261 lines
50 KiB
XML
261 lines
50 KiB
XML
<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Publish Assistant</title><link>https://pub.sqrt.fr/vincent/publish-assistant/</link><description>Recent content on Publish Assistant</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Sun, 20 Jul 2025 00:00:00 +0000</lastBuildDate><atom:link href="https://pub.sqrt.fr/vincent/publish-assistant/index.xml" rel="self" type="application/rss+xml"/><item><title>HPDC 2025 Digest</title><link>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/hpdc-2025/</link><pubDate>Sun, 20 Jul 2025 00:00:00 +0000</pubDate><guid>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/hpdc-2025/</guid><description><p>10 papers selected.</p>
|
||
<hr>
|
||
<h3 id="parameterized-algorithms-for-non-uniform-all-to-all">Parameterized Algorithms for Non-uniform All-to-all</h3>
|
||
<p><em>Ke Fan, Jens Domke, Seydou Ba, Sidharth Kumar</em></p>
|
||
<p><strong>TL;DR</strong> — Introduces parameterized algorithms that adapt non-uniform all-to-all collective communication to heterogeneous network topologies, reducing message contention and improving throughput.</p>
|
||
<p><strong>Why notable</strong> — Non-uniform all-to-all is a performance bottleneck in many HPC applications; topology-aware parameterization directly benefits MPI implementations on dragonfly and fat-tree networks at scale.</p>
|
||
<p><a href="https://doi.org/10.1145/3731545.3731590">→ Read paper</a>
|
||
</p>
|
||
<hr>
|
||
<h3 id="dpu-kv-on-the-benefits-of-dpu-offloading-for-in-memory-key-value-stores-at-the-edge">DPU-KV: On the Benefits of DPU Offloading for In-Memory Key-Value Stores at the Edge</h3>
|
||
<p><em>Arjun Kashyap, Yuke Li 0003, Xiaoyi Lu 0001</em></p></description></item><item><title>ATC 2025 Digest</title><link>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/atc-2025/</link><pubDate>Wed, 09 Jul 2025 00:00:00 +0000</pubDate><guid>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/atc-2025/</guid><description><p>13 papers selected.</p>
|
||
<hr>
|
||
<h3 id="asterinas-a-linux-abi-compatible-rust-based-framekernel-os-with-a-small-and-sound-tcb">ASTERINAS: A Linux ABI-Compatible, Rust-Based Framekernel OS with a Small and Sound TCB</h3>
|
||
<p><em>Yuke Peng, Hongliang Tian, Junyang Zhang, Ruihan Li <em>et al.</em></em></p>
|
||
<p><strong>TL;DR</strong> — A production-grade OS kernel written in Rust that exposes a full Linux ABI while confining unsafe code to a small, formally-audited framekernel core.</p>
|
||
<p><strong>Why notable</strong> — ASTERINAS demonstrates that Linux compatibility and memory-safety guarantees are not mutually exclusive — unsafe Rust is isolated to under 5 kloc of framework code, giving systems operators a credible path toward a safer Linux-compatible kernel without sacrificing application portability.</p></description></item><item><title>MobiSys 2025 Digest</title><link>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/mobisys-2025/</link><pubDate>Mon, 23 Jun 2025 00:00:00 +0000</pubDate><guid>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/mobisys-2025/</guid><description><p>12 papers selected.</p>
|
||
<hr>
|
||
<h3 id="hopter-a-safe-robust-and-responsive-embedded-operating-system">Hopter: a Safe, Robust, and Responsive Embedded Operating System</h3>
|
||
<p><em>Zhiyao Ma, Guojun Chen, Zhuo Chen 0011, Lin Zhong 0001</em></p>
|
||
<p><strong>TL;DR</strong> — Hopter is a new embedded OS that enforces memory safety and real-time responsiveness through a Rust-based task model with cooperative and preemptive scheduling co-designed from the ground up.</p>
|
||
<p><strong>Why notable</strong> — Building a ground-up safe embedded OS is a long-standing challenge; Hopter addresses it without sacrificing the determinism that IoT and robotics workloads demand, offering a credible alternative to unsafe C-based RTOSes.</p></description></item><item><title>IPDPS 2025 Digest</title><link>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/ipdps-2025/</link><pubDate>Mon, 19 May 2025 00:00:00 +0000</pubDate><guid>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/ipdps-2025/</guid><description><p>12 papers selected.</p>
|
||
<hr>
|
||
<h3 id="enhancing-ompss-2-suspendable-tasks-by-combining-operating-system-and-user-level-threads-with-c-coroutines">Enhancing OmpSs-2 Suspendable Tasks by Combining Operating System and User-Level Threads with C++ Coroutines</h3>
|
||
<p><em>Arnau Cinca, Aleix Roca, Kevin Sala, Raúl Peñacoba Veigas <em>et al.</em></em></p>
|
||
<p><strong>TL;DR</strong> — Extends the OmpSs-2 task-based runtime with C++ coroutines to implement suspendable tasks that can yield while blocked on I/O or communication without stalling the OS thread.</p>
|
||
<p><strong>Why notable</strong> — Suspendable tasks are a key missing primitive for overlapping computation and communication in task-graph runtimes; the hybrid OS/user-level thread design avoids the overhead of full context switches while remaining portable, with broad implications for OpenMP-style programming on modern heterogeneous nodes.</p></description></item><item><title>NSDI 2025 Digest</title><link>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/nsdi-2025/</link><pubDate>Mon, 28 Apr 2025 00:00:00 +0000</pubDate><guid>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/nsdi-2025/</guid><description><p>13 papers selected.</p>
|
||
<hr>
|
||
<h3 id="pred-performance-oriented-random-early-detection-for-consistently-stable-performance-in-datacenters">PRED: Performance-oriented Random Early Detection for Consistently Stable Performance in Datacenters</h3>
|
||
<p><em>Xinle Du, Tong Li 0014, Guangmeng Zhou, Zhuotao Liu <em>et al.</em></em></p>
|
||
<p><strong>TL;DR</strong> — PRED redesigns AQM by making drop probability a direct function of per-flow performance targets rather than queue length, eliminating the instability of classic RED in modern datacenter workloads.</p>
|
||
<p><strong>Why notable</strong> — RED has been a cornerstone of congestion control for decades; PRED&rsquo;s performance-centric reformulation challenges a long-held design axiom and demonstrates significantly lower tail latency at scale. It opens the door to intent-driven AQM as a first-class primitive in datacenter switches.</p></description></item><item><title>EuroSys 2025 Digest</title><link>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/eurosys-2025/</link><pubDate>Sun, 30 Mar 2025 00:00:00 +0000</pubDate><guid>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/eurosys-2025/</guid><description><p>13 papers selected.</p>
|
||
<hr>
|
||
<h3 id="empowering-webassembly-with-thin-kernel-interfaces">Empowering WebAssembly with Thin Kernel Interfaces</h3>
|
||
<p><em>Arjun Ramesh, Tianshu Huang, Ben L. Titzer, Anthony Rowe 0001</em></p>
|
||
<p><strong>TL;DR</strong> — A new OS interface design exposes thin, capability-based kernel primitives directly to WebAssembly modules, eliminating the POSIX translation layer.</p>
|
||
<p><strong>Why notable</strong> — WebAssembly is increasingly used beyond the browser as a portable, sandboxed compute substrate; this work shows that rethinking the system interface from scratch yields significantly lower overhead and better safety properties than layering Wasm on top of POSIX.</p></description></item><item><title>FGCS 2025 Digest</title><link>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/fgcs-2025/</link><pubDate>Wed, 01 Jan 2025 00:00:00 +0000</pubDate><guid>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/fgcs-2025/</guid><description><p>12 papers selected.</p>
|
||
<hr>
|
||
<h3 id="multifacets-of-lossy-compression-for-scientific-data-in-the-joint-laboratory-of-extreme-scale-computing">Multifacets of lossy compression for scientific data in the Joint-Laboratory of Extreme Scale Computing</h3>
|
||
<p><em>Franck Cappello, Mario C. Acosta, Emmanuel Agullo, Hartwig Anzt <em>et al.</em></em></p>
|
||
<p><strong>TL;DR</strong> — A joint JLESC survey covering error-bounded lossy compressors (SZ, ZFP, MGARD) across simulation, AI, and in-situ analytics use cases, with benchmarks on real scientific datasets at extreme scale.</p>
|
||
<p><strong>Why notable</strong> — The most comprehensive cross-site evaluation of scientific data compression to date, providing actionable guidance on compressor selection for different numerical kernels and accuracy requirements.</p></description></item><item><title>IC 2025 Digest</title><link>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/ic-2025/</link><pubDate>Wed, 01 Jan 2025 00:00:00 +0000</pubDate><guid>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/ic-2025/</guid><description><p>10 papers selected.</p>
|
||
<hr>
|
||
<h3 id="rethinking-computing-systems-in-the-era-of-climate-crisis-a-call-for-a-sustainable-computing-continuum">Rethinking Computing Systems in the Era of Climate Crisis: A Call for a Sustainable Computing Continuum</h3>
|
||
<p><em>Ella Peltonen, Suzan Bayhan, David Bermbach, Sebastian Buschjäger <em>et al.</em></em></p>
|
||
<p><strong>TL;DR</strong> — A multi-author position paper calling for carbon-aware design principles across the cloud-to-edge computing continuum, surveying energy measurement, workload scheduling, and hardware lifecycle challenges.</p>
|
||
<p><strong>Why notable</strong> — Establishes a community research agenda for sustainable computing infrastructure at a time when datacenter and edge energy consumption is under increasing regulatory and societal scrutiny.</p></description></item><item><title>JPDC 2025 Digest</title><link>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/jpdc-2025/</link><pubDate>Wed, 01 Jan 2025 00:00:00 +0000</pubDate><guid>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/jpdc-2025/</guid><description><p>12 papers selected.</p>
|
||
<hr>
|
||
<h3 id="throughput-of-byzantine-broadcast">Throughput of Byzantine Broadcast</h3>
|
||
<p><em>Ruomu Hou, Haifeng Yu, Prateek Saxena</em></p>
|
||
<p><strong>TL;DR</strong> — Establishes tight throughput bounds for Byzantine broadcast protocols and constructs algorithms that saturate those bounds, separating throughput from latency in the fault-tolerant broadcast landscape.</p>
|
||
<p><strong>Why notable</strong> — Provides the first rigorous throughput characterization of Byzantine broadcast, a fundamental primitive whose capacity limits were previously unquantified.</p>
|
||
<hr>
|
||
<h3 id="how-to-reduce-the-number-of-steps-for-multi-valued-validated-byzantine-agreement">How to reduce the number of steps for (multi-valued validated) Byzantine agreement?</h3>
|
||
<p><em>Baohan Huang, Haibin Zhang, Chao Liu 0039, Shengli Liu 0001 <em>et al.</em></em></p></description></item><item><title>Middleware 2025 Digest</title><link>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/middleware-2025/</link><pubDate>Wed, 01 Jan 2025 00:00:00 +0000</pubDate><guid>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/middleware-2025/</guid><description><p>12 papers selected.</p>
|
||
<hr>
|
||
<h3 id="recipe-hardware-accelerated-replication-protocols-rethinking-crash-fault-tolerance-protocols-for-untrusted-cloud-environments">Recipe: Hardware-Accelerated Replication Protocols: Rethinking Crash Fault Tolerance Protocols for Untrusted Cloud Environments</h3>
|
||
<p><em>Dimitra Giantsidi, Emmanouil Giortamis, Julian Pritzi, Maurice Bailleu <em>et al.</em></em></p>
|
||
<p><strong>TL;DR</strong> — Redesigns crash fault-tolerance protocols using hardware acceleration (TEEs/SmartNICs) to deliver replication with strong guarantees in untrusted cloud environments.</p>
|
||
<hr>
|
||
<h3 id="efficient-performance-guarantees-for-function-as-a-service-with-cloud-allocators">Efficient Performance Guarantees for Function-as-a-Service with Cloud Allocators</h3>
|
||
<p><em>Hai Duc Nguyen 0005, Andrew A. Chien</em></p>
|
||
<p><strong>TL;DR</strong> — Introduces cloud-allocator abstractions that provide formal performance guarantees for serverless functions, addressing the unpredictability of shared FaaS infrastructure.</p></description></item><item><title>OSDI 2025 Digest</title><link>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/osdi-2025/</link><pubDate>Wed, 01 Jan 2025 00:00:00 +0000</pubDate><guid>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/osdi-2025/</guid><description><p>13 papers selected.</p>
|
||
<hr>
|
||
<h3 id="basilisk-using-provenance-invariants-to-automate-proofs-of-undecidable-protocols">Basilisk: Using Provenance Invariants to Automate Proofs of Undecidable Protocols</h3>
|
||
<p><em>Tony Nuda Zhang, Keshav Singh, Tej Chajed, Manos Kapritsos <em>et al.</em></em></p>
|
||
<p><strong>TL;DR</strong> — Automates the construction of correctness proofs for distributed protocols that were previously considered undecidable, advancing the state of the art in verified systems.</p>
|
||
<hr>
|
||
<h3 id="mako-speculative-distributed-transactions-with-geo-replication">Mako: Speculative Distributed Transactions with Geo-Replication</h3>
|
||
<p><em>Weihai Shen, Yang Cui, Siddhartha Sen 0001, Sebastian Angel <em>et al.</em></em></p>
|
||
<p><strong>TL;DR</strong> — Combines speculative execution with geo-replication to deliver low-latency distributed transactions without sacrificing consistency, addressing a fundamental tension in wide-area systems.</p></description></item><item><title>SC 2025 Digest</title><link>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/sc-2025/</link><pubDate>Wed, 01 Jan 2025 00:00:00 +0000</pubDate><guid>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/sc-2025/</guid><description><p>15 papers selected.</p>
|
||
<hr>
|
||
<h3 id="cosmological-hydrodynamics-at-exascale-a-trillion-particle-leap-in-capability">Cosmological Hydrodynamics at Exascale: A Trillion-Particle Leap in Capability</h3>
|
||
<p><em>Nicholas Frontiere, J. D. Emberson, Michael Buehlmann, Esteban M. Rangel <em>et al.</em></em></p>
|
||
<p><strong>TL;DR</strong> — Delivers the first trillion-particle cosmological hydrodynamics simulation on exascale hardware, demonstrating sustained petaflop-scale performance on a flagship scientific application.</p>
|
||
<hr>
|
||
<h3 id="ab-initio-quantum-transport-with-the-gw-approximation-42-240-atoms-and-sustained-exascale-performance">Ab-initio Quantum Transport with the GW Approximation, 42, 240 Atoms, and Sustained Exascale Performance</h3>
|
||
<p><em>Nicolas Vetsch, Alexander Maeder, Vincent Maillou, Anders Winka <em>et al.</em></em></p>
|
||
<p><strong>TL;DR</strong> — Achieves sustained exascale performance for first-principles quantum transport at 42,240 atoms, establishing a new scale record for the GW many-body perturbation method.</p></description></item><item><title>SEC 2025 Digest</title><link>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/sec-2025/</link><pubDate>Wed, 01 Jan 2025 00:00:00 +0000</pubDate><guid>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/sec-2025/</guid><description><p>12 papers selected.</p>
|
||
<hr>
|
||
<h3 id="lm-meter-unveiling-runtime-inference-latency-for-on-device-language-models">lm-Meter: Unveiling Runtime Inference Latency for On-Device Language Models</h3>
|
||
<p><em>Haoxin Wang 0003</em></p>
|
||
<p><strong>TL;DR</strong> — Provides the first detailed runtime profiling framework for on-device LLM inference, revealing key latency bottlenecks across diverse edge hardware configurations.</p>
|
||
<hr>
|
||
<h3 id="sled-a-speculative-llm-decoding-framework-for-efficient-edge-serving">SLED: A Speculative LLM Decoding Framework for Efficient Edge Serving</h3>
|
||
<p><em>Xiangchen Li</em></p>
|
||
<p><strong>TL;DR</strong> — Adapts speculative decoding to edge serving constraints, reducing LLM token generation latency while respecting the tight memory and compute budgets of edge nodes.</p></description></item><item><title>SoCC 2025 Digest</title><link>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/socc-2025/</link><pubDate>Wed, 01 Jan 2025 00:00:00 +0000</pubDate><guid>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/socc-2025/</guid><description><p>13 papers selected.</p>
|
||
<hr>
|
||
<h3 id="from-bottleneck-to-breakthrough-optimizing-scheduling-for-hyperscale-containerized-clusters">From Bottleneck to Breakthrough: Optimizing Scheduling for Hyperscale Containerized Clusters</h3>
|
||
<p><em>Bing Li, Yuquan Ren, Xinyi Song, Zhilei Liu <em>et al.</em></em></p>
|
||
<p><strong>TL;DR</strong> — Documents production-scale scheduling improvements at a hyperscale cloud provider, demonstrating how targeted optimizations reduce scheduling tail latency and increase cluster utilization in real containerized workloads.</p>
|
||
<hr>
|
||
<h3 id="cpu-limits-kill-performance-time-to-rethink-resource-control">CPU-Limits kill Performance: Time to rethink Resource Control</h3>
|
||
<p><em>Chirag C. Shetty, Sarthak Chakraborty, Hubertus Franke, Larisa Shwartz <em>et al.</em></em></p>
|
||
<p><strong>TL;DR</strong> — Challenges the conventional use of CPU cgroup limits in cloud environments, showing through production evidence that CFS bandwidth throttling degrades application QoS and proposing a rethink of resource control abstractions.</p></description></item><item><title>SOSP 2025 Digest</title><link>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/sosp-2025/</link><pubDate>Wed, 01 Jan 2025 00:00:00 +0000</pubDate><guid>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/sosp-2025/</guid><description><p>14 papers selected.</p>
|
||
<hr>
|
||
<h3 id="lithos-an-operating-system-for-efficient-machine-learning-on-gpus">LithOS: An Operating System for Efficient Machine Learning on GPUs</h3>
|
||
<p><em>Patrick H. Coppock, Brian Zhang, Eliot H. Solomon, Vasilis Kypriotis <em>et al.</em></em></p>
|
||
<p><strong>TL;DR</strong> — Designs a dedicated OS for GPU ML workloads, rethinking scheduling and resource management at the kernel level for accelerator-centric computing.</p>
|
||
<hr>
|
||
<h3 id="cheriot-rtos-an-os-for-fine-grained-memory-safe-compartments-on-low-cost-embedded-devices">CHERIoT RTOS: An OS for Fine-Grained Memory-Safe Compartments on Low-Cost Embedded Devices</h3>
|
||
<p><em>Saar Amar, Tony Chen, David Chisnall, Nathaniel Wesley Filardo <em>et al.</em></em></p></description></item><item><title>TC 2025 Digest</title><link>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/tc-2025/</link><pubDate>Wed, 01 Jan 2025 00:00:00 +0000</pubDate><guid>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/tc-2025/</guid><description><p>12 papers selected.</p>
|
||
<hr>
|
||
<h3 id="rv-cure-a-risc-v-capability-architecture-for-full-memory-safety">RV-CURE: A RISC-V Capability Architecture for Full Memory Safety</h3>
|
||
<p><em>Yonghae Kim, Anurag Kar, Jaewon Lee, Jaekyu Lee <em>et al.</em></em></p>
|
||
<p><strong>TL;DR</strong> — Extends the RISC-V ISA with hardware capabilities to enforce full memory safety—including bounds checking and pointer provenance—across the entire software stack.</p>
|
||
<p><strong>Why notable</strong> — Demonstrates that capability-based memory safety can be integrated into an open ISA at low cost, with implications for deploying safe-by-default embedded and server systems.</p></description></item><item><title>TCC 2025 Digest</title><link>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/tcc-2025/</link><pubDate>Wed, 01 Jan 2025 00:00:00 +0000</pubDate><guid>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/tcc-2025/</guid><description><p>12 papers selected.</p>
|
||
<hr>
|
||
<h3 id="drkc-deep-reinforcement-learning-enhanced-microservice-scheduling-on-kubernetes-clusters-in-cloud-edge-environment">DRKC: Deep Reinforcement Learning Enhanced Microservice Scheduling on Kubernetes Clusters in Cloud-Edge Environment</h3>
|
||
<p><em>Jian Jiang, Qianmu Li, Pengchuan Wang, Yunhuai Liu</em></p>
|
||
<p><strong>TL;DR</strong> — DRKC uses deep reinforcement learning to schedule microservices across Kubernetes clusters spanning cloud and edge nodes, optimizing latency and resource utilization.</p>
|
||
<p><strong>Why notable</strong> — One of the few papers to tackle DRL-based microservice placement at the Kubernetes level in a real cloud-edge topology, making it directly actionable for practitioners.</p></description></item><item><title>TOCS 2025 Digest</title><link>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/tocs-2025/</link><pubDate>Wed, 01 Jan 2025 00:00:00 +0000</pubDate><guid>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/tocs-2025/</guid><description><p>10 papers selected.</p>
|
||
<hr>
|
||
<h3 id="whole-system-persistence-made-efficient-with-tree-structured-checkpointing-on-microkernel">Whole-system Persistence Made Efficient with Tree-structured Checkpointing on Microkernel</h3>
|
||
<p><em>Mingkai Dong, Fangnuo Wu, Gequan Mo, Haibo Chen</em></p>
|
||
<p><strong>TL;DR</strong> — A microkernel-based whole-system persistence scheme uses tree-structured incremental checkpointing to achieve low-overhead, crash-consistent snapshots of the entire OS state.</p>
|
||
<p><strong>Why notable</strong> — Whole-system persistence is a foundational building block for reliable systems; this paper shows it can be done efficiently within a microkernel architecture.</p>
|
||
<hr>
|
||
<h3 id="xputee-a-high-performance-and-practical-heterogeneous-trusted-execution-environment-for-gpus">XpuTEE: A High-Performance and Practical Heterogeneous Trusted Execution Environment for GPUs</h3>
|
||
<p><em>Shulin Fan, Zhichao Hua, Yubin Xia, Haibo Chen</em></p></description></item><item><title>TPDS 2025 Digest</title><link>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/tpds-2025/</link><pubDate>Wed, 01 Jan 2025 00:00:00 +0000</pubDate><guid>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/tpds-2025/</guid><description><p>12 papers selected.</p>
|
||
<hr>
|
||
<h3 id="harmonic-uncertainty-aware-multi-objective-optimization-for-energy-efficient-hpc-resource-management">HARMONIC: Uncertainty-Aware Multi-Objective Optimization for Energy-Efficient HPC Resource Management</h3>
|
||
<p><em>Kyrian Adimora, Hongyang Sun 0001</em></p>
|
||
<p><strong>TL;DR</strong> — HARMONIC applies uncertainty-aware multi-objective optimization to jointly minimize energy consumption and maximize performance for HPC resource allocation.</p>
|
||
<p><strong>Why notable</strong> — It directly addresses the growing demand for energy-proportional HPC scheduling with principled probabilistic models, making it relevant to both system designers and green-computing researchers.</p>
|
||
<hr>
|
||
<h3 id="mist-towards-mpi-instant-startup-and-termination-on-tianhe-hpc-systems">MIST: Towards MPI Instant Startup and Termination on Tianhe HPC Systems</h3>
|
||
<p><em>Yiqin Dai, Ruibo Wang, Yong Dong, Min Xie <em>et al.</em></em></p></description></item><item><title>Middleware 2024 Digest</title><link>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/middleware-2024/</link><pubDate>Mon, 02 Dec 2024 00:00:00 +0000</pubDate><guid>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/middleware-2024/</guid><description><p>11 papers selected.</p>
|
||
<hr>
|
||
<h3 id="chasing-lightspeed-consensus-fast-wide-area-byzantine-replication-with-mercury">Chasing Lightspeed Consensus: Fast Wide-Area Byzantine Replication with Mercury</h3>
|
||
<p><em>Christian Berger 0006, Lívio Rodrigues, Hans P. Reiser, Vinicius Vielmo Cogo <em>et al.</em></em></p>
|
||
<p><strong>TL;DR</strong> — Mercury is a wide-area Byzantine fault-tolerant replication protocol that minimises latency by exploiting geographic locality and pipelining to approach the theoretical lightspeed bound.</p>
|
||
<p><strong>Why notable</strong> — Achieving near-lightspeed latency in Byzantine replication across wide-area networks has been a long-standing open challenge; Mercury&rsquo;s design demonstrates it is practically attainable. The result raises the bar for what production BFT middleware can deliver in geo-distributed deployments.</p></description></item><item><title>SOSP 2024 Digest</title><link>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/sosp-2024/</link><pubDate>Tue, 05 Nov 2024 00:00:00 +0000</pubDate><guid>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/sosp-2024/</guid><description><p>13 papers selected.</p>
|
||
<hr>
|
||
<h3 id="verus-a-practical-foundation-for-systems-verification">Verus: A Practical Foundation for Systems Verification</h3>
|
||
<p><em>Andrea Lattuada 0001, Travis Hance, Jay Bosamiya, Matthias Brun 0002 <em>et al.</em></em></p>
|
||
<p><strong>TL;DR</strong> — Verus is a Rust-based verification framework that makes formal proofs of low-level systems code tractable at scale, covering memory safety, functional correctness, and concurrency.</p>
|
||
<p><strong>Why notable</strong> — Formal verification of real systems code has long been impractical; Verus closes the usability gap by integrating SMT-based proofs directly into a systems programming language, making it the most broadly applicable verification tool for the OS community to date.</p></description></item><item><title>SoCC 2024 Digest</title><link>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/socc-2024/</link><pubDate>Fri, 01 Nov 2024 00:00:00 +0000</pubDate><guid>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/socc-2024/</guid><description><p>12 papers selected.</p>
|
||
<hr>
|
||
<h3 id="queue-management-for-slo-oriented-large-language-model-serving">Queue Management for SLO-Oriented Large Language Model Serving</h3>
|
||
<p><em>Archit Patke, Dhemath Reddy, Saurabh Jha, Haoran Qiu <em>et al.</em></em></p>
|
||
<p><strong>TL;DR</strong> — A queue management framework that enforces latency SLOs for LLM serving by dynamically routing and prioritizing requests across heterogeneous inference capacity.</p>
|
||
<p><strong>Why notable</strong> — As LLM deployments move into production clouds, meeting strict time-to-first-token and total latency SLOs becomes critical; this work directly addresses that gap with a practical, deployable solution. It is one of the first papers to treat LLM serving as a cloud SLO-management problem rather than a pure model-optimization problem.</p></description></item><item><title>OSDI 2024 Digest</title><link>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/osdi-2024/</link><pubDate>Wed, 10 Jul 2024 00:00:00 +0000</pubDate><guid>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/osdi-2024/</guid><description><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</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></description></item><item><title>CCGrid 2024 Digest</title><link>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/ccgrid-2024/</link><pubDate>Mon, 06 May 2024 00:00:00 +0000</pubDate><guid>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/ccgrid-2024/</guid><description><p>10 papers selected.</p>
|
||
<hr>
|
||
<h3 id="fair-efficient-multi-resource-scheduling-for-stateless-serverless-functions-with-anubis">Fair, Efficient Multi-Resource Scheduling for Stateless Serverless Functions with Anubis</h3>
|
||
<p><em>Amit Samanta 0001, Ryan Stutsman</em></p>
|
||
<p><strong>TL;DR</strong> — Anubis introduces a fair, multi-resource scheduler for stateless serverless functions that achieves efficiency without sacrificing isolation between tenants.</p>
|
||
<p><strong>Why notable</strong> — Fairness in serverless resource allocation is an open problem as functions compete for heterogeneous resources (CPU, memory, I/O); Anubis provides a concrete, deployable answer. The work directly addresses a gap in production FaaS platforms where existing schedulers optimize for throughput but ignore per-tenant equity.</p></description></item><item><title>ATC 2024 Digest</title><link>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/atc-2024/</link><pubDate>Mon, 01 Jan 2024 00:00:00 +0000</pubDate><guid>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/atc-2024/</guid><description><p>12 papers selected.</p>
|
||
<hr>
|
||
<h3 id="fetchbpf-customizable-prefetching-policies-in-linux-with-ebpf">FetchBPF: Customizable Prefetching Policies in Linux with eBPF</h3>
|
||
<p><em>Xuechun Cao, Shaurya Patel, Soo-Yee Lim, Xueyuan Han <em>et al.</em></em></p>
|
||
<p><strong>TL;DR</strong> — Extends eBPF into the page-fault / prefetch path, giving user-space programs a safe, low-overhead hook to install custom hardware-prefetch policies without kernel modifications.</p>
|
||
<hr>
|
||
<h3 id="fast-trapless-kernel-probes-everywhere">Fast (Trapless) Kernel Probes Everywhere</h3>
|
||
<p><em>Jinghao Jia, Michael V. Le, Salman Ahmed 0001, Dan Williams 0001 <em>et al.</em></em></p>
|
||
<p><strong>TL;DR</strong> — Eliminates the trap-based overhead of kprobes by using binary rewriting to instrument kernel functions at near-zero cost, enabling always-on production tracing.</p></description></item><item><title>EuroSys 2024 Digest</title><link>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/eurosys-2024/</link><pubDate>Mon, 01 Jan 2024 00:00:00 +0000</pubDate><guid>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/eurosys-2024/</guid><description><p>13 papers selected.</p>
|
||
<hr>
|
||
<h3 id="pronghorn-effective-checkpoint-orchestration-for-serverless-hot-starts">Pronghorn: Effective Checkpoint Orchestration for Serverless Hot-Starts</h3>
|
||
<p><em>Sumer Kohli, Shreyas Kharbanda, Rodrigo Bruno, João Carreira <em>et al.</em></em></p>
|
||
<p><strong>TL;DR</strong> — Demonstrates how carefully orchestrated checkpointing can eliminate cold-start latency in serverless runtimes, achieving near-instant hot-starts with negligible overhead.</p>
|
||
<hr>
|
||
<h3 id="serializationdeserialization-free-state-transfer-in-serverless-workflows">Serialization/Deserialization-free State Transfer in Serverless Workflows</h3>
|
||
<p><em>Fangming Lu, Xingda Wei, Zhuobin Huang, Rong Chen 0001 <em>et al.</em></em></p>
|
||
<p><strong>TL;DR</strong> — Eliminates the dominant serialization cost in serverless function chaining by enabling direct in-memory state passing, yielding large end-to-end latency reductions.</p></description></item><item><title>FGCS 2024 Digest</title><link>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/fgcs-2024/</link><pubDate>Mon, 01 Jan 2024 00:00:00 +0000</pubDate><guid>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/fgcs-2024/</guid><description><p>12 papers selected.</p>
|
||
<hr>
|
||
<h3 id="quantum-centric-supercomputing-for-materials-science-a-perspective-on-challenges-and-future-directions">Quantum-centric supercomputing for materials science: A perspective on challenges and future directions</h3>
|
||
<p><em>Yuri Alexeev, Maximilian Amsler, Marco Antonio Barroca, Sanzio Bassini <em>et al.</em></em></p>
|
||
<p><strong>TL;DR</strong> — A comprehensive roadmap from IBM, national labs, and universities identifying key algorithmic, software, and hardware challenges for using quantum processors alongside classical HPC to advance materials science simulations.</p>
|
||
<p><strong>Why notable</strong> — Essential reading for any researcher planning quantum-classical hybrid workflows, covering the full stack from error mitigation to application mapping at scale.</p></description></item><item><title>HPDC 2024 Digest</title><link>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/hpdc-2024/</link><pubDate>Mon, 01 Jan 2024 00:00:00 +0000</pubDate><guid>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/hpdc-2024/</guid><description><p>12 papers selected.</p>
|
||
<hr>
|
||
<h3 id="efficient-all-to-all-collective-communication-schedules-for-direct-connect-topologies">Efficient all-to-all Collective Communication Schedules for Direct-connect Topologies</h3>
|
||
<p><em>Prithwish Basu, Liangyu Zhao, Jason Fantl, Siddharth Pal <em>et al.</em></em></p>
|
||
<p><strong>TL;DR</strong> — Derives near-optimal all-to-all collective communication schedules for direct-connect HPC topologies, directly improving bandwidth utilization in large-scale distributed systems.</p>
|
||
<hr>
|
||
<h3 id="reinforcement-learning-based-adaptive-mitigation-of-uncorrected-dram-errors-in-the-field">Reinforcement Learning-based Adaptive Mitigation of Uncorrected DRAM Errors in the Field</h3>
|
||
<p><em>Isaac Boixaderas, Sergi Moré, Javier Bartolome, David Vicente <em>et al.</em></em></p>
|
||
<p><strong>TL;DR</strong> — Applies reinforcement learning to dynamically mitigate uncorrected DRAM errors at production HPC scale, improving system reliability without sacrificing performance.</p></description></item><item><title>IC 2024 Digest</title><link>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/ic-2024/</link><pubDate>Mon, 01 Jan 2024 00:00:00 +0000</pubDate><guid>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/ic-2024/</guid><description><p>10 papers selected.</p>
|
||
<hr>
|
||
<h3 id="revisiting-edge-ai-opportunities-and-challenges">Revisiting Edge AI: Opportunities and Challenges</h3>
|
||
<p><em>Tobias Meuser, Lauri Lovén, Monowar Bhuyan, Shishir G. Patil <em>et al.</em></em></p>
|
||
<p><strong>TL;DR</strong> — A multi-author position paper that revisits the state of edge AI, cataloguing deployment barriers and open research problems across hardware, networking, and software layers.</p>
|
||
<p><strong>Why notable</strong> — Brings together 19 leading researchers to synthesize the field&rsquo;s most pressing edge AI challenges, making it an authoritative reference for practitioners and researchers planning edge deployments.</p></description></item><item><title>IPDPS 2024 Digest</title><link>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/ipdps-2024/</link><pubDate>Mon, 01 Jan 2024 00:00:00 +0000</pubDate><guid>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/ipdps-2024/</guid><description><p>14 papers selected.</p>
|
||
<hr>
|
||
<h3 id="low-depth-spatial-tree-algorithms">Low-Depth Spatial Tree Algorithms</h3>
|
||
<p><em>Yves Baumann, Tal Ben-Nun, Maciej Besta, Lukas Gianinazzi <em>et al.</em></em></p>
|
||
<p><strong>TL;DR</strong> — Introduces parallel spatial-tree algorithms with provably low depth, advancing the theory of work-efficient parallel data structures for geometric workloads.</p>
|
||
<hr>
|
||
<h3 id="alternative-basis-matrix-multiplication-is-fast-and-stable">Alternative Basis Matrix Multiplication is Fast and Stable</h3>
|
||
<p><em>Oded Schwartz, Sivan Toledo, Noa Vaknin, Gal Wiernik</em></p>
|
||
<p><strong>TL;DR</strong> — Demonstrates that alternative-basis matrix multiplication achieves both practical speed and numerical stability, challenging the conventional trade-off between the two.</p></description></item><item><title>JPDC 2024 Digest</title><link>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/jpdc-2024/</link><pubDate>Mon, 01 Jan 2024 00:00:00 +0000</pubDate><guid>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/jpdc-2024/</guid><description><p>12 papers selected.</p>
|
||
<hr>
|
||
<h3 id="readwrite-fence-free-work-stealing-with-multiplicity">Read/write fence-free work-stealing with multiplicity</h3>
|
||
<p><em>Armando Castañeda, Miguel Piña</em></p>
|
||
<p><strong>TL;DR</strong> — Presents a work-stealing deque algorithm that eliminates read/write memory fences while tolerating multiplicity, achieving provably correct concurrent access without costly barriers.</p>
|
||
<p><strong>Why notable</strong> — Advances the theoretical foundations of lock-free scheduler data structures by decoupling correctness from fence instructions, directly impacting runtime system design.</p>
|
||
<hr>
|
||
<h3 id="reliable-communication-in-dynamic-networks-with-locally-bounded-byzantine-faults">Reliable communication in dynamic networks with locally bounded byzantine faults</h3>
|
||
<p><em>Silvia Bonomi, Giovanni Farina, Sébastien Tixeuil</em></p></description></item><item><title>MobiSys 2024 Digest</title><link>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/mobisys-2024/</link><pubDate>Mon, 01 Jan 2024 00:00:00 +0000</pubDate><guid>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/mobisys-2024/</guid><description><p>13 papers selected.</p>
|
||
<hr>
|
||
<h3 id="wais-leveraging-wifi-for-resource-efficient-slam">WAIS: Leveraging WiFi for Resource-Efficient SLAM</h3>
|
||
<p><em>Aditya Arun 0002, William Hunter, Roshan Sai Ayyalasomayajula, Dinesh Bharadia</em></p>
|
||
<p><strong>TL;DR</strong> — Demonstrates that commodity WiFi signals can replace LiDAR for simultaneous localization and mapping, dramatically cutting the resource cost of robot/AR navigation.</p>
|
||
<hr>
|
||
<h3 id="uwb-fi-pushing-wi-fi-towards-ultra-wideband-for-fine-granularity-sensing">UWB-Fi: Pushing Wi-Fi towards Ultra-wideband for Fine-Granularity Sensing</h3>
|
||
<p><em>Xin Li 0070, Hongbo Wang, Zhe Chen 0015, Zhiping Jiang <em>et al.</em></em></p>
|
||
<p><strong>TL;DR</strong> — Extends standard Wi-Fi to UWB-class sensing resolution without hardware changes, enabling centimeter-level gesture and motion detection on existing infrastructure.</p></description></item><item><title>NSDI 2024 Digest</title><link>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/nsdi-2024/</link><pubDate>Mon, 01 Jan 2024 00:00:00 +0000</pubDate><guid>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/nsdi-2024/</guid><description><p>13 papers selected.</p>
|
||
<hr>
|
||
<h3 id="megascale-scaling-large-language-model-training-to-more-than-10-000-gpus">MegaScale: Scaling Large Language Model Training to More Than 10, 000 GPUs</h3>
|
||
<p><em>Ziheng Jiang, Haibin Lin, Yinmin Zhong, Qi Huang <em>et al.</em></em></p>
|
||
<p><strong>TL;DR</strong> — ByteDance&rsquo;s full production account of training LLMs at 10,000+ GPUs, with novel co-design of the network stack, fault tolerance, and collective communication to sustain near-linear scaling.</p>
|
||
<hr>
|
||
<h3 id="harmony-a-congestion-free-datacenter-architecture">Harmony: A Congestion-free Datacenter Architecture</h3>
|
||
<p><em>Saksham Agarwal, Qizhe Cai, Rachit Agarwal 0001, David B. Shmoys <em>et al.</em></em></p></description></item><item><title>SC 2024 Digest</title><link>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/sc-2024/</link><pubDate>Mon, 01 Jan 2024 00:00:00 +0000</pubDate><guid>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/sc-2024/</guid><description><p>15 papers selected.</p>
|
||
<hr>
|
||
<h3 id="pushing-the-limit-of-quantum-mechanical-simulation-to-the-raman-spectra-of-a-biological-system-with-100-million-atoms">Pushing the Limit of Quantum Mechanical Simulation to the Raman Spectra of a Biological System with 100 Million Atoms</h3>
|
||
<p><em>Honghui Shang, Ying Liu 0055, Zhikun Wu, Zhenchuan Chen <em>et al.</em></em></p>
|
||
<p><strong>TL;DR</strong> — Gordon Bell-class result scaling ab initio Raman spectroscopy to 100 million atoms, pushing quantum-chemical simulation well beyond prior limits.</p>
|
||
<hr>
|
||
<h3 id="breaking-the-molecular-dynamics-timescale-barrier-using-a-wafer-scale-system">Breaking the Molecular Dynamics Timescale Barrier Using a Wafer-Scale System</h3>
|
||
<p><em>Kylee Santos, Stan G. Moore, Tomas Oppelstrup, Amirali Sharifian <em>et al.</em></em></p></description></item><item><title>SEC 2024 Digest</title><link>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/sec-2024/</link><pubDate>Mon, 01 Jan 2024 00:00:00 +0000</pubDate><guid>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/sec-2024/</guid><description><p>12 papers selected.</p>
|
||
<hr>
|
||
<h3 id="edgecore-resource-dependency-aware-multi-tenant-orchestration-for-mobile-edge-clouds">EdgeCore: Resource Dependency-Aware Multi-Tenant Orchestration for Mobile Edge Clouds</h3>
|
||
<p><em>Amran Haroon</em></p>
|
||
<p><strong>TL;DR</strong> — Introduces a multi-tenant edge orchestration system that captures resource dependencies across co-located workloads, demonstrating significant improvements in task completion latency and resource utilization.</p>
|
||
<hr>
|
||
<h3 id="righteous-automatic-right-sizing-for-complex-edge-deployments">Righteous: Automatic Right-Sizing for Complex Edge Deployments</h3>
|
||
<p><em>Aniruddha Rakshit</em></p>
|
||
<p><strong>TL;DR</strong> — Presents an automated right-sizing framework for edge deployments that dynamically adjusts resource allocations to match workload demands without manual intervention.</p></description></item><item><title>TC 2024 Digest</title><link>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/tc-2024/</link><pubDate>Mon, 01 Jan 2024 00:00:00 +0000</pubDate><guid>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/tc-2024/</guid><description><p>12 papers selected.</p>
|
||
<hr>
|
||
<h3 id="achieving-dram-like-pcm-by-trading-off-capacity-for-latency">Achieving DRAM-Like PCM by Trading Off Capacity for Latency</h3>
|
||
<p><em>Irina Alam, Puneet Gupta 0001</em></p>
|
||
<p><strong>TL;DR</strong> — Proposes a capacity-for-latency trade-off in Phase Change Memory to match DRAM-level access latency without specialized process changes.</p>
|
||
<p><strong>Why notable</strong> — Offers a practical path to deploying PCM as a DRAM alternative, directly addressing the latency gap that has blocked PCM adoption in main-memory systems.</p>
|
||
<hr>
|
||
<h3 id="a-high-performance-energy-efficient-modular-dma-engine-architecture">A High-Performance, Energy-Efficient Modular DMA Engine Architecture</h3>
|
||
<p><em>Thomas Benz, Michael Rogenmoser, Paul Scheffler, Samuel Riedel <em>et al.</em></em></p></description></item><item><title>TCC 2024 Digest</title><link>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/tcc-2024/</link><pubDate>Mon, 01 Jan 2024 00:00:00 +0000</pubDate><guid>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/tcc-2024/</guid><description><p>12 papers selected.</p>
|
||
<hr>
|
||
<h3 id="faasctrl-a-comprehensive-latency-controller-for-serverless-platforms">FaaSCtrl: A Comprehensive-Latency Controller for Serverless Platforms</h3>
|
||
<p><em>Abhisek Panda, Smruti R. Sarangi</em></p>
|
||
<p><strong>TL;DR</strong> — FaaSCtrl is a feedback-control system for serverless platforms that jointly manages cold-start, queuing, and execution latency to meet end-to-end SLOs.</p>
|
||
<p><strong>Why notable</strong> — One of the few serverless controllers that addresses all three latency components together, providing a principled alternative to ad-hoc autoscaling heuristics.</p>
|
||
<hr>
|
||
<h3 id="fusionize-improving-serverless-application-performance-using-dynamic-task-inlining-and-infrastructure-optimization">FUSIONIZE++: Improving Serverless Application Performance Using Dynamic Task Inlining and Infrastructure Optimization</h3>
|
||
<p><em>Trever Schirmer, Joel Scheuner, Tobias Pfandzelter, David Bermbach</em></p></description></item><item><title>TOCS 2024 Digest</title><link>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/tocs-2024/</link><pubDate>Mon, 01 Jan 2024 00:00:00 +0000</pubDate><guid>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/tocs-2024/</guid><description><p>8 papers selected.</p>
|
||
<hr>
|
||
<h3 id="pmalloc-a-holistic-approach-to-improving-persistent-memory-allocation">PMAlloc: A Holistic Approach to Improving Persistent Memory Allocation</h3>
|
||
<p><em>Zheng Dang, Shuibing He, Xuechen Zhang, Peiyi Hong <em>et al.</em></em></p>
|
||
<p><strong>TL;DR</strong> — PMAlloc redesigns persistent memory allocation end-to-end, co-optimizing the allocator&rsquo;s data structures, concurrency, and crash consistency to dramatically reduce allocation overhead.</p>
|
||
<p><strong>Why notable</strong> — Persistent memory is still poorly understood at the allocator level; this paper offers a rare holistic treatment that will inform future PM software stacks.</p></description></item><item><title>TPDS 2024 Digest</title><link>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/tpds-2024/</link><pubDate>Mon, 01 Jan 2024 00:00:00 +0000</pubDate><guid>https://pub.sqrt.fr/vincent/publish-assistant/cloud-edge/digests/tpds-2024/</guid><description><p>12 papers selected.</p>
|
||
<hr>
|
||
<h3 id="runtime-performance-anomaly-diagnosis-in-production-hpc-systems-using-active-learning">Runtime Performance Anomaly Diagnosis in Production HPC Systems Using Active Learning</h3>
|
||
<p><em>Burak Aksar, Efe Sencan, Benjamin Schwaller, Omar Aaziz <em>et al.</em></em></p>
|
||
<p><strong>TL;DR</strong> — An active-learning framework automatically diagnoses runtime performance anomalies in production HPC systems by querying targeted job profiles to minimize labeling effort.</p>
|
||
<p><strong>Why notable</strong> — It bridges ML-based anomaly detection and operational HPC monitoring, demonstrating scalable root-cause identification on real supercomputer workloads.</p>
|
||
<hr>
|
||
<h3 id="autoddl-automatic-distributed-deep-learning-with-near-optimal-bandwidth-cost">AutoDDL: Automatic Distributed Deep Learning With Near-Optimal Bandwidth Cost</h3>
|
||
<p><em>Jinfan Chen, Shigang Li 0002, Ran Guo, Jinhui Yuan <em>et al.</em></em></p></description></item></channel></rss> |