2021
DOI: 10.48550/arxiv.2110.11466
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

MLPerf HPC: A Holistic Benchmark Suite for Scientific Machine Learning on HPC Systems

Abstract: Scientific communities are increasingly adopting machine learning and deep learning models in their applications to accelerate scientific insights. High performance computing systems are pushing the frontiers of performance with a rich diversity of hardware resources and massive scale-out capabilities. There is a critical need to understand fair and effective benchmarking of machine learning applications that are representative of real-world scientific use cases. MLPerf TM is a community-driven standard to ben… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
4
0

Year Published

2022
2022
2023
2023

Publication Types

Select...
1
1

Relationship

0
2

Authors

Journals

citations
Cited by 2 publications
(4 citation statements)
references
References 26 publications
0
4
0
Order By: Relevance
“…Following the same settings used in the MLPerf HPC Training v0.7 benchmark [21], we trained a modified version of DeepLabv3+ network on the CAM5 dataset using LAMB optimizer [35], the layer-wise adaptive optimizer for largebatch training. For the segmentation accuracy, we use the intersection over union (IoU) metric, which measures how much the given two regions are overlapped with each other.…”
Section: Performance Results Of Deepcammentioning
confidence: 99%
See 3 more Smart Citations
“…Following the same settings used in the MLPerf HPC Training v0.7 benchmark [21], we trained a modified version of DeepLabv3+ network on the CAM5 dataset using LAMB optimizer [35], the layer-wise adaptive optimizer for largebatch training. For the segmentation accuracy, we use the intersection over union (IoU) metric, which measures how much the given two regions are overlapped with each other.…”
Section: Performance Results Of Deepcammentioning
confidence: 99%
“…In the original publication describing this application [19], the IoU accuracy achieved is 73%. In the MLPerf HPC Training v0.7 benchmark [21], DeepCAM is trained until reaching the quality target, 0.82 of the validation IoU between the predictions and the targets. We adopt the same target validation accuracy to train the model until the validation accuracy reaches 0.82.…”
Section: Performance Results Of Deepcammentioning
confidence: 99%
See 2 more Smart Citations