Performance Optimization of 3D Lattice Boltzmann Flow Solver on a GPU

<div>Lattice cell with 19 discrete directions in <svg height="10.9301pt" id="M20" style="vertical-align:-2.1637pt" version="1.1" viewbox="-0.0498162 -8.7664 38.202 10.9301" width="38.202pt" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink"><g transform="matrix(.013,0,0,-0.013,0,0)"><path d="M43 650V622C120 616 128 612 128 526V124C128 39 120 33 34 27V0H270C392 0 492 25 567 83C643 141 690 230 690 350C690 444 655 517 605 565C543 625 450 650 323 650H43ZM213 547C213 587 217 598 226 604C236 612 262 617 304 617C371 617 429 604 474 576C554 529 592 439 592 336C592 176 505 36 319 36C246 36 213 55 213 131V547Z" id="g121-66"></path><glyph.data ascent="989" descent="-360" horiz-adv-x="735" vert-adv-y="735"></glyph.data></g><g transform="matrix(.013,0,0,-0.013,9.555,0)"><path d="M285 378C315 398 338 416 353 432C373 451 384 474 384 503C384 579 325 635 236 635H235C182 635 136 610 108 579L65 516L85 496C110 533 150 575 205 575C258 575 300 543 300 481C300 407 232 369 141 339L147 310C163 315 188 321 211 321C268 321 338 284 338 192C338 94 288 40 217 40C160 40 119 68 93 91C85 98 77 97 69 91C60 84 47 71 46 58C44 46 48 35 62 22C75 10 116 -12 162 -12C234 -12 424 62 424 224C424 297 373 359 285 376V378Z" id="g113-52"></path><glyph.data ascent="3473" descent="-2876" horiz-adv-x="480" vert-adv-y="480"></glyph.data></g><g transform="matrix(.013,0,0,-0.013,15.795,0)"><path d="M720 -138C627 -96 538 -41 476 2C594 39 703 153 703 331C703 532 552 665 384 665C170 665 44 499 44 315C44 215 87 129 147 73C211 11 298 -11 355 -14C476 -99 554 -136 584 -144S664 -160 712 -159L720 -138ZM348 25C231 49 146 172 146 342C146 533 249 629 360 629C497 629 601 510 601 302C601 142 523 51 443 28C434 34 425 41 416 47L348 25Z" id="g121-79"></path><glyph.data ascent="989" descent="-360" horiz-adv-x="745" vert-adv-y="745"></glyph.data></g><g transform="matrix(.013,0,0,-0.013,25.48,0)"><path d="M384 0V27C293 34 287 42 287 114V635C232 613 172 594 109 583V559L157 557C201 555 205 550 205 499V114C205 42 199 34 109 27V0H384Z" id="g113-50"></path><glyph.data ascent="3473" descent="-2876" horiz-adv-x="480" vert-adv-y="480"></glyph.data></g><g transform="matrix(.013,0,0,-0.013,31.72,0)"><path d="M244 635C114 635 38 519 38 422C38 317 111 240 217 240C236 240 255 244 277 256L345 292C311 140 203 39 59 15L64 -15C89 -15 150 -5 204 17C339 72 440 202 440 386C440 521 368 635 244 635ZM228 602C326 602 352 479 352 390C352 370 351 347 348 324C327 308 293 296 258 296C174 296 124 369 124 458C124 517 152 602 228 602Z" id="g113-58"></path><glyph.data ascent="3473" descent="-2876" horiz-adv-x="480" vert-adv-y="480"></glyph.data></g></svg> model.</div>

Scientific Programming

fig2

Figure 2

Figure 2: Performance Optimization of 3D Lattice Boltzmann Flow Solver on a GPU 