Evaluating Code Portability for Carbon-Efficient RTM Computing

• Arthur F. Lorenzon UFRGS
• Phillipe O. A. Navaux UFRGS
• Alexandre Sardinha Petróleo Brasileiro S.A.
• Bronson Messer Oak Ridge National Laboratory

Resumo

As GPU architectures continue to diversify across high-performance computing (HPC) systems, ensuring code portability and minimizing environmental impact have become critical challenges. This paper investigates how different programming models affect the carbon-performance efficiency of a Reverse Time Migration (RTM) application, a key workload in geophysics. We provide twelve implementations of the RTM code using CUDA, HIP, Kokkos, RAJA, and OpenMP Target, and evaluate their behavior on eleven GPUs from NVIDIA and AMD. Our analysis covers execution time, energy consumption, and carbon footprint. Results show that HIP, when tuned per architectures and RAJA, achieve the highest code portability in terms of carbon-efficiency, reaching up to 93.7% and 93.4% efficiency across all platforms, respectively. Overall, while HIP and CUDA deliver peak performance and the lowest emissions when properly optimized, the gap between these native models and high-level abstractions such as RAJA and Kokkos is steadily narrowing, indicating growing potential for portable and sustainable HPC development.

Palavras-chave: Energy consumption, Codes, High performance computing, Computational modeling, Graphics processing units, Computer architecture, Geophysics, Programming, Sustainable development, Hip, Code Portability, Sustainability, HPC, Carbon-Performance efficiency, RTM