AMD’s Epyc processors played a key role in Mercedes’ F1 championship successes in 2020 and 2021

Formula 1 is a data-driven sport. Since the sport was taken over by Liberty Media, cost caps have been introduced, with limited track test days and wind tunnel time. To get around this, computational fluid dynamics (CFD) has become absolutely critical to providing accurate aerodynamic simulations and data that correlate with on-track performance. That means you need massive amounts of computing power.

AMD joined as a sponsor of the Mercedes-AMG Petronas Formula 1 team in early 2020. AMD provides its Epyc server processors, Ryzen Pro laptops and various tools to help the team run smoothly. These systems are a key component of a modern F1 team’s performance.

AMD released a case study showing how its Epyc processors directly improved Mercedes’ aerodynamic testing capability, which led to Mercedes-AMG Petronas winning its eighth Constructors’ Championship in 2021. According to AMD, Epyc processors delivered a 20 percent performance improvement in the CFD calculation speed.

AMD’s Epyc processors with their high core counts and scalability are well suited for highly parallel workloads. An F1 team like Mercedes is likely developing its own internally coded software to maximize the performance of its Epyc systems.

(Image credit: AMD)

Simon Williams, head of aerodynamic development software at Mercedes-AMG Petronas F1, said: “There is also a regulation on how many geometries we can run in a given period, which is usually eight weeks. We are trying to maximize everything we can do in this period to get the most out of our CFD.” The quota equates to about 1,800 new geometry simulations over the eight-week period. “It’s about trying to maximize the work that the CFD resolution can do per clock cycle.”

Williams went on to say, “AMD Epyc servers have allowed us to run a lot more work in parallel. Aerodynamicists, if they get a result back during the day, they can do another project and do a second run overnight. In the morning, they’ll have completed two iterations instead of one. You need to have the right hardware to do this.

Nobody can deny that Mercedes dominated Formula 1 for a long time. You don’t get to the top of a sport like Formula 1 without having a well-oiled, dedicated, motivated and talented team. It also helps to have a seven-time world champion in the cockpit. But with cost caps limiting expenses, coupled with the introduction of measures aimed at leveling the playing field, getting it right as quickly as possible is vital. As we are in the 2022 season, Mercedes is facing a challenge.

The introduction of new technical regulations for the 2022 season means that most of the data collected for the 2020 and 2021 cars is no longer relevant. At the time of writing, after 3 races Mercedes find themselves behind a resurgent Ferrari and have benefited from the unreliability of Red Bull cars. Mercedes cars are suffering from so-called ‘porpoising’ problems, where the car bounces up and down at speed as a result of ground effect aerodynamics not fully understood. This is leading to configuration compromises and loss of aerodynamic performance. You can be sure the Mercedes team is busy processing data and running simulations 24/7 on all these Epyc servers at their Brackley UK base.

Yes, I am an F1 tragic.

Leave a Comment