iFDK: A Scalable Framework for Instant High-resolution Image Reconstruction

Abstract

Computed Tomography (CT) is a widely used technology that requires compute-intense algorithms for image reconstruction. We propose a novel back-projection algorithm that reduces the projection computation cost to 1/6 of the standard algorithm. We also propose an efficient implementation that takes advantage of the heterogeneity of GPU-accelerated systems by overlapping the filtering and back-projection stages on CPUs and GPUs, respectively. Finally, we propose a distributed framework for high-resolution image reconstruction on state-of-the-art GPU-accelerated supercomputers. The framework relies on an elaborate interleave of MPI collective communication steps to achieve scalable communication. Evaluation on a single Tesla V100 GPU demonstrates that our back-projection kernel performs up to 1.6x faster than the standard FDK implementation. We also demonstrate the scalability and instantaneous CT capability of the distributed framework by using up to 2,048 V100 GPUs to solve 4K and 8K problems within 30 seconds and 2 minutes, respectively (including I/O).

arXiv commentACM/IEEE Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (SC'19)

References in corpus (5)

• Evaluating Modern GPU Interconnect: PCIe, NVLink, NV-SLI, NVSwitch and GPUDirect
• GPU-based Iterative Cone Beam CT Reconstruction Using Tight Frame Regularization
• Comparing the Performance of Different x86 SIMD Instruction Sets for a Medical Imaging Application on Modern Multi- and Manycore Chips
• Pushing the limits for medical image reconstruction on recent standard multicore processors
• Performance Engineering for a Medical Imaging Application on the Intel Xeon Phi Accelerator

Cited by in corpus (4)

• Petascale XCT: 3D Image Reconstruction with Hierarchical Communications on Multi-GPU Nodes
• PERKS: a Locality-Optimized Execution Model for Iterative Memory-bound GPU Applications
• Performance Portable Back-projection Algorithms on CPUs: Agnostic Data Locality and Vectorization Optimizations
• SAFFIRA: a Framework for Assessing the Reliability of Systolic-Array-Based DNN Accelerators