arm_compute v17.12
diff --git a/documentation/class_gemm_interleaved.xhtml b/documentation/class_gemm_interleaved.xhtml
index 402a10b..525ba63 100644
--- a/documentation/class_gemm_interleaved.xhtml
+++ b/documentation/class_gemm_interleaved.xhtml
@@ -4,7 +4,7 @@
<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 1.8.6"/>
+<meta name="generator" content="Doxygen 1.8.11"/>
<meta name="robots" content="NOINDEX, NOFOLLOW" /> <!-- Prevent indexing by search engines -->
<title>Compute Library: GemmInterleaved< strategy, To, Tr > Class Template Reference</title>
<link href="tabs.css" rel="stylesheet" type="text/css"/>
@@ -12,22 +12,24 @@
<script type="text/javascript" src="dynsections.js"></script>
<link href="navtree.css" rel="stylesheet" type="text/css"/>
<script type="text/javascript" src="resize.js"></script>
+<script type="text/javascript" src="navtreedata.js"></script>
<script type="text/javascript" src="navtree.js"></script>
<script type="text/javascript">
$(document).ready(initResizable);
$(window).load(resizeHeight);
</script>
<link href="search/search.css" rel="stylesheet" type="text/css"/>
+<script type="text/javascript" src="search/searchdata.js"></script>
<script type="text/javascript" src="search/search.js"></script>
<script type="text/javascript">
- $(document).ready(function() { searchBox.OnSelectItem(0); });
+ $(document).ready(function() { init_search(); });
</script>
<script type="text/x-mathjax-config">
MathJax.Hub.Config({
extensions: ["tex2jax.js"],
jax: ["input/TeX","output/HTML-CSS"],
});
-</script><script src="http://cdn.mathjax.org/mathjax/latest/MathJax.js"></script>
+</script><script type="text/javascript" src="http://cdn.mathjax.org/mathjax/latest/MathJax.js"></script>
<link href="doxygen.css" rel="stylesheet" type="text/css" />
</head>
<body>
@@ -38,7 +40,7 @@
<tr style="height: 56px;">
<td style="padding-left: 0.5em;">
<div id="projectname">Compute Library
-  <span id="projectnumber">17.10</span>
+  <span id="projectnumber">17.12</span>
</div>
</td>
</tr>
@@ -46,7 +48,7 @@
</table>
</div>
<!-- end header part -->
-<!-- Generated by Doxygen 1.8.6 -->
+<!-- Generated by Doxygen 1.8.11 -->
<script type="text/javascript">
var searchBox = new SearchBox("searchBox", "search",false,'Search');
</script>
@@ -103,7 +105,7 @@
onmouseover="return searchBox.OnSearchSelectShow()"
onmouseout="return searchBox.OnSearchSelectHide()"
onkeydown="return searchBox.OnSearchSelectKey(event)">
-<a class="SelectItem" href="javascript:void(0)" onclick="searchBox.OnSelectItem(0)"><span class="SelectionMark"> </span>All</a><a class="SelectItem" href="javascript:void(0)" onclick="searchBox.OnSelectItem(1)"><span class="SelectionMark"> </span>Data Structures</a><a class="SelectItem" href="javascript:void(0)" onclick="searchBox.OnSelectItem(2)"><span class="SelectionMark"> </span>Namespaces</a><a class="SelectItem" href="javascript:void(0)" onclick="searchBox.OnSelectItem(3)"><span class="SelectionMark"> </span>Files</a><a class="SelectItem" href="javascript:void(0)" onclick="searchBox.OnSelectItem(4)"><span class="SelectionMark"> </span>Functions</a><a class="SelectItem" href="javascript:void(0)" onclick="searchBox.OnSelectItem(5)"><span class="SelectionMark"> </span>Variables</a><a class="SelectItem" href="javascript:void(0)" onclick="searchBox.OnSelectItem(6)"><span class="SelectionMark"> </span>Typedefs</a><a class="SelectItem" href="javascript:void(0)" onclick="searchBox.OnSelectItem(7)"><span class="SelectionMark"> </span>Enumerations</a><a class="SelectItem" href="javascript:void(0)" onclick="searchBox.OnSelectItem(8)"><span class="SelectionMark"> </span>Enumerator</a><a class="SelectItem" href="javascript:void(0)" onclick="searchBox.OnSelectItem(9)"><span class="SelectionMark"> </span>Friends</a><a class="SelectItem" href="javascript:void(0)" onclick="searchBox.OnSelectItem(10)"><span class="SelectionMark"> </span>Macros</a><a class="SelectItem" href="javascript:void(0)" onclick="searchBox.OnSelectItem(11)"><span class="SelectionMark"> </span>Pages</a></div>
+</div>
<!-- iframe showing the search results (closed by default) -->
<div id="MSearchResultsWindow">
@@ -124,7 +126,7 @@
<div class="dynheader">
Collaboration diagram for GemmInterleaved< strategy, To, Tr >:</div>
<div class="dyncontent">
-<div class="center"><iframe scrolling="no" frameborder="0" src="class_gemm_interleaved__coll__graph.svg" width="199" height="127"><p><b>This browser is not able to show SVG: try Firefox, Chrome, Safari, or Opera instead.</b></p></iframe>
+<div class="center"><iframe scrolling="no" frameborder="0" src="class_gemm_interleaved__coll__graph.svg" width="220" height="127"><p><b>This browser is not able to show SVG: try Firefox, Chrome, Safari, or Opera instead.</b></p></iframe>
</div>
<center><span class="legend">[<a target="top" href="graph_legend.xhtml">legend</a>]</span></center></div>
<table class="memberdecls">
@@ -141,11 +143,11 @@
<tr class="separator:a431c4e53fa05a1e8ba127441e8baeed2 inherit pub_methods_class_gemm_common"><td class="memSeparator" colspan="2"> </td></tr>
</table>
<a name="details" id="details"></a><h2 class="groupheader">Detailed Description</h2>
-<div class="textblock"><h3>template<typename strategy, typename To, typename Tr><br/>
+<div class="textblock"><h3>template<typename strategy, typename To, typename Tr><br />
class GemmInterleaved< strategy, To, Tr ></h3>
-<p>Definition at line <a class="el" href="gemm__interleaved_8hpp_source.xhtml#l00043">43</a> of file <a class="el" href="gemm__interleaved_8hpp_source.xhtml">gemm_interleaved.hpp</a>.</p>
+<p>Definition at line <a class="el" href="gemm__interleaved_8hpp_source.xhtml#l00044">44</a> of file <a class="el" href="gemm__interleaved_8hpp_source.xhtml">gemm_interleaved.hpp</a>.</p>
</div><h2 class="groupheader">Constructor & Destructor Documentation</h2>
<a class="anchor" id="ad4b554ff56ba355e66b70698b1393085"></a>
<div class="memitem">
@@ -203,49 +205,8 @@
</table>
</div><div class="memdoc">
-<p>Definition at line <a class="el" href="gemm__interleaved_8hpp_source.xhtml#l00077">77</a> of file <a class="el" href="gemm__interleaved_8hpp_source.xhtml">gemm_interleaved.hpp</a>.</p>
-<div class="fragment"><div class="line"><a name="l00077"></a><span class="lineno"> 77</span>  : M(M), N(N), K(K), trA(trA), trB(trB), strat(ci) {</div>
-<div class="line"><a name="l00078"></a><span class="lineno"> 78</span>  <span class="keyword">const</span> <span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> L1_size = ci->L1_size;</div>
-<div class="line"><a name="l00079"></a><span class="lineno"> 79</span>  <span class="keyword">const</span> <span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> L2_size = ci->L2_size;</div>
-<div class="line"><a name="l00080"></a><span class="lineno"> 80</span> </div>
-<div class="line"><a name="l00081"></a><span class="lineno"> 81</span>  <span class="comment">// Work out blocking parameters</span></div>
-<div class="line"><a name="l00082"></a><span class="lineno"> 82</span>  <span class="comment">// k_block: Each iteration will consume (out_width + out_height)</span></div>
-<div class="line"><a name="l00083"></a><span class="lineno"> 83</span>  <span class="comment">// operands - so how many iterations will fill the L1?</span></div>
-<div class="line"><a name="l00084"></a><span class="lineno"> 84</span>  k_block = L1_size / (<span class="keyword">sizeof</span>(Toi) * (strat.out_width + strat.out_height));</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="comment">// Needs to be a multiple of the K unroll level.</span></div>
-<div class="line"><a name="l00087"></a><span class="lineno"> 87</span>  k_block /= strat.k_unroll;</div>
-<div class="line"><a name="l00088"></a><span class="lineno"> 88</span>  k_block *= strat.k_unroll;</div>
-<div class="line"><a name="l00089"></a><span class="lineno"> 89</span> </div>
-<div class="line"><a name="l00090"></a><span class="lineno"> 90</span>  <span class="comment">// Now tune to presented problem size; this is how many blocks we need.</span></div>
-<div class="line"><a name="l00091"></a><span class="lineno"> 91</span>  <span class="keywordtype">int</span> num_k_blocks = (K + (k_block - 1)) / k_block;</div>
-<div class="line"><a name="l00092"></a><span class="lineno"> 92</span> </div>
-<div class="line"><a name="l00093"></a><span class="lineno"> 93</span>  <span class="comment">// So divide the space equally into that many blocks.</span></div>
-<div class="line"><a name="l00094"></a><span class="lineno"> 94</span>  k_block = (K + num_k_blocks - 1) / num_k_blocks;</div>
-<div class="line"><a name="l00095"></a><span class="lineno"> 95</span> </div>
-<div class="line"><a name="l00096"></a><span class="lineno"> 96</span>  <span class="comment">// And round UP to the K unroll level required.</span></div>
-<div class="line"><a name="l00097"></a><span class="lineno"> 97</span>  k_block = (k_block + strat.k_unroll - 1) / strat.k_unroll;</div>
-<div class="line"><a name="l00098"></a><span class="lineno"> 98</span>  k_block *= strat.k_unroll;</div>
-<div class="line"><a name="l00099"></a><span class="lineno"> 99</span> </div>
-<div class="line"><a name="l00100"></a><span class="lineno"> 100</span>  <span class="comment">// x_block: Work out how many rows (of length k_block) will fit in the L2</span></div>
-<div class="line"><a name="l00101"></a><span class="lineno"> 101</span>  x_block = L2_size / (<span class="keyword">sizeof</span>(Toi) * k_block);</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="comment">// Needs to be a multiple of the kernel output width.</span></div>
-<div class="line"><a name="l00104"></a><span class="lineno"> 104</span>  x_block /= strat.out_width;</div>
-<div class="line"><a name="l00105"></a><span class="lineno"> 105</span>  x_block *= strat.out_width;</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>  <span class="comment">// And tune to the presented problem size.</span></div>
-<div class="line"><a name="l00108"></a><span class="lineno"> 108</span>  <span class="keywordtype">int</span> num_x_blocks = (N + (x_block - 1)) / x_block;</div>
-<div class="line"><a name="l00109"></a><span class="lineno"> 109</span>  x_block = (N + num_x_blocks - 1) / num_x_blocks;</div>
-<div class="line"><a name="l00110"></a><span class="lineno"> 110</span> </div>
-<div class="line"><a name="l00111"></a><span class="lineno"> 111</span>  x_block = (x_block + strat.out_width - 1) / strat.out_width;</div>
-<div class="line"><a name="l00112"></a><span class="lineno"> 112</span>  x_block *= strat.out_width;</div>
-<div class="line"><a name="l00113"></a><span class="lineno"> 113</span> </div>
-<div class="line"><a name="l00114"></a><span class="lineno"> 114</span>  <span class="comment">// Work out the rounded size of M - needed for some buffers.</span></div>
-<div class="line"><a name="l00115"></a><span class="lineno"> 115</span>  Mround = (M + (strat.out_height - 1)) / strat.out_height;</div>
-<div class="line"><a name="l00116"></a><span class="lineno"> 116</span>  Mround *= strat.out_height;</div>
-<div class="line"><a name="l00117"></a><span class="lineno"> 117</span>  }</div>
-</div><!-- fragment -->
+<p>Definition at line <a class="el" href="gemm__interleaved_8hpp_source.xhtml#l00078">78</a> of file <a class="el" href="gemm__interleaved_8hpp_source.xhtml">gemm_interleaved.hpp</a>.</p>
+<div class="fragment"><div class="line"><a name="l00078"></a><span class="lineno"> 78</span>  : M(M), N(N), K(K), trA(trA), trB(trB), strat(ci) {</div><div class="line"><a name="l00079"></a><span class="lineno"> 79</span>  <span class="keyword">const</span> <span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> L1_size = ci->L1_size;</div><div class="line"><a name="l00080"></a><span class="lineno"> 80</span>  <span class="keyword">const</span> <span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> L2_size = ci->L2_size;</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>  <span class="comment">// Work out blocking parameters</span></div><div class="line"><a name="l00083"></a><span class="lineno"> 83</span>  <span class="comment">// k_block: Each iteration will consume (out_width + out_height)</span></div><div class="line"><a name="l00084"></a><span class="lineno"> 84</span>  <span class="comment">// operands - so how many iterations will fill the L1?</span></div><div class="line"><a name="l00085"></a><span class="lineno"> 85</span>  k_block = L1_size / (<span class="keyword">sizeof</span>(Toi) * (strat.out_width + strat.out_height));</div><div class="line"><a name="l00086"></a><span class="lineno"> 86</span> </div><div class="line"><a name="l00087"></a><span class="lineno"> 87</span>  <span class="comment">// Needs to be a multiple of the K unroll level.</span></div><div class="line"><a name="l00088"></a><span class="lineno"> 88</span>  k_block /= strat.k_unroll;</div><div class="line"><a name="l00089"></a><span class="lineno"> 89</span>  k_block *= strat.k_unroll;</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">// Now tune to presented problem size; this is how many blocks we need.</span></div><div class="line"><a name="l00092"></a><span class="lineno"> 92</span>  <span class="keywordtype">int</span> num_k_blocks = (K + (k_block - 1)) / k_block;</div><div class="line"><a name="l00093"></a><span class="lineno"> 93</span> </div><div class="line"><a name="l00094"></a><span class="lineno"> 94</span>  <span class="comment">// So divide the space equally into that many blocks.</span></div><div class="line"><a name="l00095"></a><span class="lineno"> 95</span>  k_block = (K + num_k_blocks - 1) / num_k_blocks;</div><div class="line"><a name="l00096"></a><span class="lineno"> 96</span> </div><div class="line"><a name="l00097"></a><span class="lineno"> 97</span>  <span class="comment">// And round UP to the K unroll level required.</span></div><div class="line"><a name="l00098"></a><span class="lineno"> 98</span>  k_block = (k_block + strat.k_unroll - 1) / strat.k_unroll;</div><div class="line"><a name="l00099"></a><span class="lineno"> 99</span>  k_block *= strat.k_unroll;</div><div class="line"><a name="l00100"></a><span class="lineno"> 100</span> </div><div class="line"><a name="l00101"></a><span class="lineno"> 101</span>  <span class="comment">// x_block: Work out how many rows (of length k_block) will fit in the L2</span></div><div class="line"><a name="l00102"></a><span class="lineno"> 102</span>  x_block = L2_size / (<span class="keyword">sizeof</span>(Toi) * k_block);</div><div class="line"><a name="l00103"></a><span class="lineno"> 103</span> </div><div class="line"><a name="l00104"></a><span class="lineno"> 104</span>  <span class="comment">// Needs to be a multiple of the kernel output width.</span></div><div class="line"><a name="l00105"></a><span class="lineno"> 105</span>  x_block /= strat.out_width;</div><div class="line"><a name="l00106"></a><span class="lineno"> 106</span>  x_block *= strat.out_width;</div><div class="line"><a name="l00107"></a><span class="lineno"> 107</span> </div><div class="line"><a name="l00108"></a><span class="lineno"> 108</span>  <span class="comment">// And tune to the presented problem size.</span></div><div class="line"><a name="l00109"></a><span class="lineno"> 109</span>  <span class="keywordtype">int</span> num_x_blocks = (N + (x_block - 1)) / x_block;</div><div class="line"><a name="l00110"></a><span class="lineno"> 110</span>  x_block = (N + num_x_blocks - 1) / num_x_blocks;</div><div class="line"><a name="l00111"></a><span class="lineno"> 111</span> </div><div class="line"><a name="l00112"></a><span class="lineno"> 112</span>  x_block = (x_block + strat.out_width - 1) / strat.out_width;</div><div class="line"><a name="l00113"></a><span class="lineno"> 113</span>  x_block *= strat.out_width;</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>  <span class="comment">// Work out the rounded size of M - needed for some buffers.</span></div><div class="line"><a name="l00116"></a><span class="lineno"> 116</span>  Mround = (M + (strat.out_height - 1)) / strat.out_height;</div><div class="line"><a name="l00117"></a><span class="lineno"> 117</span>  Mround *= strat.out_height;</div><div class="line"><a name="l00118"></a><span class="lineno"> 118</span> </div><div class="line"><a name="l00119"></a><span class="lineno"> 119</span>  }</div></div><!-- fragment -->
</div>
</div>
<h2 class="groupheader">Member Function Documentation</h2>
@@ -323,73 +284,18 @@
</table>
</div><div class="memdoc">
-<p>Implements <a class="el" href="class_gemm_common.xhtml#aabcb2e5ff8597dda52969feeba3d7ae0">GemmCommon< To, Tr ></a>.</p>
+<p>Implements <a class="el" href="class_gemm_common.xhtml#aab79882bbff1e62036bf9cb655e9c5d3">GemmCommon< To, Tr ></a>.</p>
-<p>Definition at line <a class="el" href="gemm__interleaved_8hpp_source.xhtml#l00120">120</a> of file <a class="el" href="gemm__interleaved_8hpp_source.xhtml">gemm_interleaved.hpp</a>.</p>
+<p>Definition at line <a class="el" href="gemm__interleaved_8hpp_source.xhtml#l00122">122</a> of file <a class="el" href="gemm__interleaved_8hpp_source.xhtml">gemm_interleaved.hpp</a>.</p>
-<p>References <a class="el" href="profiler_8hpp_source.xhtml#l00096">PROFILE_KERNEL</a>, <a class="el" href="profiler_8hpp_source.xhtml#l00097">PROFILE_MERGE</a>, <a class="el" href="profiler_8hpp_source.xhtml#l00094">PROFILE_PREPA</a>, and <a class="el" href="profiler_8hpp_source.xhtml#l00095">PROFILE_PREPB</a>.</p>
-<div class="fragment"><div class="line"><a name="l00120"></a><span class="lineno"> 120</span>  {</div>
-<div class="line"><a name="l00121"></a><span class="lineno"> 121</span>  <a class="code" href="classprofiler.xhtml">profiler</a> prof;</div>
-<div class="line"><a name="l00122"></a><span class="lineno"> 122</span> </div>
-<div class="line"><a name="l00123"></a><span class="lineno"> 123</span>  int8_t *working_space_bytes = <span class="keyword">reinterpret_cast<</span>int8_t *<span class="keyword">></span>(working_space);</div>
-<div class="line"><a name="l00124"></a><span class="lineno"> 124</span>  intptr_t working_space_int = <span class="keyword">reinterpret_cast<</span>intptr_t<span class="keyword">></span>(working_space_bytes);</div>
-<div class="line"><a name="l00125"></a><span class="lineno"> 125</span>  <span class="keywordtype">size_t</span> diff = 0;</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="keywordflow">if</span> (working_space_int & 0xF) {</div>
-<div class="line"><a name="l00128"></a><span class="lineno"> 128</span>  diff = 0x10 - (working_space_int & 0xF);</div>
-<div class="line"><a name="l00129"></a><span class="lineno"> 129</span>  }</div>
-<div class="line"><a name="l00130"></a><span class="lineno"> 130</span> </div>
-<div class="line"><a name="l00131"></a><span class="lineno"> 131</span>  Toi * <span class="keyword">const</span> a_panel = <span class="keyword">reinterpret_cast<</span>Toi *<span class="keyword">></span>(working_space_bytes + diff);</div>
-<div class="line"><a name="l00132"></a><span class="lineno"> 132</span>  Toi * <span class="keyword">const</span> b_panel = <span class="keyword">reinterpret_cast<</span>Toi *<span class="keyword">></span>(working_space_bytes + get_a_working_size() + diff);</div>
-<div class="line"><a name="l00133"></a><span class="lineno"> 133</span>  Tri * <span class="keyword">const</span> c_panel = <span class="keyword">reinterpret_cast<</span>Tri *<span class="keyword">></span>(working_space_bytes + get_a_working_size() + get_b_working_size() + diff);</div>
-<div class="line"><a name="l00134"></a><span class="lineno"> 134</span> </div>
-<div class="line"><a name="l00135"></a><span class="lineno"> 135</span>  <span class="keywordflow">for</span> (<span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> k0=0; k0<K; k0 += k_block) {</div>
-<div class="line"><a name="l00136"></a><span class="lineno"> 136</span>  <span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> kmax = k0 + k_block;</div>
-<div class="line"><a name="l00137"></a><span class="lineno"> 137</span>  <span class="keywordflow">if</span> (kmax > K) kmax = K;</div>
-<div class="line"><a name="l00138"></a><span class="lineno"> 138</span> </div>
-<div class="line"><a name="l00139"></a><span class="lineno"> 139</span>  <span class="comment">// Figure out how many "K" the kernel will actually process.</span></div>
-<div class="line"><a name="l00140"></a><span class="lineno"> 140</span>  <span class="keywordtype">int</span> kern_k = ((kmax - k0) + (strat.k_unroll - 1)) / strat.k_unroll;</div>
-<div class="line"><a name="l00141"></a><span class="lineno"> 141</span>  kern_k *= strat.k_unroll;</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>  prof(<a class="code" href="profiler_8hpp.xhtml#ac19bf2c5c388b9fb21cd0668475b2cf7">PROFILE_PREPA</a>, [&](<span class="keywordtype">void</span>) {</div>
-<div class="line"><a name="l00144"></a><span class="lineno"> 144</span>  <span class="keywordflow">if</span> (trA ^ strategy::A_transpose) {</div>
-<div class="line"><a name="l00145"></a><span class="lineno"> 145</span>  Transform<strategy::A_interleave, strategy::A_block, true>(a_panel, <a class="code" href="namespacearm__compute.xhtml#a1ce9b523fd4f3b5bbcadcd796183455aa7fc56270e7a70fa81a5935b72eacbe29">A</a>, lda, 0, M, k0, kmax);</div>
-<div class="line"><a name="l00146"></a><span class="lineno"> 146</span>  } <span class="keywordflow">else</span> {</div>
-<div class="line"><a name="l00147"></a><span class="lineno"> 147</span>  Transform<strategy::A_interleave, strategy::A_block, false>(a_panel, <a class="code" href="namespacearm__compute.xhtml#a1ce9b523fd4f3b5bbcadcd796183455aa7fc56270e7a70fa81a5935b72eacbe29">A</a>, lda, 0, M, k0, kmax);</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>  });</div>
-<div class="line"><a name="l00150"></a><span class="lineno"> 150</span> </div>
-<div class="line"><a name="l00151"></a><span class="lineno"> 151</span>  <span class="keywordflow">for</span> (<span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> x0=0; x0<N; x0 += x_block) {</div>
-<div class="line"><a name="l00152"></a><span class="lineno"> 152</span>  <span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> xmax = x0 + x_block;</div>
-<div class="line"><a name="l00153"></a><span class="lineno"> 153</span>  <span class="keywordflow">if</span> (xmax > N) xmax = N;</div>
-<div class="line"><a name="l00154"></a><span class="lineno"> 154</span> </div>
-<div class="line"><a name="l00155"></a><span class="lineno"> 155</span>  <span class="keywordtype">int</span> bblocks = (xmax - x0 + strat.out_width - 1) / strat.out_width;</div>
-<div class="line"><a name="l00156"></a><span class="lineno"> 156</span> </div>
-<div class="line"><a name="l00157"></a><span class="lineno"> 157</span>  prof(<a class="code" href="profiler_8hpp.xhtml#af0477dfaa86fc08825cb3f31212f423c">PROFILE_PREPB</a>, [&](<span class="keywordtype">void</span>) {</div>
-<div class="line"><a name="l00158"></a><span class="lineno"> 158</span>  <span class="keywordflow">if</span> (trB ^ strategy::B_transpose) {</div>
-<div class="line"><a name="l00159"></a><span class="lineno"> 159</span>  Transform<strategy::B_interleave, strategy::B_block, true>(b_panel, <a class="code" href="namespacearm__compute.xhtml#a1ce9b523fd4f3b5bbcadcd796183455aa9d5ed678fe57bcca610140957afab571">B</a>, ldb, x0, xmax, k0, kmax);</div>
-<div class="line"><a name="l00160"></a><span class="lineno"> 160</span>  } <span class="keywordflow">else</span> {</div>
-<div class="line"><a name="l00161"></a><span class="lineno"> 161</span>  Transform<strategy::B_interleave, strategy::B_block, false>(b_panel, <a class="code" href="namespacearm__compute.xhtml#a1ce9b523fd4f3b5bbcadcd796183455aa9d5ed678fe57bcca610140957afab571">B</a>, ldb, x0, xmax, k0, kmax);</div>
-<div class="line"><a name="l00162"></a><span class="lineno"> 162</span>  }</div>
-<div class="line"><a name="l00163"></a><span class="lineno"> 163</span>  });</div>
-<div class="line"><a name="l00164"></a><span class="lineno"> 164</span> </div>
-<div class="line"><a name="l00165"></a><span class="lineno"> 165</span>  <span class="keywordflow">for</span> (<span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> y=0; y<M; y+=strat.out_height) {</div>
-<div class="line"><a name="l00166"></a><span class="lineno"> 166</span>  <span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> ymax = y + strat.out_height;</div>
-<div class="line"><a name="l00167"></a><span class="lineno"> 167</span>  <span class="keywordflow">if</span> (ymax > M) ymax = M;</div>
-<div class="line"><a name="l00168"></a><span class="lineno"> 168</span> </div>
-<div class="line"><a name="l00169"></a><span class="lineno"> 169</span>  prof(<a class="code" href="profiler_8hpp.xhtml#a97f4e398174b5e094f5262e5d785ac20">PROFILE_KERNEL</a>, [&](<span class="keywordtype">void</span>) { strat.kernel(a_panel + (y * kern_k), b_panel, c_panel, 1, bblocks, kern_k); });</div>
-<div class="line"><a name="l00170"></a><span class="lineno"> 170</span>  prof(<a class="code" href="profiler_8hpp.xhtml#a2f7c3e65a9ccab509d7776832f562dd0">PROFILE_MERGE</a>, [&](<span class="keywordtype">void</span>) { MergeResults<strategy::out_width, strategy::out_height>(C, c_panel, ldc, y, ymax, x0, xmax, alpha, (k0==0 ? beta : <span class="keyword">static_cast<</span>Tr<span class="keyword">></span>(1))); });</div>
-<div class="line"><a name="l00171"></a><span class="lineno"> 171</span>  }</div>
-<div class="line"><a name="l00172"></a><span class="lineno"> 172</span>  }</div>
-<div class="line"><a name="l00173"></a><span class="lineno"> 173</span>  }</div>
-<div class="line"><a name="l00174"></a><span class="lineno"> 174</span>  }</div>
-<div class="ttc" id="namespacearm__compute_xhtml_a1ce9b523fd4f3b5bbcadcd796183455aa7fc56270e7a70fa81a5935b72eacbe29"><div class="ttname"><a href="namespacearm__compute.xhtml#a1ce9b523fd4f3b5bbcadcd796183455aa7fc56270e7a70fa81a5935b72eacbe29">arm_compute::Channel::A</a></div><div class="ttdoc">Alpha channel. </div></div>
-<div class="ttc" id="profiler_8hpp_xhtml_af0477dfaa86fc08825cb3f31212f423c"><div class="ttname"><a href="profiler_8hpp.xhtml#af0477dfaa86fc08825cb3f31212f423c">PROFILE_PREPB</a></div><div class="ttdeci">#define PROFILE_PREPB</div><div class="ttdef"><b>Definition:</b> <a href="profiler_8hpp_source.xhtml#l00095">profiler.hpp:95</a></div></div>
+<p>References <a class="el" href="profiler_8hpp_source.xhtml#l00100">PROFILE_KERNEL</a>, <a class="el" href="profiler_8hpp_source.xhtml#l00101">PROFILE_MERGE</a>, <a class="el" href="profiler_8hpp_source.xhtml#l00098">PROFILE_PREPA</a>, and <a class="el" href="profiler_8hpp_source.xhtml#l00099">PROFILE_PREPB</a>.</p>
+<div class="fragment"><div class="line"><a name="l00122"></a><span class="lineno"> 122</span>  {</div><div class="line"><a name="l00123"></a><span class="lineno"> 123</span>  assert(working_space);</div><div class="line"><a name="l00124"></a><span class="lineno"> 124</span>  <a class="code" href="classprofiler.xhtml">profiler</a> prof;</div><div class="line"><a name="l00125"></a><span class="lineno"> 125</span>  int8_t *working_space_bytes = <span class="keyword">reinterpret_cast<</span>int8_t *<span class="keyword">></span>(working_space);</div><div class="line"><a name="l00126"></a><span class="lineno"> 126</span>  intptr_t working_space_int = <span class="keyword">reinterpret_cast<</span>intptr_t<span class="keyword">></span>(working_space_bytes);</div><div class="line"><a name="l00127"></a><span class="lineno"> 127</span>  <span class="keywordtype">size_t</span> diff = 0;</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="keywordflow">if</span> (working_space_int & 0xF) {</div><div class="line"><a name="l00130"></a><span class="lineno"> 130</span>  diff = 0x10 - (working_space_int & 0xF);</div><div class="line"><a name="l00131"></a><span class="lineno"> 131</span>  }</div><div class="line"><a name="l00132"></a><span class="lineno"> 132</span> </div><div class="line"><a name="l00133"></a><span class="lineno"> 133</span>  Toi * <span class="keyword">const</span> a_panel = <span class="keyword">reinterpret_cast<</span>Toi *<span class="keyword">></span>(working_space_bytes + diff);</div><div class="line"><a name="l00134"></a><span class="lineno"> 134</span>  Toi * <span class="keyword">const</span> b_panel = <span class="keyword">reinterpret_cast<</span>Toi *<span class="keyword">></span>(working_space_bytes + get_a_working_size() + diff);</div><div class="line"><a name="l00135"></a><span class="lineno"> 135</span>  Tri * <span class="keyword">const</span> c_panel = <span class="keyword">reinterpret_cast<</span>Tri *<span class="keyword">></span>(working_space_bytes + get_a_working_size() + get_b_working_size() + diff);</div><div class="line"><a name="l00136"></a><span class="lineno"> 136</span> </div><div class="line"><a name="l00137"></a><span class="lineno"> 137</span>  <span class="keywordflow">for</span> (<span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> k0=0; k0<K; k0 += k_block) {</div><div class="line"><a name="l00138"></a><span class="lineno"> 138</span>  <span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> kmax = k0 + k_block;</div><div class="line"><a name="l00139"></a><span class="lineno"> 139</span>  <span class="keywordflow">if</span> (kmax > K) kmax = K;</div><div class="line"><a name="l00140"></a><span class="lineno"> 140</span> </div><div class="line"><a name="l00141"></a><span class="lineno"> 141</span>  <span class="comment">// Figure out how many "K" the kernel will actually process.</span></div><div class="line"><a name="l00142"></a><span class="lineno"> 142</span>  <span class="keywordtype">int</span> kern_k = ((kmax - k0) + (strat.k_unroll - 1)) / strat.k_unroll;</div><div class="line"><a name="l00143"></a><span class="lineno"> 143</span>  kern_k *= strat.k_unroll;</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>  prof(<a class="code" href="profiler_8hpp.xhtml#ac19bf2c5c388b9fb21cd0668475b2cf7">PROFILE_PREPA</a>, (M * (kmax-k0) * <span class="keyword">sizeof</span>(Toi)), [&](void) {</div><div class="line"><a name="l00146"></a><span class="lineno"> 146</span>  <span class="keywordflow">if</span> (trA ^ strategy::A_transpose) {</div><div class="line"><a name="l00147"></a><span class="lineno"> 147</span>  Transform<strategy::A_interleave, strategy::A_block, true>(a_panel, <a class="code" href="namespacearm__compute.xhtml#a1ce9b523fd4f3b5bbcadcd796183455aa7fc56270e7a70fa81a5935b72eacbe29">A</a>, lda, 0, M, k0, kmax);</div><div class="line"><a name="l00148"></a><span class="lineno"> 148</span>  } <span class="keywordflow">else</span> {</div><div class="line"><a name="l00149"></a><span class="lineno"> 149</span>  Transform<strategy::A_interleave, strategy::A_block, false>(a_panel, <a class="code" href="namespacearm__compute.xhtml#a1ce9b523fd4f3b5bbcadcd796183455aa7fc56270e7a70fa81a5935b72eacbe29">A</a>, lda, 0, M, k0, kmax);</div><div class="line"><a name="l00150"></a><span class="lineno"> 150</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> </div><div class="line"><a name="l00153"></a><span class="lineno"> 153</span>  <span class="keywordflow">for</span> (<span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> x0=0; x0<N; x0 += x_block) {</div><div class="line"><a name="l00154"></a><span class="lineno"> 154</span>  <span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> xmax = x0 + x_block;</div><div class="line"><a name="l00155"></a><span class="lineno"> 155</span>  <span class="keywordflow">if</span> (xmax > N) xmax = N;</div><div class="line"><a name="l00156"></a><span class="lineno"> 156</span> </div><div class="line"><a name="l00157"></a><span class="lineno"> 157</span>  <span class="keywordtype">int</span> bblocks = (xmax - x0 + strat.out_width - 1) / strat.out_width;</div><div class="line"><a name="l00158"></a><span class="lineno"> 158</span> </div><div class="line"><a name="l00159"></a><span class="lineno"> 159</span>  prof(<a class="code" href="profiler_8hpp.xhtml#af0477dfaa86fc08825cb3f31212f423c">PROFILE_PREPB</a>, (xmax-x0) * (kmax-k0) * <span class="keyword">sizeof</span>(Toi), [&](void) {</div><div class="line"><a name="l00160"></a><span class="lineno"> 160</span>  <span class="keywordflow">if</span> (trB ^ strategy::B_transpose) {</div><div class="line"><a name="l00161"></a><span class="lineno"> 161</span>  Transform<strategy::B_interleave, strategy::B_block, true>(b_panel, <a class="code" href="namespacearm__compute.xhtml#a1ce9b523fd4f3b5bbcadcd796183455aa9d5ed678fe57bcca610140957afab571">B</a>, ldb, x0, xmax, k0, kmax);</div><div class="line"><a name="l00162"></a><span class="lineno"> 162</span>  } <span class="keywordflow">else</span> {</div><div class="line"><a name="l00163"></a><span class="lineno"> 163</span>  Transform<strategy::B_interleave, strategy::B_block, false>(b_panel, <a class="code" href="namespacearm__compute.xhtml#a1ce9b523fd4f3b5bbcadcd796183455aa9d5ed678fe57bcca610140957afab571">B</a>, ldb, x0, xmax, k0, kmax);</div><div class="line"><a name="l00164"></a><span class="lineno"> 164</span>  }</div><div class="line"><a name="l00165"></a><span class="lineno"> 165</span>  });</div><div class="line"><a name="l00166"></a><span class="lineno"> 166</span> </div><div class="line"><a name="l00167"></a><span class="lineno"> 167</span>  <span class="keywordflow">for</span> (<span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> y=0; y<M; y+=strat.out_height) {</div><div class="line"><a name="l00168"></a><span class="lineno"> 168</span>  <span class="keywordtype">unsigned</span> <span class="keywordtype">int</span> ymax = y + strat.out_height;</div><div class="line"><a name="l00169"></a><span class="lineno"> 169</span>  <span class="keywordflow">if</span> (ymax > M) ymax = M;</div><div class="line"><a name="l00170"></a><span class="lineno"> 170</span> </div><div class="line"><a name="l00171"></a><span class="lineno"> 171</span>  prof(<a class="code" href="profiler_8hpp.xhtml#a97f4e398174b5e094f5262e5d785ac20">PROFILE_KERNEL</a>, (strat.out_height * bblocks * strat.out_width * kern_k), [&](<span class="keywordtype">void</span>) { strat.kernel(a_panel + (y * kern_k), b_panel, c_panel, 1, bblocks, kern_k); });</div><div class="line"><a name="l00172"></a><span class="lineno"> 172</span>  prof(<a class="code" href="profiler_8hpp.xhtml#a2f7c3e65a9ccab509d7776832f562dd0">PROFILE_MERGE</a>, (strat.out_height * bblocks * strat.out_width * <span class="keyword">sizeof</span>(Tr)), [&](<span class="keywordtype">void</span>) { MergeResults<strategy::out_width, strategy::out_height>(C, c_panel, ldc, y, ymax, x0, xmax, alpha, (k0==0 ? beta : static_cast<Tr>(1))); });</div><div class="line"><a name="l00173"></a><span class="lineno"> 173</span>  }</div><div class="line"><a name="l00174"></a><span class="lineno"> 174</span>  }</div><div class="line"><a name="l00175"></a><span class="lineno"> 175</span>  }</div><div class="line"><a name="l00176"></a><span class="lineno"> 176</span>  }</div><div class="ttc" id="namespacearm__compute_xhtml_a1ce9b523fd4f3b5bbcadcd796183455aa7fc56270e7a70fa81a5935b72eacbe29"><div class="ttname"><a href="namespacearm__compute.xhtml#a1ce9b523fd4f3b5bbcadcd796183455aa7fc56270e7a70fa81a5935b72eacbe29">arm_compute::Channel::A</a></div><div class="ttdoc">Alpha channel. </div></div>
+<div class="ttc" id="profiler_8hpp_xhtml_af0477dfaa86fc08825cb3f31212f423c"><div class="ttname"><a href="profiler_8hpp.xhtml#af0477dfaa86fc08825cb3f31212f423c">PROFILE_PREPB</a></div><div class="ttdeci">#define PROFILE_PREPB</div><div class="ttdef"><b>Definition:</b> <a href="profiler_8hpp_source.xhtml#l00099">profiler.hpp:99</a></div></div>
<div class="ttc" id="namespacearm__compute_xhtml_a1ce9b523fd4f3b5bbcadcd796183455aa9d5ed678fe57bcca610140957afab571"><div class="ttname"><a href="namespacearm__compute.xhtml#a1ce9b523fd4f3b5bbcadcd796183455aa9d5ed678fe57bcca610140957afab571">arm_compute::Channel::B</a></div><div class="ttdoc">Blue channel. </div></div>
-<div class="ttc" id="profiler_8hpp_xhtml_a97f4e398174b5e094f5262e5d785ac20"><div class="ttname"><a href="profiler_8hpp.xhtml#a97f4e398174b5e094f5262e5d785ac20">PROFILE_KERNEL</a></div><div class="ttdeci">#define PROFILE_KERNEL</div><div class="ttdef"><b>Definition:</b> <a href="profiler_8hpp_source.xhtml#l00096">profiler.hpp:96</a></div></div>
-<div class="ttc" id="profiler_8hpp_xhtml_ac19bf2c5c388b9fb21cd0668475b2cf7"><div class="ttname"><a href="profiler_8hpp.xhtml#ac19bf2c5c388b9fb21cd0668475b2cf7">PROFILE_PREPA</a></div><div class="ttdeci">#define PROFILE_PREPA</div><div class="ttdef"><b>Definition:</b> <a href="profiler_8hpp_source.xhtml#l00094">profiler.hpp:94</a></div></div>
-<div class="ttc" id="classprofiler_xhtml"><div class="ttname"><a href="classprofiler.xhtml">profiler</a></div><div class="ttdef"><b>Definition:</b> <a href="profiler_8hpp_source.xhtml#l00084">profiler.hpp:84</a></div></div>
-<div class="ttc" id="profiler_8hpp_xhtml_a2f7c3e65a9ccab509d7776832f562dd0"><div class="ttname"><a href="profiler_8hpp.xhtml#a2f7c3e65a9ccab509d7776832f562dd0">PROFILE_MERGE</a></div><div class="ttdeci">#define PROFILE_MERGE</div><div class="ttdef"><b>Definition:</b> <a href="profiler_8hpp_source.xhtml#l00097">profiler.hpp:97</a></div></div>
+<div class="ttc" id="profiler_8hpp_xhtml_a97f4e398174b5e094f5262e5d785ac20"><div class="ttname"><a href="profiler_8hpp.xhtml#a97f4e398174b5e094f5262e5d785ac20">PROFILE_KERNEL</a></div><div class="ttdeci">#define PROFILE_KERNEL</div><div class="ttdef"><b>Definition:</b> <a href="profiler_8hpp_source.xhtml#l00100">profiler.hpp:100</a></div></div>
+<div class="ttc" id="profiler_8hpp_xhtml_ac19bf2c5c388b9fb21cd0668475b2cf7"><div class="ttname"><a href="profiler_8hpp.xhtml#ac19bf2c5c388b9fb21cd0668475b2cf7">PROFILE_PREPA</a></div><div class="ttdeci">#define PROFILE_PREPA</div><div class="ttdef"><b>Definition:</b> <a href="profiler_8hpp_source.xhtml#l00098">profiler.hpp:98</a></div></div>
+<div class="ttc" id="classprofiler_xhtml"><div class="ttname"><a href="classprofiler.xhtml">profiler</a></div><div class="ttdef"><b>Definition:</b> <a href="profiler_8hpp_source.xhtml#l00088">profiler.hpp:88</a></div></div>
+<div class="ttc" id="profiler_8hpp_xhtml_a2f7c3e65a9ccab509d7776832f562dd0"><div class="ttname"><a href="profiler_8hpp.xhtml#a2f7c3e65a9ccab509d7776832f562dd0">PROFILE_MERGE</a></div><div class="ttdeci">#define PROFILE_MERGE</div><div class="ttdef"><b>Definition:</b> <a href="profiler_8hpp_source.xhtml#l00101">profiler.hpp:101</a></div></div>
</div><!-- fragment -->
</div>
</div>
@@ -416,11 +322,8 @@
<p>Implements <a class="el" href="class_gemm_common.xhtml#a190aa5a4547b7d8d8cbf7b7dc46ca32d">GemmCommon< To, Tr ></a>.</p>
-<p>Definition at line <a class="el" href="gemm__interleaved_8hpp_source.xhtml#l00073">73</a> of file <a class="el" href="gemm__interleaved_8hpp_source.xhtml">gemm_interleaved.hpp</a>.</p>
-<div class="fragment"><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>  <span class="keywordflow">return</span> get_a_working_size() + get_b_working_size() + get_c_working_size();</div>
-<div class="line"><a name="l00075"></a><span class="lineno"> 75</span>  }</div>
-</div><!-- fragment -->
+<p>Definition at line <a class="el" href="gemm__interleaved_8hpp_source.xhtml#l00074">74</a> of file <a class="el" href="gemm__interleaved_8hpp_source.xhtml">gemm_interleaved.hpp</a>.</p>
+<div class="fragment"><div class="line"><a name="l00074"></a><span class="lineno"> 74</span>  {</div><div class="line"><a name="l00075"></a><span class="lineno"> 75</span>  <span class="keywordflow">return</span> get_a_working_size() + get_b_working_size() + get_c_working_size();</div><div class="line"><a name="l00076"></a><span class="lineno"> 76</span>  }</div></div><!-- fragment -->
</div>
</div>
<hr/>The documentation for this class was generated from the following file:<ul>
@@ -432,9 +335,9 @@
<div id="nav-path" class="navpath"><!-- id is needed for treeview function! -->
<ul>
<li class="navelem"><a class="el" href="class_gemm_interleaved.xhtml">GemmInterleaved</a></li>
- <li class="footer">Generated on Thu Oct 12 2017 14:26:35 for Compute Library by
+ <li class="footer">Generated on Thu Dec 14 2017 23:48:34 for Compute Library by
<a href="http://www.doxygen.org/index.html">
- <img class="footer" src="doxygen.png" alt="doxygen"/></a> 1.8.6 </li>
+ <img class="footer" src="doxygen.png" alt="doxygen"/></a> 1.8.11 </li>
</ul>
</div>
</body>