Metadata makes finding scientific data much easier, both to an individual user as well as to an entire organization. A file system may only keep track of the file location, owner and various time stamps. With a sophisticated metadata system, significant more information can be stored along with the actual data itself. This allows for more efficient workflow within an organization, enabling better collaboration.
“Henry wants to codify rules that span all competitions in order to provide a level playing field and to satisfy his authoritarian nature. Dan isn’t so sure that would work, given that each of the sponsoring organizations have their own ideas about how to best run a competition. However, both of them believe that the competitions need to become more real world when it comes to systems, applications, and how they’re used. One of the first steps along this road, the guys agree, is to add a storage component to the competitions.”
“HPC is transforming our everyday lives, as well as our not-so-ordinary ones. From nanomaterials to jet aircrafts, from medical treatments to disaster preparedness, and even the way we wash our clothes; the HPC community has transformed the world in multifaceted ways. For its 27th anniversary, the annual SC Conference will return to Austin, TX, a city that continues to develop new ways of engaging our senses and incubating technology of all types, including supercomputing.”
In this video from SC14, Mark O’Conner from Allinea demonstrates the company’s new Forge software development suite. “A shared, intuitive user interface between the debugger and profiler with a single, shallow learning curve ensures scientific developers and HPC experts alike get the maximum value from your tools investment.”
“Deep neural networks have recently emerged as an important tool for difficult AI problems, and have found success in many fields ranging from computer vision to speech recognition. Training deep neural networks is computationally intensive, and so practical application of these networks requires careful attention to parallelism. GPUs have been instrumental in the success of deep neural networks, because they significantly reduce the cost of network training, which then has allowed many researchers to train better networks. In this talk, I will discuss how we were able to duplicate results from a 1000 node cluster using only 3 nodes, each with 4 GPUs.”