Search results
-
Achieving 100Gbps Intrusion Prevention on a Single Server
100K+ concurrent connections by deploying IDS/IPSes to search for 10K+ rules concurrently. In this paper ...admin - November 27, 2021 - 2:57 am
-
Do OS abstractions make sense on FPGAs?
execution environment (virtual memory, processes, etc.) on the FPGA. In this paper we ask a different ...admin - November 27, 2021 - 2:57 am
-
Byzantine Ordered Consensus without Byzantine Oligarchy
Lorenzo Alvisi, Cornell University Awarded Best Paper! The specific order of commands agreed upon when ... of SMR correctness, however, has no language to express these concerns. This paper introduces ...admin - November 27, 2021 - 2:57 am
-
Overload Control for µs-scale RPCs with Breakwater
characteristics under overload is difficult, especially for RPCs with short service times. In this paper, we ...admin - November 27, 2021 - 2:57 am
-
PACEMAKER: Avoiding HeART attacks in storage clusters with disk-adaptive redundancy
infrastructure (termed transition overload). This paper analyzes traces for millions of disks from production ...admin - November 27, 2021 - 3:59 am
-
A large scale analysis of hundreds of in-memory cache clusters at Twitter
Juncheng Yang, Carnegie Mellon University; Yao Yue, Twitter; K. V. Rashmi, Carnegie Mellon University Modern web services use in-memory caching extensively to increase throughput and reduce latency. There have been several workload analyses of production ...admin - November 27, 2021 - 3:59 am
-
AIFM: High-Performance, Application-Integrated Far Memory
Zhenyuan Ruan, MIT CSAIL; Malte Schwarzkopf, Brown University; Marcos K. Aguilera, VMware Research; Adam Belay, MIT CSAIL Memory is the most contended and least elastic resource in datacenter servers today. Applications can use only local memory—which may ...admin - November 27, 2021 - 3:59 am
-
Performance-Optimal Read-Only Transactions
Haonan Lu, Princeton University; Siddhartha Sen, Microsoft Research; Wyatt Lloyd, Princeton University Read-only transactions are critical for consistently reading data spread across a distributed storage system but have worse performance than simple, non ...admin - November 27, 2021 - 3:59 am
-
Fast RDMA-based Ordered Key-Value Store using Remote Learned Cache
Xingda Wei, Rong Chen, and Haibo Chen, Shanghai Jiao Tong University RDMA (Remote Direct Memory Access) has gained considerable interests in network-attached in-memory key-value stores. However, traversing the remote tree-based index in ordered stores wit ...admin - November 27, 2021 - 3:59 am
-
A Unified Architecture for Accelerating Distributed DNN Training in Heterogeneous GPU/CPU Clusters
Parameter Server (PS), cannot fully utilize such heterogeneous resources. In this paper, we present a new ...admin - November 27, 2021 - 4:30 am
-
A Simpler and Faster NIC Driver Model for Network Functions
Solal Pirelli and George Candea, EPFL The advent of software network functions calls for stronger correctness guarantees and higher performance at every level of the stack. Current network stacks trade simplicity for performance and flexibility, especiall ...admin - November 27, 2021 - 4:30 am
-
Generalized Sub-Query Fusion for Eliminating Redundant I/O from Big-Data Queries
identify and eliminate the redundant I/O. This paper proposes RESIN an optimizer extension that adds ...admin - November 27, 2021 - 4:30 am
-
From WiscKey to Bourbon: A Learned Index for Log-Structured Merge Trees
Yifan Dai, Yien Xu, Aishwarya Ganesan, and Ramnatthan Alagappan, University of Wisconsin- Madison; Brian Kroth, Microsoft Gray Systems Lab; Andrea Arpaci-Dusseau and Remzi Arpaci-Dusseau, University of Wisconsin- Madison We introduce BOURBON, a log-struct ...admin - November 27, 2021 - 4:30 am
-
Storage Systems are Distributed Systems (So Verify Them That Way!)
Travis Hance, Carnegie Mellon University; Andrea Lattuada, ETH Zurich; Chris Hawblitzel, Microsoft Research; Jon Howell and Rob Johnson, VMware Research; Bryan Parno, Carnegie Mellon University To verify distributed systems, prior work introduced a method ...admin - November 27, 2021 - 4:30 am
-
PANIC: A High-Performance Programmable NIC for Multi-tenant Networks
performance. This paper presents Frenzy, a new programmable NIC. There are two new key components of the Frenzy ...admin - November 27, 2021 - 4:30 am
-
hXDP: Efficient Software Packet Processing on FPGA NICs
Rome Tor Vergata; Roberto Bifulco, NEC Laboratories Europe Awarded Best Paper! FPGA accelerators on the ...admin - November 27, 2021 - 5:30 am
-
Efficiently Mitigating Transient Execution Attacks using the Unmapped Speculation Contract
Meltdown and Spectre. To address this performance penalty, this paper articulates the unmapped speculation ... execution. To demonstrate the value of this contract, the paper presents Ward, a new kernel design that ...admin - November 27, 2021 - 5:30 am
-
Orchard: Differentially Private Analytics at Scale
This paper presents Orchard, a system that can answer queries about sensitive data that is held by ...admin - November 27, 2021 - 5:30 am
-
RISC-V: #AlphanumericShellcoding
Hadrien Barral and Rémi Géraud-Stewart, DIENS, École normale supérieure, CNRS, PSL University, Paris, France; Georges-Axel Jaloyan, DIENS, École normale supérieure, CNRS, PSL University, Paris, France/CEA, DAM, DIF, F-91297 Arpajon, France; David Naccache ...admin - December 1, 2021 - 4:30 am
-
Distributed Password Hash Computation on Commodity Heterogeneous Programmable Platforms
Computing; Katja Pericin, ReversingLabs Ltd. In this paper, we present the Cool Cracker Cluster cCc: ...admin - December 1, 2021 - 4:30 am
-
Automatic Wireless Protocol Reverse Engineering
Johannes Pohl and Andreas Noack, University of Applied Sciences Stralsund Internet of Things manufacturers often implement their own wireless protocols in order to save licensing fees. Deviating from standard, however, sometimes paves the way for critical ...admin - December 1, 2021 - 4:30 am
-
A better zip bomb
David Fifield Awarded Best Paper! We show how to construct a non-recursive zip bomb that achieves ...admin - December 1, 2021 - 5:30 am
-
D-TIME: Distributed Threadless Independent Malware Execution for Runtime Obfuscation
paper, we propose D-TIME, a new distributed threadless independent malware execution framework to evade ...[email protected] - December 1, 2021 - 5:30 am
-
Unicorefuzz: On the Viability of Emulation for Kernelspace Fuzzing
components. In this paper, we explore the use of CPU emulation to fuzz arbitrary parsers in kernelspace with ...admin - December 1, 2021 - 5:30 am
-
PHMon: A Programmable Hardware Monitor and Its Security Use Cases
actions, considerable performance and power overheads, or an invasive design. In this paper, we propose ... = {https://www.usenix.org/conference/usenixsecurity20/presentation/delshadtehrani}, publisher = {USENIX Association}, month = aug} Download Delshadtehrani PDF Delshadtehrani Paper ...[email protected] - November 27, 2021 - 11:30 am