I don’t know what the language of the year 2000 will look like, but I know it will be called Fortran.
–Tony Hoare, winner of the 1980 Turing Award
Fortran is a general-purpose, parallel programming language that excels in scientific and engineering applications. Originally called FORTRAN (FORmula TRANslation) in 1957, it has evolved over decades to become a robust, mature, and high perfomance-oriented programming language. Today, Fortran keeps churning under the hood of many systems that we take for granted:
- Numerical weather, ocean, and surf prediction
- Climate science and prediction
- Computational fluid dynamics software used in mechanical and civil engineering
- Aerodynamics solvers for designing cars, airplanes, and spacecraft
- Fast linear algebra libraries used by machine learning frameworks
- Benchmarking the fastest supercomputers in the world (https://top500.org)
Here’s a specific example. In my work, I develop numerical models of weather, ocean surface waves, and deep ocean circulation. Talking about it over the years, I found that most people didn’t know where weather forecasts came from. They had the idea that meteorologists would get together and draw a chart of what the weather would be like tomorrow, next week, or a month from now. This is only partly true. In reality, we use sophisticated numerical models that crunch a huge amount of numbers on computers the size of a warehouse. These models simulate the atmosphere to create an educated guess about what the weather will be like in the future. Meteorologists use the output of these models to create a meaningful weather map, like the one shown in figure 1.1. This map shows just a sliver of all the data that this model produces. The output size of a weather forecast like this is counted in hundreds of gigabytes.
Figure 1.1 A forecast of Hurricane Irma on September 10, 2017, computed by an operational weather prediction model written in Fortran. Shading and barbs show surface wind speed in meters per second, and contours are isolines of sea-level pressure. A typical weather forecast is computed in parallel using hundreds or thousands of CPUs. (Data provided by the NOAA National Center for Environmental Prediction [NCEP])
The most powerful Fortran applications run in parallel on hundreds or thousands of CPUs. Development of the Fortran language and its libraries has been largely driven by the need to solve extremely large computational problems in physics, engineering, and biomedicine. To access even more computational power than what the most powerful single computer at the time could offer, in the late 20th century we started connecting many computers with high-bandwidth networks and let them each work on a piece of the problem. The result is the supercomputer, a massive computer made up of thousands of commodity CPUs (figure 1.2). Supercomputers are similar to modern server farms hosted by Google or Amazon, except that the network infrastructure in supercomputers is designed to maximize bandwidth and minimize latency between the servers themselves, rather than between them and the outside world. As a result, the CPUs in a supercomputer act like one giant processor with distributed-memory access that’s nearly as fast as local memory access. To this day, Fortran remains the dominant language used for such massive-scale parallel computations.
Figure 1.2 The MareNostrum 4 supercomputer at the Barcelona Supercomputing Center. The computer is housed inside the Torre Girona Chapel in Barcelona, Catalonia, Spain. A high-speed network connects all of the cabinets to each another. With 153,216 Intel Xeon cores, MareNostrum 4 is the fastest supercomputer in Spain, and the 37th fastest in the world as of June 2020. (https://www.top500.org/lists/2020/06). It’s used for many scientific applications, from astrophysics and materials physics, to climate and atmospheric dust transport prediction, to biomedicine. (Image source: https://www.bsc.es/marenostrum/marenostrum)