[{"PlanS_conform":"1","keyword":["Distributed systems","byzantine fault tolerance","blockchain","vote aggregation","pipelining"],"das_tickbox":"0","language":[{"iso":"eng"}],"date_updated":"2026-07-23T10:07:17Z","article_number":"12","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","year":"2026","supplementarymaterial":"no","author":[{"orcid":"0000-0001-7227-8309","id":"f09651b9-fec0-11ec-b5d8-934aff0e52a4","full_name":"Neiheiser, Ray","last_name":"Neiheiser","first_name":"Ray"},{"first_name":"Miguel","last_name":"Matos","full_name":"Matos, Miguel"},{"full_name":"Rodrigues, Luis","last_name":"Rodrigues","first_name":"Luis"}],"corr_author":"1","status":"public","volume":44,"article_processing_charge":"Yes (via OA deal)","title":"Kauri: BFT consensus with pipelined tree-based dissemination and aggregation","OA_place":"publisher","date_created":"2026-01-20T10:14:23Z","publisher":"Association for Computing Machinery","issue":"2","ddc":["000"],"tmp":{"image":"/images/cc_by.png","legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode","short":"CC BY (4.0)","name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)"},"oa_version":"Published Version","file_date_updated":"2026-07-23T10:04:06Z","type":"journal_article","publication_status":"published","fulldoi":"https://doi.org/10.1145/3769423","intvolume":"        44","day":"01","project":[{"_id":"34a1b658-11ca-11ed-8bc3-c75229f0241e","name":"Interface Theory for Security and Privacy","grant_number":"F8502"},{"_id":"7bdd2f70-9f16-11ee-852c-b7950bc6d277","name":"SeCure, privAte, and interoperabLe layEr 2","grant_number":"ICT22-045"}],"department":[{"_id":"KrPi"}],"article_type":"original","date_published":"2026-05-01T00:00:00Z","doi":"10.1145/3769423","publication_identifier":{"eissn":["1557-7333"],"issn":["0734-2071"]},"citation":{"mla":"Neiheiser, Ray, et al. “Kauri: BFT Consensus with Pipelined Tree-Based Dissemination and Aggregation.” <i>ACM Transactions on Computer Systems</i>, vol. 44, no. 2, 12, Association for Computing Machinery, 2026, doi:<a href=\"https://doi.org/10.1145/3769423\">10.1145/3769423</a>.","chicago":"Neiheiser, Ray, Miguel Matos, and Luis Rodrigues. “Kauri: BFT Consensus with Pipelined Tree-Based Dissemination and Aggregation.” <i>ACM Transactions on Computer Systems</i>. Association for Computing Machinery, 2026. <a href=\"https://doi.org/10.1145/3769423\">https://doi.org/10.1145/3769423</a>.","ista":"Neiheiser R, Matos M, Rodrigues L. 2026. Kauri: BFT consensus with pipelined tree-based dissemination and aggregation. ACM Transactions on Computer Systems. 44(2), 12.","short":"R. Neiheiser, M. Matos, L. Rodrigues, ACM Transactions on Computer Systems 44 (2026).","ieee":"R. Neiheiser, M. Matos, and L. Rodrigues, “Kauri: BFT consensus with pipelined tree-based dissemination and aggregation,” <i>ACM Transactions on Computer Systems</i>, vol. 44, no. 2. Association for Computing Machinery, 2026.","apa":"Neiheiser, R., Matos, M., &#38; Rodrigues, L. (2026). Kauri: BFT consensus with pipelined tree-based dissemination and aggregation. <i>ACM Transactions on Computer Systems</i>. Association for Computing Machinery. <a href=\"https://doi.org/10.1145/3769423\">https://doi.org/10.1145/3769423</a>","ama":"Neiheiser R, Matos M, Rodrigues L. Kauri: BFT consensus with pipelined tree-based dissemination and aggregation. <i>ACM Transactions on Computer Systems</i>. 2026;44(2). doi:<a href=\"https://doi.org/10.1145/3769423\">10.1145/3769423</a>"},"scopus_import":"1","file":[{"file_name":"2026_TransCompSyst_Neiheiser.pdf","checksum":"b64822f3d2bcac3c68c887ced45a6008","success":1,"file_id":"22392","relation":"main_file","date_updated":"2026-07-23T10:04:06Z","file_size":676867,"content_type":"application/pdf","date_created":"2026-07-23T10:04:06Z","access_level":"open_access","creator":"dernst"}],"has_accepted_license":"1","acknowledgement":"We thank the ACM TOCS Editors and the reviewers for their help in improving the manuscript. This work was partially supported by CAPES - Brazil (Coordenação de Aperfeiçoamento de Pessoal de Nível Superior) and byFundação para a Ciência e Tecnologia (FCT) under project UIDB/50021/2020 and grant 2020.05270.BD, and via project COSMOS (via the OE with ref. PTDC/EEI-COM/29271/2017, via the łPrograma Operacional Regional de Lisboa na sua componente FEDER” with ref. Lisboa-01-0145-FEDER-029271) and project Angainor with reference LISBOA-01-0145-FEDER-031456, grant agreement number 952226, and project GLOG, with reference LISBOA2030-FEDER-00771200, and project BIG (Enhancing the research and innovation potential of Tecnico through blockchain technologies and design Innovation for social Good), and project ScalableCosmosConsensus, and the Austrian Science Fund (FWF) SFB project SpyCoDe F8502 and the Vienna Science and Technology Fund (WWTF) project SCALE2 CT22-045","quality_controlled":"1","publication":"ACM Transactions on Computer Systems","researchdata_availability":"no","abstract":[{"lang":"eng","text":"With the growing interest in blockchains, permissioned approaches to consensus have received increasing attention. Unfortunately, the BFT consensus algorithms that are the backbone of most of these blockchains scale poorly and offer limited throughput. In fact, many state-of-the-art BFT consensus algorithms require a single leader process to receive and validate votes from a quorum of processes and then broadcast the result, which is inherently non-scalable. Recent approaches avoid this bottleneck by using dissemination/aggregation trees to propagate values and collect and validate votes. However, the use of trees increases the round latency, which limits the throughput for deeper trees. In this paper we propose Kauri, a BFT communication abstraction that sustains high throughput as the system size grows by leveraging a novel pipelining technique to perform scalable dissemination and aggregation on trees. Furthermore, when the number of faults is moderate (arguably the most common case in practice), our construction is able to recover from faults in an optimal number of reconfiguration steps. We implemented and experimentally evaluated Kauri with up to 800 processes. Our results show that Kauri outperforms the throughput of state-of-the-art permissioned blockchain protocols, by up to 58x without compromising latency. Interestingly, in some cases, the parallelization provided by Kauri can also decrease the latency."}],"OA_type":"hybrid","month":"05","oa":1,"_id":"21017"},{"language":[{"iso":"eng"}],"main_file_link":[{"open_access":"1","url":"https://doi.org/10.48550/arXiv.1804.10969"}],"date_updated":"2024-10-15T07:47:22Z","page":"1-15","year":"2021","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","status":"public","author":[{"first_name":"Chaim","full_name":"Baskin, Chaim","last_name":"Baskin"},{"full_name":"Liss, Natan","last_name":"Liss","first_name":"Natan"},{"full_name":"Schwartz, Eli","last_name":"Schwartz","first_name":"Eli"},{"first_name":"Evgenii","last_name":"Zheltonozhskii","full_name":"Zheltonozhskii, Evgenii"},{"first_name":"Raja","full_name":"Giryes, Raja","last_name":"Giryes"},{"orcid":"0000-0001-9699-8730","first_name":"Alexander","id":"58f3726e-7cba-11ef-ad8b-e6e8cb3904e6","last_name":"Bronstein","full_name":"Bronstein, Alexander"},{"full_name":"Mendelson, Avi","last_name":"Mendelson","first_name":"Avi"}],"volume":37,"article_processing_charge":"No","title":"UNIQ: Uniform Noise Injection for Non-Uniform Quantization of neural networks","date_created":"2024-10-08T12:58:26Z","OA_place":"repository","publisher":"Association for Computing Machinery","external_id":{"arxiv":["1804.10969"]},"oa_version":"Preprint","issue":"1-4","arxiv":1,"publication_status":"published","fulldoi":"https://doi.org/10.1145/3444943","type":"journal_article","day":"26","intvolume":"        37","date_published":"2021-03-26T00:00:00Z","article_type":"original","citation":{"ista":"Baskin C, Liss N, Schwartz E, Zheltonozhskii E, Giryes R, Bronstein AM, Mendelson A. 2021. UNIQ: Uniform Noise Injection for Non-Uniform Quantization of neural networks. ACM Transactions on Computer Systems. 37(1–4), 1–15.","short":"C. Baskin, N. Liss, E. Schwartz, E. Zheltonozhskii, R. Giryes, A.M. Bronstein, A. Mendelson, ACM Transactions on Computer Systems 37 (2021) 1–15.","mla":"Baskin, Chaim, et al. “UNIQ: Uniform Noise Injection for Non-Uniform Quantization of Neural Networks.” <i>ACM Transactions on Computer Systems</i>, vol. 37, no. 1–4, Association for Computing Machinery, 2021, pp. 1–15, doi:<a href=\"https://doi.org/10.1145/3444943\">10.1145/3444943</a>.","chicago":"Baskin, Chaim, Natan Liss, Eli Schwartz, Evgenii Zheltonozhskii, Raja Giryes, Alex M. Bronstein, and Avi Mendelson. “UNIQ: Uniform Noise Injection for Non-Uniform Quantization of Neural Networks.” <i>ACM Transactions on Computer Systems</i>. Association for Computing Machinery, 2021. <a href=\"https://doi.org/10.1145/3444943\">https://doi.org/10.1145/3444943</a>.","ama":"Baskin C, Liss N, Schwartz E, et al. UNIQ: Uniform Noise Injection for Non-Uniform Quantization of neural networks. <i>ACM Transactions on Computer Systems</i>. 2021;37(1-4):1-15. doi:<a href=\"https://doi.org/10.1145/3444943\">10.1145/3444943</a>","apa":"Baskin, C., Liss, N., Schwartz, E., Zheltonozhskii, E., Giryes, R., Bronstein, A. M., &#38; Mendelson, A. (2021). UNIQ: Uniform Noise Injection for Non-Uniform Quantization of neural networks. <i>ACM Transactions on Computer Systems</i>. Association for Computing Machinery. <a href=\"https://doi.org/10.1145/3444943\">https://doi.org/10.1145/3444943</a>","ieee":"C. Baskin <i>et al.</i>, “UNIQ: Uniform Noise Injection for Non-Uniform Quantization of neural networks,” <i>ACM Transactions on Computer Systems</i>, vol. 37, no. 1–4. Association for Computing Machinery, pp. 1–15, 2021."},"doi":"10.1145/3444943","publication_identifier":{"eissn":["1557-7333"],"issn":["0734-2071"]},"scopus_import":"1","quality_controlled":"1","publication":"ACM Transactions on Computer Systems","abstract":[{"lang":"eng","text":"We present a novel method for neural network quantization. Our method, named UNIQ, emulates a non-uniform k-quantile quantizer and adapts the model to perform well with quantized weights by injecting noise to the weights at training time. As a by-product of injecting noise to weights, we find that activations can also be quantized to as low as 8-bit with only a minor accuracy degradation. Our non-uniform quantization approach provides a novel alternative to the existing uniform quantization techniques for neural networks. We further propose a novel complexity metric of number of bit operations performed (BOPs), and we show that this metric has a linear relation with logic utilization and power. We suggest evaluating the trade-off of accuracy vs. complexity (BOPs). The proposed method, when evaluated on ResNet18/34/50 and MobileNet on ImageNet, outperforms the prior state of the art both in the low-complexity regime and the high accuracy regime. We demonstrate the practical applicability of this approach, by implementing our non-uniformly quantized CNN on FPGA."}],"OA_type":"green","oa":1,"month":"03","_id":"18237","extern":"1"},{"publication_status":"published","fulldoi":"https://doi.org/10.1145/265924.265925","type":"journal_article","day":"01","intvolume":"        15","date_published":"1997-11-01T00:00:00Z","article_type":"original","doi":"10.1145/265924.265925","publication_identifier":{"eissn":["1557-7333"],"issn":["0734-2071"]},"citation":{"chicago":"Anderson, Jennifer M., Lance M. Berc, Jeffrey Dean, Sanjay Ghemawat, Monika Henzinger, Shun-Tak A. Leung, Richard L. Sites, Mark T. Vandevoorde, Carl A. Waldspurger, and William E. Weihl. “Continuous Profiling: Where Have All the Cycles Gone?” <i>ACM Transactions on Computer Systems</i>. Association for Computing Machinery, 1997. <a href=\"https://doi.org/10.1145/265924.265925\">https://doi.org/10.1145/265924.265925</a>.","mla":"Anderson, Jennifer M., et al. “Continuous Profiling: Where Have All the Cycles Gone?” <i>ACM Transactions on Computer Systems</i>, vol. 15, no. 4, Association for Computing Machinery, 1997, pp. 357–90, doi:<a href=\"https://doi.org/10.1145/265924.265925\">10.1145/265924.265925</a>.","short":"J.M. Anderson, L.M. Berc, J. Dean, S. Ghemawat, M. Henzinger, S.-T.A. Leung, R.L. Sites, M.T. Vandevoorde, C.A. Waldspurger, W.E. Weihl, ACM Transactions on Computer Systems 15 (1997) 357–390.","ista":"Anderson JM, Berc LM, Dean J, Ghemawat S, Henzinger M, Leung S-TA, Sites RL, Vandevoorde MT, Waldspurger CA, Weihl WE. 1997. Continuous profiling: Where have all the cycles gone? ACM Transactions on Computer Systems. 15(4), 357–390.","ieee":"J. M. Anderson <i>et al.</i>, “Continuous profiling: Where have all the cycles gone?,” <i>ACM Transactions on Computer Systems</i>, vol. 15, no. 4. Association for Computing Machinery, pp. 357–390, 1997.","apa":"Anderson, J. M., Berc, L. M., Dean, J., Ghemawat, S., Henzinger, M., Leung, S.-T. A., … Weihl, W. E. (1997). Continuous profiling: Where have all the cycles gone? <i>ACM Transactions on Computer Systems</i>. Association for Computing Machinery. <a href=\"https://doi.org/10.1145/265924.265925\">https://doi.org/10.1145/265924.265925</a>","ama":"Anderson JM, Berc LM, Dean J, et al. Continuous profiling: Where have all the cycles gone? <i>ACM Transactions on Computer Systems</i>. 1997;15(4):357-390. doi:<a href=\"https://doi.org/10.1145/265924.265925\">10.1145/265924.265925</a>"},"scopus_import":"1","acknowledgement":"We would like to thank Mike Burrows, Allan Heydon, Hal Murray, Sharon Perl, and Sharon Smith for helpful comments that greatly improved the content and presentation of this article; the anonymous referees for SOSP and TOCS also provided numerous helpful comments. We would also like to thank Dawson Engler for initially suggesting the use of interprocessor interrupts to avoid expensive synchronization operations in the interrupt handler, Mitch Lichtenberg for his work on the Alpha/NT version of our system and in general for his help and suggestions on the project, and the developers of iprobe for supplying us with source code that helped us get off the ground in building the early versions of our data collection system. Finally, we would like to thank Gary Carleton and Bob Davies of Intel for answering our questions about VTune and Marty Itzkowitz of SGI for answering our questions about SpeedShop.","quality_controlled":"1","publication":"ACM Transactions on Computer Systems","abstract":[{"lang":"eng","text":"This article describes the Digital Continuous Profiling Infrastructure, a sampling-based profiling system designed to run continuously on production systems. The system supports multiprocessors, works on unmodified executables, and collects profiles for entire systems, including user programs, shared libraries, and the operating system kernel. Samples are collected at a high rate (over 5200 samples/sec. per 333MHz processor), yet with low overhead (1–3% slowdown for most workloads). Analysis tools supplied with the profiling system use the sample data to produce a precise and accurate accounting, down to the level of pipeline stalls incurred by individual instructions, of where time is bring spent. When instructions incur stalls, the tools identify possible reasons, such as cache misses, branch mispredictions, and functional unit contention. The fine-grained instruction-level analysis guides users and automated optimizers to the causes of performance problems and provides important insights for fixing them."}],"month":"11","extern":"1","_id":"11666","language":[{"iso":"eng"}],"date_updated":"2024-11-06T12:06:16Z","page":"357-390","year":"1997","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","status":"public","author":[{"first_name":"Jennifer M.","full_name":"Anderson, Jennifer M.","last_name":"Anderson"},{"first_name":"Lance M.","last_name":"Berc","full_name":"Berc, Lance M."},{"last_name":"Dean","full_name":"Dean, Jeffrey","first_name":"Jeffrey"},{"last_name":"Ghemawat","full_name":"Ghemawat, Sanjay","first_name":"Sanjay"},{"last_name":"Henzinger","full_name":"Henzinger, Monika H","id":"540c9bbd-f2de-11ec-812d-d04a5be85630","first_name":"Monika H","orcid":"0000-0002-5008-6530"},{"last_name":"Leung","full_name":"Leung, Shun-Tak A.","first_name":"Shun-Tak A."},{"first_name":"Richard L.","full_name":"Sites, Richard L.","last_name":"Sites"},{"first_name":"Mark T.","full_name":"Vandevoorde, Mark T.","last_name":"Vandevoorde"},{"first_name":"Carl A.","last_name":"Waldspurger","full_name":"Waldspurger, Carl A."},{"full_name":"Weihl, William E.","last_name":"Weihl","first_name":"William E."}],"volume":15,"article_processing_charge":"No","title":"Continuous profiling: Where have all the cycles gone?","date_created":"2022-07-27T11:42:25Z","publisher":"Association for Computing Machinery","oa_version":"None","issue":"4"}]