<html xmlns="http://www.w3.org/1999/xhtml">
<head>
<meta charset="utf-8">
<meta name="generator" content="pdf2htmlEX">
<meta http-equiv="X-UA-Compatible" content="IE=edge,chrome=1">
<link rel="stylesheet" href="https://static.pudn.com/base/css/base.min.css">
<link rel="stylesheet" href="https://static.pudn.com/base/css/fancy.min.css">
<link rel="stylesheet" href="https://static.pudn.com/prod/directory_preview_static/625230016caf5961926028c9/raw.css">
<script src="https://static.pudn.com/base/js/compatibility.min.js"></script>
<script src="https://static.pudn.com/base/js/pdf2htmlEX.min.js"></script>
<script>
try{
pdf2htmlEX.defaultViewer = new pdf2htmlEX.Viewer({});
}catch(e){}
</script>
<title></title>
</head>
<body>
<div id="sidebar" style="display: none">
<div id="outline">
</div>
</div>
<div id="pf1" class="pf w0 h0" data-page-no="1"><div class="pc pc1 w0 h0"><img class="bi x0 y0 w1 h1" alt="" src="https://static.pudn.com/prod/directory_preview_static/625230016caf5961926028c9/bg1.jpg"><div class="c x0 y1 w2 h0"><div class="t m0 x1 h2 y2 ff1 fs0 fc0 sc0 ls0 ws0">CUDA<span class="_ _0"> </span><span class="ls1">INTRODUCTION <span class="_ _1"></span>AND FUNDAMENT<span class="_ _2"></span>AL<span class="_ _3"></span> </span></div><div class="t m0 x2 h2 y3 ff1 fs0 fc0 sc0 ls1 ws0">OPTIMIZA<span class="_ _2"></span>TION</div><div class="t m0 x3 h3 y4 ff1 fs1 fc0 sc0 ls1 ws0">W<span class="_ _3"></span>en Xie</div><div class="t m0 x4 h3 y5 ff1 fs1 fc0 sc0 ls1 ws0">HPC Developer T<span class="_ _1"></span>echnology<span class="_ _3"></span> <span class="_ _4"></span>Engineer</div></div></div><div class="pi" data-data='{"ctm":[1.111111,0.000000,0.000000,1.111111,0.000000,0.000000]}'></div></div>
</body>
</html>
<div id="pf2" class="pf w0 h0" data-page-no="2"><div class="pc pc2 w0 h0"><img class="bi x0 y0 w1 h1" alt="" src="https://static.pudn.com/prod/directory_preview_static/625230016caf5961926028c9/bg2.jpg"><div class="c x0 y1 w2 h0"><div class="t m0 x5 h4 y6 ff2 fs2 fc0 sc0 ls1 ws0">No.<span class="_ _5"> </span>Cour<span class="_ _6"></span>se <span class="_ _4"></span>Name</div></div><div class="c x6 y7 w3 h5"><div class="t m0 x7 h4 y8 ff2 fs2 fc0 sc0 ls1 ws0">Speak<span class="_ _3"></span>er </div><div class="t m0 x7 h4 y9 ff2 fs2 fc0 sc0 ls1 ws0">Name</div></div><div class="c x0 y1 w2 h0"><div class="t m0 x8 h4 ya ff2 fs2 fc0 sc0 ls1 ws0">W<span class="_ _3"></span>ebinar Date</div><div class="t m0 x9 h4 yb ff2 fs2 fc0 sc0 ls2 ws0">Q2<span class="_ _7"> </span>Q3<span class="_ _7"> </span>Q4</div><div class="t m0 xa h6 yc ff3 fs3 fc1 sc0 ls1 ws0">1</div></div><div class="c xb yd w4 h7"><div class="t m0 x7 h8 ye ff3 fs4 fc1 sc0 ls1 ws0">CUDA</div></div><div class="c x0 y1 w2 h0"><div class="t m0 xc h8 yf ff3 fs4 fc1 sc0 ls1 ws0">Introduction + CUDA<span class="_ _8"> </span>F<span class="_ _3"></span>undamental </div></div><div class="c xb yd w4 h7"><div class="t m0 x7 h8 y10 ff3 fs4 fc1 sc0 ls1 ws0">Optimization</div></div><div class="c x6 y11 w3 h9"><div class="t m0 x7 h8 y12 ff3 fs4 fc1 sc0 ls1 ws0">Ross Xie</div></div><div class="c xd y11 w5 h9"><div class="t m0 x7 ha y12 ff4 fs4 fc1 sc0 ls3 ws0">11</div></div><div class="c x0 y1 w2 h0"><div class="t m0 xe ha y13 ff4 fs4 fc1 sc0 ls1 ws0">-Jun</div><div class="t m0 xa hb y14 ff4 fs3 fc1 sc0 ls1 ws0">2</div></div><div class="c xb y15 w4 h9"><div class="t m0 x7 ha y16 ff4 fs4 fc1 sc0 ls1 ws0">CUDA</div></div><div class="c x0 y1 w2 h0"><div class="t m0 xf ha y17 ff4 fs4 fc1 sc0 ls1 ws0">Optimization<span class="_ _4"></span> <span class="_ _3"></span>i<span class="_ _4"></span>n Depth </div></div><div class="c x6 y15 w3 h9"><div class="t m0 x7 ha y16 ff4 fs4 fc1 sc0 ls1 ws0">Joey W<span class="_ _3"></span>ang</div></div><div class="c xd y15 w5 h9"><div class="t m0 x7 ha y16 ff4 fs4 fc1 sc0 ls3 ws0">23</div></div><div class="c x0 y1 w2 h0"><div class="t m0 xe ha y17 ff4 fs4 fc1 sc0 ls1 ws0">-Jul</div><div class="t m0 xa hb y18 ff4 fs3 fc1 sc0 ls1 ws0">3</div></div><div class="c xb y19 w4 h7"><div class="t m0 x7 ha y1a ff4 fs4 fc1 sc0 ls1 ws0">CUDA</div></div><div class="c x0 y1 w2 h0"><div class="t m0 xf ha y1b ff4 fs4 fc1 sc0 ls1 ws0">New Features <span class="_ _3"></span>Co<span class="_ _4"></span>llection (6.0/<span class="_ _6"></span>6.5/7.0) <span class="_ _3"></span>+ </div></div><div class="c xb y19 w4 h7"><div class="t m0 x7 ha y1c ff4 fs4 fc1 sc0 ls1 ws0">CUDA</div></div><div class="c x0 y1 w2 h0"><div class="t m0 xf ha y1d ff4 fs4 fc1 sc0 ls1 ws0">T<span class="_ _1"></span>ools an<span class="_ _4"></span>d Librarie<span class="_ _6"></span>s</div></div><div class="c x6 y1e w3 h9"><div class="t m0 x7 ha y1f ff4 fs4 fc1 sc0 ls1 ws0">Chandle</div></div><div class="c x0 y1 w2 h0"><div class="t m0 x10 ha y1d ff4 fs4 fc1 sc0 ls1 ws0">Zhou</div></div><div class="c x11 y1e w5 h9"><div class="t m0 x7 ha y1f ff4 fs4 fc1 sc0 ls3 ws0">13</div></div><div class="c x0 y1 w2 h0"><div class="t m0 x12 ha y1d ff4 fs4 fc1 sc0 ls1 ws0">-Aug</div><div class="t m0 xa hb y20 ff4 fs3 fc1 sc0 ls1 ws0">4</div></div><div class="c xb y21 w4 h9"><div class="t m0 x7 ha y16 ff4 fs4 fc1 sc0 ls1 ws0">OpenACC</div></div><div class="c x6 y21 w3 h9"><div class="t m0 x7 ha y16 ff4 fs4 fc1 sc0 ls1 ws0">Zhen W<span class="_ _9"></span>ang</div></div><div class="c x11 y21 w5 h9"><div class="t m0 x7 ha y16 ff4 fs4 fc1 sc0 ls3 ws0">27</div></div><div class="c x0 y1 w2 h0"><div class="t m0 x12 ha y22 ff4 fs4 fc1 sc0 ls1 ws0">-Aug</div><div class="t m0 xa hb y23 ff4 fs3 fc1 sc0 ls1 ws0">5</div></div><div class="c xb y24 w4 h9"><div class="t m0 x7 ha y25 ff4 fs4 fc1 sc0 ls1 ws0">GPU</div></div><div class="c x0 y1 w2 h0"><div class="t m0 x13 ha y26 ff4 fs4 fc1 sc0 ls1 ws0">accelerate <span class="_ _6"></span>Deep Learning </div></div><div class="c x6 y24 w3 h9"><div class="t m0 x7 ha y25 ff4 fs4 fc1 sc0 ls1 ws0">Julien Lai</div></div><div class="c x11 y24 w5 h9"><div class="t m0 x7 ha y25 ff4 fs4 fc1 sc0 ls3 ws0">10</div></div><div class="c x0 y1 w2 h0"><div class="t m0 x12 ha y26 ff4 fs4 fc1 sc0 ls1 ws0">-Sep</div><div class="t m0 xa hb y27 ff4 fs3 fc1 sc0 ls1 ws0">6</div></div><div class="c xb y28 w4 h9"><div class="t m0 x7 ha y29 ff4 fs4 fc1 sc0 ls1 ws0">MUL<span class="_ _a"></span>TI</div></div><div class="c x0 y1 w2 h0"><div class="t m0 xf ha y2a ff4 fs4 fc1 sc0 ls1 ws0">-GPU<span class="_"> </span>P<span class="_ _3"></span>rogramming + CUDA<span class="_ _b"> </span>A<span class="_ _3"></span>ware MPI</div></div><div class="c x6 y28 w3 h9"><div class="t m0 x7 ha y29 ff4 fs4 fc1 sc0 ls1 ws0">Joey W<span class="_ _9"></span>ang</div></div><div class="c x14 y28 w5 h9"><div class="t m0 x7 ha y29 ff4 fs4 fc1 sc0 ls3 ws0">29</div></div><div class="c x0 y1 w2 h0"><div class="t m0 x15 ha y2a ff4 fs4 fc1 sc0 ls1 ws0">-Oct</div><div class="t m0 xa hc y2b ff4 fs5 fc1 sc0 ls1 ws0">7</div></div><div class="c xb y1 w4 hd"><div class="t m0 x7 ha y2c ff4 fs4 fc1 sc0 ls1 ws0">CUDA<span class="_ _c"> </span>T<span class="_ _1"></span>utorial (Collecting <span class="_ _3"></span>Que<span class="_ _4"></span>stions <span class="_ _6"></span>in P<span class="_ _9"></span>re<span class="_ _4"></span>vious </div><div class="t m0 x7 he y2d ff4 fs6 fc1 sc0 ls1 ws0">Lectures)</div></div><div class="c x6 y2e w3 h9"><div class="t m0 x7 he y2f ff4 fs6 fc1 sc0 ls1 ws0">Joey W<span class="_ _a"></span>a<span class="_ _4"></span>ng</div></div><div class="c x14 y2e w5 h9"><div class="t m0 x7 he y2f ff4 fs6 fc1 sc0 ls4 ws0">10</div></div><div class="c x0 y1 w2 h0"><div class="t m0 x15 he y2d ff4 fs6 fc1 sc0 ls1 ws0">-Dec</div></div></div><div class="pi" data-data='{"ctm":[1.111111,0.000000,0.000000,1.111111,0.000000,0.000000]}'></div></div>
<div id="pf3" class="pf w0 h0" data-page-no="3"><div class="pc pc3 w0 h0"><img class="bi x0 y0 w1 h1" alt="" src="https://static.pudn.com/prod/directory_preview_static/625230016caf5961926028c9/bg3.jpg"><div class="c x0 y1 w2 h0"><div class="t m0 x16 hf y30 ff4 fs7 fc2 sc0 ls1 ws0"><span class="fc5 sc0">3</span></div></div><div class="c x17 y31 w6 h10"><div class="t m0 x18 hb y32 ff4 fs3 fc0 sc0 ls1 ws0">1</div></div><div class="c x19 y31 w7 h10"><div class="t m0 x1a hb y32 ff4 fs3 fc3 sc0 ls1 ws0">Access <span class="_ _3"></span>The <span class="_ _4"></span>P<span class="_ _9"></span>ower of </div></div><div class="c x0 y1 w2 h0"><div class="t m0 x1b hb y33 ff4 fs3 fc3 sc0 ls1 ws0">GPU</div></div><div class="c x17 y34 w6 h10"><div class="t m0 x18 hb y32 ff4 fs3 fc0 sc0 ls1 ws0">2</div></div><div class="c x19 y34 w7 h10"><div class="t m0 x1a hb y32 ff4 fs3 fc3 sc0 ls1 ws0">GPU</div></div><div class="c x0 y1 w2 h0"><div class="t m0 x1c hb y35 ff4 fs3 fc3 sc0 ls1 ws0">Architecture</div></div><div class="c x17 y36 w6 h10"><div class="t m0 x18 hb y32 ff4 fs3 fc0 sc0 ls1 ws0">3</div></div><div class="c x19 y36 w7 h10"><div class="t m0 x1a hb y32 ff4 fs3 fc3 sc0 ls1 ws0">CUDA</div></div><div class="c x0 y1 w2 h0"><div class="t m0 x1d hb y37 ff4 fs3 fc3 sc0 ls1 ws0">P<span class="_ _9"></span>rogramming Basics</div></div><div class="c x17 y38 w6 h10"><div class="t m0 x18 hb y39 ff4 fs3 fc0 sc0 ls1 ws0">4</div></div><div class="c x19 y38 w7 h10"><div class="t m0 x1a hb y39 ff4 fs3 fc3 sc0 ls1 ws0">Simple Optimization sample</div></div><div class="c x17 y3a w6 h10"><div class="t m0 x18 hb y39 ff4 fs3 fc0 sc0 ls1 ws0">5</div></div><div class="c x19 y3a w7 h10"><div class="t m0 x1a hb y39 ff4 fs3 fc3 sc0 ls1 ws0">R<span class="_ _9"></span>eferences</div></div><div class="c x0 y1 w2 h0"><div class="t m0 x1e hb y3b ff4 fs3 fc4 sc0 ls1 ws0">AGENDA</div></div></div><div class="pi" data-data='{"ctm":[1.111111,0.000000,0.000000,1.111111,0.000000,0.000000]}'></div></div>
<div id="pf4" class="pf w0 h0" data-page-no="4"><div class="pc pc4 w0 h0"><img class="bi x0 y0 w1 h1" alt="" src="https://static.pudn.com/prod/directory_preview_static/625230016caf5961926028c9/bg4.jpg"><div class="c x0 y1 w2 h0"><div class="t m0 x16 hf y30 ff4 fs7 fc2 sc0 ls1 ws0"><span class="fc5 sc0">4</span></div><div class="t m0 x1f h11 y3c ff5 fs8 fc3 sc0 ls1 ws0">1. Access The Power<span class="_ _6"></span> of GPU</div></div></div><div class="pi" data-data='{"ctm":[1.111111,0.000000,0.000000,1.111111,0.000000,0.000000]}'></div></div>
<div id="pf5" class="pf w0 h0" data-page-no="5"><div class="pc pc5 w0 h0"><img class="bi x0 y0 w1 h1" alt="" src="https://static.pudn.com/prod/directory_preview_static/625230016caf5961926028c9/bg5.jpg"><div class="c x0 y1 w2 h0"><div class="t m0 x16 hf y30 ff4 fs7 fc2 sc0 ls1 ws0">5</div><div class="t m0 x20 h12 y3d ff1 fs9 fc6 sc0 ls1 ws0">3 Ways to Accelerate <span class="_ _4"></span>Applications</div><div class="t m0 x21 h13 y3e ff6 fsa fc0 sc0 ls1 ws0">Libraries<span class="_ _d"> </span>OpenACC</div><div class="t m0 x8 h14 y3f ff6 fs8 fc0 sc0 ls1 ws0">Program<span class="_ _6"></span>ming </div><div class="t m0 x22 h15 y40 ff6 fs0 fc0 sc0 ls5 ws0">Languages</div><div class="t m0 x23 h13 y41 ff6 fsa fc0 sc0 ls1 ws0">Applications</div><div class="t m0 x24 h16 y42 ff3 fsb fc3 sc0 ls1 ws0">Easiest <span class="_ _1"></span>Approach<span class="_ _e"> </span>Maximum </div><div class="t m0 x12 h17 y43 ff3 fs1 fc3 sc0 ls1 ws0">P<span class="_ _a"></span>erformance</div></div></div><div class="pi" data-data='{"ctm":[1.111111,0.000000,0.000000,1.111111,0.000000,0.000000]}'></div></div>
CUDA