As global specialist HPC recruiters we are excited for the ISC high performance exhibition @ to kick off this week in Germany!
Gathering from across the world and into Europe, the ISC event contains the worlds largest collection of HPC vendors, universities and research organisations.Together this group represent innovation, diversity and creativity that hallmark the global HPC community. Not only are there a number of tech giants such as Intel, Samsung, HP and IBM but a long list of influential speakers giving keynote talks on topics they are most passionate about.
Our first talk of interest is the ISC 2016 conference keynote: How HPC is supercharging machine learning by Dr Andrew Ng a chief scientist at Baidu. This talk will describe the latest trends in AI in greater detail, and share how HPC researchers now and in the future will drive significant progress in AI. The second talk of interest is by Dr Jacqueline H.Chen, a Distinguished Member of technical staff at Sandia National Laboratories who will be discussing ‘Towards exascale simulation of turbulent combustion’. In the keynote, the current state of petascale turbulent combustion simulation will be reviewed, followed by a discussion of current combustion exascale combustion co-design topics investigated by exascale combustion.
The main talk of interest is ‘The Path to Capable Exascale Computing’ by Dr Paul Messina who is the Senior Strategic Advisor & Argonne Distinguished Fellow, Argonne National Laboratory. This talk will present an overview of the research and efforts underway to put in place a joint DOE-SC and NNSA project that will result in a capable exascale ecosystem. The keynote overview sparked a thought, prompting us to question and research into ‘When will we have an exascale supercomputer?’
Exascale computing has been the subject of study and analysis for almost ten years. Exascale computing refers to a computing system which is capable of a billion billion calculations per second. There is currently a global race on to build the most powerful super computer, the milestone being to create a supercomputer capable of performing 1 million trillion floating point operation per second (1 exaflop).
To overcome this milestone, the system will need a large overhaul of how these machines compute, how they transfer data and how they are programmed. In order for them to hit that target, engineers will need to do three things. Firstly they’ll need new computer architectures who are capable of combining tens of thousands of CPUs and graphics-processor-based accelerators. Secondly engineers will also need to deal with the growing energy costs required to move data from a supercomputer’s memory to the processors. Finally, software developers will have to learn how to build programs that can make use of the new architecture.
The latest news is that China and Japan are focused on building an exascale super computer by 2020 and USA is set to have created one by 2023.
Gaining this knowledge from all the events we go to is extremely important as we are able to further educate ourselves and then pass this knowledge on to our clients and candidates. For more information on the services that Osmii offer, please contact Neil Mitchell via: email@example.com