Green computing toward SKA era with RICK
🤖 AI Summary
To address the challenge of efficiently and sustainably processing hundreds of petabytes of radio astronomy data annually in the Square Kilometre Array (SKA) era, this work proposes RICK—a high-performance radio imaging kernel designed for heterogeneous HPC platforms (CPU/GPU). It refactors the w-stacking algorithm and enables multi-node production deployment. We introduce the novel “green productivity” metric to jointly quantify energy efficiency and computational timeliness. A hybrid parallel framework—integrating MPI, OpenMP, and CUDA—is developed, coupled with an energy-efficiency modeling and analysis methodology. Validation on Setonix (ranked #28 on the Top500 list) demonstrates that the GPU-accelerated implementation achieves 3.2× higher green productivity than the CPU-only baseline. Moreover, optimal single-node configuration sustains 92% of peak throughput while reducing energy consumption by 47%. This work establishes a scalable, low-carbon computational paradigm for real-time SKA imaging.
Application Category
📝 Abstract
Square Kilometer Array is expected to generate hundreds of petabytes of data per year, two orders of magnitude more than current radio interferometers. Data processing at this scale necessitates advanced High Performance Computing (HPC) resources. However, modern HPC platforms consume up to tens of M W , i.e. megawatts, and energy-to-solution in algorithms will become of utmost importance in the next future. In this work we study the trade-off between energy-to-solution and time-to-solution of our RICK code (Radio Imaging Code Kernels), which is a novel approach to implement the w-stacking algorithm designed to run on state-of-the-art HPC systems. The code can run on heterogeneous systems exploiting the accelerators. We did both single-node tests and multi-node tests with both CPU and GPU solutions, in order to study which one is the greenest and which one is the fastest. We then defined the green productivity, i.e. a quantity which relates energy-to-solution and time-to-solution in different code configurations compared to a reference one. Configurations with the highest green productivities are the most efficient ones. The tests have been run on the Setonix machine available at the Pawsey Supercomputing Research Centre (PSC) in Perth (WA), ranked as 28th in Top500 list, updated at June 2024.
Problem
Research questions and friction points this paper is trying to address.
Optimizing energy-to-solution for SKA data processing
Balancing performance and energy efficiency in HPC
Evaluating green productivity of CPU and GPU solutions
Innovation
Methods, ideas, or system contributions that make the work stand out.
RICK code optimizes w-stacking algorithm efficiency
Heterogeneous systems leverage CPU and GPU accelerators
Green productivity metric balances energy and speed
🔎 Similar Papers
No similar papers found.
