@inproceedings{b8f5a6d317424302a864c75870f23c7e,
title = "Exploring high bandwidth memory for PET image reconstruction",
abstract = "Memory bandwidth plays an essential role in high performance computing. Its impact on system performance is evident when running applications with a low arithmetic intensity. Therefore, high bandwidth memory is on the agenda of many vendors. However, depending on the memory architecture, other optimizations are required to exploit the performance gain from high bandwidth memory technology. 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 MCDRAM when compared to multi-channel DRAM. We further identify that the latency of the MCDRAM becomes a new limiting factor, requiring further optimization. Ultimately, after implementing cache-blocking optimization, we achieved a total memory bandwidth of up to 180 GB/s for the SpMV operation.",
keywords = "Intel Xeon Phi, MCDRAM, Maximum Likelihood Expectation-Maximization, Positron Emission Tomography, Sparse Matrix-Vector Multiplication",
author = "Dai Yang and Tilman K{\"u}stner and Rami Al-Rihawi and Martin Schulz",
note = "Publisher Copyright: {\textcopyright} 2020 The authors and IOS Press.",
year = "2020",
doi = "10.3233/APC200044",
language = "English",
series = "Advances in Parallel Computing",
publisher = "IOS Press BV",
pages = "219--228",
editor = "Ian Foster and Joubert, {Gerhard R.} and Ludek Kucera and Nagel, {Wolfgang E.} and Frans Peters",
booktitle = "Parallel Computing",
}