One of the consistent markets for high performance computing vendors has been in the military and aerospace industry. As an article on military and aerospace applications of HPC discussed this week, this area is expanding as more avenues reliant on modeling and simulation open.
As SGI’s Bill Mannel noted this week, “HPC is well suited and steadily being adopted for myriad defense and aerospace applications. HPC currently is playing a role in training and simulation, on-board systems for navigation, defense and attack, command, control, communications, intelligence, surveillance, and reconnaissance”
Mannel points to the use of flight simulators as an example, noting that in addition to the simulations themselves, the systems that back them are more complex. He says that “intelligence data from multiple spectra and media (radar, visual, signals, emissions, infrared, ultraviolet, etc.) is exploding in volume, requiring HPC systems to analyze quickly and provide decomposition in hours vs. days. Many times the data is gathered in real-time and analyzed on the fly, providing data immediately to fighters in the middle of missions.” He notes that in addition to these tasks, the processes of encryption and decryption is frequently carried out today on HPC-class machines.
A number of leading figures behind some of the world’s largest high performance computing vendors weighed on their roles in military and defense computing in the article. Among these were NVIDIA’s Sumit Gupta who stated that HPC is becoming much more mainstream and not just limited to science and engineering.
Gupta weighed in on his company’s sense of uptake in the military and aerospace industry, noting that they are seeing a flurry of activity in the arena in areas like “satellite image processing, signal and intelligence processing and video analytics.” He says that “Just being able to process this data in real time or near real time is a big challenge…A lot of people have been talking about how they are drowning in data…traditional techniques just don’t cut it; they’re not fast enough. All this processing requires a much higher-performance computing solution.”
Naturally, Gupta points to the power of GPU computing as a solution for these big data and big compute power-hungry applications, but others, including interconnect giant Mellanox see their role as equally important in this new breed of military applications.
According to Gilad Shainer of Mellanox, “Providing the capability to send a lot of data between those compute systems, and do it fast and without too much load on the CPUs (central processing units), is the secret sauce behind clusters.”
The article offers an excellent sense of where military and aerospace adoption stands today; a patriotic-themed read on this American Independence holiday.