anticache

Dai Yang presented his paper "Exploring high bandwidth memory for PET Image Reconstruction" at Parco 2019 in Prague, Czech Republic

26.09.2019


Exploring high bandwidth memory for PET Image Reconstruction

Authors: Dai Yang, Tilman Küstner, Rami Al-Rihawi, Martin Schulz

Memory bandwidth plays an important role in high performance computing. Its impact on system performance is evident when running applications with a low arithmetic intensity. In this paper, we present our optimizations for the Maximum Likelihood Expectation Maximization (MLEM) algorithm, a method for positron emission tomography (PET) image reconstruction, with a sparse matrix-vector (SpMV) kernel. The results show significant improvement in performance when executing the code on an Intel Xeon Phi processor with multi-channel DRAM. The latency of the MCDRAM becomes the limiting factor. After implementing cache-blocking optimization, we achieved a total memory bandwidth of up to 180 GB/s for the SpMV operation.