Get started
Work

Performance Study of an MRI Motion-Compensated Reconstruction Program on Intel CPUs, AMD EPYC CPUs, and NVIDIA GPUs

Year: 2024
Type: article
Abstract: Motion-compensated image reconstruction enables new clinical applications of magnetic resonance imaging (MRI), but it relies on computationally intensive algorithms. This study focuses on the Generalized Reconstruction by Inversion of Coupled Systems (GRICS) program, applied to the reconstruction of 3D images in cases of non-rigid or rigid motion. GRICS utilizes hybrid parallelization with MPI (Message Passing Interface) and OpenMP (Open Multi-Processing). For clinical integration, GRICS needs to efficiently utilize the computational resources of compute nodes. We aim to improve GRICS's performance without any code modification. This paper presents a performance study of GRICS on two CPU architectures: Intel Xeon Gold and AMD EPYC. The roofline model is used to study the software-hardware interaction and quantify the code's performance. For CPU-GPU comparison purposes, we propose a Matlab-GPU implementation of GRICS's reconstruction kernel. We establish the roofline model of the kernel on two NVIDIA GPU architectures: Quadro RTX 5000 and A100. After the performance study, we propose optimization patterns for the code's execution on CPUs, first considering only the OpenMP implementation, using thread binding and affinity, and appropriate architecture-compilation flags, and then looking for the optimal combination of MPI processes and OpenMP threads in the case of the hybrid MPI-OpenMP implementation. Results show that GRICS performs well on AMD EPYC CPUs, with an architectural efficiency of 52\%. The kernel's execution is fast on the NVIDIA A100 GPU, but the roofline model reports low architectural efficiency and utilization.
DOI: 10.3390/app14219663
Language: English
Open Access status: gold
Estimated APC paid: $2,728
OpenAlex ID: W4403689019
FWCI: 0.938
Cites: 33
Cited by: 3
Related to: 10