While yours truly was preparing to submit the papers for this years' GPU Technology Conference, I received a "heads up" from Victoria Crimmins (conference organizer) about nVidia delaying the GTC to April/May 2012. Another follow up came from Mark Priscaro (Snr. PR Manager) which explained the reasons for delay.
GTC 2011 will take place in five locations, while the main event is shifting from October 2011 to April/May 2012
The company decided that following excellent sales results of its Tesla GPGPU boards and the rise of GPU computing they're going to host no less than six GPU Technology Conferences in 2012. For current year, nVidia will organize five smaller events on the Asian continent. Why Europe and North America got passed over, we'll leave you to comment on. One of answers might be that the rate of GPU Computing adoption in Asia is astounding.
Be that as it may, the GPU Technology Conference in 2011 will take place in following locations:
- Singapore - May 12, 2011
- Taipei - May 19, 2011
- Tel Aviv - May 30, 2011
- Tokyo - July 22, 2011
- Beijing - December 15-16, 2011
We now expect for nVidia to organize the flagship event in April, after the NAB 2012 conference in Las Vegas, to continue with Singapore, Taipei, Tel Aviv, Tokyo and Beijing. Since GTC 2010 was visited by approximately 2,000 visitors from 40 countries, we expect that GTC 2012 could even double the number of attendees, hence the reason for why nVidia is no longer listing conference taking place in San Jose, but rather negotiating with other conference centers such as Moscone Center in San Francisco (where Apple, Intel, Oracle host their conferences). According to nVidia, the location and timing of the event is going to be revealed in two weeks time.
Personally, I expect that nVidia will align the GPU Technology Conference 2012 in San Francisco Bay Area with the official unveiling of Tesla boards based on Kepler, their next-gen 28nm architecture. If rumors are to believe, due to problems TSMC is experiencing with the 28nm process the initial 28nm silicon from AMD will be nothing more than a die-shrink of current 40nm GPUs (AMD Radeon HD 6000 Series). nVidia's 28nm Kepler though is expected to hit the stores as a consumer part in late 2011 and appear as a mission-critical part a few months afterwards. After all, as Teslas or Quadros, GPUs have no room for any silicon-related issues.