Critique of "MemXCT: Memory-Centric X-Ray CT Reconstruction with Massive Parallelization" by SCC team from Nanyang Technological University
In this technical report, we focus on reproducing the results reported in the paper MemXCT: Memory-Centric X-ray CT Reconstruction with Massive Parallelization [1]. MemXCT is a scalable approach to X-ray Computed Tomography reconstruction which removes redundant computation. We reproduced the single...
Saved in:
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
2022
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/162125 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-162125 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1621252022-10-04T08:41:24Z Critique of "MemXCT: Memory-Centric X-Ray CT Reconstruction with Massive Parallelization" by SCC team from Nanyang Technological University Li, Shenggui Lee, Bu-Sung School of Computer Science and Engineering Engineering::Computer science and engineering X-Ray CT Reproducible Computation In this technical report, we focus on reproducing the results reported in the paper MemXCT: Memory-Centric X-ray CT Reconstruction with Massive Parallelization [1]. MemXCT is a scalable approach to X-ray Computed Tomography reconstruction which removes redundant computation. We reproduced the single CPU/GPU performance as well as strong scaling experiments. We set up our configurations on Microsoft Azure CycleCloud and have two clusters. One cluster has 4 nodes with 60 CPUs on each node and the other cluster has 4 nodes with 4 NVIDIA V100 GPUs on each node. Both clusters come with InfiniBand. The original author conducted his experiments on Theta and Blue Waters supercomputers. We were able to reproduce part of the results in the original paper, however, failed to produce similar performance on other experiments. This report was submitted as part of the reproducibility challenge in SC20 Student Cluster Competition. Digital artifacts from these experiments are available at: 10.5281/zenodo.5598108. 2022-10-04T08:41:24Z 2022-10-04T08:41:24Z 2021 Journal Article Li, S. & Lee, B. (2021). Critique of "MemXCT: Memory-Centric X-Ray CT Reconstruction with Massive Parallelization" by SCC team from Nanyang Technological University. IEEE Transactions On Parallel and Distributed Systems, 33(9), 2058-2061. https://dx.doi.org/10.1109/TPDS.2021.3128040 1045-9219 https://hdl.handle.net/10356/162125 10.1109/TPDS.2021.3128040 2-s2.0-85124384909 9 33 2058 2061 en IEEE Transactions on Parallel and Distributed Systems © 2021 IEEE. All rights reserved. |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Engineering::Computer science and engineering X-Ray CT Reproducible Computation |
spellingShingle |
Engineering::Computer science and engineering X-Ray CT Reproducible Computation Li, Shenggui Lee, Bu-Sung Critique of "MemXCT: Memory-Centric X-Ray CT Reconstruction with Massive Parallelization" by SCC team from Nanyang Technological University |
description |
In this technical report, we focus on reproducing the results reported in the paper MemXCT: Memory-Centric X-ray CT Reconstruction with Massive Parallelization [1]. MemXCT is a scalable approach to X-ray Computed Tomography reconstruction which removes redundant computation. We reproduced the single CPU/GPU performance as well as strong scaling experiments. We set up our configurations on Microsoft Azure CycleCloud and have two clusters. One cluster has 4 nodes with 60 CPUs on each node and the other cluster has 4 nodes with 4 NVIDIA V100 GPUs on each node. Both clusters come with InfiniBand. The original author conducted his experiments on Theta and Blue Waters supercomputers. We were able to reproduce part of the results in the original paper, however, failed to produce similar performance on other experiments. This report was submitted as part of the reproducibility challenge in SC20 Student Cluster Competition. Digital artifacts from these experiments are available at: 10.5281/zenodo.5598108. |
author2 |
School of Computer Science and Engineering |
author_facet |
School of Computer Science and Engineering Li, Shenggui Lee, Bu-Sung |
format |
Article |
author |
Li, Shenggui Lee, Bu-Sung |
author_sort |
Li, Shenggui |
title |
Critique of "MemXCT: Memory-Centric X-Ray CT Reconstruction with Massive Parallelization" by SCC team from Nanyang Technological University |
title_short |
Critique of "MemXCT: Memory-Centric X-Ray CT Reconstruction with Massive Parallelization" by SCC team from Nanyang Technological University |
title_full |
Critique of "MemXCT: Memory-Centric X-Ray CT Reconstruction with Massive Parallelization" by SCC team from Nanyang Technological University |
title_fullStr |
Critique of "MemXCT: Memory-Centric X-Ray CT Reconstruction with Massive Parallelization" by SCC team from Nanyang Technological University |
title_full_unstemmed |
Critique of "MemXCT: Memory-Centric X-Ray CT Reconstruction with Massive Parallelization" by SCC team from Nanyang Technological University |
title_sort |
critique of "memxct: memory-centric x-ray ct reconstruction with massive parallelization" by scc team from nanyang technological university |
publishDate |
2022 |
url |
https://hdl.handle.net/10356/162125 |
_version_ |
1746219665081761792 |