Export to

• Google Calendar
• iCalendar file
• hCalendar markup
  <div class="vevent h-event"> <h1 class="summary p-name">Galois Tech Talk: GpuGen: Bringing the Power of GPUs into the Haskell World</h1> <div class='date'><time class="dtstart dt-start" title="2008-09-02T10:30:00" datetime="2008-09-02T10:30:00">Tuesday, September 2, 2008 from 10:30</time>–<time class="dtend dt-end" title="2008-09-02T11:30:00" datetime="2008-09-02T11:30:00">11:30am</time></div> <div class="location vcard p-location h-card"> <a class="url" href='http://calagator.org/venues/202390439'><span class='fn org p-name'>Galois, Inc</span></a> <div class="adr p-adr h-adr"> <div class="street-address p-street-address">421 SW 6th Ave. Suite 300</div> <span class="locality p-locality">Portland</span> , <span class="region p-region">OR</span> <span class="postal-code p-postal-code">97204</span> <div class="country-name p-country-name">US</div> (<a href='https://maps.google.com/maps?q=421%20SW%206th%20Ave.%20Suite%20300,%20Portland%20OR%2097204%20US'>map</a>) </div> </div> <div class="description p-description"> <p>Title: GpuGen: Bringing the Power of GPUs into the Haskell World</p> <p>Speaker: Sean Lee</p> <pre><code> Programming Languages & Systems UNSW, Sydney </code></pre> <p>Date: Tuesday, September 2nd.</p> <pre><code> 10.30am </code></pre> <p>Location: Galois, Inc.</p> <pre><code> 421 SW 6th Ave. Suite 300 (3rd floor of the Commonwealth Building) Portland, Oregon </code></pre> <p>Abstract:</p> <p>For the last decade, the performance of GPUs has out-grown CPUs, and their programmability has also improved to the level where they can be used fo general-purpose computations. Nonetheless, GPU programming is still limited only to those who understand the hardware architecture and the parallel processing. This is because the current GPU programming systems are based on the specialized parallel processing model, and require low-level attention in many aspects such as thread launching and synchronization.</p> <p>The need for a programming system which provides a high-level abstraction layer on top of the GPU programming systems without losing the performance gain arises to facilitate the use of GPUs. Instead of writing a programming system from the scratch, the development of a Haskell extension has been chosen as the ideal approach, since the Haskell community has already accumulated a significant amount of research and resources for Nested Data Parallelism, which could be adopted to provide a high-level abstraction on GPU programming and even to broaden the applicability of GPU programming. In addition, the Foreign Function Interface of Haskell is sufficient to be the communication medium to the GPU.</p> <p>GpuGen is what connects these two dots: GPUs and Haskell. It compiles the collective data operations such as scan, fold, map, etc, which incur most computation cost, to the GPU. The design of the system, the structure of the GpuGen compiler, and the current development status are to be discussed in the talk.</p> <p>Biographical details:</p> <p> Sean Lee is a PhD candidate at the UNSW, Sydney, working in the Programming Languages & Systems Group. This summer he's been interning at Nvidia in Santa Clara, working on programming GPUs with Haskell.</p> <p>About the Galois Tech Talks.</p> <p> Galois (<a href="http://galois.com">http://galois.com</a>) has been holding weekly technical seminars for several years on topics from functional programming, formal methods, compiler and language design, to cryptography, and operating system construction, with talks by many figures from the programming language and formal methods communities.</p> <p> The talks are open and free. If you're planning to attend, dropping a note to <a href="mailto:dons@galois.com">dons@galois.com</a> is appreciated, but not required. If you're interested in giving a talk, we're always looking for new speakers.</p> </div> <h3>Links</h3> <ul> <li><a class="url u-url" href="http://groups.google.com/group/pdxfunc/browse_thread/thread/33da952d002bb1c7">Website</a></li> </ul> </div>