Advancements in Next-Generation Sequencing (NGS) have significantly reduced the cost of generating DNA sequence data and increased the speed of data production. However, such high-throughput data production has increased the need for efficient data analysis programs. One of the most computationally demanding steps in analyzing sequencing data is mapping short reads produced by NGS to a reference DNA sequence, such as a human genome. The mapping program BWA-MEM and its newer version BWA-MEM2, optimized for CPUs, are some of the most popular choices for this task. In this study, we discuss the implementation of BWA-MEM on GPUs. This is a challenging task because many algorithms and data structures in BWA-MEM do not execute efficiently on the GPU architecture. This paper identifies major challenges in developing efficient GPU code on all major stages of the BWA-MEM program, including seeding, seed chaining, Smith-Waterman alignment, memory management, and I/O handling. We conduct comparison experiments against BWA-MEM and BWA-MEM2 running on a 64-thread CPU. The results show that our implementation achieved up to 3.2x speedup over BWA-MEM2 and up to 5.8x over BWA-MEM when using an NVIDIA A40. Using an NVIDIA A6000 and an NVIDIA A100, we achieved a wall-time speedup of up to 3.4x/3.8x over BWA-MEM2 and up to 6.1x/6.8x over BWA-MEM, respectively. In stage-wise comparison, the A40/A6000/A100 GPUs respectively achieved up to 3.7/3.8/4x, 2/2.3/2.5x, and 3.1/5/7.9x speedup on the three major stages of BWA-MEM: seeding and seed chaining, Smith-Waterman, and making SAM output. To the best of our knowledge, this is the first study that attempts to implement the entire BWA-MEM program on GPUs.
{"title":"Accelerating BWA-MEM Read Mapping on GPUs.","authors":"Minh Pham, Yicheng Tu, Xiaoyi Lv","doi":"10.1145/3577193.3593703","DOIUrl":"https://doi.org/10.1145/3577193.3593703","url":null,"abstract":"<p><p>Advancements in Next-Generation Sequencing (NGS) have significantly reduced the cost of generating DNA sequence data and increased the speed of data production. However, such high-throughput data production has increased the need for efficient data analysis programs. One of the most computationally demanding steps in analyzing sequencing data is mapping short reads produced by NGS to a reference DNA sequence, such as a human genome. The mapping program BWA-MEM and its newer version BWA-MEM2, optimized for CPUs, are some of the most popular choices for this task. In this study, we discuss the implementation of BWA-MEM on GPUs. This is a challenging task because many algorithms and data structures in BWA-MEM do not execute efficiently on the GPU architecture. This paper identifies major challenges in developing efficient GPU code on all major stages of the BWA-MEM program, including seeding, seed chaining, Smith-Waterman alignment, memory management, and I/O handling. We conduct comparison experiments against BWA-MEM and BWA-MEM2 running on a 64-thread CPU. The results show that our implementation achieved up to 3.2x speedup over BWA-MEM2 and up to 5.8x over BWA-MEM when using an NVIDIA A40. Using an NVIDIA A6000 and an NVIDIA A100, we achieved a wall-time speedup of up to 3.4x/3.8x over BWA-MEM2 and up to 6.1x/6.8x over BWA-MEM, respectively. In stage-wise comparison, the A40/A6000/A100 GPUs respectively achieved up to 3.7/3.8/4x, 2/2.3/2.5x, and 3.1/5/7.9x speedup on the three major stages of BWA-MEM: seeding and seed chaining, Smith-Waterman, and making SAM output. To the best of our knowledge, this is the first study that attempts to implement the entire BWA-MEM program on GPUs.</p>","PeriodicalId":73273,"journal":{"name":"ICS ... : proceedings of the ... ACM International Conference on Supercomputing. International Conference on Supercomputing","volume":"2023 ","pages":"155-166"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10425913/pdf/nihms-1917800.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10075809","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Due to the high level of parallelism, there are unique challenges in developing system software on massively parallel hardware such as GPUs. One such challenge is designing a dynamic memory allocator whose task is to allocate memory chunks to requesting threads at runtime. State-of-the-art GPU memory allocators maintain a global data structure holding metadata to facilitate allocation/deallocation. However, the centralized data structure can easily become a bottleneck in a massively parallel system. In this paper, we present a novel approach for designing dynamic memory allocation without a centralized data structure. The core idea is to let threads follow a random search procedure to locate free pages. Then we further extend to more advanced designs and algorithms that can achieve an order of magnitude improvement over the basic idea. We present mathematical proofs to demonstrate that (1) the basic random search design achieves asymptotically lower latency than the traditional queue-based design and (2) the advanced designs achieve significant improvement over the basic idea. Extensive experiments show consistency to our mathematical models and demonstrate that our solutions can achieve up to two orders of magnitude improvement in latency over the best-known existing solutions.
{"title":"Dynamic Memory Management in Massively Parallel Systems: A Case on GPUs.","authors":"Minh Pham, Hao Li, Yongke Yuan, Chengcheng Mou, Kandethody Ramachandran, Zichen Xu, Yicheng Tu","doi":"10.1145/3524059.3532387","DOIUrl":"10.1145/3524059.3532387","url":null,"abstract":"<p><p>Due to the high level of parallelism, there are unique challenges in developing system software on massively parallel hardware such as GPUs. One such challenge is designing a dynamic memory allocator whose task is to allocate memory chunks to requesting threads at runtime. State-of-the-art GPU memory allocators maintain a global data structure holding metadata to facilitate allocation/deallocation. However, the centralized data structure can easily become a bottleneck in a massively parallel system. In this paper, we present a novel approach for designing dynamic memory allocation without a centralized data structure. The core idea is to let threads follow a random search procedure to locate free pages. Then we further extend to more advanced designs and algorithms that can achieve an order of magnitude improvement over the basic idea. We present mathematical proofs to demonstrate that (1) the basic random search design achieves asymptotically lower latency than the traditional queue-based design and (2) the advanced designs achieve significant improvement over the basic idea. Extensive experiments show consistency to our mathematical models and demonstrate that our solutions can achieve up to two orders of magnitude improvement in latency over the best-known existing solutions.</p>","PeriodicalId":73273,"journal":{"name":"ICS ... : proceedings of the ... ACM International Conference on Supercomputing. International Conference on Supercomputing","volume":"2022 ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9357265/pdf/nihms-1823919.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"40681699","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-02-21DOI: 10.1007/978-981-19-9582-8_3
Hans-Joachim Böckenhauer, F. Frei, Silvan Horvath
{"title":"Priority Algorithms with Advice for Disjoint Path Allocation Problems","authors":"Hans-Joachim Böckenhauer, F. Frei, Silvan Horvath","doi":"10.1007/978-981-19-9582-8_3","DOIUrl":"https://doi.org/10.1007/978-981-19-9582-8_3","url":null,"abstract":"","PeriodicalId":73273,"journal":{"name":"ICS ... : proceedings of the ... ACM International Conference on Supercomputing. International Conference on Supercomputing","volume":"4 1","pages":"25-36"},"PeriodicalIF":0.0,"publicationDate":"2022-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91168122","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 : 2022-01-01DOI: 10.1007/978-981-19-9582-8_49
Sheng-Ming Wang, M. Yaqin, Fu-Hsiang Hsu
{"title":"AHP-Based Assessment of Developing Online Virtual Reality Services with Progressive Web Apps","authors":"Sheng-Ming Wang, M. Yaqin, Fu-Hsiang Hsu","doi":"10.1007/978-981-19-9582-8_49","DOIUrl":"https://doi.org/10.1007/978-981-19-9582-8_49","url":null,"abstract":"","PeriodicalId":73273,"journal":{"name":"ICS ... : proceedings of the ... ACM International Conference on Supercomputing. International Conference on Supercomputing","volume":"41 1","pages":"553-566"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78713011","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}
{"title":"Computation Offloading Algorithm Based on Deep Reinforcement Learning and Multi-Task Dependency for Edge Computing","authors":"Tengxiang Lin, Cheng-Kuan Lin, Zhen Chen, Hongju Cheng","doi":"10.1007/978-981-19-9582-8_10","DOIUrl":"https://doi.org/10.1007/978-981-19-9582-8_10","url":null,"abstract":"","PeriodicalId":73273,"journal":{"name":"ICS ... : proceedings of the ... ACM International Conference on Supercomputing. International Conference on Supercomputing","volume":"C-20 1","pages":"111-122"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85068769","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 : 2022-01-01DOI: 10.1007/978-981-19-9582-8_15
Su-nong Wu, B. Cheng, Yan Wang, Yuejuan Han, Jianxi Fan
{"title":"Hamiltonian Properties of the Dragonfly Network","authors":"Su-nong Wu, B. Cheng, Yan Wang, Yuejuan Han, Jianxi Fan","doi":"10.1007/978-981-19-9582-8_15","DOIUrl":"https://doi.org/10.1007/978-981-19-9582-8_15","url":null,"abstract":"","PeriodicalId":73273,"journal":{"name":"ICS ... : proceedings of the ... ACM International Conference on Supercomputing. International Conference on Supercomputing","volume":"48 1","pages":"167-179"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87978371","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 : 2022-01-01DOI: 10.1007/978-981-19-9582-8_21
R. Banaszak, Anna Kobusińska
{"title":"The Use of Serverless Processing in Web Application Development","authors":"R. Banaszak, Anna Kobusińska","doi":"10.1007/978-981-19-9582-8_21","DOIUrl":"https://doi.org/10.1007/978-981-19-9582-8_21","url":null,"abstract":"","PeriodicalId":73273,"journal":{"name":"ICS ... : proceedings of the ... ACM International Conference on Supercomputing. International Conference on Supercomputing","volume":"96 1","pages":"230-242"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86084050","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 : 2022-01-01DOI: 10.1007/978-981-19-9582-8_27
Yunhan Ling, Rengbo Yang, Sheng-De Wang
{"title":"Difficulty-Aware Mixup for Replay-based Continual Learning","authors":"Yunhan Ling, Rengbo Yang, Sheng-De Wang","doi":"10.1007/978-981-19-9582-8_27","DOIUrl":"https://doi.org/10.1007/978-981-19-9582-8_27","url":null,"abstract":"","PeriodicalId":73273,"journal":{"name":"ICS ... : proceedings of the ... ACM International Conference on Supercomputing. International Conference on Supercomputing","volume":"95 1","pages":"305-316"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86655275","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 : 2022-01-01DOI: 10.1007/978-981-19-9582-8_22
Ming-Huang Tsai, Yun Wang, Wu-Chun Chung
{"title":"Scaling Model for vIMS on the Cloud","authors":"Ming-Huang Tsai, Yun Wang, Wu-Chun Chung","doi":"10.1007/978-981-19-9582-8_22","DOIUrl":"https://doi.org/10.1007/978-981-19-9582-8_22","url":null,"abstract":"","PeriodicalId":73273,"journal":{"name":"ICS ... : proceedings of the ... ACM International Conference on Supercomputing. International Conference on Supercomputing","volume":"63 1","pages":"243-254"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74495851","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 : 2022-01-01DOI: 10.1007/978-981-19-9582-8_47
Pai-Ching Tseng, Yi-Li Liou, I. Lin, Tzu-Ching Weng
{"title":"The Impact of Live Streaming on Personal Purchase Behavior","authors":"Pai-Ching Tseng, Yi-Li Liou, I. Lin, Tzu-Ching Weng","doi":"10.1007/978-981-19-9582-8_47","DOIUrl":"https://doi.org/10.1007/978-981-19-9582-8_47","url":null,"abstract":"","PeriodicalId":73273,"journal":{"name":"ICS ... : proceedings of the ... ACM International Conference on Supercomputing. International Conference on Supercomputing","volume":"167 1","pages":"533-544"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89254307","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}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号