24 lines
27 KiB
HTML
24 lines
27 KiB
HTML
<!doctype html><html lang=en dir=auto data-theme=auto><head><meta charset=utf-8><meta http-equiv=X-UA-Compatible content="IE=edge"><meta name=viewport content="width=device-width,initial-scale=1,shrink-to-fit=no"><meta name=robots content="index, follow"><title>OSDI 2024 Digest | Publish Assistant</title><meta name=keywords content="llm-serving,distributed-systems,verification,memory,networking,storage"><meta name=description content="11 papers selected.
|
||
|
||
DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving
|
||
Yinmin Zhong, Shengyu Liu, Junda Chen, Jianbo Hu et al.
|
||
TL;DR — Separates the compute-heavy prefill phase from the memory-bound decoding phase onto different GPU pools, eliminating head-of-line blocking and significantly improving LLM serving throughput.
|
||
Why notable — Became one of the most influential LLM systems papers of 2024; the prefill–decode disaggregation insight is now widely adopted in production inference stacks (vLLM, SGLang, etc.)."><meta name=author content="Publish Assistant"><link rel=canonical href=https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/osdi-2024/><link crossorigin=anonymous href=/vincent/publish-assistant/assets/css/stylesheet.d72f07832e13c592b3edba91680bfe70f01daac396179bcace0ac36e8e0494c6.css integrity="sha256-1y8Hgy4TxZKz7bqRaAv+cPAdqsOWF5vKzgrDbo4ElMY=" rel="preload stylesheet" as=style><link rel=icon href=https://pub.sqrt.fr/vincent/publish-assistant/favicon.ico><link rel=icon type=image/png sizes=16x16 href=https://pub.sqrt.fr/vincent/publish-assistant/favicon-16x16.png><link rel=icon type=image/png sizes=32x32 href=https://pub.sqrt.fr/vincent/publish-assistant/favicon-32x32.png><link rel=apple-touch-icon href=https://pub.sqrt.fr/vincent/publish-assistant/apple-touch-icon.png><link rel=mask-icon href=https://pub.sqrt.fr/vincent/publish-assistant/safari-pinned-tab.svg><meta name=theme-color content="#2e2e33"><meta name=msapplication-TileColor content="#2e2e33"><link rel=alternate hreflang=en href=https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/osdi-2024/><noscript><style>#theme-toggle,.top-link{display:none}</style><style>@media(prefers-color-scheme:dark){:root{--theme:rgb(29, 30, 32);--entry:rgb(46, 46, 51);--primary:rgb(218, 218, 219);--secondary:rgb(155, 156, 157);--tertiary:rgb(65, 66, 68);--content:rgb(196, 196, 197);--code-block-bg:rgb(46, 46, 51);--code-bg:rgb(55, 56, 62);--border:rgb(51, 51, 51);color-scheme:dark}.list{background:var(--theme)}.toc{background:var(--entry)}}</style></noscript><script>localStorage.getItem("pref-theme")==="dark"?document.querySelector("html").dataset.theme="dark":localStorage.getItem("pref-theme")==="light"?document.querySelector("html").dataset.theme="light":window.matchMedia("(prefers-color-scheme: dark)").matches?document.querySelector("html").dataset.theme="dark":document.querySelector("html").dataset.theme="light"</script><meta property="og:url" content="https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/osdi-2024/"><meta property="og:site_name" content="Publish Assistant"><meta property="og:title" content="OSDI 2024 Digest"><meta property="og:description" content="11 papers selected.
|
||
DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving Yinmin Zhong, Shengyu Liu, Junda Chen, Jianbo Hu et al.
|
||
TL;DR — Separates the compute-heavy prefill phase from the memory-bound decoding phase onto different GPU pools, eliminating head-of-line blocking and significantly improving LLM serving throughput.
|
||
Why notable — Became one of the most influential LLM systems papers of 2024; the prefill–decode disaggregation insight is now widely adopted in production inference stacks (vLLM, SGLang, etc.)."><meta property="og:locale" content="en_us"><meta property="og:type" content="article"><meta property="article:section" content="cloud-edge"><meta property="article:published_time" content="2024-07-10T00:00:00+00:00"><meta property="article:modified_time" content="2024-07-10T00:00:00+00:00"><meta property="article:tag" content="Llm-Serving"><meta property="article:tag" content="Distributed-Systems"><meta property="article:tag" content="Verification"><meta property="article:tag" content="Memory"><meta property="article:tag" content="Networking"><meta property="article:tag" content="Storage"><meta name=twitter:card content="summary"><meta name=twitter:title content="OSDI 2024 Digest"><meta name=twitter:description content="11 papers selected.
|
||
DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving Yinmin Zhong, Shengyu Liu, Junda Chen, Jianbo Hu et al.
|
||
TL;DR — Separates the compute-heavy prefill phase from the memory-bound decoding phase onto different GPU pools, eliminating head-of-line blocking and significantly improving LLM serving throughput.
|
||
Why notable — Became one of the most influential LLM systems papers of 2024; the prefill–decode disaggregation insight is now widely adopted in production inference stacks (vLLM, SGLang, etc.)."><script type=application/ld+json>{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Edge and Cloud Systems","item":"https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/"},{"@type":"ListItem","position":2,"name":"Digests","item":"https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/"},{"@type":"ListItem","position":3,"name":"OSDI 2024 Digest","item":"https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/osdi-2024/"}]}</script><script type=application/ld+json>{"@context":"https://schema.org","@type":"BlogPosting","headline":"OSDI 2024 Digest","name":"OSDI 2024 Digest","description":"11 papers selected.\nDistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving Yinmin Zhong, Shengyu Liu, Junda Chen, Jianbo Hu et al.\nTL;DR — Separates the compute-heavy prefill phase from the memory-bound decoding phase onto different GPU pools, eliminating head-of-line blocking and significantly improving LLM serving throughput.\nWhy notable — Became one of the most influential LLM systems papers of 2024; the prefill–decode disaggregation insight is now widely adopted in production inference stacks (vLLM, SGLang, etc.).\n","keywords":["llm-serving","distributed-systems","verification","memory","networking","storage"],"articleBody":"11 papers selected.\nDistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving Yinmin Zhong, Shengyu Liu, Junda Chen, Jianbo Hu et al.\nTL;DR — Separates the compute-heavy prefill phase from the memory-bound decoding phase onto different GPU pools, eliminating head-of-line blocking and significantly improving LLM serving throughput.\nWhy notable — Became one of the most influential LLM systems papers of 2024; the prefill–decode disaggregation insight is now widely adopted in production inference stacks (vLLM, SGLang, etc.).\n→ Read paper Fairness in Serving Large Language Models Ying Sheng 0007, Shiyi Cao, Dacheng Li, Banghua Zhu et al.\nTL;DR — Introduces VTC, a token-count-weighted fair scheduling policy that prevents long-prompt users from monopolising GPU capacity in multi-tenant LLM services.\nWhy notable — First paper to formally study multi-tenant fairness in LLM serving; directly influenced subsequent work on SLA-aware serving and resource allocation in shared inference clusters.\n→ Read paper Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve Amey Agrawal, Nitin Kedia, Ashish Panwar, Jayashree Mohan et al.\nTL;DR — Introduces chunked prefill and stall-free scheduling to decouple throughput and latency goals, letting the same serving system meet both SLOs simultaneously.\nWhy notable — Elegant framing of the throughput–latency tension; chunked prefill became a standard technique in open-source inference engines within months of publication.\n→ Read paper Llumnix: Dynamic Scheduling for Large Language Model Serving Biao Sun 0002, Ziming Huang, Hanyu Zhao, Wencong Xiao et al.\nTL;DR — Treats in-flight LLM requests as migratable units, enabling load balancing and SLO recovery by live-migrating KV-cache state across GPU instances.\nWhy notable — Request migration for LLM serving was considered impractical due to KV-cache size; this paper shows it is feasible and impactful, opening a new design dimension for inference schedulers.\n→ Read paper MAST: Global Scheduling of ML Training across Geo-Distributed Datacenters at Hyperscale Arnab Choudhury, Yang Wang 0009, Tuomas Pelkonen, Kutta Srinivasan et al.\nTL;DR — Describes Google’s production system for scheduling ML training jobs across geographically distributed datacenters, balancing GPU utilisation, job deadlines, and cross-datacenter bandwidth costs.\nWhy notable — Rare large-scale production paper on global ML scheduling; the insights on heterogeneous cluster management and placement constraints are directly useful for anyone operating multi-site GPU infrastructure.\n→ Read paper SquirrelFS: using the Rust compiler to check file-system crash consistency Hayley LeBlanc, Nathan Taylor, James Bornholt, Vijay Chidambaram\nTL;DR — Encodes crash-consistency invariants in Rust’s type system so that a file system that compiles is guaranteed not to leave the storage in an inconsistent state after a crash.\nWhy notable — A clean demonstration that language-level type checking can replace runtime or proof-assistant-based verification for an important systems property; the approach is general and practically viable.\n→ Read paper Anvil: Verifying Liveness of Cluster Management Controllers Xudong Sun 0013, Wenjie Ma, Jiawei Tyler Gu, Zicheng Ma et al.\nTL;DR — Presents the first framework for mechanically verifying liveness (eventual progress) of Kubernetes-style reconciliation controllers, with proofs for real controllers including ZooKeeper and RabbitMQ operators.\nWhy notable — Liveness proofs for real-world cloud controllers were previously out of reach; Anvil’s methodology closes a critical gap in the formal verification of cloud infrastructure.\n→ Read paper DRust: Language-Guided Distributed Shared Memory with Fine Granularity, Full Transparency, and Ultra Efficiency Haoran Ma, Yifan Qiao 0002, Shi Liu, Shan Yu et al.\nTL;DR — Exploits Rust’s ownership model to implement distributed shared memory at cache-line granularity, achieving near-local performance with no programmer annotations.\nWhy notable — Prior DSM systems required explicit data placement or suffered high coherence overhead; DRust shows that a language’s ownership semantics can serve as a zero-overhead coherence protocol.\n→ Read paper Nomad: Non-Exclusive Memory Tiering via Transactional Page Migration Lingfeng Xiang, Zhen Lin, Weishu Deng, Hui Lu 0001 et al.\nTL;DR — Enables tiered-memory systems to migrate pages concurrently with ongoing accesses using a transactional protocol, eliminating the stop-the-world pauses of existing page-migration approaches.\nWhy notable — CXL-based memory tiering is becoming essential for cost-effective cloud deployments; Nomad’s non-exclusive migration is a key enabling mechanism for practical tiering at scale.\n→ Read paper Fast and Scalable In-network Lock Management Using Lock Fission Hanze Zhang, Ke Cheng, Rong Chen 0001, Haibo Chen 0001\nTL;DR — Splits a distributed lock into independent sub-locks held in programmable switches, allowing lock acquisition to complete in a single network round-trip without touching any server CPU.\nWhy notable — Achieves latencies previously only possible with RDMA using commodity programmable switching hardware; the lock-fission abstraction generalises cleanly to other in-network coordination primitives.\n→ Read paper Chop Chop: Byzantine Atomic Broadcast to the Network Limit Martina Camaioni, Rachid Guerraoui, Matteo Monti, Pierre-Louis Roman et al.\nTL;DR — Achieves Byzantine fault-tolerant atomic broadcast at near-network-bandwidth rates by batching, pipelining, and carefully overlapping cryptographic operations with network I/O.\nWhy notable — Closes the gap between the theoretical throughput of BFT protocols and what commodity hardware can actually deliver; relevant baseline for any production BFT system design.\n→ Read paper ","wordCount":"818","inLanguage":"en","datePublished":"2024-07-10T00:00:00Z","dateModified":"2024-07-10T00:00:00Z","author":{"@type":"Person","name":"Publish Assistant"},"mainEntityOfPage":{"@type":"WebPage","@id":"https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/osdi-2024/"},"publisher":{"@type":"Organization","name":"Publish Assistant","logo":{"@type":"ImageObject","url":"https://pub.sqrt.fr/vincent/publish-assistant/favicon.ico"}}}</script></head><body id=top><header class=header><nav class=header-nav><div class=logo><a href=https://pub.sqrt.fr/vincent/publish-assistant/ accesskey=h title="Publish Assistant (Alt + H)">Publish Assistant</a>
|
||
<span class=logo-sep>/</span>
|
||
<a class=logo-topic href=/vincent/publish-assistant/cloud-edge/ title="Edge and Cloud Systems">Edge and Cloud Systems</a><div class=logo-switches><button id=theme-toggle class=theme-toggle accesskey=t title="(Alt + T)" aria-label="Toggle theme">
|
||
<svg class="moon" width="18" height="18" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round"><path d="M21 12.79A9 9 0 1111.21 3 7 7 0 0021 12.79z"/></svg>
|
||
<svg class="sun" width="18" height="18" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round"><circle cx="12" cy="12" r="5"/><line x1="12" y1="1" x2="12" y2="3"/><line x1="12" y1="21" x2="12" y2="23"/><line x1="4.22" y1="4.22" x2="5.64" y2="5.64"/><line x1="18.36" y1="18.36" x2="19.78" y2="19.78"/><line x1="1" y1="12" x2="3" y2="12"/><line x1="21" y1="12" x2="23" y2="12"/><line x1="4.22" y1="19.78" x2="5.64" y2="18.36"/><line x1="18.36" y1="5.64" x2="19.78" y2="4.22"/></svg></button></div></div><ul id=menu class=menu><li><a href=/vincent/publish-assistant/cloud-edge/venues/ title=Venues><span>Venues</span></a></li><li><a href=/vincent/publish-assistant/cloud-edge/calendar/ title=Calendar><span>Calendar</span></a></li><li><a href=/vincent/publish-assistant/cloud-edge/digests/ title=Digests><span class=active>Digests</span></a></li></ul></nav></header><main class=main><article class=post-single><header class=post-header><nav class=breadcrumbs role=navigation aria-label=Breadcrumb><a href=/vincent/publish-assistant/cloud-edge/digests/>Digests</a>
|
||
<svg viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="feather feather-chevron-right"><polyline points="9 18 15 12 9 6"/></svg></nav><h1 class="post-title entry-hint-parent">OSDI 2024 Digest</h1><div class=post-meta><span title='2024-07-10 00:00:00 +0000 UTC'>July 10, 2024</span> · <span>Publish Assistant</span></div></header><div class="post-content md-content"><p>11 papers selected.</p><hr><h3 id=distserve-disaggregating-prefill-and-decoding-for-goodput-optimized-large-language-model-serving>DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving<a hidden class=anchor aria-hidden=true href=#distserve-disaggregating-prefill-and-decoding-for-goodput-optimized-large-language-model-serving>#</a></h3><p><em>Yinmin Zhong, Shengyu Liu, Junda Chen, Jianbo Hu <em>et al.</em></em></p><p><strong>TL;DR</strong> — Separates the compute-heavy prefill phase from the memory-bound decoding phase onto different GPU pools, eliminating head-of-line blocking and significantly improving LLM serving throughput.</p><p><strong>Why notable</strong> — Became one of the most influential LLM systems papers of 2024; the prefill–decode disaggregation insight is now widely adopted in production inference stacks (vLLM, SGLang, etc.).</p><p><a href=https://www.usenix.org/conference/osdi24/presentation/zhong-yinmin>→ Read paper</a></p><hr><h3 id=fairness-in-serving-large-language-models>Fairness in Serving Large Language Models<a hidden class=anchor aria-hidden=true href=#fairness-in-serving-large-language-models>#</a></h3><p><em>Ying Sheng 0007, Shiyi Cao, Dacheng Li, Banghua Zhu <em>et al.</em></em></p><p><strong>TL;DR</strong> — Introduces VTC, a token-count-weighted fair scheduling policy that prevents long-prompt users from monopolising GPU capacity in multi-tenant LLM services.</p><p><strong>Why notable</strong> — First paper to formally study multi-tenant fairness in LLM serving; directly influenced subsequent work on SLA-aware serving and resource allocation in shared inference clusters.</p><p><a href=https://www.usenix.org/conference/osdi24/presentation/sheng>→ Read paper</a></p><hr><h3 id=taming-throughput-latency-tradeoff-in-llm-inference-with-sarathi-serve>Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve<a hidden class=anchor aria-hidden=true href=#taming-throughput-latency-tradeoff-in-llm-inference-with-sarathi-serve>#</a></h3><p><em>Amey Agrawal, Nitin Kedia, Ashish Panwar, Jayashree Mohan <em>et al.</em></em></p><p><strong>TL;DR</strong> — Introduces chunked prefill and stall-free scheduling to decouple throughput and latency goals, letting the same serving system meet both SLOs simultaneously.</p><p><strong>Why notable</strong> — Elegant framing of the throughput–latency tension; chunked prefill became a standard technique in open-source inference engines within months of publication.</p><p><a href=https://www.usenix.org/conference/osdi24/presentation/agrawal>→ Read paper</a></p><hr><h3 id=llumnix-dynamic-scheduling-for-large-language-model-serving>Llumnix: Dynamic Scheduling for Large Language Model Serving<a hidden class=anchor aria-hidden=true href=#llumnix-dynamic-scheduling-for-large-language-model-serving>#</a></h3><p><em>Biao Sun 0002, Ziming Huang, Hanyu Zhao, Wencong Xiao <em>et al.</em></em></p><p><strong>TL;DR</strong> — Treats in-flight LLM requests as migratable units, enabling load balancing and SLO recovery by live-migrating KV-cache state across GPU instances.</p><p><strong>Why notable</strong> — Request migration for LLM serving was considered impractical due to KV-cache size; this paper shows it is feasible and impactful, opening a new design dimension for inference schedulers.</p><p><a href=https://www.usenix.org/conference/osdi24/presentation/sun-biao>→ Read paper</a></p><hr><h3 id=mast-global-scheduling-of-ml-training-across-geo-distributed-datacenters-at-hyperscale>MAST: Global Scheduling of ML Training across Geo-Distributed Datacenters at Hyperscale<a hidden class=anchor aria-hidden=true href=#mast-global-scheduling-of-ml-training-across-geo-distributed-datacenters-at-hyperscale>#</a></h3><p><em>Arnab Choudhury, Yang Wang 0009, Tuomas Pelkonen, Kutta Srinivasan <em>et al.</em></em></p><p><strong>TL;DR</strong> — Describes Google’s production system for scheduling ML training jobs across geographically distributed datacenters, balancing GPU utilisation, job deadlines, and cross-datacenter bandwidth costs.</p><p><strong>Why notable</strong> — Rare large-scale production paper on global ML scheduling; the insights on heterogeneous cluster management and placement constraints are directly useful for anyone operating multi-site GPU infrastructure.</p><p><a href=https://www.usenix.org/conference/osdi24/presentation/choudhury>→ Read paper</a></p><hr><h3 id=squirrelfs-using-the-rust-compiler-to-check-file-system-crash-consistency>SquirrelFS: using the Rust compiler to check file-system crash consistency<a hidden class=anchor aria-hidden=true href=#squirrelfs-using-the-rust-compiler-to-check-file-system-crash-consistency>#</a></h3><p><em>Hayley LeBlanc, Nathan Taylor, James Bornholt, Vijay Chidambaram</em></p><p><strong>TL;DR</strong> — Encodes crash-consistency invariants in Rust’s type system so that a file system that compiles is guaranteed not to leave the storage in an inconsistent state after a crash.</p><p><strong>Why notable</strong> — A clean demonstration that language-level type checking can replace runtime or proof-assistant-based verification for an important systems property; the approach is general and practically viable.</p><p><a href=https://www.usenix.org/conference/osdi24/presentation/leblanc>→ Read paper</a></p><hr><h3 id=anvil-verifying-liveness-of-cluster-management-controllers>Anvil: Verifying Liveness of Cluster Management Controllers<a hidden class=anchor aria-hidden=true href=#anvil-verifying-liveness-of-cluster-management-controllers>#</a></h3><p><em>Xudong Sun 0013, Wenjie Ma, Jiawei Tyler Gu, Zicheng Ma <em>et al.</em></em></p><p><strong>TL;DR</strong> — Presents the first framework for mechanically verifying liveness (eventual progress) of Kubernetes-style reconciliation controllers, with proofs for real controllers including ZooKeeper and RabbitMQ operators.</p><p><strong>Why notable</strong> — Liveness proofs for real-world cloud controllers were previously out of reach; Anvil’s methodology closes a critical gap in the formal verification of cloud infrastructure.</p><p><a href=https://www.usenix.org/conference/osdi24/presentation/sun-xudong>→ Read paper</a></p><hr><h3 id=drust-language-guided-distributed-shared-memory-with-fine-granularity-full-transparency-and-ultra-efficiency>DRust: Language-Guided Distributed Shared Memory with Fine Granularity, Full Transparency, and Ultra Efficiency<a hidden class=anchor aria-hidden=true href=#drust-language-guided-distributed-shared-memory-with-fine-granularity-full-transparency-and-ultra-efficiency>#</a></h3><p><em>Haoran Ma, Yifan Qiao 0002, Shi Liu, Shan Yu <em>et al.</em></em></p><p><strong>TL;DR</strong> — Exploits Rust’s ownership model to implement distributed shared memory at cache-line granularity, achieving near-local performance with no programmer annotations.</p><p><strong>Why notable</strong> — Prior DSM systems required explicit data placement or suffered high coherence overhead; DRust shows that a language’s ownership semantics can serve as a zero-overhead coherence protocol.</p><p><a href=https://www.usenix.org/conference/osdi24/presentation/ma-haoran>→ Read paper</a></p><hr><h3 id=nomad-non-exclusive-memory-tiering-via-transactional-page-migration>Nomad: Non-Exclusive Memory Tiering via Transactional Page Migration<a hidden class=anchor aria-hidden=true href=#nomad-non-exclusive-memory-tiering-via-transactional-page-migration>#</a></h3><p><em>Lingfeng Xiang, Zhen Lin, Weishu Deng, Hui Lu 0001 <em>et al.</em></em></p><p><strong>TL;DR</strong> — Enables tiered-memory systems to migrate pages concurrently with ongoing accesses using a transactional protocol, eliminating the stop-the-world pauses of existing page-migration approaches.</p><p><strong>Why notable</strong> — CXL-based memory tiering is becoming essential for cost-effective cloud deployments; Nomad’s non-exclusive migration is a key enabling mechanism for practical tiering at scale.</p><p><a href=https://www.usenix.org/conference/osdi24/presentation/xiang>→ Read paper</a></p><hr><h3 id=fast-and-scalable-in-network-lock-management-using-lock-fission>Fast and Scalable In-network Lock Management Using Lock Fission<a hidden class=anchor aria-hidden=true href=#fast-and-scalable-in-network-lock-management-using-lock-fission>#</a></h3><p><em>Hanze Zhang, Ke Cheng, Rong Chen 0001, Haibo Chen 0001</em></p><p><strong>TL;DR</strong> — Splits a distributed lock into independent sub-locks held in programmable switches, allowing lock acquisition to complete in a single network round-trip without touching any server CPU.</p><p><strong>Why notable</strong> — Achieves latencies previously only possible with RDMA using commodity programmable switching hardware; the lock-fission abstraction generalises cleanly to other in-network coordination primitives.</p><p><a href=https://www.usenix.org/conference/osdi24/presentation/zhang-hanze>→ Read paper</a></p><hr><h3 id=chop-chop-byzantine-atomic-broadcast-to-the-network-limit>Chop Chop: Byzantine Atomic Broadcast to the Network Limit<a hidden class=anchor aria-hidden=true href=#chop-chop-byzantine-atomic-broadcast-to-the-network-limit>#</a></h3><p><em>Martina Camaioni, Rachid Guerraoui, Matteo Monti, Pierre-Louis Roman <em>et al.</em></em></p><p><strong>TL;DR</strong> — Achieves Byzantine fault-tolerant atomic broadcast at near-network-bandwidth rates by batching, pipelining, and carefully overlapping cryptographic operations with network I/O.</p><p><strong>Why notable</strong> — Closes the gap between the theoretical throughput of BFT protocols and what commodity hardware can actually deliver; relevant baseline for any production BFT system design.</p><p><a href=https://www.usenix.org/conference/osdi24/presentation/camaioni>→ Read paper</a></p></div><footer class=post-footer><ul class=post-tags><li><a href=https://pub.sqrt.fr/vincent/publish-assistant/tags/llm-serving/>Llm-Serving</a></li><li><a href=https://pub.sqrt.fr/vincent/publish-assistant/tags/distributed-systems/>Distributed-Systems</a></li><li><a href=https://pub.sqrt.fr/vincent/publish-assistant/tags/verification/>Verification</a></li><li><a href=https://pub.sqrt.fr/vincent/publish-assistant/tags/memory/>Memory</a></li><li><a href=https://pub.sqrt.fr/vincent/publish-assistant/tags/networking/>Networking</a></li><li><a href=https://pub.sqrt.fr/vincent/publish-assistant/tags/storage/>Storage</a></li></ul><nav class=paginav><a class=prev href=https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/socc-2024/><span class=title>« Prev</span>
|
||
<span>SoCC 2024 Digest</span>
|
||
</a><a class=next href=https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/ccgrid-2024/><span class=title>Next »</span>
|
||
<span>CCGrid 2024 Digest</span></a></nav></footer></article></main><footer class=footer><span>© 2026 <a href=https://pub.sqrt.fr/vincent/publish-assistant/>Publish Assistant</a></span> ·
|
||
<span>Powered by
|
||
<a href="https://gohugo.io/?utm_source=papermod" rel=noopener target=_blank>Hugo</a> &
|
||
<a href=https://github.com/adityatelange/hugo-PaperMod/ rel=noopener target=_blank>PaperMod</a></span></footer><a href=#top id=top-link class="top-link hidden" aria-label="go to top" title="Go to Top (Alt + G)" accesskey=g><svg viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="feather feather-chevrons-up"><polyline points="17 11 12 6 7 11"/><polyline points="17 18 12 13 7 18"/></svg>
|
||
</a><script>let menu=document.getElementById("menu");if(menu){const e=localStorage.getItem("menu-scroll-position");e&&(menu.scrollLeft=parseInt(e,10)),menu.onscroll=function(){localStorage.setItem("menu-scroll-position",menu.scrollLeft)}}document.querySelectorAll('a[href^="#"]').forEach(e=>{e.addEventListener("click",function(e){e.preventDefault();var t=this.getAttribute("href").substr(1);window.matchMedia("(prefers-reduced-motion: reduce)").matches?document.querySelector(`[id='${decodeURIComponent(t)}']`).scrollIntoView():document.querySelector(`[id='${decodeURIComponent(t)}']`).scrollIntoView({behavior:"smooth"}),t==="top"?history.replaceState(null,null," "):history.pushState(null,null,`#${t}`)})})</script><script>var toplink=document.getElementById("top-link");window.onscroll=function(){const e=window.innerHeight;document.body.scrollTop>e||document.documentElement.scrollTop>e?toplink.classList.remove("hidden"):toplink.classList.add("hidden")}</script><script>document.getElementById("theme-toggle").addEventListener("click",()=>{const e=document.querySelector("html");e.dataset.theme==="dark"?(e.dataset.theme="light",localStorage.setItem("pref-theme","light")):(e.dataset.theme="dark",localStorage.setItem("pref-theme","dark"))})</script></body></html> |