Releases

[in reverse chronological order]

FAJITA [CoNEXT 2024]

• Code is at https://github.com/FAJITA-Packet-Processing-Framework/FAJITA  
• Experiments are at https://github.com/FAJITA-Packet-Processing-Framework/FAJITA-experiments

NetConfEval [CoNEXT 2024]

• Code repository: https://github.com/NetConfEval/NetConfEval
• Datasets on Hugging Face: https://huggingface.co/datasets/NetConfEval/NetConfEval

GPU-centric Networking [EdgeSys 2024]

• The code is on GitHub with GNU GPL v3 license at https://github.com/rdma-from-gpu
• This is also archived on Zenodo with proper DOI:
  https://zenodo.org/records/13332456 – https://doi.org/10.5281/zenodo.13332456

FlowMage [EuroMLSys ’24]

• Link to the paper: https://dl.acm.org/doi/abs/10.1145/3642970.3655836
• Github repository: https://github.com/hamidgh09/FlowMage

Switcharoo [CoNEXT 2023]

• Main repository: https://github.com/orgs/Switcharoo-P4/repositories
• Archived code: https://doi.org/10.5281/zenodo.10184685

Ribosome [NSDI 2023]

• Main repository: https://github.com/orgs/Ribosome-Packet-Processor/repositories

IOTLB Wall [PeerJ CS 2023]

• Archived codes: 

• • https://doi.org/10.5281/zenodo.7278161 
  • https://doi.org/10.5281/zenodo.7278172 
  • https://doi.org/10.5281/zenodo.7278174 
• Archived raw data: https://doi.org/10.5281/zenodo.7727193 
• Main repository: https://github.com/aliireza/iommu-bench
  • This repository contains a general description of the project and some information to redo some experiments from the article.
• Linux kernel patches: 
  • https://github.com/aliireza/linux/tree/page-pool-bulk-5.15 

• • • This branch contains the changes to use 2-MiB hugepage-backed buffers in the Linux kernel for the mlx5 driver.
  • https://github.com/aliireza/linux/tree/luigi-patch-v5.15 
    • This branch contains the changes to artificially drop TCP packets. 

OrderMatters [NSDI ’22]

• Main repository: https://github.com/hamidgh09/Reframer
  • The repository contains information to use Reframer and perform some experiments.
• Synthetic trace file:
  https://zenodo.org/record/5576176/#.Y-uQzHbMKUk
• Source code is merged into Fastclick as an element named SFMaker: https://github.com/tbarbette/fastclick

RedN [NSDI ’22]

•  Project homepage is at: https://www.redn.io/, while the repository is hosted at this link: https://github.com/redn-io/RedN/

NIC Bench [PAM’21]

• Experiment scripts: https://github.com/nic-bench/experiments
• Modified FastClick with benchmarking utilities: https://github.com/nic-bench/fastclick  now reverted into mainline FastClick!
• DPDK with support for lazy deletion hashtables : https://github.com/nic-bench/dpdk

Connection tracking [HPSR ’21]

• Code is at https://github.com/conntrackHPSR21/

PacketMill [ASPLOS’21] 

• Archived artifact: https://doi.org/10.5281/zenodo.4435970 
• Main repository: https://github.com/aliireza/packetmill  This repository contains information to use PacketMill and perform some sample experiments.
• PacketMill source code (modified FastClick): https://github.com/tbarbette/fastclick/tree/packetmill 
• X-Change (modified DPDK): https://github.com/tbarbette/xchange
• Artifact for the ASPLOS paper: https://cknowledge.io/c/lib/40c29d7d6d862734/    

Assise [OSDI ’20]

• The Assise artifact can be accessed at: https://github.com/ut-osa/assise​. This repository contains Assise’s source code and benchmarking scripts.

CrossRSS [CoNEXT 2020 Poster]

• The experiment repository is at https://github.com/tbarbette/crossrss

For our work on DDIO [ATC’20] we have the following releases:

• ddio-bench [ATC’20] (https://github.com/aliireza/ddio-bench​)
  Information/source code to perform the experiments/microbenchmarks done in our DDIO paper.

For our work on Path Persistence in the Cloud [CCR’20] we have the following releases

• Our data is publicly available for reproducibility and further analysis at
  http://goo.gl/25BKte.

Cheetah [NSDI ’20]

• the code is at  https://github.com/cheetahlb/

RSS++ [CoNEXT ’19]

• the code at https://github.com/rsspp with experiments scripts (experiments), RSS++ code itself (fastclick), the modified Linux
• kernel(linux) and the modified iperf that makes use of the new kernel option (iperf).

Slice-aware LLC and CacheDirector [EuroSys ’19] releases:

• ​Slice-aware Memory Management: A set of libraries that can be used to measure NUCA characteristics of LLC and exploited to improve the performance of applications.

• ​CacheDirector​: A network I/O solution that extends Data Direct I/O (DDIO), by exploiting slice-aware memory management, and sends each packet’s header directly to the correct slice in the LLC.

Datasets related to our Kurma paper [SOCC ’18]:

• 16 months of latency measurements across EC2 (430GB)

http://gofile.me/6BmT5/u38u0yxFB

• Synchronised traceroute measurements among 10 EC2 DCs (14 + 4 days)

http://gofile.me/6BmT5/AUatCi0lQ