In this feature article from our friends over at Mellanox, we discuss how weather and climate models are both compute and data intensive. Forecast quality scales with modeling complexity and resolution. Resolution depends on the performance of supercomputers. And supercomputer performance depends on the underlying interconnect technology: to get higher performance, the interconnect must be able to move data quickly, effectively and in a scalable manner across compute resources.
Compendium of articles published on Numerical Algorithms for HPC Science
February 10, 2020 by
The Royal Society Publishing has recently released a special compendium of articles based on a recent scientific discussion meeting with HPC Industry thought leaders. “This issue contains contributions from those who develop and implement numerical algorithms and software libraries – numerical analysts, computer scientists, and high-performance computing researchers – with those who use them in some of today’s most challenging applications.”
Latest Climate Models Predict Thinner Clouds and More Global Warming
January 10, 2020 by
Thanks to clouds, latest climate models predict more global warming than their predecessors. Researchers at LLNL in collaboration with colleagues from the University of Leeds and Imperial College London have found that the latest generation of global climate models predict more warming in response to increasing carbon dioxide. “If global warming leads to fewer or thinner clouds, it causes additional warming above and beyond that coming from carbon dioxide alone. In other words, an amplifying feedback to warming occurs.”
Energy Exascale Earth System Model to Accelerate Climate Research
October 18, 2019 by
As one of the Grand Challenges of our time, climate modeling typically requires long run times and huge computational resources. Sandia National Laboratories has awarded Kelsey DiPietro a Jill Hruby Fellowship to tackle this issue. As an applied mathematician, DiPietro has proposed a way to make computer models more efficient — improving accuracy without increasing time or resources to run them.
Real-World Applications in Numerical Ocean Modeling
July 18, 2019 by
Fangli Qiao from the First Institute of Oceanography in China gave this talk at PASC19. “In this interdisciplinary dialogue we will address such questions as – what is state-of-the-art in numerical ocean modeling? And what are the current trends in model improvement? We will consider several applications of the surface wave-tide-circulation coupled numerical ocean model, such as nuclear radiation spread prediction following damage to the Fukushima Nuclear Power in 2011, and the rescue of lives at sea after boats capsized near Phuket in 2018.”
Epic HPC Road Trip Continues to NCAR
May 23, 2019 by
In this special guest feature, Dan Olds from OrionX continues his Epic HPC Road Trip series with a stop at NCAR in Boulder. “Their ability to increase model precision/resolution and to increase throughput at the same time is becoming more difficult over time due to core speed slowing down as more cores are added. In other words, new chips aren’t providing the same increase in performance as we’ve become accustomed to over the years.”
Video: Exascale Deep Learning for Climate Analytics
May 20, 2019 by
Thorsten Kurth Josh Romero gave this talk at the GPU Technology Conference. “We’ll discuss how we scaled the training of a single deep learning model to 27,360 V100 GPUs (4,560 nodes) on the OLCF Summit HPC System using the high-productivity TensorFlow framework. This talk is targeted at deep learning practitioners who are interested in learning what optimizations are necessary for training their models efficiently at massive scale.”
Evolving NASA’s Data and Information Systems for Earth Science
April 19, 2019 by
Rahul Ramachandran from NASA gave this talk at the HPC User Forum. “NASA’s Earth Science Division (ESD) missions help us to understand our planet’s interconnected systems, from a global scale down to minute processes. ESD delivers the technology, expertise and global observations that help us to map the myriad connections between our planet’s vital processes and the effects of ongoing natural and human-caused changes.”
Job of the Week: HPC Specialist in Software Development at DKRZ
March 23, 2019 by
The German Climate Computing Centre (DKRZ) is seeking and HPC and Specialist in Software Development in our Job of the Week. “DKRZ is involved in numerous national and international projects in the field of high-performance computing for climate and weather research. In addition to the direct user support, depending on your interest and ability, you will also be able to participate in this development work.”
Gordon Bell Prize Highlights the Impact of Ai
February 14, 2019 by
In this special guest feature from Scientific Computing World, Robert Roe reports on the Gordon Bell Prize finalists for 2018. “The finalist’s research ranges from AI to mixed precision workloads, with some taking advantage of the Tensor Cores available in the latest generation of Nvidia GPUs. This highlights the impact of AI and GPU technologies, which are opening up not only new applications to HPC users but also the opportunity to accelerate mixed precision workloads on large scale HPC systems.”
