  MSG3 = vsha1su1q_u32(MSG3, MSG2);</div><div class="line"><a name="l00772"></a><span class="lineno"> 772</span>  MSG0 = vsha1su0q_u32(MSG0, MSG1, MSG2);</div><div class="line"><a name="l00773"></a><span class="lineno"> 773</span> </div><div class="line"><a name="l00774"></a><span class="lineno"> 774</span>  <span class="comment">// Rounds 68-71</span></div><div class="line"><a name="l00775"></a><span class="lineno"> 775</span>  E0 = vsha1h_u32(vgetq_lane_u32(ABCD, 0));</div><div class="line"><a name="l00776"></a><span class="lineno"> 776</span>  ABCD = vsha1pq_u32(ABCD, E1, TMP1);</div><div class="line"><a name="l00777"></a><span class="lineno"> 777</span>  TMP1 = vaddq_u32(MSG3, C3);</div><div class="line"><a name="l00778"></a><span class="lineno"> 778</span>  MSG0 = vsha1su1q_u32(MSG0, MSG3);</div><div class="line"><a name="l00779"></a><span class="lineno"> 779</span> </div><div class="line"><a name="l00780"></a><span class="lineno"> 780</span>  <span class="comment">// Rounds 72-75</span></div><div class="line"><a name="l00781"></a><span class="lineno"> 781</span>  E1 = vsha1h_u32(vgetq_lane_u32(ABCD, 0));</div><div class="line"><a name="l00782"></a><span class="lineno"> 782</span>  ABCD = vsha1pq_u32(ABCD, E0, TMP0);</div><div class="line"><a name="l00783"></a><span class="lineno"> 783</span> </div><div class="line"><a name="l00784"></a><span class="lineno"> 784</span>  <span class="comment">// Rounds 76-79</span></div><div class="line"><a name="l00785"></a><span class="lineno"> 785</span>  E0 = vsha1h_u32(vgetq_lane_u32(ABCD, 0));</div><div class="line"><a name="l00786"></a><span class="lineno"> 786</span>  ABCD = vsha1pq_u32(ABCD, E1, TMP1);</div><div class="line"><a name="l00787"></a><span class="lineno"> 787</span> </div><div class="line"><a name="l00788"></a><span class="lineno"> 788</span>  E0 += E0_SAVED;</div><div class="line"><a name="l00789"></a><span class="lineno"> 789</span>  ABCD = vaddq_u32(ABCD_SAVED, ABCD);</div><div class="line"><a name="l00790"></a><span class="lineno"> 790</span> </div><div class="line"><a name="l00791"></a><span class="lineno"> 791</span>  data += SHA1::BLOCKSIZE/<span class="keyword">sizeof</span>(word32);</div><div class="line"><a name="l00792"></a><span class="lineno"> 792</span>  length -= SHA1::BLOCKSIZE;</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="comment">// Save state</span></div><div class="line"><a name="l00796"></a><span class="lineno"> 796</span>  vst1q_u32(&state[0], ABCD);</div><div class="line"><a name="l00797"></a><span class="lineno"> 797</span>  state[4] = E0;</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> </div><div class="line"><a name="l00800"></a><span class="lineno"> 800</span> <span class="keywordtype">void</span> SHA256_HashMultipleBlocks_ARMV8(word32 *state, <span class="keyword">const</span> word32 *data, <span class="keywordtype">size_t</span> length, <a class="code" href="cryptlib_8h.html#aaeb92d42f5a6e27b8ba19f18d69d142b">ByteOrder</a> order)</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>  <a class="code" href="trap_8h.html#adf3b392588bc94cbeae9f415a78c7b95">CRYPTOPP_ASSERT</a>(state);</div><div class="line"><a name="l00803"></a><span class="lineno"> 803</span>  <a class="code" href="trap_8h.html#adf3b392588bc94cbeae9f415a78c7b95">CRYPTOPP_ASSERT</a>(data);</div><div class="line"><a name="l00804"></a><span class="lineno"> 804</span>  <a class="code" href="trap_8h.html#adf3b392588bc94cbeae9f415a78c7b95">CRYPTOPP_ASSERT</a>(length >= SHA256::BLOCKSIZE);</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>  uint32x4_t STATE0, STATE1, ABEF_SAVE, CDGH_SAVE;</div><div class="line"><a name="l00807"></a><span class="lineno"> 807</span>  uint32x4_t MSG0, MSG1, MSG2, MSG3;</div><div class="line"><a name="l00808"></a><span class="lineno"> 808</span>  uint32x4_t TMP0, TMP1, TMP2;</div><div class="line"><a name="l00809"></a><span class="lineno"> 809</span> </div><div class="line"><a name="l00810"></a><span class="lineno"> 810</span>  <span class="comment">// Load initial values</span></div><div class="line"><a name="l00811"></a><span class="lineno"> 811</span>  STATE0 = vld1q_u32(&state[0]);</div><div class="line"><a name="l00812"></a><span class="lineno"> 812</span>  STATE1 = vld1q_u32(&state[4]);</div><div class="line"><a name="l00813"></a><span class="lineno"> 813</span> </div><div class="line"><a name="l00814"></a><span class="lineno"> 814</span>  <span class="keywordflow">while</span> (length >= SHA256::BLOCKSIZE)</div><div class="line"><a name="l00815"></a><span class="lineno"> 815</span>  {</div><div class="line"><a name="l00816"></a><span class="lineno"> 816</span>  <span class="comment">// Save current hash</span></div><div class="line"><a name="l00817"></a><span class="lineno"> 817</span>  ABEF_SAVE = STATE0;</div><div class="line"><a name="l00818"></a><span class="lineno"> 818</span>  CDGH_SAVE = STATE1;</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>  <span class="comment">// Load message</span></div><div class="line"><a name="l00821"></a><span class="lineno"> 821</span>  MSG0 = vld1q_u32(data + 0);</div><div class="line"><a name="l00822"></a><span class="lineno"> 822</span>  MSG1 = vld1q_u32(data + 4);</div><div class="line"><a name="l00823"></a><span class="lineno"> 823</span>  MSG2 = vld1q_u32(data + 8);</div><div class="line"><a name="l00824"></a><span class="lineno"> 824</span>  MSG3 = vld1q_u32(data + 12);</div><div class="line"><a name="l00825"></a><span class="lineno"> 825</span> </div><div class="line"><a name="l00826"></a><span class="lineno"> 826</span>  <span class="keywordflow">if</span> (order == <a class="code" href="cryptlib_8h.html#aaeb92d42f5a6e27b8ba19f18d69d142baf0c3bb6c718cc7ff0bffef4e8f178c57">BIG_ENDIAN_ORDER</a>) <span class="comment">// Data arrangement</span></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>  MSG0 = vreinterpretq_u32_u8(vrev32q_u8(vreinterpretq_u8_u32(MSG0)));</div><div class="line"><a name="l00829"></a><span class="lineno"> 829</span>  MSG1 = vreinterpretq_u32_u8(vrev32q_u8(vreinterpretq_u8_u32(MSG1)));</div><div class="line"><a name="l00830"></a><span class="lineno"> 830</span>  MSG2 = vreinterpretq_u32_u8(vrev32q_u8(vreinterpretq_u8_u32(MSG2)));</div><div class="line"><a name="l00831"></a><span class="lineno"> 831</span>  MSG3 = vreinterpretq_u32_u8(vrev32q_u8(vreinterpretq_u8_u32(MSG3)));</div><div class="line"><a name="l00832"></a><span class="lineno"> 832</span>  }</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>  TMP0 = vaddq_u32(MSG0, vld1q_u32(&SHA256_K[0x00]));</div><div class="line"><a name="l00835"></a><span class="lineno"> 835</span> </div><div class="line"><a name="l00836"></a><span class="lineno"> 836</span>  <span class="comment">// Rounds 0-3</span></div><div class="line"><a name="l00837"></a><span class="lineno"> 837</span>  MSG0 = vsha256su0q_u32(MSG0, MSG1);</div><div class="line"><a name="l00838"></a><span class="lineno"> 838</span>  TMP2 = STATE0;</div><div class="line"><a name="l00839"></a><span class="lineno"> 839</span>  TMP1 = vaddq_u32(MSG1, vld1q_u32(&SHA256_K[0x04]));</div><div class="line"><a name="l00840"></a><span class="lineno"> 840</span>  STATE0 = vsha256hq_u32(STATE0, STATE1, TMP0);</div><div class="line"><a name="l00841"></a><span class="lineno"> 841</span>  STATE1 = vsha256h2q_u32(STATE1, TMP2, TMP0);</div><div class="line"><a name="l00842"></a><span class="lineno"> 842</span>  MSG0 = vsha256su1q_u32(MSG0, MSG2, MSG3);;</div><div class="line"><a name="l00843"></a><span class="lineno"> 843</span> </div><div class="line"><a name="l00844"></a><span class="lineno"> 844</span>  <span class="comment">// Rounds 4-7</span></div><div class="line"><a name="l00845"></a><span class="lineno"> 845</span>  MSG1 = vsha256su0q_u32(MSG1, MSG2);</div><div class="line"><a name="l00846"></a><span class="lineno"> 846</span>  TMP2 = STATE0;</div><div class="line"><a name="l00847"></a><span class="lineno"> 847</span>  TMP0 = vaddq_u32(MSG2, vld1q_u32(&SHA256_K[0x08]));</div><div class="line"><a name="l00848"></a><span class="lineno"> 848</span>  STATE0 = vsha256hq_u32(STATE0, STATE1, TMP1);</div><div class="line"><a name="l00849"></a><span class="lineno"> 849</span>  STATE1 = vsha256h2q_u32(STATE1, TMP2, TMP1);</div><div class="line"><a name="l00850"></a><span class="lineno"> 850</span>  MSG1 = vsha256su1q_u32(MSG1, MSG3, MSG0);;</div><div class="line"><a name="l00851"></a><span class="lineno"> 851</span> </div><div class="line"><a name="l00852"></a><span class="lineno"> 852</span>  <span class="comment">// Rounds 8-11</span></div><div class="line"><a name="l00853"></a><span class="lineno"> 853</span>  MSG2 = vsha256su0q_u32(MSG2, MSG3);</div><div class="line"><a name="l00854"></a><span class="lineno"> 854</span>  TMP2 = STATE0;</div><div class="line"><a name="l00855"></a><span class="lineno"> 855</span>  TMP1 = vaddq_u32(MSG3, vld1q_u32(&SHA256_K[0x0c]));</div><div class="line"><a name="l00856"></a><span class="lineno"> 856</span>  STATE0 = vsha256hq_u32(STATE0, STATE1, TMP0);</div><div class="line"><a name="l00857"></a><span class="lineno"> 857</span>  STATE1 = vsha256h2q_u32(STATE1, TMP2, TMP0);</div><div class="line"><a name="l00858"></a><span class="lineno"> 858</span>  MSG2 = vsha256su1q_u32(MSG2, MSG0, MSG1);;</div><div class="line"><a name="l00859"></a><span class="lineno"> 859</span> </div><div class="line"><a name="l00860"></a><span class="lineno"> 860</span>  <span class="comment">// Rounds 12-15</span></div><div class="line"><a name="l00861"></a><span class="lineno"> 861</span>  MSG3 = vsha256su0q_u32(MSG3, MSG0);</div><div class="line"><a name="l00862"></a><span class="lineno"> 862</span>  TMP2 = STATE0;</div><div class="line"><a name="l00863"></a><span class="lineno"> 863</span>  TMP0 = vaddq_u32(MSG0, vld1q_u32(&SHA256_K[0x10]));</div><div class="line"><a name="l00864"></a><span class="lineno"> 864</span>  STATE0 = vsha256hq_u32(STATE0, STATE1, TMP1);</div><div class="line"><a name="l00865"></a><span class="lineno"> 865</span>  STATE1 = vsha256h2q_u32(STATE1, TMP2, TMP1);</div><div class="line"><a name="l00866"></a><span class="lineno"> 866</span>  MSG3 = vsha256su1q_u32(MSG3, MSG1, MSG2);;</div><div class="line"><a name="l00867"></a><span class="lineno"> 867</span> </div><div class="line"><a name="l00868"></a><span class="lineno"> 868</span>  <span class="comment">// Rounds 16-19</span></div><div class="line"><a name="l00869"></a><span class="lineno"> 869</span>  MSG0 = vsha256su0q_u32(MSG0, MSG1);</div><div class="line"><a name="l00870"></a><span class="lineno"> 870</span>  TMP2 = STATE0;</div><div class="line"><a name="l00871"></a><span class="lineno"> 871</span>  TMP1 = vaddq_u32(MSG1, vld1q_u32(&SHA256_K[0x14]));</div><div class="line"><a name="l00872"></a><span class="lineno"> 872</span>  STATE0 = vsha256hq_u32(STATE0, STATE1, TMP0);</div><div class="line"><a name="l00873"></a><span class="lineno"> 873</span>  STATE1 = vsha256h2q_u32(STATE1, TMP2, TMP0);</div><div class="line"><a name="l00874"></a><span class="lineno"> 874</span>  MSG0 = vsha256su1q_u32(MSG0, MSG2, MSG3);;</div><div class="line"><a name="l00875"></a><span class="lineno"> 875</span> </div><div class="line"><a name="l00876"></a><span class="lineno"> 876</span>  <span class="comment">// Rounds 20-23</span></div><div class="line"><a name="l00877"></a><span class="lineno"> 877</span>  MSG1 = vsha256su0q_u32(MSG1, MSG2);</div><div class="line"><a name="l00878"></a><span class="lineno"> 878</span>  TMP2 = STATE0;</div><div class="line"><a name="l00879"></a><span class="lineno"> 879</span>  TMP0 = vaddq_u32(MSG2, vld1q_u32(&SHA256_K[0x18]));</div><div class="line"><a name="l00880"></a><span class="lineno"> 880</span>  STATE0 = vsha256hq_u32(STATE0, STATE1, TMP1);</div><div class="line"><a name="l00881"></a><span class="lineno"> 881</span>  STATE1 = vsha256h2q_u32(STATE1, TMP2, TMP1);</div><div class="line"><a name="l00882"></a><span class="lineno"> 882</span>  MSG1 = vsha256su1q_u32(MSG1, MSG3, MSG0);;</div><div class="line"><a name="l00883"></a><span class="lineno"> 883</span> </div><div class="line"><a name="l00884"></a><span class="lineno"> 884</span>  <span class="comment">// Rounds 24-27</span></div><div class="line"><a name="l00885"></a><span class="lineno"> 885</span>  MSG2 = vsha256su0q_u32(MSG2, MSG3);</div><div class="line"><a name="l00886"></a><span class="lineno"> 886</span>  TMP2 = STATE0;</div><div class="line"><a name="l00887"></a><span class="lineno"> 887</span>  TMP1 = vaddq_u32(MSG3, vld1q_u32(&SHA256_K[0x1c]));</div><div class="line"><a name="l00888"></a><span class="lineno"> 888</span>  STATE0 = vsha256hq_u32(STATE0, STATE1, TMP0);</div><div class="line"><a name="l00889"></a><span class="lineno"> 889</span>  STATE1 = vsha256h2q_u32(STATE1, TMP2, TMP0);</div><div class="line"><a name="l00890"></a><span class="lineno"> 890</span>  MSG2 = vsha256su1q_u32(MSG2, MSG0, MSG1);;</div><div class="line"><a name="l00891"></a><span class="lineno"> 891</span> </div><div class="line"><a name="l00892"></a><span class="lineno"> 892</span>  <span class="comment">// Rounds 28-31</span></div><div class="line"><a name="l00893"></a><span class="lineno"> 893</span>  MSG3 = vsha256su0q_u32(MSG3, MSG0);</div><div class="line"><a name="l00894"></a><span class="lineno"> 894</span>  TMP2 = STATE0;</div><div class="line"><a name="l00895"></a><span class="lineno"> 895</span>  TMP0 = vaddq_u32(MSG0, vld1q_u32(&SHA256_K[0x20]));</div><div class="line"><a name="l00896"></a><span class="lineno"> 896</span>  STATE0 = vsha256hq_u32(STATE0, STATE1, TMP1);</div><div class="line"><a name="l00897"></a><span class="lineno"> 897</span>  STATE1 = vsha256h2q_u32(STATE1, TMP2, TMP1);</div><div class="line"><a name="l00898"></a><span class="lineno"> 898</span>  MSG3 = vsha256su1q_u32(MSG3, MSG1, MSG2);;</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">// Rounds 32-35</span></div><div class="line"><a name="l00901"></a><span class="lineno"> 901</span>  MSG0 = vsha256su0q_u32(MSG0, MSG1);</div><div class="line"><a name="l00902"></a><span class="lineno"> 902</span>  TMP2 = STATE0;</div><div class="line"><a name="l00903"></a><span class="lineno"> 903</span>  TMP1 = vaddq_u32(MSG1, vld1q_u32(&SHA256_K[0x24]));</div><div class="line"><a name="l00904"></a><span class="lineno"> 904</span>  STATE0 = vsha256hq_u32(STATE0, STATE1, TMP0);</div><div class="line"><a name="l00905"></a><span class="lineno"> 905</span>  STATE1 = vsha256h2q_u32(STATE1, TMP2, TMP0);</div><div class="line"><a name="l00906"></a><span class="lineno"> 906</span>  MSG0 = vsha256su1q_u32(MSG0, MSG2, MSG3);;</div><div class="line"><a name="l00907"></a><span class="lineno"> 907</span> </div><div class="line"><a name="l00908"></a><span class="lineno"> 908</span>  <span class="comment">// Rounds 36-39</span></div><div class="line"><a name="l00909"></a><span class="lineno"> 909</span>  MSG1 = vsha256su0q_u32(MSG1, MSG2);</div><div class="line"><a name="l00910"></a><span class="lineno"> 910</span>  TMP2 = STATE0;</div><div class="line"><a name="l00911"></a><span class="lineno"> 911</span>  TMP0 = vaddq_u32(MSG2, vld1q_u32(&SHA256_K[0x28]));</div><div class="line"><a name="l00912"></a><span class="lineno"> 912</span>  STATE0 = vsha256hq_u32(STATE0, STATE1, TMP1);</div><div class="line"><a name="l00913"></a><span class="lineno"> 913</span>  STATE1 = vsha256h2q_u32(STATE1, TMP2, TMP1);</div><div class="line"><a name="l00914"></a><span class="lineno"> 914</span>  MSG1 = vsha256su1q_u32(MSG1, MSG3, MSG0);;</div><div class="line"><a name="l00915"></a><span class="lineno"> 915</span> </div><div class="line"><a name="l00916"></a><span class="lineno"> 916</span>  <span class="comment">// Rounds 40-43</span></div><div class="line"><a name="l00917"></a><span class="lineno"> 917</span>  MSG2 = vsha256su0q_u32(MSG2, MSG3);</div><div class="line"><a name="l00918"></a><span class="lineno"> 918</span>  TMP2 = STATE0;</div><div class="line"><a name="l00919"></a><span class="lineno"> 919</span>  TMP1 = vaddq_u32(MSG3, vld1q_u32(&SHA256_K[0x2c]));</div><div class="line"><a name="l00920"></a><span class="lineno"> 920</span>  STATE0 = vsha256hq_u32(STATE0, STATE1, TMP0);</div><div class="line"><a name="l00921"></a><span class="lineno"> 921</span>  STATE1 = vsha256h2q_u32(STATE1, TMP2, TMP0);</div><div class="line"><a name="l00922"></a><span class="lineno"> 922</span>  MSG2 = vsha256su1q_u32(MSG2, MSG0, MSG1);;</div><div class="line"><a name="l00923"></a><span class="lineno"> 923</span> </div><div class="line"><a name="l00924"></a><span class="lineno"> 924</span>  <span class="comment">// Rounds 44-47</span></div><div class="line"><a name="l00925"></a><span class="lineno"> 925</span>  MSG3 = vsha256su0q_u32(MSG3, MSG0);</div><div class="line"><a name="l00926"></a><span class="lineno"> 926</span>  TMP2 = STATE0;</div><div class="line"><a name="l00927"></a><span class="lineno"> 927</span>  TMP0 = vaddq_u32(MSG0, vld1q_u32(&SHA256_K[0x30]));</div><div class="line"><a name="l00928"></a><span class="lineno"> 928</span>  STATE0 = vsha256hq_u32(STATE0, STATE1, TMP1);</div><div class="line"><a name="l00929"></a><span class="lineno"> 929</span>  STATE1 = vsha256h2q_u32(STATE1, TMP2, TMP1);</div><div class="line"><a name="l00930"></a><span class="lineno"> 930</span>  MSG3 = vsha256su1q_u32(MSG3, MSG1, MSG2);;</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="comment">// Rounds 48-51</span></div><div class="line"><a name="l00933"></a><span class="lineno"> 933</span>  TMP2 = STATE0;</div><div class="line"><a name="l00934"></a><span class="lineno"> 934</span>  TMP1 = vaddq_u32(MSG1, vld1q_u32(&SHA256_K[0x34]));</div><div class="line"><a name="l00935"></a><span class="lineno"> 935</span>  STATE0 = vsha256hq_u32(STATE0, STATE1, TMP0);</div><div class="line"><a name="l00936"></a><span class="lineno"> 936</span>  STATE1 = vsha256h2q_u32(STATE1, TMP2, TMP0);;</div><div class="line"><a name="l00937"></a><span class="lineno"> 937</span> </div><div class="line"><a name="l00938"></a><span class="lineno"> 938</span>  <span class="comment">// Rounds 52-55</span></div><div class="line"><a name="l00939"></a><span class="lineno"> 939</span>  TMP2 = STATE0;</div><div class="line"><a name="l00940"></a><span class="lineno"> 940</span>  TMP0 = vaddq_u32(MSG2, vld1q_u32(&SHA256_K[0x38]));</div><div class="line"><a name="l00941"></a><span class="lineno"> 941</span>  STATE0 = vsha256hq_u32(STATE0, STATE1, TMP1);</div><div class="line"><a name="l00942"></a><span class="lineno"> 942</span>  STATE1 = vsha256h2q_u32(STATE1, TMP2, TMP1);;</div><div class="line"><a name="l00943"></a><span class="lineno"> 943</span> </div><div class="line"><a name="l00944"></a><span class="lineno"> 944</span>  <span class="comment">// Rounds 56-59</span></div><div class="line"><a name="l00945"></a><span class="lineno"> 945</span>  TMP2 = STATE0;</div><div class="line"><a name="l00946"></a><span class="lineno"> 946</span>  TMP1 = vaddq_u32(MSG3, vld1q_u32(&SHA256_K[0x3c]));</div><div class="line"><a name="l00947"></a><span class="lineno"> 947</span>  STATE0 = vsha256hq_u32(STATE0, STATE1, TMP0);</div><div class="line"><a name="l00948"></a><span class="lineno"> 948</span>  STATE1 = vsha256h2q_u32(STATE1, TMP2, TMP0);;</div><div class="line"><a name="l00949"></a><span class="lineno"> 949</span> </div><div class="line"><a name="l00950"></a><span class="lineno"> 950</span>  <span class="comment">// Rounds 60-63</span></div><div class="line"><a name="l00951"></a><span class="lineno"> 951</span>  TMP2 = STATE0;</div><div class="line"><a name="l00952"></a><span class="lineno"> 952</span>  STATE0 = vsha256hq_u32(STATE0, STATE1, TMP1);</div><div class="line"><a name="l00953"></a><span class="lineno"> 953</span>  STATE1 = vsha256h2q_u32(STATE1, TMP2, TMP1);;</div><div class="line"><a name="l00954"></a><span class="lineno"> 954</span> </div><div class="line"><a name="l00955"></a><span class="lineno"> 955</span>  <span class="comment">// Add back to state</span></div><div class="line"><a name="l00956"></a><span class="lineno"> 956</span>  STATE0 = vaddq_u32(STATE0, ABEF_SAVE);</div><div class="line"><a name="l00957"></a><span class="lineno"> 957</span>  STATE1 = vaddq_u32(STATE1, CDGH_SAVE);</div><div class="line"><a name="l00958"></a><span class="lineno"> 958</span> </div><div class="line"><a name="l00959"></a><span class="lineno"> 959</span>  data += SHA256::BLOCKSIZE/<span class="keyword">sizeof</span>(word32);</div><div class="line"><a name="l00960"></a><span class="lineno"> 960</span>  length -= SHA256::BLOCKSIZE;</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> </div><div class="line"><a name="l00963"></a><span class="lineno"> 963</span>  <span class="comment">// Save state</span></div><div class="line"><a name="l00964"></a><span class="lineno"> 964</span>  vst1q_u32(&state[0], STATE0);</div><div class="line"><a name="l00965"></a><span class="lineno"> 965</span>  vst1q_u32(&state[4], STATE1);</div><div class="line"><a name="l00966"></a><span class="lineno"> 966</span> }</div><div class="line"><a name="l00967"></a><span class="lineno"> 967</span> <span class="preprocessor">#endif // CRYPTOPP_ARM_SHA_AVAILABLE</span></div><div class="line"><a name="l00968"></a><span class="lineno"> 968</span> <span class="comment"></span></div><div class="line"><a name="l00969"></a><span class="lineno"> 969</span> <span class="comment">///////////////////////////////////////////////////////////</span></div><div class="line"><a name="l00970"></a><span class="lineno"> 970</span> <span class="comment"></span><span class="comment">// end of Walton, Schneiders, O'Rourke and Hovsmith code //</span><span class="comment"></span></div><div class="line"><a name="l00971"></a><span class="lineno"> 971</span> <span class="comment">///////////////////////////////////////////////////////////</span></div><div class="line"><a name="l00972"></a><span class="lineno"> 972</span> <span class="comment"></span></div><div class="line"><a name="l00973"></a><span class="lineno"> 973</span> <span class="comment">// ***************** Power8 SHA ********************</span></div><div class="line"><a name="l00974"></a><span class="lineno"> 974</span> <span class="comment"></span></div><div class="line"><a name="l00975"></a><span class="lineno"> 975</span> <span class="comment">//////////////////////////////////////////////////</span></div><div class="line"><a name="l00976"></a><span class="lineno"> 976</span> <span class="comment"></span><span class="comment">// start Gustavo, Serra, Scalet and Walton code //</span><span class="comment"></span></div><div class="line"><a name="l00977"></a><span class="lineno"> 977</span> <span class="comment">//////////////////////////////////////////////////</span></div><div class="line"><a name="l00978"></a><span class="lineno"> 978</span> <span class="comment"></span></div><div class="line"><a name="l00979"></a><span class="lineno"> 979</span> <span class="preprocessor">#if CRYPTOPP_POWER8_SHA_AVAILABLE</span></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="comment">// Indexes into the S[] array</span></div><div class="line"><a name="l00982"></a><span class="lineno"> 982</span> <span class="keyword">enum</span> {A=0, B=1, C, D, E, F, G, H};</div><div class="line"><a name="l00983"></a><span class="lineno"> 983</span> </div><div class="line"><a name="l00984"></a><span class="lineno"> 984</span> <span class="keyword">typedef</span> __vector <span class="keywordtype">unsigned</span> <span class="keywordtype">char</span> uint8x16_p8;</div><div class="line"><a name="l00985"></a><span class="lineno"> 985</span> <span class="keyword">typedef</span> __vector <span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> uint32x4_p8;</div><div class="line"><a name="l00986"></a><span class="lineno"> 986</span> <span class="keyword">typedef</span> __vector <span class="keywordtype">unsigned</span> <span class="keywordtype">long</span> <span class="keywordtype">long</span> uint64x2_p8;</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> uint32x4_p8 VEC_XL_BE(<span class="keywordtype">int</span> offset, <span class="keyword">const</span> uint8_t* data)</div><div class="line"><a name="l00989"></a><span class="lineno"> 989</span> {</div><div class="line"><a name="l00990"></a><span class="lineno"> 990</span> <span class="preprocessor">#if defined(CRYPTOPP_XLC_VERSION)</span></div><div class="line"><a name="l00991"></a><span class="lineno"> 991</span>  <span class="keywordflow">return</span> vec_xl_be(offset, data);</div><div class="line"><a name="l00992"></a><span class="lineno"> 992</span> <span class="preprocessor">#else</span></div><div class="line"><a name="l00993"></a><span class="lineno"> 993</span>  uint32x4_p8 res;</div><div class="line"><a name="l00994"></a><span class="lineno"> 994</span>  __asm(<span class="stringliteral">" lxvd2x %x0, %1, %2 \n\t"</span></div><div class="line"><a name="l00995"></a><span class="lineno"> 995</span>  : <span class="stringliteral">"=wa"</span> (res)</div><div class="line"><a name="l00996"></a><span class="lineno"> 996</span>  : <span class="stringliteral">"b"</span> (data), <span class="stringliteral">"r"</span> (offset));</div><div class="line"><a name="l00997"></a><span class="lineno"> 997</span>  <span class="keywordflow">return</span> res;</div><div class="line"><a name="l00998"></a><span class="lineno"> 998</span> <span class="preprocessor">#endif</span></div><div class="line"><a name="l00999"></a><span class="lineno"> 999</span> }</div><div class="line"><a name="l01000"></a><span class="lineno"> 1000</span> </div><div class="line"><a name="l01001"></a><span class="lineno"> 1001</span> <span class="preprocessor">#endif // CRYPTOPP_POWER8_SHA_AVAILABLE</span></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="preprocessor">#if CRYPTOPP_POWER8_SHA_AVAILABLE</span></div><div class="line"><a name="l01004"></a><span class="lineno"> 1004</span> </div><div class="line"><a name="l01005"></a><span class="lineno"> 1005</span> <span class="comment">// Aligned load</span></div><div class="line"><a name="l01006"></a><span class="lineno"> 1006</span> <span class="keyword">template</span> <<span class="keyword">class</span> T> <span class="keyword">static</span> <span class="keyword">inline</span></div><div class="line"><a name="l01007"></a><span class="lineno"> 1007</span> uint32x4_p8 VectorLoad32x4(<span class="keyword">const</span> T* data, <span class="keywordtype">int</span> offset)</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="keywordflow">return</span> (uint32x4_p8)vec_ld(offset, data);</div><div class="line"><a name="l01010"></a><span class="lineno"> 1010</span> }</div><div class="line"><a name="l01011"></a><span class="lineno"> 1011</span> </div><div class="line"><a name="l01012"></a><span class="lineno"> 1012</span> <span class="comment">// Unaligned load</span></div><div class="line"><a name="l01013"></a><span class="lineno"> 1013</span> <span class="keyword">template</span> <<span class="keyword">class</span> T> <span class="keyword">static</span> <span class="keyword">inline</span></div><div class="line"><a name="l01014"></a><span class="lineno"> 1014</span> uint32x4_p8 VectorLoad32x4u(<span class="keyword">const</span> T* data, <span class="keywordtype">int</span> offset)</div><div class="line"><a name="l01015"></a><span class="lineno"> 1015</span> {</div><div class="line"><a name="l01016"></a><span class="lineno"> 1016</span> <span class="preprocessor">#if defined(CRYPTOPP_XLC_VERSION)</span></div><div class="line"><a name="l01017"></a><span class="lineno"> 1017</span>  <span class="keywordflow">return</span> (uint32x4_p8)vec_xl(offset, data);</div><div class="line"><a name="l01018"></a><span class="lineno"> 1018</span> <span class="preprocessor">#else</span></div><div class="line"><a name="l01019"></a><span class="lineno"> 1019</span>  <span class="keywordflow">return</span> (uint32x4_p8)vec_vsx_ld(offset, data);</div><div class="line"><a name="l01020"></a><span class="lineno"> 1020</span> <span class="preprocessor">#endif</span></div><div class="line"><a name="l01021"></a><span class="lineno"> 1021</span> }</div><div class="line"><a name="l01022"></a><span class="lineno"> 1022</span> </div><div class="line"><a name="l01023"></a><span class="lineno"> 1023</span> <span class="comment">// Aligned store</span></div><div class="line"><a name="l01024"></a><span class="lineno"> 1024</span> <span class="keyword">template</span> <<span class="keyword">class</span> T> <span class="keyword">static</span> <span class="keyword">inline</span></div><div class="line"><a name="l01025"></a><span class="lineno"> 1025</span> <span class="keywordtype">void</span> VectorStore32x4(<span class="keyword">const</span> uint32x4_p8 val, T* data, <span class="keywordtype">int</span> offset)</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>  vec_st((uint8x16_p8)val, offset, data);</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> </div><div class="line"><a name="l01030"></a><span class="lineno"> 1030</span> <span class="comment">// Unaligned store</span></div><div class="line"><a name="l01031"></a><span class="lineno"> 1031</span> <span class="keyword">template</span> <<span class="keyword">class</span> T> <span class="keyword">static</span> <span class="keyword">inline</span></div><div class="line"><a name="l01032"></a><span class="lineno"> 1032</span> <span class="keywordtype">void</span> VectorStore32x4u(<span class="keyword">const</span> uint32x4_p8 val, T* data, <span class="keywordtype">int</span> offset)</div><div class="line"><a name="l01033"></a><span class="lineno"> 1033</span> {</div><div class="line"><a name="l01034"></a><span class="lineno"> 1034</span> <span class="preprocessor">#if defined(CRYPTOPP_XLC_VERSION)</span></div><div class="line"><a name="l01035"></a><span class="lineno"> 1035</span>  vec_xst((uint8x16_p8)val, offset, (uint8_t*)data);</div><div class="line"><a name="l01036"></a><span class="lineno"> 1036</span> <span class="preprocessor">#else</span></div><div class="line"><a name="l01037"></a><span class="lineno"> 1037</span>  vec_vsx_st((uint8x16_p8)val, offset, (uint8_t*)data);</div><div class="line"><a name="l01038"></a><span class="lineno"> 1038</span> <span class="preprocessor">#endif</span></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> </div><div class="line"><a name="l01041"></a><span class="lineno"> 1041</span> <span class="comment">// Unaligned load of a user message. The load is big-endian,</span></div><div class="line"><a name="l01042"></a><span class="lineno"> 1042</span> <span class="comment">// and then the message is permuted for 32-bit words.</span></div><div class="line"><a name="l01043"></a><span class="lineno"> 1043</span> <span class="keyword">template</span> <<span class="keyword">class</span> T> <span class="keyword">static</span> <span class="keyword">inline</span></div><div class="line"><a name="l01044"></a><span class="lineno"> 1044</span> uint32x4_p8 VectorLoadMsg32x4(<span class="keyword">const</span> T* data, <span class="keywordtype">int</span> offset)</div><div class="line"><a name="l01045"></a><span class="lineno"> 1045</span> {</div><div class="line"><a name="l01046"></a><span class="lineno"> 1046</span> <span class="preprocessor">#if defined(CRYPTOPP_LITTLE_ENDIAN)</span></div><div class="line"><a name="l01047"></a><span class="lineno"> 1047</span>  <span class="keyword">const</span> uint8x16_p8 mask = {3,2,1,0, 7,6,5,4, 11,10,9,8, 15,14,13,12};</div><div class="line"><a name="l01048"></a><span class="lineno"> 1048</span>  <span class="keyword">const</span> uint32x4_p8 r = VectorLoad32x4u(data, offset);</div><div class="line"><a name="l01049"></a><span class="lineno"> 1049</span>  <span class="keywordflow">return</span> (uint32x4_p8)vec_perm(r, r, mask);</div><div class="line"><a name="l01050"></a><span class="lineno"> 1050</span> <span class="preprocessor">#else</span></div><div class="line"><a name="l01051"></a><span class="lineno"> 1051</span>  <span class="keywordflow">return</span> VectorLoad32x4u(data, offset);</div><div class="line"><a name="l01052"></a><span class="lineno"> 1052</span> <span class="preprocessor">#endif</span></div><div class="line"><a name="l01053"></a><span class="lineno"> 1053</span> }</div><div class="line"><a name="l01054"></a><span class="lineno"> 1054</span> </div><div class="line"><a name="l01055"></a><span class="lineno"> 1055</span> <span class="keyword">static</span> <span class="keyword">inline</span></div><div class="line"><a name="l01056"></a><span class="lineno"> 1056</span> uint32x4_p8 VectorCh(<span class="keyword">const</span> uint32x4_p8 x, <span class="keyword">const</span> uint32x4_p8 y, <span class="keyword">const</span> uint32x4_p8 z)</div><div class="line"><a name="l01057"></a><span class="lineno"> 1057</span> {</div><div class="line"><a name="l01058"></a><span class="lineno"> 1058</span>  <span class="comment">// The trick below is due to Andy Polyakov and Jack Lloyd</span></div><div class="line"><a name="l01059"></a><span class="lineno"> 1059</span>  <span class="keywordflow">return</span> vec_sel(z,y,x);</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> </div><div class="line"><a name="l01062"></a><span class="lineno"> 1062</span> <span class="keyword">static</span> <span class="keyword">inline</span></div><div class="line"><a name="l01063"></a><span class="lineno"> 1063</span> uint32x4_p8 VectorMaj(<span class="keyword">const</span> uint32x4_p8 x, <span class="keyword">const</span> uint32x4_p8 y, <span class="keyword">const</span> uint32x4_p8 z)</div><div class="line"><a name="l01064"></a><span class="lineno"> 1064</span> {</div><div class="line"><a name="l01065"></a><span class="lineno"> 1065</span>  <span class="comment">// The trick below is due to Andy Polyakov and Jack Lloyd</span></div><div class="line"><a name="l01066"></a><span class="lineno"> 1066</span>  <span class="keywordflow">return</span> vec_sel(y, z, vec_xor(x, y));</div><div class="line"><a name="l01067"></a><span class="lineno"> 1067</span> }</div><div class="line"><a name="l01068"></a><span class="lineno"> 1068</span> </div><div class="line"><a name="l01069"></a><span class="lineno"> 1069</span> <span class="keyword">static</span> <span class="keyword">inline</span></div><div class="line"><a name="l01070"></a><span class="lineno"> 1070</span> uint32x4_p8 Vector_sigma0(<span class="keyword">const</span> uint32x4_p8 val)</div><div class="line"><a name="l01071"></a><span class="lineno"> 1071</span> {</div><div class="line"><a name="l01072"></a><span class="lineno"> 1072</span> <span class="preprocessor">#if defined(CRYPTOPP_XLC_VERSION)</span></div><div class="line"><a name="l01073"></a><span class="lineno"> 1073</span>  <span class="keywordflow">return</span> __vshasigmaw(val, 0, 0);</div><div class="line"><a name="l01074"></a><span class="lineno"> 1074</span> <span class="preprocessor">#else</span></div><div class="line"><a name="l01075"></a><span class="lineno"> 1075</span>  <span class="keywordflow">return</span> __builtin_crypto_vshasigmaw(val, 0, 0);</div><div class="line"><a name="l01076"></a><span class="lineno"> 1076</span> <span class="preprocessor">#endif</span></div><div class="line"><a name="l01077"></a><span class="lineno"> 1077</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="keyword">static</span> <span class="keyword">inline</span></div><div class="line"><a name="l01080"></a><span class="lineno"> 1080</span> uint32x4_p8 Vector_sigma1(<span class="keyword">const</span> uint32x4_p8 val)</div><div class="line"><a name="l01081"></a><span class="lineno"> 1081</span> {</div><div class="line"><a name="l01082"></a><span class="lineno"> 1082</span> <span class="preprocessor">#if defined(CRYPTOPP_XLC_VERSION)</span></div><div class="line"><a name="l01083"></a><span class="lineno"> 1083</span>  <span class="keywordflow">return</span> __vshasigmaw(val, 0, 0xf);</div><div class="line"><a name="l01084"></a><span class="lineno"> 1084</span> <span class="preprocessor">#else</span></div><div class="line"><a name="l01085"></a><span class="lineno"> 1085</span>  <span class="keywordflow">return</span> __builtin_crypto_vshasigmaw(val, 0, 0xf);</div><div class="line"><a name="l01086"></a><span class="lineno"> 1086</span> <span class="preprocessor">#endif</span></div><div class="line"><a name="l01087"></a><span class="lineno"> 1087</span> }</div><div class="line"><a name="l01088"></a><span class="lineno"> 1088</span> </div><div class="line"><a name="l01089"></a><span class="lineno"> 1089</span> <span class="keyword">static</span> <span class="keyword">inline</span></div><div class="line"><a name="l01090"></a><span class="lineno"> 1090</span> uint32x4_p8 VectorSigma0(<span class="keyword">const</span> uint32x4_p8 val)</div><div class="line"><a name="l01091"></a><span class="lineno"> 1091</span> {</div><div class="line"><a name="l01092"></a><span class="lineno"> 1092</span> <span class="preprocessor">#if defined(CRYPTOPP_XLC_VERSION)</span></div><div class="line"><a name="l01093"></a><span class="lineno"> 1093</span>  <span class="keywordflow">return</span> __vshasigmaw(val, 1, 0);</div><div class="line"><a name="l01094"></a><span class="lineno"> 1094</span> <span class="preprocessor">#else</span></div><div class="line"><a name="l01095"></a><span class="lineno"> 1095</span>  <span class="keywordflow">return</span> __builtin_crypto_vshasigmaw(val, 1, 0);</div><div class="line"><a name="l01096"></a><span class="lineno"> 1096</span> <span class="preprocessor">#endif</span></div><div class="line"><a name="l01097"></a><span class="lineno"> 1097</span> }</div><div class="line"><a name="l01098"></a><span class="lineno"> 1098</span> </div><div class="line"><a name="l01099"></a><span class="lineno"> 1099</span> <span class="keyword">static</span> <span class="keyword">inline</span></div><div class="line"><a name="l01100"></a><span class="lineno"> 1100</span> uint32x4_p8 VectorSigma1(<span class="keyword">const</span> uint32x4_p8 val)</div><div class="line"><a name="l01101"></a><span class="lineno"> 1101</span> {</div><div class="line"><a name="l01102"></a><span class="lineno"> 1102</span> <span class="preprocessor">#if defined(CRYPTOPP_XLC_VERSION)</span></div><div class="line"><a name="l01103"></a><span class="lineno"> 1103</span>  <span class="keywordflow">return</span> __vshasigmaw(val, 1, 0xf);</div><div class="line"><a name="l01104"></a><span class="lineno"> 1104</span> <span class="preprocessor">#else</span></div><div class="line"><a name="l01105"></a><span class="lineno"> 1105</span>  <span class="keywordflow">return</span> __builtin_crypto_vshasigmaw(val, 1, 0xf);</div><div class="line"><a name="l01106"></a><span class="lineno"> 1106</span> <span class="preprocessor">#endif</span></div><div class="line"><a name="l01107"></a><span class="lineno"> 1107</span> }</div><div class="line"><a name="l01108"></a><span class="lineno"> 1108</span> </div><div class="line"><a name="l01109"></a><span class="lineno"> 1109</span> <span class="keyword">static</span> <span class="keyword">inline</span></div><div class="line"><a name="l01110"></a><span class="lineno"> 1110</span> uint32x4_p8 VectorPack(<span class="keyword">const</span> uint32x4_p8 a, <span class="keyword">const</span> uint32x4_p8 b,</div><div class="line"><a name="l01111"></a><span class="lineno"> 1111</span>  <span class="keyword">const</span> uint32x4_p8 c, <span class="keyword">const</span> uint32x4_p8 d)</div><div class="line"><a name="l01112"></a><span class="lineno"> 1112</span> {</div><div class="line"><a name="l01113"></a><span class="lineno"> 1113</span>  <span class="keyword">const</span> uint8x16_p8 m1 = {0,1,2,3, 16,17,18,19, 0,0,0,0, 0,0,0,0};</div><div class="line"><a name="l01114"></a><span class="lineno"> 1114</span>  <span class="keyword">const</span> uint8x16_p8 m2 = {0,1,2,3, 4,5,6,7, 16,17,18,19, 20,21,22,23};</div><div class="line"><a name="l01115"></a><span class="lineno"> 1115</span>  <span class="keywordflow">return</span> vec_perm(vec_perm(a,b,m1), vec_perm(c,d,m1), m2);</div><div class="line"><a name="l01116"></a><span class="lineno"> 1116</span> }</div><div class="line"><a name="l01117"></a><span class="lineno"> 1117</span> </div><div class="line"><a name="l01118"></a><span class="lineno"> 1118</span> <span class="keyword">template</span> <<span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> L> <span class="keyword">static</span> <span class="keyword">inline</span></div><div class="line"><a name="l01119"></a><span class="lineno"> 1119</span> uint32x4_p8 <a class="code" href="ppc-simd_8h.html#ab73b86116b8a0520419ad240b760ac39">VectorShiftLeft</a>(<span class="keyword">const</span> uint32x4_p8 val)</div><div class="line"><a name="l01120"></a><span class="lineno"> 1120</span> {</div><div class="line"><a name="l01121"></a><span class="lineno"> 1121</span> <span class="preprocessor">#if (defined(CRYPTOPP_LITTLE_ENDIAN))</span></div><div class="line"><a name="l01122"></a><span class="lineno"> 1122</span>  <span class="keywordflow">return</span> (uint32x4_p8)vec_sld((uint8x16_p8)val, (uint8x16_p8)val, (16-L)&0xf);</div><div class="line"><a name="l01123"></a><span class="lineno"> 1123</span> <span class="preprocessor">#else</span></div><div class="line"><a name="l01124"></a><span class="lineno"> 1124</span>  <span class="keywordflow">return</span> (uint32x4_p8)vec_sld((uint8x16_p8)val, (uint8x16_p8)val, L&0xf);</div><div class="line"><a name="l01125"></a><span class="lineno"> 1125</span> <span class="preprocessor">#endif</span></div><div class="line"><a name="l01126"></a><span class="lineno"> 1126</span> }</div><div class="line"><a name="l01127"></a><span class="lineno"> 1127</span> </div><div class="line"><a name="l01128"></a><span class="lineno"> 1128</span> <span class="keyword">template</span> <></div><div class="line"><a name="l01129"></a><span class="lineno"> 1129</span> uint32x4_p8 VectorShiftLeft<0>(<span class="keyword">const</span> uint32x4_p8 val) { <span class="keywordflow">return</span> val; }</div><div class="line"><a name="l01130"></a><span class="lineno"> 1130</span> </div><div class="line"><a name="l01131"></a><span class="lineno"> 1131</span> <span class="keyword">template</span> <></div><div class="line"><a name="l01132"></a><span class="lineno"> 1132</span> uint32x4_p8 VectorShiftLeft<16>(<span class="keyword">const</span> uint32x4_p8 val) { <span class="keywordflow">return</span> val; }</div><div class="line"><a name="l01133"></a><span class="lineno"> 1133</span> </div><div class="line"><a name="l01134"></a><span class="lineno"> 1134</span> <span class="keyword">template</span> <<span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> R> <span class="keyword">static</span> <span class="keyword">inline</span></div><div class="line"><a name="l01135"></a><span class="lineno"> 1135</span> <span class="keywordtype">void</span> SHA256_ROUND1(uint32x4_p8 W[16], uint32x4_p8 S[8], <span class="keyword">const</span> uint32x4_p8 K, <span class="keyword">const</span> uint32x4_p8 M)</div><div class="line"><a name="l01136"></a><span class="lineno"> 1136</span> {</div><div class="line"><a name="l01137"></a><span class="lineno"> 1137</span>  uint32x4_p8 T1, T2;</div><div class="line"><a name="l01138"></a><span class="lineno"> 1138</span> </div><div class="line"><a name="l01139"></a><span class="lineno"> 1139</span>  W[R] = M;</div><div class="line"><a name="l01140"></a><span class="lineno"> 1140</span>  T1 = S[H] + VectorSigma1(S[E]) + VectorCh(S[E],S[F],S[G]) + K + M;</div><div class="line"><a name="l01141"></a><span class="lineno"> 1141</span>  T2 = VectorSigma0(S[A]) + VectorMaj(S[A],S[B],S[C]);</div><div class="line"><a name="l01142"></a><span class="lineno"> 1142</span> </div><div class="line"><a name="l01143"></a><span class="lineno"> 1143</span>  S[H] = S[G]; S[G] = S[F]; S[F] = S[E];</div><div class="line"><a name="l01144"></a><span class="lineno"> 1144</span>  S[E] = S[D] + T1;</div><div class="line"><a name="l01145"></a><span class="lineno"> 1145</span>  S[D] = S[C]; S[C] = S[B]; S[B] = S[A];</div><div class="line"><a name="l01146"></a><span class="lineno"> 1146</span>  S[A] = T1 + T2;</div><div class="line"><a name="l01147"></a><span class="lineno"> 1147</span> }</div><div class="line"><a name="l01148"></a><span class="lineno"> 1148</span> </div><div class="line"><a name="l01149"></a><span class="lineno"> 1149</span> <span class="keyword">template</span> <<span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> R> <span class="keyword">static</span> <span class="keyword">inline</span></div><div class="line"><a name="l01150"></a><span class="lineno"> 1150</span> <span class="keywordtype">void</span> SHA256_ROUND2(uint32x4_p8 W[16], uint32x4_p8 S[8], <span class="keyword">const</span> uint32x4_p8 K)</div><div class="line"><a name="l01151"></a><span class="lineno"> 1151</span> {</div><div class="line"><a name="l01152"></a><span class="lineno"> 1152</span>  <span class="comment">// Indexes into the W[] array</span></div><div class="line"><a name="l01153"></a><span class="lineno"> 1153</span>  <span class="keyword">enum</span> {IDX0=(R+0)&0xf, IDX1=(R+1)&0xf, IDX9=(R+9)&0xf, IDX14=(R+14)&0xf};</div><div class="line"><a name="l01154"></a><span class="lineno"> 1154</span> </div><div class="line"><a name="l01155"></a><span class="lineno"> 1155</span>  <span class="keyword">const</span> uint32x4_p8 s0 = Vector_sigma0(W[IDX1]);</div><div class="line"><a name="l01156"></a><span class="lineno"> 1156</span>  <span class="keyword">const</span> uint32x4_p8 s1 = Vector_sigma1(W[IDX14]);</div><div class="line"><a name="l01157"></a><span class="lineno"> 1157</span> </div><div class="line"><a name="l01158"></a><span class="lineno"> 1158</span>  uint32x4_p8 T1 = (W[IDX0] += s0 + s1 + W[IDX9]);</div><div class="line"><a name="l01159"></a><span class="lineno"> 1159</span>  T1 += S[H] + VectorSigma1(S[E]) + VectorCh(S[E],S[F],S[G]) + K;</div><div class="line"><a name="l01160"></a><span class="lineno"> 1160</span>  uint32x4_p8 T2 = VectorSigma0(S[A]) + VectorMaj(S[A],S[B],S[C]);</div><div class="line"><a name="l01161"></a><span class="lineno"> 1161</span> </div><div class="line"><a name="l01162"></a><span class="lineno"> 1162</span>  S[H] = S[G]; S[G] = S[F]; S[F] = S[E];</div><div class="line"><a name="l01163"></a><span class="lineno"> 1163</span>  S[E] = S[D] + T1;</div><div class="line"><a name="l01164"></a><span class="lineno"> 1164</span>  S[D] = S[C]; S[C] = S[B]; S[B] = S[A];</div><div class="line"><a name="l01165"></a><span class="lineno"> 1165</span>  S[A] = T1 + T2;</div><div class="line"><a name="l01166"></a><span class="lineno"> 1166</span> }</div><div class="line"><a name="l01167"></a><span class="lineno"> 1167</span> </div><div class="line"><a name="l01168"></a><span class="lineno"> 1168</span> <span class="keywordtype">void</span> SHA256_HashMultipleBlocks_POWER8(word32 *state, <span class="keyword">const</span> word32 *data, <span class="keywordtype">size_t</span> length, <a class="code" href="cryptlib_8h.html#aaeb92d42f5a6e27b8ba19f18d69d142b">ByteOrder</a> order)</div><div class="line"><a name="l01169"></a><span class="lineno"> 1169</span> {</div><div class="line"><a name="l01170"></a><span class="lineno"> 1170</span>  <a class="code" href="trap_8h.html#adf3b392588bc94cbeae9f415a78c7b95">CRYPTOPP_ASSERT</a>(state); <a class="code" href="trap_8h.html#adf3b392588bc94cbeae9f415a78c7b95">CRYPTOPP_ASSERT</a>(data);</div><div class="line"><a name="l01171"></a><span class="lineno"> 1171</span>  <a class="code" href="trap_8h.html#adf3b392588bc94cbeae9f415a78c7b95">CRYPTOPP_ASSERT</a>(length >= SHA256::BLOCKSIZE);</div><div class="line"><a name="l01172"></a><span class="lineno"> 1172</span>  CRYPTOPP_UNUSED(order);</div><div class="line"><a name="l01173"></a><span class="lineno"> 1173</span> </div><div class="line"><a name="l01174"></a><span class="lineno"> 1174</span>  <span class="keyword">const</span> uint32_t* k = <span class="keyword">reinterpret_cast<</span><span class="keyword">const </span>uint32_t*<span class="keyword">></span>(SHA256_K);</div><div class="line"><a name="l01175"></a><span class="lineno"> 1175</span>  <span class="keyword">const</span> uint32_t* m = <span class="keyword">reinterpret_cast<</span><span class="keyword">const </span>uint32_t*<span class="keyword">></span>(data);</div><div class="line"><a name="l01176"></a><span class="lineno"> 1176</span> </div><div class="line"><a name="l01177"></a><span class="lineno"> 1177</span>  uint32x4_p8 abcd = VectorLoad32x4u(state+0, 0);</div><div class="line"><a name="l01178"></a><span class="lineno"> 1178</span>  uint32x4_p8 efgh = VectorLoad32x4u(state+4, 0);</div><div class="line"><a name="l01179"></a><span class="lineno"> 1179</span>  uint32x4_p8 W[16], S[8], vm, vk;</div><div class="line"><a name="l01180"></a><span class="lineno"> 1180</span> </div><div class="line"><a name="l01181"></a><span class="lineno"> 1181</span>  <span class="keywordtype">size_t</span> blocks = length / SHA256::BLOCKSIZE;</div><div class="line"><a name="l01182"></a><span class="lineno"> 1182</span>  <span class="keywordflow">while</span> (blocks--)</div><div class="line"><a name="l01183"></a><span class="lineno"> 1183</span>  {</div><div class="line"><a name="l01184"></a><span class="lineno"> 1184</span>  <span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> i, offset=0;</div><div class="line"><a name="l01185"></a><span class="lineno"> 1185</span> </div><div class="line"><a name="l01186"></a><span class="lineno"> 1186</span>  S[A] = abcd; S[E] = efgh;</div><div class="line"><a name="l01187"></a><span class="lineno"> 1187</span>  S[B] = VectorShiftLeft<4>(S[A]);</div><div class="line"><a name="l01188"></a><span class="lineno"> 1188</span>  S[F] = VectorShiftLeft<4>(S[E]);</div><div class="line"><a name="l01189"></a><span class="lineno"> 1189</span>  S[C] = VectorShiftLeft<4>(S[B]);</div><div class="line"><a name="l01190"></a><span class="lineno"> 1190</span>  S[G] = VectorShiftLeft<4>(S[F]);</div><div class="line"><a name="l01191"></a><span class="lineno"> 1191</span>  S[D] = VectorShiftLeft<4>(S[C]);</div><div class="line"><a name="l01192"></a><span class="lineno"> 1192</span>  S[H] = VectorShiftLeft<4>(S[G]);</div><div class="line"><a name="l01193"></a><span class="lineno"> 1193</span> </div><div class="line"><a name="l01194"></a><span class="lineno"> 1194</span>  <span class="comment">// Unroll the loop to provide the round number as a constexpr</span></div><div class="line"><a name="l01195"></a><span class="lineno"> 1195</span>  <span class="comment">// for (unsigned int i=0; i<16; ++i)</span></div><div class="line"><a name="l01196"></a><span class="lineno"> 1196</span>  {</div><div class="line"><a name="l01197"></a><span class="lineno"> 1197</span>  vk = VectorLoad32x4(k, offset);</div><div class="line"><a name="l01198"></a><span class="lineno"> 1198</span>  vm = VectorLoadMsg32x4(m, offset);</div><div class="line"><a name="l01199"></a><span class="lineno"> 1199</span>  SHA256_ROUND1<0>(W,S, vk,vm);</div><div class="line"><a name="l01200"></a><span class="lineno"> 1200</span>  offset+=16;</div><div class="line"><a name="l01201"></a><span class="lineno"> 1201</span> </div><div class="line"><a name="l01202"></a><span class="lineno"> 1202</span>  vk = VectorShiftLeft<4>(vk);</div><div class="line"><a name="l01203"></a><span class="lineno"> 1203</span>  vm = VectorShiftLeft<4>(vm);</div><div class="line"><a name="l01204"></a><span class="lineno"> 1204</span>  SHA256_ROUND1<1>(W,S, vk,vm);</div><div class="line"><a name="l01205"></a><span class="lineno"> 1205</span> </div><div class="line"><a name="l01206"></a><span class="lineno"> 1206</span>  vk = VectorShiftLeft<4>(vk);</div><div class="line"><a name="l01207"></a><span class="lineno"> 1207</span>  vm = VectorShiftLeft<4>(vm);</div><div class="line"><a name="l01208"></a><span class="lineno"> 1208</span>  SHA256_ROUND1<2>(W,S, vk,vm);</div><div class="line"><a name="l01209"></a><span class="lineno"> 1209</span> </div><div class="line"><a name="l01210"></a><span class="lineno"> 1210</span>  vk = VectorShiftLeft<4>(vk);</div><div class="line"><a name="l01211"></a><span class="lineno"> 1211</span>  vm = VectorShiftLeft<4>(vm);</div><div class="line"><a name="l01212"></a><span class="lineno"> 1212</span>  SHA256_ROUND1<3>(W,S, vk,vm);</div><div class="line"><a name="l01213"></a><span class="lineno"> 1213</span> </div><div class="line"><a name="l01214"></a><span class="lineno"> 1214</span>  vk = VectorLoad32x4(k, offset);</div><div class="line"><a name="l01215"></a><span class="lineno"> 1215</span>  vm = VectorLoadMsg32x4(m, offset);</div><div class="line"><a name="l01216"></a><span class="lineno"> 1216</span>  SHA256_ROUND1<4>(W,S, vk,vm);</div><div class="line"><a name="l01217"></a><span class="lineno"> 1217</span>  offset+=16;</div><div class="line"><a name="l01218"></a><span class="lineno"> 1218</span> </div><div class="line"><a name="l01219"></a><span class="lineno"> 1219</span>  vk = VectorShiftLeft<4>(vk);</div><div class="line"><a name="l01220"></a><span class="lineno"> 1220</span>  vm = VectorShiftLeft<4>(vm);</div><div class="line"><a name="l01221"></a><span class="lineno"> 1221</span>  SHA256_ROUND1<5>(W,S, vk,vm);</div><div class="line"><a name="l01222"></a><span class="lineno"> 1222</span> </div><div class="line"><a name="l01223"></a><span class="lineno"> 1223</span>  vk = VectorShiftLeft<4>(vk);</div><div class="line"><a name="l01224"></a><span class="lineno"> 1224</span>  vm = VectorShiftLeft<4>(vm);</div><div class="line"><a name="l01225"></a><span class="lineno"> 1225</span>  SHA256_ROUND1<6>(W,S, vk,vm);</div><div class="line"><a name="l01226"></a><span class="lineno"> 1226</span> </div><div class="line"><a name="l01227"></a><span class="lineno"> 1227</span>  vk = VectorShiftLeft<4>(vk);</div><div class="line"><a name="l01228"></a><span class="lineno"> 1228</span>  vm = VectorShiftLeft<4>(vm);</div><div class="line"><a name="l01229"></a><span class="lineno"> 1229</span>  SHA256_ROUND1<7>(W,S, vk,vm);</div><div class="line"><a name="l01230"></a><span class="lineno"> 1230</span> </div><div class="line"><a name="l01231"></a><span class="lineno"> 1231</span>  vk = VectorLoad32x4(k, offset);</div><div class="line"><a name="l01232"></a><span class="lineno"> 1232</span>  vm = VectorLoadMsg32x4(m, offset);</div><div class="line"><a name="l01233"></a><span class="lineno"> 1233</span>  SHA256_ROUND1<8>(W,S, vk,vm);</div><div class="line"><a name="l01234"></a><span class="lineno"> 1234</span>  offset+=16;</div><div class="line"><a name="l01235"></a><span class="lineno"> 1235</span> </div><div class="line"><a name="l01236"></a><span class="lineno"> 1236</span>  vk = VectorShiftLeft<4>(vk);</div><div class="line"><a name="l01237"></a><span class="lineno"> 1237</span>  vm = VectorShiftLeft<4>(vm);</div><div class="line"><a name="l01238"></a><span class="lineno"> 1238</span>  SHA256_ROUND1<9>(W,S, vk,vm);</div><div class="line"><a name="l01239"></a><span class="lineno"> 1239</span> </div><div class="line"><a name="l01240"></a><span class="lineno"> 1240</span>  vk = VectorShiftLeft<4>(vk);</div><div class="line"><a name="l01241"></a><span class="lineno"> 1241</span>  vm = VectorShiftLeft<4>(vm);</div><div class="line"><a name="l01242"></a><span class="lineno"> 1242</span>  SHA256_ROUND1<10>(W,S, vk,vm);</div><div class="line"><a name="l01243"></a><span class="lineno"> 1243</span> </div><div class="line"><a name="l01244"></a><span class="lineno"> 1244</span>  vk = VectorShiftLeft<4>(vk);</div><div class="line"><a name="l01245"></a><span class="lineno"> 1245</span>  vm = VectorShiftLeft<4>(vm);</div><div class="line"><a name="l01246"></a><span class="lineno"> 1246</span>  SHA256_ROUND1<11>(W,S, vk,vm);</div><div class="line"><a name="l01247"></a><span class="lineno"> 1247</span> </div><div class="line"><a name="l01248"></a><span class="lineno"> 1248</span>  vk = VectorLoad32x4(k, offset);</div><div class="line"><a name="l01249"></a><span class="lineno"> 1249</span>  vm = VectorLoadMsg32x4(m, offset);</div><div class="line"><a name="l01250"></a><span class="lineno"> 1250</span>  SHA256_ROUND1<12>(W,S, vk,vm);</div><div class="line"><a name="l01251"></a><span class="lineno"> 1251</span>  offset+=16;</div><div class="line"><a name="l01252"></a><span class="lineno"> 1252</span> </div><div class="line"><a name="l01253"></a><span class="lineno"> 1253</span>  vk = VectorShiftLeft<4>(vk);</div><div class="line"><a name="l01254"></a><span class="lineno"> 1254</span>  vm = VectorShiftLeft<4>(vm);</div><div class="line"><a name="l01255"></a><span class="lineno"> 1255</span>  SHA256_ROUND1<13>(W,S, vk,vm);</div><div class="line"><a name="l01256"></a><span class="lineno"> 1256</span> </div><div class="line"><a name="l01257"></a><span class="lineno"> 1257</span>  vk = VectorShiftLeft<4>(vk);</div><div class="line"><a name="l01258"></a><span class="lineno"> 1258</span>  vm = VectorShiftLeft<4>(vm);</div><div class="line"><a name="l01259"></a><span class="lineno"> 1259</span>  SHA256_ROUND1<14>(W,S, vk,vm);</div><div class="line"><a name="l01260"></a><span class="lineno"> 1260</span> </div><div class="line"><a name="l01261"></a><span class="lineno"> 1261</span>  vk = VectorShiftLeft<4>(vk);</div><div class="line"><a name="l01262"></a><span class="lineno"> 1262</span>  vm = VectorShiftLeft<4>(vm);</div><div class="line"><a name="l01263"></a><span class="lineno"> 1263</span>  SHA256_ROUND1<15>(W,S, vk,vm);</div><div class="line"><a name="l01264"></a><span class="lineno"> 1264</span>  }</div><div class="line"><a name="l01265"></a><span class="lineno"> 1265</span> </div><div class="line"><a name="l01266"></a><span class="lineno"> 1266</span>  m += 16; <span class="comment">// 32-bit words, not bytes</span></div><div class="line"><a name="l01267"></a><span class="lineno"> 1267</span> </div><div class="line"><a name="l01268"></a><span class="lineno"> 1268</span>  <span class="keywordflow">for</span> (i=16; i<64; i+=16)</div><div class="line"><a name="l01269"></a><span class="lineno"> 1269</span>  {</div><div class="line"><a name="l01270"></a><span class="lineno"> 1270</span>  vk = VectorLoad32x4(k, offset);</div><div class="line"><a name="l01271"></a><span class="lineno"> 1271</span>  SHA256_ROUND2<0>(W,S, vk);</div><div class="line"><a name="l01272"></a><span class="lineno"> 1272</span>  SHA256_ROUND2<1>(W,S, VectorShiftLeft<4>(vk));</div><div class="line"><a name="l01273"></a><span class="lineno"> 1273</span>  SHA256_ROUND2<2>(W,S, VectorShiftLeft<8>(vk));</div><div class="line"><a name="l01274"></a><span class="lineno"> 1274</span>  SHA256_ROUND2<3>(W,S, VectorShiftLeft<12>(vk));</div><div class="line"><a name="l01275"></a><span class="lineno"> 1275</span>  offset+=16;</div><div class="line"><a name="l01276"></a><span class="lineno"> 1276</span> </div><div class="line"><a name="l01277"></a><span class="lineno"> 1277</span>  vk = VectorLoad32x4(k, offset);</div><div class="line"><a name="l01278"></a><span class="lineno"> 1278</span>  SHA256_ROUND2<4>(W,S, vk);</div><div class="line"><a name="l01279"></a><span class="lineno"> 1279</span>  SHA256_ROUND2<5>(W,S, VectorShiftLeft<4>(vk));</div><div class="line"><a name="l01280"></a><span class="lineno"> 1280</span>  SHA256_ROUND2<6>(W,S, VectorShiftLeft<8>(vk));</div><div class="line"><a name="l01281"></a><span class="lineno"> 1281</span>  SHA256_ROUND2<7>(W,S, VectorShiftLeft<12>(vk));</div><div class="line"><a name="l01282"></a><span class="lineno"> 1282</span>  offset+=16;</div><div class="line"><a name="l01283"></a><span class="lineno"> 1283</span> </div><div class="line"><a name="l01284"></a><span class="lineno"> 1284</span>  vk = VectorLoad32x4(k, offset);</div><div class="line"><a name="l01285"></a><span class="lineno"> 1285</span>  SHA256_ROUND2<8>(W,S, vk);</div><div class="line"><a name="l01286"></a><span class="lineno"> 1286</span>  SHA256_ROUND2<9>(W,S, VectorShiftLeft<4>(vk));</div><div class="line"><a name="l01287"></a><span class="lineno"> 1287</span>  SHA256_ROUND2<10>(W,S, VectorShiftLeft<8>(vk));</div><div class="line"><a name="l01288"></a><span class="lineno"> 1288</span>  SHA256_ROUND2<11>(W,S, VectorShiftLeft<12>(vk));</div><div class="line"><a name="l01289"></a><span class="lineno"> 1289</span>  offset+=16;</div><div class="line"><a name="l01290"></a><span class="lineno"> 1290</span> </div><div class="line"><a name="l01291"></a><span class="lineno"> 1291</span>  vk = VectorLoad32x4(k, offset);</div><div class="line"><a name="l01292"></a><span class="lineno"> 1292</span>  SHA256_ROUND2<12>(W,S, vk);</div><div class="line"><a name="l01293"></a><span class="lineno"> 1293</span>  SHA256_ROUND2<13>(W,S, VectorShiftLeft<4>(vk));</div><div class="line"><a name="l01294"></a><span class="lineno"> 1294</span>  SHA256_ROUND2<14>(W,S, VectorShiftLeft<8>(vk));</div><div class="line"><a name="l01295"></a><span class="lineno"> 1295</span>  SHA256_ROUND2<15>(W,S, VectorShiftLeft<12>(vk));</div><div class="line"><a name="l01296"></a><span class="lineno"> 1296</span>  offset+=16;</div><div class="line"><a name="l01297"></a><span class="lineno"> 1297</span>  }</div><div class="line"><a name="l01298"></a><span class="lineno"> 1298</span> </div><div class="line"><a name="l01299"></a><span class="lineno"> 1299</span>  abcd += VectorPack(S[A],S[B],S[C],S[D]);</div><div class="line"><a name="l01300"></a><span class="lineno"> 1300</span>  efgh += VectorPack(S[E],S[F],S[G],S[H]);</div><div class="line"><a name="l01301"></a><span class="lineno"> 1301</span>  }</div><div class="line"><a name="l01302"></a><span class="lineno"> 1302</span> </div><div class="line"><a name="l01303"></a><span class="lineno"> 1303</span>  VectorStore32x4u(abcd, state+0, 0);</div><div class="line"><a name="l01304"></a><span class="lineno"> 1304</span>  VectorStore32x4u(efgh, state+4, 0);</div><div class="line"><a name="l01305"></a><span class="lineno"> 1305</span> }</div><div class="line"><a name="l01306"></a><span class="lineno"> 1306</span> </div><div class="line"><a name="l01307"></a><span class="lineno"> 1307</span> <span class="keyword">static</span> <span class="keyword">inline</span></div><div class="line"><a name="l01308"></a><span class="lineno"> 1308</span> uint64x2_p8 VectorPermute64x2(<span class="keyword">const</span> uint64x2_p8 val, <span class="keyword">const</span> uint8x16_p8 mask)</div><div class="line"><a name="l01309"></a><span class="lineno"> 1309</span> {</div><div class="line"><a name="l01310"></a><span class="lineno"> 1310</span>  <span class="keywordflow">return</span> (uint64x2_p8)vec_perm(val, val, mask);</div><div class="line"><a name="l01311"></a><span class="lineno"> 1311</span> }</div><div class="line"><a name="l01312"></a><span class="lineno"> 1312</span> </div><div class="line"><a name="l01313"></a><span class="lineno"> 1313</span> <span class="comment">// Aligned load</span></div><div class="line"><a name="l01314"></a><span class="lineno"> 1314</span> <span class="keyword">template</span> <<span class="keyword">class</span> T> <span class="keyword">static</span> <span class="keyword">inline</span></div><div class="line"><a name="l01315"></a><span class="lineno"> 1315</span> uint64x2_p8 VectorLoad64x2(<span class="keyword">const</span> T* data, <span class="keywordtype">int</span> offset)</div><div class="line"><a name="l01316"></a><span class="lineno"> 1316</span> {</div><div class="line"><a name="l01317"></a><span class="lineno"> 1317</span>  <span class="keywordflow">return</span> (uint64x2_p8)vec_ld(offset, (<span class="keyword">const</span> uint8_t*)data);</div><div class="line"><a name="l01318"></a><span class="lineno"> 1318</span> }</div><div class="line"><a name="l01319"></a><span class="lineno"> 1319</span> </div><div class="line"><a name="l01320"></a><span class="lineno"> 1320</span> <span class="comment">// Unaligned load</span></div><div class="line"><a name="l01321"></a><span class="lineno"> 1321</span> <span class="keyword">template</span> <<span class="keyword">class</span> T> <span class="keyword">static</span> <span class="keyword">inline</span></div><div class="line"><a name="l01322"></a><span class="lineno"> 1322</span> uint64x2_p8 VectorLoad64x2u(<span class="keyword">const</span> T* data, <span class="keywordtype">int</span> offset)</div><div class="line"><a name="l01323"></a><span class="lineno"> 1323</span> {</div><div class="line"><a name="l01324"></a><span class="lineno"> 1324</span> <span class="preprocessor">#if defined(CRYPTOPP_XLC_VERSION)</span></div><div class="line"><a name="l01325"></a><span class="lineno"> 1325</span>  <span class="keywordflow">return</span> (uint64x2_p8)vec_xl(offset, (<span class="keyword">const</span> uint8_t*)data);</div><div class="line"><a name="l01326"></a><span class="lineno"> 1326</span> <span class="preprocessor">#else</span></div><div class="line"><a name="l01327"></a><span class="lineno"> 1327</span>  <span class="keywordflow">return</span> (uint64x2_p8)vec_vsx_ld(offset, (<span class="keyword">const</span> uint8_t*)data);</div><div class="line"><a name="l01328"></a><span class="lineno"> 1328</span> <span class="preprocessor">#endif</span></div><div class="line"><a name="l01329"></a><span class="lineno"> 1329</span> }</div><div class="line"><a name="l01330"></a><span class="lineno"> 1330</span> </div><div class="line"><a name="l01331"></a><span class="lineno"> 1331</span> <span class="comment">// Aligned store</span></div><div class="line"><a name="l01332"></a><span class="lineno"> 1332</span> <span class="keyword">template</span> <<span class="keyword">class</span> T> <span class="keyword">static</span> <span class="keyword">inline</span></div><div class="line"><a name="l01333"></a><span class="lineno"> 1333</span> <span class="keywordtype">void</span> VectorStore64x2(<span class="keyword">const</span> uint64x2_p8 val, T* data, <span class="keywordtype">int</span> offset)</div><div class="line"><a name="l01334"></a><span class="lineno"> 1334</span> {</div><div class="line"><a name="l01335"></a><span class="lineno"> 1335</span>  vec_st((uint8x16_p8)val, offset, (uint8_t*)data);</div><div class="line"><a name="l01336"></a><span class="lineno"> 1336</span> }</div><div class="line"><a name="l01337"></a><span class="lineno"> 1337</span> </div><div class="line"><a name="l01338"></a><span class="lineno"> 1338</span> <span class="comment">// Unaligned store</span></div><div class="line"><a name="l01339"></a><span class="lineno"> 1339</span> <span class="keyword">template</span> <<span class="keyword">class</span> T> <span class="keyword">static</span> <span class="keyword">inline</span></div><div class="line"><a name="l01340"></a><span class="lineno"> 1340</span> <span class="keywordtype">void</span> VectorStore64x2u(<span class="keyword">const</span> uint64x2_p8 val, T* data, <span class="keywordtype">int</span> offset)</div><div class="line"><a name="l01341"></a><span class="lineno"> 1341</span> {</div><div class="line"><a name="l01342"></a><span class="lineno"> 1342</span> <span class="preprocessor">#if defined(CRYPTOPP_XLC_VERSION)</span></div><div class="line"><a name="l01343"></a><span class="lineno"> 1343</span>  vec_xst((uint8x16_p8)val, offset, (uint8_t*)data);</div><div class="line"><a name="l01344"></a><span class="lineno"> 1344</span> <span class="preprocessor">#else</span></div><div class="line"><a name="l01345"></a><span class="lineno"> 1345</span>  vec_vsx_st((uint8x16_p8)val, offset, (uint8_t*)data);</div><div class="line"><a name="l01346"></a><span class="lineno"> 1346</span> <span class="preprocessor">#endif</span></div><div class="line"><a name="l01347"></a><span class="lineno"> 1347</span> }</div><div class="line"><a name="l01348"></a><span class="lineno"> 1348</span> </div><div class="line"><a name="l01349"></a><span class="lineno"> 1349</span> <span class="comment">// Unaligned load of a user message. The load is big-endian,</span></div><div class="line"><a name="l01350"></a><span class="lineno"> 1350</span> <span class="comment">// and then the message is permuted for 32-bit words.</span></div><div class="line"><a name="l01351"></a><span class="lineno"> 1351</span> <span class="keyword">template</span> <<span class="keyword">class</span> T> <span class="keyword">static</span> <span class="keyword">inline</span></div><div class="line"><a name="l01352"></a><span class="lineno"> 1352</span> uint64x2_p8 VectorLoadMsg64x2(<span class="keyword">const</span> T* data, <span class="keywordtype">int</span> offset)</div><div class="line"><a name="l01353"></a><span class="lineno"> 1353</span> {</div><div class="line"><a name="l01354"></a><span class="lineno"> 1354</span> <span class="preprocessor">#if defined(CRYPTOPP_LITTLE_ENDIAN)</span></div><div class="line"><a name="l01355"></a><span class="lineno"> 1355</span>  <span class="keyword">const</span> uint8x16_p8 mask = {0,1,2,3, 4,5,6,7, 8,9,10,11, 12,13,14,15};</div><div class="line"><a name="l01356"></a><span class="lineno"> 1356</span>  <span class="keywordflow">return</span> VectorPermute64x2(VectorLoad64x2u(data, offset), mask);</div><div class="line"><a name="l01357"></a><span class="lineno"> 1357</span> <span class="preprocessor">#else</span></div><div class="line"><a name="l01358"></a><span class="lineno"> 1358</span>  <span class="keywordflow">return</span> VectorLoad64x2u(data, offset);</div><div class="line"><a name="l01359"></a><span class="lineno"> 1359</span> <span class="preprocessor">#endif</span></div><div class="line"><a name="l01360"></a><span class="lineno"> 1360</span> }</div><div class="line"><a name="l01361"></a><span class="lineno"> 1361</span> </div><div class="line"><a name="l01362"></a><span class="lineno"> 1362</span> <span class="keyword">static</span> <span class="keyword">inline</span></div><div class="line"><a name="l01363"></a><span class="lineno"> 1363</span> uint64x2_p8 VectorCh(<span class="keyword">const</span> uint64x2_p8 x, <span class="keyword">const</span> uint64x2_p8 y, <span class="keyword">const</span> uint64x2_p8 z)</div><div class="line"><a name="l01364"></a><span class="lineno"> 1364</span> {</div><div class="line"><a name="l01365"></a><span class="lineno"> 1365</span>  <span class="comment">// The trick below is due to Andy Polyakov and Jack Lloyd</span></div><div class="line"><a name="l01366"></a><span class="lineno"> 1366</span>  <span class="keywordflow">return</span> vec_sel(z,y,x);</div><div class="line"><a name="l01367"></a><span class="lineno"> 1367</span> }</div><div class="line"><a name="l01368"></a><span class="lineno"> 1368</span> </div><div class="line"><a name="l01369"></a><span class="lineno"> 1369</span> <span class="keyword">static</span> <span class="keyword">inline</span></div><div class="line"><a name="l01370"></a><span class="lineno"> 1370</span> uint64x2_p8 VectorMaj(<span class="keyword">const</span> uint64x2_p8 x, <span class="keyword">const</span> uint64x2_p8 y, <span class="keyword">const</span> uint64x2_p8 z)</div><div class="line"><a name="l01371"></a><span class="lineno"> 1371</span> {</div><div class="line"><a name="l01372"></a><span class="lineno"> 1372</span>  <span class="comment">// The trick below is due to Andy Polyakov and Jack Lloyd</span></div><div class="line"><a name="l01373"></a><span class="lineno"> 1373</span>  <span class="keywordflow">return</span> vec_sel(y, z, vec_xor(x, y));</div><div class="line"><a name="l01374"></a><span class="lineno"> 1374</span> }</div><div class="line"><a name="l01375"></a><span class="lineno"> 1375</span> </div><div class="line"><a name="l01376"></a><span class="lineno"> 1376</span> <span class="keyword">static</span> <span class="keyword">inline</span></div><div class="line"><a name="l01377"></a><span class="lineno"> 1377</span> uint64x2_p8 Vector_sigma0(<span class="keyword">const</span> uint64x2_p8 val)</div><div class="line"><a name="l01378"></a><span class="lineno"> 1378</span> {</div><div class="line"><a name="l01379"></a><span class="lineno"> 1379</span> <span class="preprocessor">#if defined(CRYPTOPP_XLC_VERSION)</span></div><div class="line"><a name="l01380"></a><span class="lineno"> 1380</span>  <span class="keywordflow">return</span> __vshasigmad(val, 0, 0);</div><div class="line"><a name="l01381"></a><span class="lineno"> 1381</span> <span class="preprocessor">#else</span></div><div class="line"><a name="l01382"></a><span class="lineno"> 1382</span>  <span class="keywordflow">return</span> __builtin_crypto_vshasigmad(val, 0, 0);</div><div class="line"><a name="l01383"></a><span class="lineno"> 1383</span> <span class="preprocessor">#endif</span></div><div class="line"><a name="l01384"></a><span class="lineno"> 1384</span> }</div><div class="line"><a name="l01385"></a><span class="lineno"> 1385</span> </div><div class="line"><a name="l01386"></a><span class="lineno"> 1386</span> <span class="keyword">static</span> <span class="keyword">inline</span></div><div class="line"><a name="l01387"></a><span class="lineno"> 1387</span> uint64x2_p8 Vector_sigma1(<span class="keyword">const</span> uint64x2_p8 val)</div><div class="line"><a name="l01388"></a><span class="lineno"> 1388</span> {</div><div class="line"><a name="l01389"></a><span class="lineno"> 1389</span> <span class="preprocessor">#if defined(CRYPTOPP_XLC_VERSION)</span></div><div class="line"><a name="l01390"></a><span class="lineno"> 1390</span>  <span class="keywordflow">return</span> __vshasigmad(val, 0, 0xf);</div><div class="line"><a name="l01391"></a><span class="lineno"> 1391</span> <span class="preprocessor">#else</span></div><div class="line"><a name="l01392"></a><span class="lineno"> 1392</span>  <span class="keywordflow">return</span> __builtin_crypto_vshasigmad(val, 0, 0xf);</div><div class="line"><a name="l01393"></a><span class="lineno"> 1393</span> <span class="preprocessor">#endif</span></div><div class="line"><a name="l01394"></a><span class="lineno"> 1394</span> }</div><div class="line"><a name="l01395"></a><span class="lineno"> 1395</span> </div><div class="line"><a name="l01396"></a><span class="lineno"> 1396</span> <span class="keyword">static</span> <span class="keyword">inline</span></div><div class="line"><a name="l01397"></a><span class="lineno"> 1397</span> uint64x2_p8 VectorSigma0(<span class="keyword">const</span> uint64x2_p8 val)</div><div class="line"><a name="l01398"></a><span class="lineno"> 1398</span> {</div><div class="line"><a name="l01399"></a><span class="lineno"> 1399</span> <span class="preprocessor">#if defined(CRYPTOPP_XLC_VERSION)</span></div><div class="line"><a name="l01400"></a><span class="lineno"> 1400</span>  <span class="keywordflow">return</span> __vshasigmad(val, 1, 0);</div><div class="line"><a name="l01401"></a><span class="lineno"> 1401</span> <span class="preprocessor">#else</span></div><div class="line"><a name="l01402"></a><span class="lineno"> 1402</span>  <span class="keywordflow">return</span> __builtin_crypto_vshasigmad(val, 1, 0);</div><div class="line"><a name="l01403"></a><span class="lineno"> 1403</span> <span class="preprocessor">#endif</span></div><div class="line"><a name="l01404"></a><span class="lineno"> 1404</span> }</div><div class="line"><a name="l01405"></a><span class="lineno"> 1405</span> </div><div class="line"><a name="l01406"></a><span class="lineno"> 1406</span> <span class="keyword">static</span> <span class="keyword">inline</span></div><div class="line"><a name="l01407"></a><span class="lineno"> 1407</span> uint64x2_p8 VectorSigma1(<span class="keyword">const</span> uint64x2_p8 val)</div><div class="line"><a name="l01408"></a><span class="lineno"> 1408</span> {</div><div class="line"><a name="l01409"></a><span class="lineno"> 1409</span> <span class="preprocessor">#if defined(CRYPTOPP_XLC_VERSION)</span></div><div class="line"><a name="l01410"></a><span class="lineno"> 1410</span>  <span class="keywordflow">return</span> __vshasigmad(val, 1, 0xf);</div><div class="line"><a name="l01411"></a><span class="lineno"> 1411</span> <span class="preprocessor">#else</span></div><div class="line"><a name="l01412"></a><span class="lineno"> 1412</span>  <span class="keywordflow">return</span> __builtin_crypto_vshasigmad(val, 1, 0xf);</div><div class="line"><a name="l01413"></a><span class="lineno"> 1413</span> <span class="preprocessor">#endif</span></div><div class="line"><a name="l01414"></a><span class="lineno"> 1414</span> }</div><div class="line"><a name="l01415"></a><span class="lineno"> 1415</span> </div><div class="line"><a name="l01416"></a><span class="lineno"> 1416</span> <span class="keyword">static</span> <span class="keyword">inline</span></div><div class="line"><a name="l01417"></a><span class="lineno"> 1417</span> uint64x2_p8 VectorPack(<span class="keyword">const</span> uint64x2_p8 x, <span class="keyword">const</span> uint64x2_p8 y)</div><div class="line"><a name="l01418"></a><span class="lineno"> 1418</span> {</div><div class="line"><a name="l01419"></a><span class="lineno"> 1419</span>  <span class="keyword">const</span> uint8x16_p8 m = {0,1,2,3, 4,5,6,7, 16,17,18,19, 20,21,22,23};</div><div class="line"><a name="l01420"></a><span class="lineno"> 1420</span>  <span class="keywordflow">return</span> vec_perm(x,y,m);</div><div class="line"><a name="l01421"></a><span class="lineno"> 1421</span> }</div><div class="line"><a name="l01422"></a><span class="lineno"> 1422</span> </div><div class="line"><a name="l01423"></a><span class="lineno"> 1423</span> <span class="keyword">template</span> <<span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> L> <span class="keyword">static</span> <span class="keyword">inline</span></div><div class="line"><a name="l01424"></a><span class="lineno"> 1424</span> uint64x2_p8 <a class="code" href="ppc-simd_8h.html#ab73b86116b8a0520419ad240b760ac39">VectorShiftLeft</a>(<span class="keyword">const</span> uint64x2_p8 val)</div><div class="line"><a name="l01425"></a><span class="lineno"> 1425</span> {</div><div class="line"><a name="l01426"></a><span class="lineno"> 1426</span> <span class="preprocessor">#if (defined(CRYPTOPP_LITTLE_ENDIAN))</span></div><div class="line"><a name="l01427"></a><span class="lineno"> 1427</span>  <span class="keywordflow">return</span> (uint64x2_p8)vec_sld((uint8x16_p8)val, (uint8x16_p8)val, (16-L)&0xf);</div><div class="line"><a name="l01428"></a><span class="lineno"> 1428</span> <span class="preprocessor">#else</span></div><div class="line"><a name="l01429"></a><span class="lineno"> 1429</span>  <span class="keywordflow">return</span> (uint64x2_p8)vec_sld((uint8x16_p8)val, (uint8x16_p8)val, L&0xf);</div><div class="line"><a name="l01430"></a><span class="lineno"> 1430</span> <span class="preprocessor">#endif</span></div><div class="line"><a name="l01431"></a><span class="lineno"> 1431</span> }</div><div class="line"><a name="l01432"></a><span class="lineno"> 1432</span> </div><div class="line"><a name="l01433"></a><span class="lineno"> 1433</span> <span class="keyword">template</span> <></div><div class="line"><a name="l01434"></a><span class="lineno"> 1434</span> uint64x2_p8 VectorShiftLeft<0>(<span class="keyword">const</span> uint64x2_p8 val) { <span class="keywordflow">return</span> val; }</div><div class="line"><a name="l01435"></a><span class="lineno"> 1435</span> </div><div class="line"><a name="l01436"></a><span class="lineno"> 1436</span> <span class="keyword">template</span> <></div><div class="line"><a name="l01437"></a><span class="lineno"> 1437</span> uint64x2_p8 VectorShiftLeft<16>(<span class="keyword">const</span> uint64x2_p8 val) { <span class="keywordflow">return</span> val; }</div><div class="line"><a name="l01438"></a><span class="lineno"> 1438</span> </div><div class="line"><a name="l01439"></a><span class="lineno"> 1439</span> <span class="keyword">template</span> <<span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> R> <span class="keyword">static</span> <span class="keyword">inline</span></div><div class="line"><a name="l01440"></a><span class="lineno"> 1440</span> <span class="keywordtype">void</span> SHA512_ROUND1(uint64x2_p8 W[16], uint64x2_p8 S[8], <span class="keyword">const</span> uint64x2_p8 K, <span class="keyword">const</span> uint64x2_p8 M)</div><div class="line"><a name="l01441"></a><span class="lineno"> 1441</span> {</div><div class="line"><a name="l01442"></a><span class="lineno"> 1442</span>  uint64x2_p8 T1, T2;</div><div class="line"><a name="l01443"></a><span class="lineno"> 1443</span> </div><div class="line"><a name="l01444"></a><span class="lineno"> 1444</span>  W[R] = M;</div><div class="line"><a name="l01445"></a><span class="lineno"> 1445</span>  T1 = S[H] + VectorSigma1(S[E]) + VectorCh(S[E],S[F],S[G]) + K + M;</div><div class="line"><a name="l01446"></a><span class="lineno"> 1446</span>  T2 = VectorSigma0(S[A]) + VectorMaj(S[A],S[B],S[C]);</div><div class="line"><a name="l01447"></a><span class="lineno"> 1447</span> </div><div class="line"><a name="l01448"></a><span class="lineno"> 1448</span>  S[H] = S[G]; S[G] = S[F]; S[F] = S[E];</div><div class="line"><a name="l01449"></a><span class="lineno"> 1449</span>  S[E] = S[D] + T1;</div><div class="line"><a name="l01450"></a><span class="lineno"> 1450</span>  S[D] = S[C]; S[C] = S[B]; S[B] = S[A];</div><div class="line"><a name="l01451"></a><span class="lineno"> 1451</span>  S[A] = T1 + T2;</div><div class="line"><a name="l01452"></a><span class="lineno"> 1452</span> }</div><div class="line"><a name="l01453"></a><span class="lineno"> 1453</span> </div><div class="line"><a name="l01454"></a><span class="lineno"> 1454</span> <span class="keyword">template</span> <<span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> R> <span class="keyword">static</span> <span class="keyword">inline</span></div><div class="line"><a name="l01455"></a><span class="lineno"> 1455</span> <span class="keywordtype">void</span> SHA512_ROUND2(uint64x2_p8 W[16], uint64x2_p8 S[8], <span class="keyword">const</span> uint64x2_p8 K)</div><div class="line"><a name="l01456"></a><span class="lineno"> 1456</span> {</div><div class="line"><a name="l01457"></a><span class="lineno"> 1457</span>  <span class="comment">// Indexes into the W[] array</span></div><div class="line"><a name="l01458"></a><span class="lineno"> 1458</span>  <span class="keyword">enum</span> {IDX0=(R+0)&0xf, IDX1=(R+1)&0xf, IDX9=(R+9)&0xf, IDX14=(R+14)&0xf};</div><div class="line"><a name="l01459"></a><span class="lineno"> 1459</span> </div><div class="line"><a name="l01460"></a><span class="lineno"> 1460</span>  <span class="keyword">const</span> uint64x2_p8 s0 = Vector_sigma0(W[IDX1]);</div><div class="line"><a name="l01461"></a><span class="lineno"> 1461</span>  <span class="keyword">const</span> uint64x2_p8 s1 = Vector_sigma1(W[IDX14]);</div><div class="line"><a name="l01462"></a><span class="lineno"> 1462</span> </div><div class="line"><a name="l01463"></a><span class="lineno"> 1463</span>  uint64x2_p8 T1 = (W[IDX0] += s0 + s1 + W[IDX9]);</div><div class="line"><a name="l01464"></a><span class="lineno"> 1464</span>  T1 += S[H] + VectorSigma1(S[E]) + VectorCh(S[E],S[F],S[G]) + K;</div><div class="line"><a name="l01465"></a><span class="lineno"> 1465</span>  uint64x2_p8 T2 = VectorSigma0(S[A]) + VectorMaj(S[A],S[B],S[C]);</div><div class="line"><a name="l01466"></a><span class="lineno"> 1466</span> </div><div class="line"><a name="l01467"></a><span class="lineno"> 1467</span>  S[H] = S[G]; S[G] = S[F]; S[F] = S[E];</div><div class="line"><a name="l01468"></a><span class="lineno"> 1468</span>  S[E] = S[D] + T1;</div><div class="line"><a name="l01469"></a><span class="lineno"> 1469</span>  S[D] = S[C]; S[C] = S[B]; S[B] = S[A];</div><div class="line"><a name="l01470"></a><span class="lineno"> 1470</span>  S[A] = T1 + T2;</div><div class="line"><a name="l01471"></a><span class="lineno"> 1471</span> }</div><div class="line"><a name="l01472"></a><span class="lineno"> 1472</span> </div><div class="line"><a name="l01473"></a><span class="lineno"> 1473</span> <span class="keywordtype">void</span> SHA512_HashMultipleBlocks_POWER8(word64 *state, <span class="keyword">const</span> word64 *data, <span class="keywordtype">size_t</span> length, <a class="code" href="cryptlib_8h.html#aaeb92d42f5a6e27b8ba19f18d69d142b">ByteOrder</a> order)</div><div class="line"><a name="l01474"></a><span class="lineno"> 1474</span> {</div><div class="line"><a name="l01475"></a><span class="lineno"> 1475</span>  <a class="code" href="trap_8h.html#adf3b392588bc94cbeae9f415a78c7b95">CRYPTOPP_ASSERT</a>(state); <a class="code" href="trap_8h.html#adf3b392588bc94cbeae9f415a78c7b95">CRYPTOPP_ASSERT</a>(data);</div><div class="line"><a name="l01476"></a><span class="lineno"> 1476</span>  <a class="code" href="trap_8h.html#adf3b392588bc94cbeae9f415a78c7b95">CRYPTOPP_ASSERT</a>(length >= SHA512::BLOCKSIZE);</div><div class="line"><a name="l01477"></a><span class="lineno"> 1477</span>  CRYPTOPP_UNUSED(order);</div><div class="line"><a name="l01478"></a><span class="lineno"> 1478</span> </div><div class="line"><a name="l01479"></a><span class="lineno"> 1479</span>  <span class="keyword">const</span> uint64_t* k = <span class="keyword">reinterpret_cast<</span><span class="keyword">const </span>uint64_t*<span class="keyword">></span>(SHA512_K);</div><div class="line"><a name="l01480"></a><span class="lineno"> 1480</span>  <span class="keyword">const</span> uint64_t* m = <span class="keyword">reinterpret_cast<</span><span class="keyword">const </span>uint64_t*<span class="keyword">></span>(data);</div><div class="line"><a name="l01481"></a><span class="lineno"> 1481</span> </div><div class="line"><a name="l01482"></a><span class="lineno"> 1482</span>  uint64x2_p8 ab = VectorLoad64x2u(state+0, 0);</div><div class="line"><a name="l01483"></a><span class="lineno"> 1483</span>  uint64x2_p8 cd = VectorLoad64x2u(state+2, 0);</div><div class="line"><a name="l01484"></a><span class="lineno"> 1484</span>  uint64x2_p8 ef = VectorLoad64x2u(state+4, 0);</div><div class="line"><a name="l01485"></a><span class="lineno"> 1485</span>  uint64x2_p8 gh = VectorLoad64x2u(state+6, 0);</div><div class="line"><a name="l01486"></a><span class="lineno"> 1486</span>  uint64x2_p8 W[16], S[8], vm, vk;</div><div class="line"><a name="l01487"></a><span class="lineno"> 1487</span> </div><div class="line"><a name="l01488"></a><span class="lineno"> 1488</span>  <span class="keywordtype">size_t</span> blocks = length / SHA512::BLOCKSIZE;</div><div class="line"><a name="l01489"></a><span class="lineno"> 1489</span>  <span class="keywordflow">while</span> (blocks--)</div><div class="line"><a name="l01490"></a><span class="lineno"> 1490</span>  {</div><div class="line"><a name="l01491"></a><span class="lineno"> 1491</span>  <span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> i, offset=0;</div><div class="line"><a name="l01492"></a><span class="lineno"> 1492</span> </div><div class="line"><a name="l01493"></a><span class="lineno"> 1493</span>  S[A] = ab; S[C] = cd;</div><div class="line"><a name="l01494"></a><span class="lineno"> 1494</span>  S[E] = ef; S[G] = gh;</div><div class="line"><a name="l01495"></a><span class="lineno"> 1495</span>  S[B] = VectorShiftLeft<8>(S[A]);</div><div class="line"><a name="l01496"></a><span class="lineno"> 1496</span>  S[D] = VectorShiftLeft<8>(S[C]);</div><div class="line"><a name="l01497"></a><span class="lineno"> 1497</span>  S[F] = VectorShiftLeft<8>(S[E]);</div><div class="line"><a name="l01498"></a><span class="lineno"> 1498</span>  S[H] = VectorShiftLeft<8>(S[G]);</div><div class="line"><a name="l01499"></a><span class="lineno"> 1499</span> </div><div class="line"><a name="l01500"></a><span class="lineno"> 1500</span>  <span class="comment">// Unroll the loop to provide the round number as a constexpr</span></div><div class="line"><a name="l01501"></a><span class="lineno"> 1501</span>  <span class="comment">// for (unsigned int i=0; i<16; ++i)</span></div><div class="line"><a name="l01502"></a><span class="lineno"> 1502</span>  {</div><div class="line"><a name="l01503"></a><span class="lineno"> 1503</span>  vk = VectorLoad64x2(k, offset);</div><div class="line"><a name="l01504"></a><span class="lineno"> 1504</span>  vm = VectorLoadMsg64x2(m, offset);</div><div class="line"><a name="l01505"></a><span class="lineno"> 1505</span>  SHA512_ROUND1<0>(W,S, vk,vm);</div><div class="line"><a name="l01506"></a><span class="lineno"> 1506</span>  offset+=16;</div><div class="line"><a name="l01507"></a><span class="lineno"> 1507</span> </div><div class="line"><a name="l01508"></a><span class="lineno"> 1508</span>  vk = VectorShiftLeft<8>(vk);</div><div class="line"><a name="l01509"></a><span class="lineno"> 1509</span>  vm = VectorShiftLeft<8>(vm);</div><div class="line"><a name="l01510"></a><span class="lineno"> 1510</span>  SHA512_ROUND1<1>(W,S, vk,vm);</div><div class="line"><a name="l01511"></a><span class="lineno"> 1511</span> </div><div class="line"><a name="l01512"></a><span class="lineno"> 1512</span>  vk = VectorLoad64x2(k, offset);</div><div class="line"><a name="l01513"></a><span class="lineno"> 1513</span>  vm = VectorLoadMsg64x2(m, offset);</div><div class="line"><a name="l01514"></a><span class="lineno"> 1514</span>  SHA512_ROUND1<2>(W,S, vk,vm);</div><div class="line"><a name="l01515"></a><span class="lineno"> 1515</span>  offset+=16;</div><div class="line"><a name="l01516"></a><span class="lineno"> 1516</span> </div><div class="line"><a name="l01517"></a><span class="lineno"> 1517</span>  vk = VectorShiftLeft<8>(vk);</div><div class="line"><a name="l01518"></a><span class="lineno"> 1518</span>  vm = VectorShiftLeft<8>(vm);</div><div class="line"><a name="l01519"></a><span class="lineno"> 1519</span>  SHA512_ROUND1<3>(W,S, vk,vm);</div><div class="line"><a name="l01520"></a><span class="lineno"> 1520</span> </div><div class="line"><a name="l01521"></a><span class="lineno"> 1521</span>  vk = VectorLoad64x2(k, offset);</div><div class="line"><a name="l01522"></a><span class="lineno"> 1522</span>  vm = VectorLoadMsg64x2(m, offset);</div><div class="line"><a name="l01523"></a><span class="lineno"> 1523</span>  SHA512_ROUND1<4>(W,S, vk,vm);</div><div class="line"><a name="l01524"></a><span class="lineno"> 1524</span>  offset+=16;</div><div class="line"><a name="l01525"></a><span class="lineno"> 1525</span> </div><div class="line"><a name="l01526"></a><span class="lineno"> 1526</span>  vk = VectorShiftLeft<8>(vk);</div><div class="line"><a name="l01527"></a><span class="lineno"> 1527</span>  vm = VectorShiftLeft<8>(vm);</div><div class="line"><a name="l01528"></a><span class="lineno"> 1528</span>  SHA512_ROUND1<5>(W,S, vk,vm);</div><div class="line"><a name="l01529"></a><span class="lineno"> 1529</span> </div><div class="line"><a name="l01530"></a><span class="lineno"> 1530</span>  vk = VectorLoad64x2(k, offset);</div><div class="line"><a name="l01531"></a><span class="lineno"> 1531</span>  vm = VectorLoadMsg64x2(m, offset);</div><div class="line"><a name="l01532"></a><span class="lineno"> 1532</span>  SHA512_ROUND1<6>(W,S, vk,vm);</div><div class="line"><a name="l01533"></a><span class="lineno"> 1533</span>  offset+=16;</div><div class="line"><a name="l01534"></a><span class="lineno"> 1534</span> </div><div class="line"><a name="l01535"></a><span class="lineno"> 1535</span>  vk = VectorShiftLeft<8>(vk);</div><div class="line"><a name="l01536"></a><span class="lineno"> 1536</span>  vm = VectorShiftLeft<8>(vm);</div><div class="line"><a name="l01537"></a><span class="lineno"> 1537</span>  SHA512_ROUND1<7>(W,S, vk,vm);</div><div class="line"><a name="l01538"></a><span class="lineno"> 1538</span> </div><div class="line"><a name="l01539"></a><span class="lineno"> 1539</span>  vk = VectorLoad64x2(k, offset);</div><div class="line"><a name="l01540"></a><span class="lineno"> 1540</span>  vm = VectorLoadMsg64x2(m, offset);</div><div class="line"><a name="l01541"></a><span class="lineno"> 1541</span>  SHA512_ROUND1<8>(W,S, vk,vm);</div><div class="line"><a name="l01542"></a><span class="lineno"> 1542</span>  offset+=16;</div><div class="line"><a name="l01543"></a><span class="lineno"> 1543</span> </div><div class="line"><a name="l01544"></a><span class="lineno"> 1544</span>  vk = VectorShiftLeft<8>(vk);</div><div class="line"><a name="l01545"></a><span class="lineno"> 1545</span>  vm = VectorShiftLeft<8>(vm);</div><div class="line"><a name="l01546"></a><span class="lineno"> 1546</span>  SHA512_ROUND1<9>(W,S, vk,vm);</div><div class="line"><a name="l01547"></a><span class="lineno"> 1547</span> </div><div class="line"><a name="l01548"></a><span class="lineno"> 1548</span>  vk = VectorLoad64x2(k, offset);</div><div class="line"><a name="l01549"></a><span class="lineno"> 1549</span>  vm = VectorLoadMsg64x2(m, offset);</div><div class="line"><a name="l01550"></a><span class="lineno"> 1550</span>  SHA512_ROUND1<10>(W,S, vk,vm);</div><div class="line"><a name="l01551"></a><span class="lineno"> 1551</span>  offset+=16;</div><div class="line"><a name="l01552"></a><span class="lineno"> 1552</span> </div><div class="line"><a name="l01553"></a><span class="lineno"> 1553</span>  vk = VectorShiftLeft<8>(vk);</div><div class="line"><a name="l01554"></a><span class="lineno"> 1554</span>  vm = VectorShiftLeft<8>(vm);</div><div class="line"><a name="l01555"></a><span class="lineno"> 1555</span>  SHA512_ROUND1<11>(W,S, vk,vm);</div><div class="line"><a name="l01556"></a><span class="lineno"> 1556</span> </div><div class="line"><a name="l01557"></a><span class="lineno"> 1557</span>  vk = VectorLoad64x2(k, offset);</div><div class="line"><a name="l01558"></a><span class="lineno"> 1558</span>  vm = VectorLoadMsg64x2(m, offset);</div><div class="line"><a name="l01559"></a><span class="lineno"> 1559</span>  SHA512_ROUND1<12>(W,S, vk,vm);</div><div class="line"><a name="l01560"></a><span class="lineno"> 1560</span>  offset+=16;</div><div class="line"><a name="l01561"></a><span class="lineno"> 1561</span> </div><div class="line"><a name="l01562"></a><span class="lineno"> 1562</span>  vk = VectorShiftLeft<8>(vk);</div><div class="line"><a name="l01563"></a><span class="lineno"> 1563</span>  vm = VectorShiftLeft<8>(vm);</div><div class="line"><a name="l01564"></a><span class="lineno"> 1564</span>  SHA512_ROUND1<13>(W,S, vk,vm);</div><div class="line"><a name="l01565"></a><span class="lineno"> 1565</span> </div><div class="line"><a name="l01566"></a><span class="lineno"> 1566</span>  vk = VectorLoad64x2(k, offset);</div><div class="line"><a name="l01567"></a><span class="lineno"> 1567</span>  vm = VectorLoadMsg64x2(m, offset);</div><div class="line"><a name="l01568"></a><span class="lineno"> 1568</span>  SHA512_ROUND1<14>(W,S, vk,vm);</div><div class="line"><a name="l01569"></a><span class="lineno"> 1569</span>  offset+=16;</div><div class="line"><a name="l01570"></a><span class="lineno"> 1570</span> </div><div class="line"><a name="l01571"></a><span class="lineno"> 1571</span>  vk = VectorShiftLeft<8>(vk);</div><div class="line"><a name="l01572"></a><span class="lineno"> 1572</span>  vm = VectorShiftLeft<8>(vm);</div><div class="line"><a name="l01573"></a><span class="lineno"> 1573</span>  SHA512_ROUND1<15>(W,S, vk,vm);</div><div class="line"><a name="l01574"></a><span class="lineno"> 1574</span>  }</div><div class="line"><a name="l01575"></a><span class="lineno"> 1575</span> </div><div class="line"><a name="l01576"></a><span class="lineno"> 1576</span>  m += 16; <span class="comment">// 64-bit words, not bytes</span></div><div class="line"><a name="l01577"></a><span class="lineno"> 1577</span> </div><div class="line"><a name="l01578"></a><span class="lineno"> 1578</span>  <span class="keywordflow">for</span> (i=16 ; i<80; i+=16)</div><div class="line"><a name="l01579"></a><span class="lineno"> 1579</span>  {</div><div class="line"><a name="l01580"></a><span class="lineno"> 1580</span>  vk = VectorLoad64x2(k, offset);</div><div class="line"><a name="l01581"></a><span class="lineno"> 1581</span>  SHA512_ROUND2<0>(W,S, vk);</div><div class="line"><a name="l01582"></a><span class="lineno"> 1582</span>  SHA512_ROUND2<1>(W,S, VectorShiftLeft<8>(vk));</div><div class="line"><a name="l01583"></a><span class="lineno"> 1583</span>  offset+=16;</div><div class="line"><a name="l01584"></a><span class="lineno"> 1584</span> </div><div class="line"><a name="l01585"></a><span class="lineno"> 1585</span>  vk = VectorLoad64x2(k, offset);</div><div class="line"><a name="l01586"></a><span class="lineno"> 1586</span>  SHA512_ROUND2<2>(W,S, vk);</div><div class="line"><a name="l01587"></a><span class="lineno"> 1587</span>  SHA512_ROUND2<3>(W,S, VectorShiftLeft<8>(vk));</div><div class="line"><a name="l01588"></a><span class="lineno"> 1588</span>  offset+=16;</div><div class="line"><a name="l01589"></a><span class="lineno"> 1589</span> </div><div class="line"><a name="l01590"></a><span class="lineno"> 1590</span>  vk = VectorLoad64x2(k, offset);</div><div class="line"><a name="l01591"></a><span class="lineno"> 1591</span>  SHA512_ROUND2<4>(W,S, vk);</div><div class="line"><a name="l01592"></a><span class="lineno"> 1592</span>  SHA512_ROUND2<5>(W,S, VectorShiftLeft<8>(vk));</div><div class="line"><a name="l01593"></a><span class="lineno"> 1593</span>  offset+=16;</div><div class="line"><a name="l01594"></a><span class="lineno"> 1594</span> </div><div class="line"><a name="l01595"></a><span class="lineno"> 1595</span>  vk = VectorLoad64x2(k, offset);</div><div class="line"><a name="l01596"></a><span class="lineno"> 1596</span>  SHA512_ROUND2<6>(W,S, vk);</div><div class="line"><a name="l01597"></a><span class="lineno"> 1597</span>  SHA512_ROUND2<7>(W,S, VectorShiftLeft<8>(vk));</div><div class="line"><a name="l01598"></a><span class="lineno"> 1598</span>  offset+=16;</div><div class="line"><a name="l01599"></a><span class="lineno"> 1599</span> </div><div class="line"><a name="l01600"></a><span class="lineno"> 1600</span>  vk = VectorLoad64x2(k, offset);</div><div class="line"><a name="l01601"></a><span class="lineno"> 1601</span>  SHA512_ROUND2<8>(W,S, vk);</div><div class="line"><a name="l01602"></a><span class="lineno"> 1602</span>  SHA512_ROUND2<9>(W,S, VectorShiftLeft<8>(vk));</div><div class="line"><a name="l01603"></a><span class="lineno"> 1603</span>  offset+=16;</div><div class="line"><a name="l01604"></a><span class="lineno"> 1604</span> </div><div class="line"><a name="l01605"></a><span class="lineno"> 1605</span>  vk = VectorLoad64x2(k, offset);</div><div class="line"><a name="l01606"></a><span class="lineno"> 1606</span>  SHA512_ROUND2<10>(W,S, vk);</div><div class="line"><a name="l01607"></a><span class="lineno"> 1607</span>  SHA512_ROUND2<11>(W,S, VectorShiftLeft<8>(vk));</div><div class="line"><a name="l01608"></a><span class="lineno"> 1608</span>  offset+=16;</div><div class="line"><a name="l01609"></a><span class="lineno"> 1609</span> </div><div class="line"><a name="l01610"></a><span class="lineno"> 1610</span>  vk = VectorLoad64x2(k, offset);</div><div class="line"><a name="l01611"></a><span class="lineno"> 1611</span>  SHA512_ROUND2<12>(W,S, vk);</div><div class="line"><a name="l01612"></a><span class="lineno"> 1612</span>  SHA512_ROUND2<13>(W,S, VectorShiftLeft<8>(vk));</div><div class="line"><a name="l01613"></a><span class="lineno"> 1613</span>  offset+=16;</div><div class="line"><a name="l01614"></a><span class="lineno"> 1614</span> </div><div class="line"><a name="l01615"></a><span class="lineno"> 1615</span>  vk = VectorLoad64x2(k, offset);</div><div class="line"><a name="l01616"></a><span class="lineno"> 1616</span>  SHA512_ROUND2<14>(W,S, vk);</div><div class="line"><a name="l01617"></a><span class="lineno"> 1617</span>  SHA512_ROUND2<15>(W,S, VectorShiftLeft<8>(vk));</div><div class="line"><a name="l01618"></a><span class="lineno"> 1618</span>  offset+=16;</div><div class="line"><a name="l01619"></a><span class="lineno"> 1619</span>  }</div><div class="line"><a name="l01620"></a><span class="lineno"> 1620</span> </div><div class="line"><a name="l01621"></a><span class="lineno"> 1621</span>  ab += VectorPack(S[A],S[B]);</div><div class="line"><a name="l01622"></a><span class="lineno"> 1622</span>  cd += VectorPack(S[C],S[D]);</div><div class="line"><a name="l01623"></a><span class="lineno"> 1623</span>  ef += VectorPack(S[E],S[F]);</div><div class="line"><a name="l01624"></a><span class="lineno"> 1624</span>  gh += VectorPack(S[G],S[H]);</div><div class="line"><a name="l01625"></a><span class="lineno"> 1625</span>  }</div><div class="line"><a name="l01626"></a><span class="lineno"> 1626</span> </div><div class="line"><a name="l01627"></a><span class="lineno"> 1627</span>  VectorStore64x2u(ab, state+0, 0);</div><div class="line"><a name="l01628"></a><span class="lineno"> 1628</span>  VectorStore64x2u(cd, state+2, 0);</div><div class="line"><a name="l01629"></a><span class="lineno"> 1629</span>  VectorStore64x2u(ef, state+4, 0);</div><div class="line"><a name="l01630"></a><span class="lineno"> 1630</span>  VectorStore64x2u(gh, state+6, 0);</div><div class="line"><a name="l01631"></a><span class="lineno"> 1631</span> }</div><div class="line"><a name="l01632"></a><span class="lineno"> 1632</span> </div><div class="line"><a name="l01633"></a><span class="lineno"> 1633</span> <span class="preprocessor">#endif // CRYPTOPP_POWER8_SHA_AVAILABLE</span></div><div class="line"><a name="l01634"></a><span class="lineno"> 1634</span> <span class="comment"></span></div><div class="line"><a name="l01635"></a><span class="lineno"> 1635</span> <span class="comment">////////////////////////////////////////////////</span></div><div class="line"><a name="l01636"></a><span class="lineno"> 1636</span> <span class="comment"></span><span class="comment">// end Gustavo, Serra, Scalet and Walton code //</span><span class="comment"></span></div><div class="line"><a name="l01637"></a><span class="lineno"> 1637</span> <span class="comment">////////////////////////////////////////////////</span></div><div class="line"><a name="l01638"></a><span class="lineno"> 1638</span> <span class="comment"></span></div><div class="line"><a name="l01639"></a><span class="lineno"> 1639</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="cryptlib_8h_html_aaeb92d42f5a6e27b8ba19f18d69d142b"><div class="ttname"><a href="cryptlib_8h.html#aaeb92d42f5a6e27b8ba19f18d69d142b">ByteOrder</a></div><div class="ttdeci">ByteOrder</div><div class="ttdoc">Provides the byte ordering. </div><div class="ttdef"><b>Definition:</b> <a href="cryptlib_8h_source.html#l00140">cryptlib.h:140</a></div></div> <div class="ttc" id="ppc-simd_8h_html_ab73b86116b8a0520419ad240b760ac39"><div class="ttname"><a href="ppc-simd_8h.html#ab73b86116b8a0520419ad240b760ac39">VectorShiftLeft</a></div><div class="ttdeci">T1 VectorShiftLeft(const T1 &vec1, const T2 &vec2)</div><div class="ttdoc">Shift two vectors left. </div><div class="ttdef"><b>Definition:</b> <a href="ppc-simd_8h_source.html#l00416">ppc-simd.h:416</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="ppc-simd_8h_html"><div class="ttname"><a href="ppc-simd_8h.html">ppc-simd.h</a></div><div class="ttdoc">Support functions for PowerPC and vector operations. </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="cryptlib_8h_html_aaeb92d42f5a6e27b8ba19f18d69d142baf0c3bb6c718cc7ff0bffef4e8f178c57"><div class="ttname"><a href="cryptlib_8h.html#aaeb92d42f5a6e27b8ba19f18d69d142baf0c3bb6c718cc7ff0bffef4e8f178c57">BIG_ENDIAN_ORDER</a></div><div class="ttdoc">byte order is big-endian </div><div class="ttdef"><b>Definition:</b> <a href="cryptlib_8h_source.html#l00144">cryptlib.h:144</a></div></div> <div class="ttc" id="trap_8h_html_adf3b392588bc94cbeae9f415a78c7b95"><div class="ttname"><a href="trap_8h.html#adf3b392588bc94cbeae9f415a78c7b95">CRYPTOPP_ASSERT</a></div><div class="ttdeci">#define CRYPTOPP_ASSERT(exp)</div><div class="ttdoc">Debugging and diagnostic assertion. </div><div class="ttdef"><b>Definition:</b> <a href="trap_8h_source.html#l00060">trap.h:60</a></div></div> <div class="ttc" id="sha_8h_html"><div class="ttname"><a href="sha_8h.html">sha.h</a></div><div class="ttdoc">Classes for SHA-1 and SHA-2 family of message digests. </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><!-- fragment --></div><!-- contents --> <!-- start footer part --> <hr class="footer"/><address class="footer"><small> Generated on Sun Sep 16 2018 07:58:03 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>