Benzinga – August 16, 2023
Harvard researcher has reportedly cloned a supercomputer using Alphabet Inc’s Google’s cloud platform for a groundbreaking heart disease study.
The step is taken to address the lack of robust computing capabilities and accelerate their projects.
The research modeled a treatment designed to break down blood clots and tumor cells in the human circulatory system. This demanded a vast computational capacity usually provided by supercomputers, stated Harvard’s Professor Petros Koumoutsakos.
“The big problem that we had (was) we could run one simulation using a full-scale supercomputer,” Reuters reported citing Koumoutsakos, adding that refining or optimizing the simulation required further access to the supercomputer.
Costas Bekas, the head of the research platform at Citadel Securities, notes that the limited number of machines adept at conducting such research has led to slowdowns in the scientific workflow. To address these bottlenecks, researchers and entities like Citadel, needing substantial computing power typically found in supercomputers, are increasingly turning to public cloud solutions.
Cloud computing systems are not inherently tailored to meet the specific needs of researchers. Instead, they are structured to manage millions of individual, comparatively minor computing tasks, such as video streaming, web page hosting, or database queries. Typically, the cloud emphasizes stability and durability.
“Folks are realizing the potential for cloud to solve problems and technical scientific engineering computing to really unlock productivity and get to better answers, better insights, faster,” said Bill Magro, chief high-performance computing technologist at Google Cloud.