---
OA_place: publisher
OA_type: hybrid
PlanS_conform: '1'
_id: '21017'
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.
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
article_number: '12'
article_processing_charge: Yes (via OA deal)
article_type: original
author:
- first_name: Ray
full_name: Neiheiser, Ray
id: f09651b9-fec0-11ec-b5d8-934aff0e52a4
last_name: Neiheiser
orcid: 0000-0001-7227-8309
- first_name: Miguel
full_name: Matos, Miguel
last_name: Matos
- first_name: Luis
full_name: Rodrigues, Luis
last_name: Rodrigues
citation:
ama: 'Neiheiser R, Matos M, Rodrigues L. Kauri: BFT consensus with pipelined tree-based
dissemination and aggregation. ACM Transactions on Computer Systems. 2026;44(2).
doi:10.1145/3769423'
apa: 'Neiheiser, R., Matos, M., & Rodrigues, L. (2026). Kauri: BFT consensus
with pipelined tree-based dissemination and aggregation. ACM Transactions on
Computer Systems. Association for Computing Machinery. https://doi.org/10.1145/3769423'
chicago: 'Neiheiser, Ray, Miguel Matos, and Luis Rodrigues. “Kauri: BFT Consensus
with Pipelined Tree-Based Dissemination and Aggregation.” ACM Transactions
on Computer Systems. Association for Computing Machinery, 2026. https://doi.org/10.1145/3769423.'
ieee: 'R. Neiheiser, M. Matos, and L. Rodrigues, “Kauri: BFT consensus with pipelined
tree-based dissemination and aggregation,” ACM Transactions on Computer Systems,
vol. 44, no. 2. Association for Computing Machinery, 2026.'
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.'
mla: 'Neiheiser, Ray, et al. “Kauri: BFT Consensus with Pipelined Tree-Based Dissemination
and Aggregation.” ACM Transactions on Computer Systems, vol. 44, no. 2,
12, Association for Computing Machinery, 2026, doi:10.1145/3769423.'
short: R. Neiheiser, M. Matos, L. Rodrigues, ACM Transactions on Computer Systems
44 (2026).
corr_author: '1'
das_tickbox: '0'
date_created: 2026-01-20T10:14:23Z
date_published: 2026-05-01T00:00:00Z
date_updated: 2026-07-23T10:07:17Z
day: '01'
ddc:
- '000'
department:
- _id: KrPi
doi: 10.1145/3769423
file:
- access_level: open_access
checksum: b64822f3d2bcac3c68c887ced45a6008
content_type: application/pdf
creator: dernst
date_created: 2026-07-23T10:04:06Z
date_updated: 2026-07-23T10:04:06Z
file_id: '22392'
file_name: 2026_TransCompSyst_Neiheiser.pdf
file_size: 676867
relation: main_file
success: 1
file_date_updated: 2026-07-23T10:04:06Z
fulldoi: https://doi.org/10.1145/3769423
has_accepted_license: '1'
intvolume: ' 44'
issue: '2'
keyword:
- Distributed systems
- byzantine fault tolerance
- blockchain
- vote aggregation
- pipelining
language:
- iso: eng
license: https://creativecommons.org/licenses/by/4.0/
month: '05'
oa: 1
oa_version: Published Version
project:
- _id: 34a1b658-11ca-11ed-8bc3-c75229f0241e
grant_number: F8502
name: Interface Theory for Security and Privacy
- _id: 7bdd2f70-9f16-11ee-852c-b7950bc6d277
grant_number: ICT22-045
name: SeCure, privAte, and interoperabLe layEr 2
publication: ACM Transactions on Computer Systems
publication_identifier:
eissn:
- 1557-7333
issn:
- 0734-2071
publication_status: published
publisher: Association for Computing Machinery
quality_controlled: '1'
researchdata_availability: no
scopus_import: '1'
status: public
supplementarymaterial: no
title: 'Kauri: BFT consensus with pipelined tree-based dissemination and aggregation'
tmp:
image: /images/cc_by.png
legal_code_url: https://creativecommons.org/licenses/by/4.0/legalcode
name: Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)
short: CC BY (4.0)
type: journal_article
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
volume: 44
year: '2026'
...
---
OA_place: repository
OA_type: green
_id: '18237'
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.
article_processing_charge: No
article_type: original
arxiv: 1
author:
- first_name: Chaim
full_name: Baskin, Chaim
last_name: Baskin
- first_name: Natan
full_name: Liss, Natan
last_name: Liss
- first_name: Eli
full_name: Schwartz, Eli
last_name: Schwartz
- first_name: Evgenii
full_name: Zheltonozhskii, Evgenii
last_name: Zheltonozhskii
- first_name: Raja
full_name: Giryes, Raja
last_name: Giryes
- first_name: Alexander
full_name: Bronstein, Alexander
id: 58f3726e-7cba-11ef-ad8b-e6e8cb3904e6
last_name: Bronstein
orcid: 0000-0001-9699-8730
- first_name: Avi
full_name: Mendelson, Avi
last_name: Mendelson
citation:
ama: 'Baskin C, Liss N, Schwartz E, et al. UNIQ: Uniform Noise Injection for Non-Uniform
Quantization of neural networks. ACM Transactions on Computer Systems.
2021;37(1-4):1-15. doi:10.1145/3444943'
apa: 'Baskin, C., Liss, N., Schwartz, E., Zheltonozhskii, E., Giryes, R., Bronstein,
A. M., & Mendelson, A. (2021). UNIQ: Uniform Noise Injection for Non-Uniform
Quantization of neural networks. ACM Transactions on Computer Systems.
Association for Computing Machinery. https://doi.org/10.1145/3444943'
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.” ACM Transactions on Computer
Systems. Association for Computing Machinery, 2021. https://doi.org/10.1145/3444943.'
ieee: 'C. Baskin et al., “UNIQ: Uniform Noise Injection for Non-Uniform Quantization
of neural networks,” ACM Transactions on Computer Systems, vol. 37, no.
1–4. Association for Computing Machinery, pp. 1–15, 2021.'
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.'
mla: 'Baskin, Chaim, et al. “UNIQ: Uniform Noise Injection for Non-Uniform Quantization
of Neural Networks.” ACM Transactions on Computer Systems, vol. 37, no.
1–4, Association for Computing Machinery, 2021, pp. 1–15, doi:10.1145/3444943.'
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.
date_created: 2024-10-08T12:58:26Z
date_published: 2021-03-26T00:00:00Z
date_updated: 2024-10-15T07:47:22Z
day: '26'
doi: 10.1145/3444943
extern: '1'
external_id:
arxiv:
- '1804.10969'
fulldoi: https://doi.org/10.1145/3444943
intvolume: ' 37'
issue: 1-4
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://doi.org/10.48550/arXiv.1804.10969
month: '03'
oa: 1
oa_version: Preprint
page: 1-15
publication: ACM Transactions on Computer Systems
publication_identifier:
eissn:
- 1557-7333
issn:
- 0734-2071
publication_status: published
publisher: Association for Computing Machinery
quality_controlled: '1'
scopus_import: '1'
status: public
title: 'UNIQ: Uniform Noise Injection for Non-Uniform Quantization of neural networks'
type: journal_article
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
volume: 37
year: '2021'
...
---
_id: '11666'
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.
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.
article_processing_charge: No
article_type: original
author:
- first_name: Jennifer M.
full_name: Anderson, Jennifer M.
last_name: Anderson
- first_name: Lance M.
full_name: Berc, Lance M.
last_name: Berc
- first_name: Jeffrey
full_name: Dean, Jeffrey
last_name: Dean
- first_name: Sanjay
full_name: Ghemawat, Sanjay
last_name: Ghemawat
- first_name: Monika H
full_name: Henzinger, Monika H
id: 540c9bbd-f2de-11ec-812d-d04a5be85630
last_name: Henzinger
orcid: 0000-0002-5008-6530
- first_name: Shun-Tak A.
full_name: Leung, Shun-Tak A.
last_name: Leung
- 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.
full_name: Waldspurger, Carl A.
last_name: Waldspurger
- first_name: William E.
full_name: Weihl, William E.
last_name: Weihl
citation:
ama: 'Anderson JM, Berc LM, Dean J, et al. Continuous profiling: Where have all
the cycles gone? ACM Transactions on Computer Systems. 1997;15(4):357-390.
doi:10.1145/265924.265925'
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? ACM Transactions on Computer Systems. Association for Computing Machinery.
https://doi.org/10.1145/265924.265925'
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?”
ACM Transactions on Computer Systems. Association for Computing Machinery,
1997. https://doi.org/10.1145/265924.265925.'
ieee: 'J. M. Anderson et al., “Continuous profiling: Where have all the cycles
gone?,” ACM Transactions on Computer Systems, vol. 15, no. 4. Association
for Computing Machinery, pp. 357–390, 1997.'
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.'
mla: 'Anderson, Jennifer M., et al. “Continuous Profiling: Where Have All the Cycles
Gone?” ACM Transactions on Computer Systems, vol. 15, no. 4, Association
for Computing Machinery, 1997, pp. 357–90, doi:10.1145/265924.265925.'
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.
date_created: 2022-07-27T11:42:25Z
date_published: 1997-11-01T00:00:00Z
date_updated: 2024-11-06T12:06:16Z
day: '01'
doi: 10.1145/265924.265925
extern: '1'
fulldoi: https://doi.org/10.1145/265924.265925
intvolume: ' 15'
issue: '4'
language:
- iso: eng
month: '11'
oa_version: None
page: 357-390
publication: ACM Transactions on Computer Systems
publication_identifier:
eissn:
- 1557-7333
issn:
- 0734-2071
publication_status: published
publisher: Association for Computing Machinery
quality_controlled: '1'
scopus_import: '1'
status: public
title: 'Continuous profiling: Where have all the cycles gone?'
type: journal_article
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
volume: 15
year: '1997'
...