[QUOTE="clyde46"][QUOTE="Cherokee_Jack"] This card is designed for more than just gaming though. Given the massive number of CUDA cores it has a lot of miliage in the direct compute world, distrubted computing sector and programs that use GPU accelerated effects such as Adobe After Effects.wis3boi
Yeah, this is the Titan supercomputer, for example
GPUs are used for more than gaming dekstops these days, they are becomign excellent at raw number crunching
[QUOTE="Wikipedia"] itan uses the same building and 200 cabinets covering 404 square metres (4352 ft2) that Jaguar did, replacing the internals and upgrading networking facilities.[17][18] Reusing the power and cooling systems already in place for Jaguar saved the lab approximately US$20 million.[19] Titan draws 8.2 MW,[20] 1.2 MW more than Jaguar did, but it is almost ten times as fast in terms of floating point calculations.[17][21] Power is provided to each cabinet at 480 V to use thinner cables than the US standard 208 V, saving US $1 million in copper.[21] In the event of a power failure, carbon fibre flywheels power generators that can keep the networking and storage infrastructure running for up to 16 seconds.[22] If power is not restored within 2 seconds, diesel engines are started, taking approximately 7 seconds, and assume the role of powering the generators indefinitely.[22] The flywheels and generators are designed only to keep the networking and storage components powered so that a reboot is much quicker, the generators are not capable of powering the processing infrastructure to continue simulations.[22] Titan's components are air-cooled by heatsinks, but the air is chilled before being pumped through the cabinets.[23] The noise of the fans cooling the components is so loud that hearing protection is required for people spending more than 15 minutes in the same room as the machine.[24] The cooling system has a cooling capacity of 6600 tons and works by cooling water to 5.5 °C (42 °F), which in turn chills the recirculated air.[23] Titan has 18,688 nodes (4 nodes per blade, 24 blades per cabinet),[25] each containing a 16-core AMD Opteron 6274 CPU with 32 GB of DDR3 ECC memory and an Nvidia Tesla K20X GPU with 6 GB GDDR5 ECC memory.[26] The total number of processor cores is 299, 008 and the total amount of RAM is over 710 TB.[21] 10 PB of storage (made up of 13, 400 7200 rpm 1 TB hard drives) is available with a transfer speed of 240 GB/s.[18][21][27] The next storage upgrade is due in 2013, it will up the total storage to between 20 and 30 PB with a transfer speed of approximately 1 TB/s.[21][28] Titan runs the Cray Linux Environment, a full version of Linux on the login nodes but a scaled down, more efficient version on the compute nodes.[29] GPUs were selected for their vastly higher parallel processing efficiency over CPUs.[26] Although the GPUs have a slower clock speed than the CPUs, each GPU contains 2, 688 CUDA cores at 732 MHz,[30] resulting in a faster overall system.[18][31] Consequently, the CPUs cores are used to allocate tasks to the GPUs rather than for directly processing the data as in previous supercomputers.[26] Titan's hardware has a theoretical peak performance of 27 petaFLOPS with perfectly optimised software.[32] On November 12, 2012 the TOP500 organisation that ranks the worlds' supercomputers by their LINPACK performance announced that Titan was ranked first at 17.59 petaFLOPS, displacing IBM Sequoia.[1][33] Titan was also ranked third on the Green500, the same 500 supercomputers but re-ordered in terms of energy efficiency.[34] Researchers also have access to EVEREST (Exploratory Visualisation Environment for Research and Technology) to better understand the data that Titan outputs. EVEREST is a visualisation room with a 10 by 3 metre screen and a smaller, secondary screen. The screens are 37 and 33 megapixels respectively with stereoscopic 3D capability.[35] My god!
Log in to comment