{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T15:35:00Z","timestamp":1772724900085,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":21,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,6,6]],"date-time":"2022-06-06T00:00:00Z","timestamp":1654473600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,6,6]]},"DOI":"10.1145\/3489048.3522661","type":"proceedings-article","created":{"date-parts":[[2022,6,2]],"date-time":"2022-06-02T10:30:55Z","timestamp":1654165855000},"page":"33-34","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Towards Efficient Sparse Matrix Vector Multiplication on Real Processing-In-Memory Architectures"],"prefix":"10.1145","author":[{"given":"Christina","family":"Giannoula","sequence":"first","affiliation":[{"name":"ETH Z\u00fcrich & National Technical University of Athens, Athens, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ivan","family":"Fernandez","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich & University of Malaga, Malaga, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juan","family":"G\u00f3mez-Luna","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich, Z\u00fcrich, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nectarios","family":"Koziris","sequence":"additional","affiliation":[{"name":"National Technical University of Athens, Athens, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Georgios","family":"Goumas","sequence":"additional","affiliation":[{"name":"National Technical University of Athens, Athens, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Onur","family":"Mutlu","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich, Z\u00fcrich, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,6,6]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"F. Devaux. 2019. The True Processing In Memory Accelerator. In Hot Chips .  F. Devaux. 2019. The True Processing In Memory Accelerator. In Hot Chips .","DOI":"10.1109\/HOTCHIPS.2019.8875680"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Christina Giannoula et al. 2021 a. SynCron: Efficient Synchronization Support for Near-Data-Processing Architectures. In HPCA .  Christina Giannoula et al. 2021 a. SynCron: Efficient Synchronization Support for Near-Data-Processing Architectures. In HPCA .","DOI":"10.1109\/HPCA51647.2021.00031"},{"key":"e_1_3_2_1_3_1","volume-title":"Proc. ACM Meas. Anal. Comput. Syst.","author":"Christina","unstructured":"Christina Giannoula et al. 2022 a. SparseP: Towards Efficient Sparse Matrix Vector Multiplication on Real Processing-In-Memory Architectures . Proc. ACM Meas. Anal. Comput. Syst. Christina Giannoula et al. 2022 a. SparseP: Towards Efficient Sparse Matrix Vector Multiplication on Real Processing-In-Memory Architectures . Proc. ACM Meas. Anal. Comput. Syst."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"Christina Giannoula et al. 2022 b. SparseP: Towards Efficient Sparse Matrix Vector Multiplication on Real Processing-In-Memory Systems. In CoRR . https:\/\/arxiv.org\/abs\/2201.05072  Christina Giannoula et al. 2022 b. SparseP: Towards Efficient Sparse Matrix Vector Multiplication on Real Processing-In-Memory Systems. In CoRR . https:\/\/arxiv.org\/abs\/2201.05072","DOI":"10.1109\/ISVLSI54635.2022.00063"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Georgios Goumas et al. 2009. Performance Evaluation of the Sparse Matrix-Vector Multiplication on Modern Architectures. In J. Supercomput.  Georgios Goumas et al. 2009. Performance Evaluation of the Sparse Matrix-Vector Multiplication on Modern Architectures. In J. Supercomput.","DOI":"10.1007\/s11227-008-0251-8"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Ivan Fernandez et al. 2020 a. NATSA: A Near-Data Processing Accelerator for Time Series Analysis. In ICCD .  Ivan Fernandez et al. 2020 a. NATSA: A Near-Data Processing Accelerator for Time Series Analysis. In ICCD .","DOI":"10.1109\/ICCD50377.2020.00035"},{"key":"e_1_3_2_1_7_1","unstructured":"Junwhan Ahn et al. 2015. A Scalable Processing-In-Memory Accelerator for Parallel Graph Processing. In ISCA .  Junwhan Ahn et al. 2015. A Scalable Processing-In-Memory Accelerator for Parallel Graph Processing. In ISCA ."},{"key":"e_1_3_2_1_8_1","unstructured":"Juan G\u00f3 mez-Luna etal 2021 b. Benchmarking a New Paradigm: An Experimental Analysis of a Real Processing-in-Memory Architecture. In CoRR .  Juan G\u00f3 mez-Luna et al. 2021 b. Benchmarking a New Paradigm: An Experimental Analysis of a Real Processing-in-Memory Architecture. In CoRR ."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"crossref","unstructured":"Juan G\u00f3mez-Luna etal 2021 c. Benchmarking Memory-Centric Computing Systems: Analysis of Real Processing-In-Memory Hardware. In IGSC .  Juan G\u00f3mez-Luna et al. 2021 c. Benchmarking Memory-Centric Computing Systems: Analysis of Real Processing-In-Memory Hardware. In IGSC .","DOI":"10.1109\/IGSC54211.2021.9651614"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Kevin Chang et al. 2016. Low-Cost Inter-Linked Subarrays (LISA): Enabling Fast Inter-Subarray Data Movement in DRAM. In HPCA .  Kevin Chang et al. 2016. Low-Cost Inter-Linked Subarrays (LISA): Enabling Fast Inter-Subarray Data Movement in DRAM. In HPCA .","DOI":"10.1109\/HPCA.2016.7446095"},{"key":"e_1_3_2_1_11_1","volume-title":"2019 a","author":"Konstantinos Kanellopoulos","unstructured":"Konstantinos Kanellopoulos et al. 2019 a . SMASH : Co-Designing Software Compression and Hardware-Accelerated Indexing for Efficient Sparse Matrix Operations. In MICRO . Konstantinos Kanellopoulos et al. 2019 a. SMASH: Co-Designing Software Compression and Hardware-Accelerated Indexing for Efficient Sparse Matrix Operations. In MICRO ."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Onur Mutlu et al. 2019 b. Processing Data Where It Makes Sense: Enabling In-Memory Computation. In MICPRO .  Onur Mutlu et al. 2019 b. Processing Data Where It Makes Sense: Enabling In-Memory Computation. In MICPRO .","DOI":"10.1145\/3299874.3322805"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Onur Mutlu et al. 2021 d. A Modern Primer on Processing in Memory. In Emerging Computing: From Devices to Systems - Looking Beyond Moore and Von Neumann.  Onur Mutlu et al. 2021 d. A Modern Primer on Processing in Memory. In Emerging Computing: From Devices to Systems - Looking Beyond Moore and Von Neumann.","DOI":"10.1007\/978-981-16-7487-7_7"},{"key":"e_1_3_2_1_14_1","unstructured":"Saugata Ghose et al. 2019 c. Processing-in-Memory: A Workload-Driven Perspective. In IBM JRD .  Saugata Ghose et al. 2019 c. Processing-in-Memory: A Workload-Driven Perspective. In IBM JRD ."},{"key":"e_1_3_2_1_15_1","volume-title":"2020 b. NoM: Network-on-Memory for Inter-Bank Data Transfer in Highly-Banked Memories","author":"SeyyedAghaei Rezaei Seyyed Hossein","unstructured":"Seyyed Hossein SeyyedAghaei Rezaei 2020 b. NoM: Network-on-Memory for Inter-Bank Data Transfer in Highly-Banked Memories . In IEEE CAL . Seyyed Hossein SeyyedAghaei Rezaei et al. 2020 b. NoM: Network-on-Memory for Inter-Bank Data Transfer in Highly-Banked Memories. In IEEE CAL ."},{"key":"e_1_3_2_1_16_1","unstructured":"Sukhan Lee et al. 2021 e. Hardware Architecture and Software Stack for PIM Based on Commercial DRAM Technology: Industrial Product. In ISCA .  Sukhan Lee et al. 2021 e. Hardware Architecture and Software Stack for PIM Based on Commercial DRAM Technology: Industrial Product. In ISCA ."},{"key":"e_1_3_2_1_17_1","unstructured":"Seongju Lee et al. 2022 c. A 1ynm 1.25V 8Gb 16Gb\/s\/pin GDDR6-based Accelerator-in-Memory Supporting 1TFLOPS MAC Operation and Various Activation Functions for Deep-Learning Applications. In ISSCC .  Seongju Lee et al. 2022 c. A 1ynm 1.25V 8Gb 16Gb\/s\/pin GDDR6-based Accelerator-in-Memory Supporting 1TFLOPS MAC Operation and Various Activation Functions for Deep-Learning Applications. In ISSCC ."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"Vivek Seshadri et al. 2013. RowClone: Fast and energy-efficient in-DRAM bulk data copy and initialization. In MICRO .  Vivek Seshadri et al. 2013. RowClone: Fast and energy-efficient in-DRAM bulk data copy and initialization. In MICRO .","DOI":"10.1145\/2540708.2540725"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"Yoongu Kim et al. 2012. A Case for Exploiting Subarray-Level Parallelism (SALP) in DRAM. In ISCA .  Yoongu Kim et al. 2012. A Case for Exploiting Subarray-Level Parallelism (SALP) in DRAM. In ISCA .","DOI":"10.1109\/ISCA.2012.6237032"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"crossref","unstructured":"Yaohua Wang et al. 2020 c. FIGARO: Improving System Performance via Fine-Grained In-DRAM Data Relocation and Caching. In MICRO .  Yaohua Wang et al. 2020 c. FIGARO: Improving System Performance via Fine-Grained In-DRAM Data Relocation and Caching. In MICRO .","DOI":"10.1109\/MICRO50266.2020.00036"},{"key":"e_1_3_2_1_21_1","unstructured":"SAFARI Research Group. 2022. SparseP Software Package . https:\/\/github.com\/Carnegie Mellon University-SAFARI\/SparseP  SAFARI Research Group. 2022. SparseP Software Package . https:\/\/github.com\/Carnegie Mellon University-SAFARI\/SparseP"}],"event":{"name":"SIGMETRICS\/PERFORMANCE '22: ACM SIGMETRICS\/IFIP PERFORMANCE Joint International Conference on Measurement and Modeling of Computer Systems","location":"Mumbai India","acronym":"SIGMETRICS\/PERFORMANCE '22","sponsor":["SIGMETRICS ACM Special Interest Group on Measurement and Evaluation"]},"container-title":["Abstract Proceedings of the 2022 ACM SIGMETRICS\/IFIP PERFORMANCE Joint International Conference on Measurement and Modeling of Computer Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3489048.3522661","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3489048.3522661","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:49:00Z","timestamp":1750178940000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3489048.3522661"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,6]]},"references-count":21,"alternative-id":["10.1145\/3489048.3522661","10.1145\/3489048"],"URL":"https:\/\/doi.org\/10.1145\/3489048.3522661","relation":{"is-identical-to":[{"id-type":"doi","id":"10.1145\/3547353.3522661","asserted-by":"object"}]},"subject":[],"published":{"date-parts":[[2022,6,6]]},"assertion":[{"value":"2022-06-06","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}