Alireza Farshin
Research Subjects
Research Interests
Alireza Farshin has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Dejan Kostić
Medical Faculty of the Military Medical Academy, Belgrade, Serbia
6 shared publications - Marco Chiesa
KTH Royal Institute of Technology, Stockholm, Sweden
3 shared publications - Mariano Scazzariello
RISE Research Institutes of Sweden, Kista, Sweden
3 shared publications - Saeed Sharifian
Department of Electrical Engineering, Amirkabir University of Technology, 15914, Tehran, Iran
3 shared publications - Adel Sefiane
Imperial College London, London, United Kingdom and NVIDIA, Roskilde, Denmark
2 shared publications - Gerald Q. Maguire
KTH Royal Institute of Technology
2 shared publications
Latest Publications
- Open Access
- 5 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 239-245
CheckWork: Enabling Trace-Driven Analysis of Checkpointing Overhead in Distributed ML Training
- 5 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 239-245
Open AccessCheckWork: Enabling Trace-Driven Analysis of Checkpointing Overhead in Distributed ML Training
- Open Access
- 8 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 98-104
MLSynth: Towards Synthetic ML Traces
- 8 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 98-104
Open AccessMLSynth: Towards Synthetic ML Traces
- Open Access
- 18 August 2024
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Networking
- Vol. 2 (CoNEXT3) , 1-22
FAJITA: Stateful Packet Processing at 100 Million pps
Data centers increasingly utilize commodity servers to deploy low-latency Network Functions (NFs). However, the emergence of multi-hundred-gigabit-per-second network interface cards (NICs) has drastically increased the performance expected from commodity servers. Additionally, recently introduced systems that store packet payloads in temporary off-CPU locations (e.g., programmable switches, NICs, and RDMA servers) further increase the load on NF servers, making packet processing even more challenging. This paper demonstrates existing bottlenecks and challenges of state-of-the-art stateful packet processing frameworks and proposes a system, called FAJITA, to tackle these challenges & accelerate stateful packet processing on commodity hardware. FAJITA proposes an optimized processing pipeline for stateful network functions to minimize memory accesses and overcome the overheads of accessing shared data structures while ensuring efficient batch processing at every stage of the pipeline. Furthermore, FAJITA provides a performant architecture to deploy high-performance network functions service chains containing stateful elements with different state granularities. FAJITA improves the throughput and latency of high-speed stateful network functions by ~2.43x compared to the most performant state-of-the-art solutions, enabling commodity hardware to process up to ~178 Million 64-B packets per second (pps) using 16 cores.
- 18 August 2024
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Networking
- Vol. 2 (CoNEXT3) , 1-22
Open AccessFAJITA: Stateful Packet Processing at 100 Million pps
Data centers increasingly utilize commodity servers to deploy low-latency Network Functions (NFs). However, the emergence of multi-hundred-gigabit-per-second network interface cards (NICs) has drastically increased the performance expected from commodity servers. Additionally, recently introduced systems that store packet payloads in temporary off-CPU locations (e.g., programmable switches, NICs, and RDMA servers) further increase the load on NF servers, making packet processing even more challenging. This paper demonstrates existing bottlenecks and challenges of state-of-the-art stateful packet processing frameworks and proposes a system, called FAJITA, to tackle these challenges & accelerate stateful packet processing on commodity hardware. FAJITA proposes an optimized processing pipeline for stateful network functions to minimize memory accesses and overcome the overheads of accessing shared data structures while ensuring efficient batch processing at every stage of the pipeline. Furthermore, FAJITA provides a performant architecture to deploy high-performance network functions service chains containing stateful elements with different state granularities. FAJITA improves the throughput and latency of high-speed stateful network functions by ~2.43x compared to the most performant state-of-the-art solutions, enabling commodity hardware to process up to ~178 Million 64-B packets per second (pps) using 16 cores.
- Top Cited PapersOpen Access
- 13 June 2024
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Networking
- Vol. 2 (CoNEXT2) , 1-25
NetConfEval: Can LLMs Facilitate Network Configuration?
This paper explores opportunities to utilize Large Language Models (LLMs) to make network configuration human-friendly, simplifying the configuration of network devices & development of routing algorithms and minimizing errors. We design a set of benchmarks (NetConfEval) to examine the effectiveness of different models in facilitating and automating network configuration. More specifically, we focus on the scenarios where LLMs translate high-level policies, requirements, and descriptions (i.e., specified in natural language) into low-level network configurations & Python code. NetConfEval considers four tasks that could potentially facilitate network configuration, such as (i) generating high-level requirements into a formal specification format, (ii) generating API/function calls from high-level requirements, (iii) developing routing algorithms based on high-level descriptions, and (iv) generating low-level configuration for existing and new protocols based on input documentation. Learning from the results of our study, we propose a set of principles to design LLM-based systems to configure networks. Finally, we present two GPT-4-based prototypes to (i) automatically configure P4-enabled devices from a set of high-level requirements and (ii) integrate LLMs into existing network synthesizers.
- 13 June 2024
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Networking
- Vol. 2 (CoNEXT2) , 1-25
Top Cited PapersOpen AccessNetConfEval: Can LLMs Facilitate Network Configuration?
This paper explores opportunities to utilize Large Language Models (LLMs) to make network configuration human-friendly, simplifying the configuration of network devices & development of routing algorithms and minimizing errors. We design a set of benchmarks (NetConfEval) to examine the effectiveness of different models in facilitating and automating network configuration. More specifically, we focus on the scenarios where LLMs translate high-level policies, requirements, and descriptions (i.e., specified in natural language) into low-level network configurations & Python code. NetConfEval considers four tasks that could potentially facilitate network configuration, such as (i) generating high-level requirements into a formal specification format, (ii) generating API/function calls from high-level requirements, (iii) developing routing algorithms based on high-level descriptions, and (iv) generating low-level configuration for existing and new protocols based on input documentation. Learning from the results of our study, we propose a set of principles to design LLM-based systems to configure networks. Finally, we present two GPT-4-based prototypes to (i) automatically configure P4-enabled devices from a set of high-level requirements and (ii) integrate LLMs into existing network synthesizers.
- Open Access
- 22 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 28-38
Deploying Stateful Network Functions Efficiently using Large Language Models
Stateful network functions are increasingly used in data centers. However, their scalability remains a significant challenge since parallelizing packet processing across multiple cores requires careful configuration t o avoid compromising the application's semantics or performance. This challenge is particularly important when deploying multiple stateful functions on multi-core servers. This paper proposes FlowMage, a system that leverages Large Language Models (LLMs) to perform code analysis and extract essential information from stateful network functions (NFs) prior to their deployment on a server. FlowMage uses this data to find an efficient configuration of an NF chain that maximizes performance while preserving the semantics of the NF chain. Our evaluation shows that, utilizing GPT-4, FlowMage is able to find and apply optimized configuration when deploying stateful NFs chain on a server, resulting in significant p erformance improvement (up to 11×) in comparison to the default configuration of the system.
- 22 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 28-38
Open AccessDeploying Stateful Network Functions Efficiently using Large Language Models
Stateful network functions are increasingly used in data centers. However, their scalability remains a significant challenge since parallelizing packet processing across multiple cores requires careful configuration t o avoid compromising the application's semantics or performance. This challenge is particularly important when deploying multiple stateful functions on multi-core servers. This paper proposes FlowMage, a system that leverages Large Language Models (LLMs) to perform code analysis and extract essential information from stateful network functions (NFs) prior to their deployment on a server. FlowMage uses this data to find an efficient configuration of an NF chain that maximizes performance while preserving the semantics of the NF chain. Our evaluation shows that, utilizing GPT-4, FlowMage is able to find and apply optimized configuration when deploying stateful NFs chain on a server, resulting in significant p erformance improvement (up to 11×) in comparison to the default configuration of the system.
- Open Access
- 16 May 2023
- Published by PeerJ in PeerJ Computer Science
- Vol. 9, e1385
Overcoming the IOTLB wall for multi-100-Gbps Linux-based networking
This article explores opportunities to mitigate the performance impact of IOMMU on high-speed network traffic, as used in the Linux kernel. We first characterize IOTLB behavior and its effects on recent Intel Xeon Scalable & AMD EPYC processors at 200 Gbps, by analyzing the impact of different factors contributing to IOTLB misses and causing throughput drop (up to 20% compared to the no-IOMMU case in our experiments). Secondly, we discuss and analyze possible mitigations, including proposals and evaluation of a practical hugepage-aware memory allocator for the network device drivers to employ hugepage IOTLB entries in the Linux kernel. Our evaluation shows that using hugepage-backed buffers can completely recover the throughput drop introduced by IOMMU. Moreover, we formulate a set of guidelines that enable network developers to tune their systems to avoid the “IOTLB wall”, i.e., the point where excessive IOTLB misses cause throughput drop. Our takeaways signify the importance of having a call to arms to rethink Linux-based I/O management at higher data rates.
- 16 May 2023
- Published by PeerJ in PeerJ Computer Science
- Vol. 9, e1385
Open AccessOvercoming the IOTLB wall for multi-100-Gbps Linux-based networking
This article explores opportunities to mitigate the performance impact of IOMMU on high-speed network traffic, as used in the Linux kernel. We first characterize IOTLB behavior and its effects on recent Intel Xeon Scalable & AMD EPYC processors at 200 Gbps, by analyzing the impact of different factors contributing to IOTLB misses and causing throughput drop (up to 20% compared to the no-IOMMU case in our experiments). Secondly, we discuss and analyze possible mitigations, including proposals and evaluation of a practical hugepage-aware memory allocator for the network device drivers to employ hugepage IOTLB entries in the Linux kernel. Our evaluation shows that using hugepage-backed buffers can completely recover the throughput drop introduced by IOMMU. Moreover, we formulate a set of guidelines that enable network developers to tune their systems to avoid the “IOTLB wall”, i.e., the point where excessive IOTLB misses cause throughput drop. Our takeaways signify the importance of having a call to arms to rethink Linux-based I/O management at higher data rates.
- Open Access
- 17 April 2021
- Published by Association for Computing Machinery (ACM)
- p. 1-17
PacketMill: toward per-Core 100-Gbps networking
We present PacketMill, a system for optimizing software packet processing, which (i) introduces a new model to efficiently manage packet metadata and (ii) employs code-optimization techniques to better utilize commodity hardware. PacketMill grinds the whole packet processing stack, from the high-level network function configuration file to the low-level userspace network (specifically DPDK) drivers, to mitigate inefficiencies and produce a customized binary for a given network function. Our evaluation results show that PacketMill increases throughput (up to 36.4 Gbps -- 70%) & reduces latency (up to 101 us -- 28%) and enables nontrivial packet processing (e.g., router) at ~100 Gbps, when new packets arrive >10× faster than main memory access times, while using only one processing core.
- 17 April 2021
- Published by Association for Computing Machinery (ACM)
- p. 1-17
Open AccessPacketMill: toward per-Core 100-Gbps networking
We present PacketMill, a system for optimizing software packet processing, which (i) introduces a new model to efficiently manage packet metadata and (ii) employs code-optimization techniques to better utilize commodity hardware. PacketMill grinds the whole packet processing stack, from the high-level network function configuration file to the low-level userspace network (specifically DPDK) drivers, to mitigate inefficiencies and produce a customized binary for a given network function. Our evaluation results show that PacketMill increases throughput (up to 36.4 Gbps -- 70%) & reduces latency (up to 101 us -- 28%) and enables nontrivial packet processing (e.g., router) at ~100 Gbps, when new packets arrive >10× faster than main memory access times, while using only one processing core.
- Open Access
- 25 March 2019
- Published by Association for Computing Machinery (ACM)
- p. 1-17
Make the Most out of Last Level Cache in Intel Processors
- 25 March 2019
- Published by Association for Computing Machinery (ACM)
- p. 1-17
Open AccessMake the Most out of Last Level Cache in Intel Processors
- 16 March 2019
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 75 (8) , 5520-5550
A modified knowledge-based ant colony algorithm for virtual machine placement and simultaneous routing of NFV in distributed cloud architecture
- 16 March 2019
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 75 (8) , 5520-5550
A modified knowledge-based ant colony algorithm for virtual machine placement and simultaneous routing of NFV in distributed cloud architecture
- 1 August 2017
- Published by Elsevier in Computer Communications
- Vol. 108, 94-109
A chaotic grey wolf controller allocator for Software Defined Mobile Network (SDMN) for 5th generation of cloud-based cellular systems (5G)
- 1 August 2017
- Published by Elsevier in Computer Communications
- Vol. 108, 94-109
A chaotic grey wolf controller allocator for Software Defined Mobile Network (SDMN) for 5th generation of cloud-based cellular systems (5G)