Data movement is a key bottleneck in terms of both performance and energy efficiency in modern HPC systems. The NEC SX-series supercomputers have a long history of accelerating memory-intensive HPC applications by providing sufficient memory bandwidth to applications. In this paper, we analyze the performance of a prototype SX-Aurora TSUBASA supercomputer equipped with the brand-new Vector Engine (VE30) processor. VE30 is the first major update to the Vector Engine processor series, and offers significantly improved memory access performance due to its renewed memory subsystem. Moreover, it introduces new instructions and incorporates architectural advancements tailored for accelerating memory-intensive applications. Using standard benchmarks, we demonstrate that VE30 considerably outperforms other processors in both performance and efficiency of memory-intensive applications. We also evaluate VE30 using applications including SPEChpc, and show that VE30 can run real-world applications with high performance. Finally, we discuss performance tuning techniques to obtain maximum performance from VE30.
{"title":"Performance Evaluation of a Next-Generation SX-Aurora TSUBASA Vector Supercomputer","authors":"Keichi Takahashi, Soya Fujimoto, Satoru Nagase, Yoko Isobe, Yoichi Shimomura, Ryusuke Egawa, H. Takizawa","doi":"10.48550/arXiv.2304.11921","DOIUrl":"https://doi.org/10.48550/arXiv.2304.11921","url":null,"abstract":"Data movement is a key bottleneck in terms of both performance and energy efficiency in modern HPC systems. The NEC SX-series supercomputers have a long history of accelerating memory-intensive HPC applications by providing sufficient memory bandwidth to applications. In this paper, we analyze the performance of a prototype SX-Aurora TSUBASA supercomputer equipped with the brand-new Vector Engine (VE30) processor. VE30 is the first major update to the Vector Engine processor series, and offers significantly improved memory access performance due to its renewed memory subsystem. Moreover, it introduces new instructions and incorporates architectural advancements tailored for accelerating memory-intensive applications. Using standard benchmarks, we demonstrate that VE30 considerably outperforms other processors in both performance and efficiency of memory-intensive applications. We also evaluate VE30 using applications including SPEChpc, and show that VE30 can run real-world applications with high performance. Finally, we discuss performance tuning techniques to obtain maximum performance from VE30.","PeriodicalId":92039,"journal":{"name":"ICT systems security and privacy protection : 32nd IFIP TC 11 International Conference, SEC 2017, Rome, Italy, May 29-31, 2017, Proceedings. IFIP TC11 International Information Security Conference (32nd : 2017 : Rome, Italy)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73893777","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-03-14DOI: 10.48550/arXiv.2303.08169
Hikaru Ibayashi, Taufeq Mohammed Razakh, Liqiu Yang, Thomas M Linker, M. Olguin, Shinnosuke Hattori, Ye Luo, R. Kalia, A. Nakano, K. Nomura, P. Vashishta
Neural-network quantum molecular dynamics (NNQMD) simulations based on machine learning are revolutionizing atomistic simulations of materials by providing quantum-mechanical accuracy but orders-of-magnitude faster, illustrated by ACM Gordon Bell prize (2020) and finalist (2021). State-of-the-art (SOTA) NNQMD model founded on group theory featuring rotational equivariance and local descriptors has provided much higher accuracy and speed than those models, thus named Allegro (meaning fast). On massively parallel supercomputers, however, it suffers a fidelity-scaling problem, where growing number of unphysical predictions of interatomic forces prohibits simulations involving larger numbers of atoms for longer times. Here, we solve this problem by combining the Allegro model with sharpness aware minimization (SAM) for enhancing the robustness of model through improved smoothness of the loss landscape. The resulting Allegro-Legato (meaning fast and"smooth") model was shown to elongate the time-to-failure $t_textrm{failure}$, without sacrificing computational speed or accuracy. Specifically, Allegro-Legato exhibits much weaker dependence of timei-to-failure on the problem size, $t_{textrm{failure}} propto N^{-0.14}$ ($N$ is the number of atoms) compared to the SOTA Allegro model $left(t_{textrm{failure}} propto N^{-0.29}right)$, i.e., systematically delayed time-to-failure, thus allowing much larger and longer NNQMD simulations without failure. The model also exhibits excellent computational scalability and GPU acceleration on the Polaris supercomputer at Argonne Leadership Computing Facility. Such scalable, accurate, fast and robust NNQMD models will likely find broad applications in NNQMD simulations on emerging exaflop/s computers, with a specific example of accounting for nuclear quantum effects in the dynamics of ammonia.
{"title":"Allegro-Legato: Scalable, Fast, and Robust Neural-Network Quantum Molecular Dynamics via Sharpness-Aware Minimization","authors":"Hikaru Ibayashi, Taufeq Mohammed Razakh, Liqiu Yang, Thomas M Linker, M. Olguin, Shinnosuke Hattori, Ye Luo, R. Kalia, A. Nakano, K. Nomura, P. Vashishta","doi":"10.48550/arXiv.2303.08169","DOIUrl":"https://doi.org/10.48550/arXiv.2303.08169","url":null,"abstract":"Neural-network quantum molecular dynamics (NNQMD) simulations based on machine learning are revolutionizing atomistic simulations of materials by providing quantum-mechanical accuracy but orders-of-magnitude faster, illustrated by ACM Gordon Bell prize (2020) and finalist (2021). State-of-the-art (SOTA) NNQMD model founded on group theory featuring rotational equivariance and local descriptors has provided much higher accuracy and speed than those models, thus named Allegro (meaning fast). On massively parallel supercomputers, however, it suffers a fidelity-scaling problem, where growing number of unphysical predictions of interatomic forces prohibits simulations involving larger numbers of atoms for longer times. Here, we solve this problem by combining the Allegro model with sharpness aware minimization (SAM) for enhancing the robustness of model through improved smoothness of the loss landscape. The resulting Allegro-Legato (meaning fast and\"smooth\") model was shown to elongate the time-to-failure $t_textrm{failure}$, without sacrificing computational speed or accuracy. Specifically, Allegro-Legato exhibits much weaker dependence of timei-to-failure on the problem size, $t_{textrm{failure}} propto N^{-0.14}$ ($N$ is the number of atoms) compared to the SOTA Allegro model $left(t_{textrm{failure}} propto N^{-0.29}right)$, i.e., systematically delayed time-to-failure, thus allowing much larger and longer NNQMD simulations without failure. The model also exhibits excellent computational scalability and GPU acceleration on the Polaris supercomputer at Argonne Leadership Computing Facility. Such scalable, accurate, fast and robust NNQMD models will likely find broad applications in NNQMD simulations on emerging exaflop/s computers, with a specific example of accounting for nuclear quantum effects in the dynamics of ammonia.","PeriodicalId":92039,"journal":{"name":"ICT systems security and privacy protection : 32nd IFIP TC 11 International Conference, SEC 2017, Rome, Italy, May 29-31, 2017, Proceedings. IFIP TC11 International Information Security Conference (32nd : 2017 : Rome, Italy)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81168347","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-02-11DOI: 10.48550/arXiv.2302.05730
Ioannis Sakiotis, K. Arumugam, M. Paterno, D. Ranjan, B. Terzić, M. Zubair
We present our experience in porting optimized CUDA implementations to oneAPI. We focus on the use case of numerical integration, particularly the CUDA implementations of PAGANI and $m$-Cubes. We faced several challenges that caused performance degradation in the oneAPI ports. These include differences in utilized registers per thread, compiler optimizations, and mappings of CUDA library calls to oneAPI equivalents. After addressing those challenges, we tested both the PAGANI and m-Cubes integrators on numerous integrands of various characteristics. To evaluate the quality of the ports, we collected performance metrics of the CUDA and oneAPI implementations on the Nvidia V100 GPU. We found that the oneAPI ports often achieve comparable performance to the CUDA versions, and that they are at most 10% slower.
{"title":"Porting numerical integration codes from CUDA to oneAPI: a case study","authors":"Ioannis Sakiotis, K. Arumugam, M. Paterno, D. Ranjan, B. Terzić, M. Zubair","doi":"10.48550/arXiv.2302.05730","DOIUrl":"https://doi.org/10.48550/arXiv.2302.05730","url":null,"abstract":"We present our experience in porting optimized CUDA implementations to oneAPI. We focus on the use case of numerical integration, particularly the CUDA implementations of PAGANI and $m$-Cubes. We faced several challenges that caused performance degradation in the oneAPI ports. These include differences in utilized registers per thread, compiler optimizations, and mappings of CUDA library calls to oneAPI equivalents. After addressing those challenges, we tested both the PAGANI and m-Cubes integrators on numerous integrands of various characteristics. To evaluate the quality of the ports, we collected performance metrics of the CUDA and oneAPI implementations on the Nvidia V100 GPU. We found that the oneAPI ports often achieve comparable performance to the CUDA versions, and that they are at most 10% slower.","PeriodicalId":92039,"journal":{"name":"ICT systems security and privacy protection : 32nd IFIP TC 11 International Conference, SEC 2017, Rome, Italy, May 29-31, 2017, Proceedings. IFIP TC11 International Information Security Conference (32nd : 2017 : Rome, Italy)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87267350","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-01-20DOI: 10.1007/978-3-031-32041-5_6
O. Taubert, Marie Weiel, D. Coquelin, Anis Farshian, C. Debus, A. Schug, Achim Streit, Markus Götz
{"title":"Massively Parallel Genetic Optimization through Asynchronous Propagation of Populations","authors":"O. Taubert, Marie Weiel, D. Coquelin, Anis Farshian, C. Debus, A. Schug, Achim Streit, Markus Götz","doi":"10.1007/978-3-031-32041-5_6","DOIUrl":"https://doi.org/10.1007/978-3-031-32041-5_6","url":null,"abstract":"","PeriodicalId":92039,"journal":{"name":"ICT systems security and privacy protection : 32nd IFIP TC 11 International Conference, SEC 2017, Rome, Italy, May 29-31, 2017, Proceedings. IFIP TC11 International Information Security Conference (32nd : 2017 : Rome, Italy)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75695492","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-01-12DOI: 10.48550/arXiv.2301.05145
Jie Li, George Michelogiannakis, B. Cook, Dulanya Cooray, Yong Chen
Resource demands of HPC applications vary significantly. However, it is common for HPC systems to primarily assign resources on a per-node basis to prevent interference from co-located workloads. This gap between the coarse-grained resource allocation and the varying resource demands can lead to HPC resources being not fully utilized. In this study, we analyze the resource usage and application behavior of NERSC's Perlmutter, a state-of-the-art open-science HPC system with both CPU-only and GPU-accelerated nodes. Our one-month usage analysis reveals that CPUs are commonly not fully utilized, especially for GPU-enabled jobs. Also, around 64% of both CPU and GPU-enabled jobs used 50% or less of the available host memory capacity. Additionally, about 50% of GPU-enabled jobs used up to 25% of the GPU memory, and the memory capacity was not fully utilized in some ways for all jobs. While our study comes early in Perlmutter's lifetime thus policies and application workload may change, it provides valuable insights on performance characterization, application behavior, and motivates systems with more fine-grain resource allocation.
{"title":"Analyzing Resource Utilization in an HPC System: A Case Study of NERSC Perlmutter","authors":"Jie Li, George Michelogiannakis, B. Cook, Dulanya Cooray, Yong Chen","doi":"10.48550/arXiv.2301.05145","DOIUrl":"https://doi.org/10.48550/arXiv.2301.05145","url":null,"abstract":"Resource demands of HPC applications vary significantly. However, it is common for HPC systems to primarily assign resources on a per-node basis to prevent interference from co-located workloads. This gap between the coarse-grained resource allocation and the varying resource demands can lead to HPC resources being not fully utilized. In this study, we analyze the resource usage and application behavior of NERSC's Perlmutter, a state-of-the-art open-science HPC system with both CPU-only and GPU-accelerated nodes. Our one-month usage analysis reveals that CPUs are commonly not fully utilized, especially for GPU-enabled jobs. Also, around 64% of both CPU and GPU-enabled jobs used 50% or less of the available host memory capacity. Additionally, about 50% of GPU-enabled jobs used up to 25% of the GPU memory, and the memory capacity was not fully utilized in some ways for all jobs. While our study comes early in Perlmutter's lifetime thus policies and application workload may change, it provides valuable insights on performance characterization, application behavior, and motivates systems with more fine-grain resource allocation.","PeriodicalId":92039,"journal":{"name":"ICT systems security and privacy protection : 32nd IFIP TC 11 International Conference, SEC 2017, Rome, Italy, May 29-31, 2017, Proceedings. IFIP TC11 International Information Security Conference (32nd : 2017 : Rome, Italy)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83007776","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-01-02DOI: 10.1007/978-3-031-32041-5_13
Elijah Pelofske, Andreas Bärtschi, S. Eidenbenz
{"title":"Quantum Annealing vs. QAOA: 127 Qubit Higher-Order Ising Problems on NISQ Computers","authors":"Elijah Pelofske, Andreas Bärtschi, S. Eidenbenz","doi":"10.1007/978-3-031-32041-5_13","DOIUrl":"https://doi.org/10.1007/978-3-031-32041-5_13","url":null,"abstract":"","PeriodicalId":92039,"journal":{"name":"ICT systems security and privacy protection : 32nd IFIP TC 11 International Conference, SEC 2017, Rome, Italy, May 29-31, 2017, Proceedings. IFIP TC11 International Information Security Conference (32nd : 2017 : Rome, Italy)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80059266","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-01-01DOI: 10.1007/978-3-031-32041-5_17
Amir Raoofy, Roman Karlstetter, Martin Schreiber, C. Trinitis, Martin Schulz
{"title":"Overcoming Weak Scaling Challenges in Tree-Based Nearest Neighbor Time Series Mining","authors":"Amir Raoofy, Roman Karlstetter, Martin Schreiber, C. Trinitis, Martin Schulz","doi":"10.1007/978-3-031-32041-5_17","DOIUrl":"https://doi.org/10.1007/978-3-031-32041-5_17","url":null,"abstract":"","PeriodicalId":92039,"journal":{"name":"ICT systems security and privacy protection : 32nd IFIP TC 11 International Conference, SEC 2017, Rome, Italy, May 29-31, 2017, Proceedings. IFIP TC11 International Information Security Conference (32nd : 2017 : Rome, Italy)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75815551","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-01-01DOI: 10.1007/978-3-031-32041-5_5
C. Alt, Tobias Kenter, S. Faghih-Naini, Jennifer Faj, Jan-Oliver Opdenhövel, Christian Plessl, V. Aizinger, Jan Hönig, H. Köstler
{"title":"Shallow Water DG Simulations on FPGAs: Design and Comparison of a Novel Code Generation Pipeline","authors":"C. Alt, Tobias Kenter, S. Faghih-Naini, Jennifer Faj, Jan-Oliver Opdenhövel, Christian Plessl, V. Aizinger, Jan Hönig, H. Köstler","doi":"10.1007/978-3-031-32041-5_5","DOIUrl":"https://doi.org/10.1007/978-3-031-32041-5_5","url":null,"abstract":"","PeriodicalId":92039,"journal":{"name":"ICT systems security and privacy protection : 32nd IFIP TC 11 International Conference, SEC 2017, Rome, Italy, May 29-31, 2017, Proceedings. IFIP TC11 International Information Security Conference (32nd : 2017 : Rome, Italy)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86146015","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-01-01DOI: 10.1007/978-3-031-32041-5_7
H. Ltaief, Yuxi Hong, A. Dabah, Rabab Alomairy, Sameh Abdulah, Chris Goreczny, P. Gepner, M. Ravasi, D. Gratadour, D. Keyes
{"title":"Steering Customized AI Architectures for HPC Scientific Applications","authors":"H. Ltaief, Yuxi Hong, A. Dabah, Rabab Alomairy, Sameh Abdulah, Chris Goreczny, P. Gepner, M. Ravasi, D. Gratadour, D. Keyes","doi":"10.1007/978-3-031-32041-5_7","DOIUrl":"https://doi.org/10.1007/978-3-031-32041-5_7","url":null,"abstract":"","PeriodicalId":92039,"journal":{"name":"ICT systems security and privacy protection : 32nd IFIP TC 11 International Conference, SEC 2017, Rome, Italy, May 29-31, 2017, Proceedings. IFIP TC11 International Information Security Conference (32nd : 2017 : Rome, Italy)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90762973","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：