Mythili Vutukuru
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Mythili Vutukuru has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Ashwin Kumar
Microsoft Research, India, Bangalore, India
2 shared publications - Preeti
Indian Institute of Technology, Bombay, Mumbai, India
2 shared publications - Abuhujair Khan
Indian Institute of Technology, Bombay, India
1 shared publication - Aditya Kansara
Indian Institute of Technology Bombay, Mumbai, India
1 shared publication - Ajinkya Tanksale
Indian Institute of Technology, Bombay, India
1 shared publication Akanksha Patel
Indian Institute of Technology Bombay
1 shared publication
Latest Publications
- Open Access
- 14 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 50-66
Requests of a Feather Must Flock Together: Batch Size vs. Prefix Homogeneity in LLM Inference
- 14 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 50-66
Open AccessRequests of a Feather Must Flock Together: Batch Size vs. Prefix Homogeneity in LLM Inference
- Open Access
- 22 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 2015-2029
Toasty: Speeding Up Network I/O with Cache-Warm Buffers
Modern NICs DMA packets directly to the LLC using technologies like DDIO, reducing access latencies for networking applications. Prior work has observed several performance issues with DDIO when the working set of packet buffers does not fit into LLC. For example, the leaky DMA problem arises when incoming packets evict older packets that have not yet been processed by the application from LLC, causing them to be fetched again from main memory. While using a smaller pool of packet buffers that fits in cache is an obvious solution, this may result in the NIC running out of buffers to DMA packets into when a burst of packets arrives. This paper proposes Toasty, a system that mitigates this tradeoff between high throughput and resilience to packet loss that arises when sizing the network packet buffer pool. While prior work has proposed hardware-based solutions to this problem, Toasty is a software-only solution that can be deployed on commodity NIC hardware. Toasty manages the packet buffer pool as a LIFO stack instead of a FIFO queue, and adapts the number of buffers populated into the NIC hardware RX ring based on incoming packet load and application processing rate. Together, these changes enable Toasty to recirculate a small working set of cache-warm buffers in steady state, while falling back to a larger pool of buffers during traffic bursts. We implement Toasty over the AF_XDP kernel bypass framework, and our evaluation shows that Toasty improves network throughput for a variety of network functions by up to 78% over the default buffer pool implementation of AF_XDP. We also show that Toasty matches the performance of a small buffer pool that fits in cache, while being more resilient to traffic bursts.
- 22 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 2015-2029
Open AccessToasty: Speeding Up Network I/O with Cache-Warm Buffers
Modern NICs DMA packets directly to the LLC using technologies like DDIO, reducing access latencies for networking applications. Prior work has observed several performance issues with DDIO when the working set of packet buffers does not fit into LLC. For example, the leaky DMA problem arises when incoming packets evict older packets that have not yet been processed by the application from LLC, causing them to be fetched again from main memory. While using a smaller pool of packet buffers that fits in cache is an obvious solution, this may result in the NIC running out of buffers to DMA packets into when a burst of packets arrives. This paper proposes Toasty, a system that mitigates this tradeoff between high throughput and resilience to packet loss that arises when sizing the network packet buffer pool. While prior work has proposed hardware-based solutions to this problem, Toasty is a software-only solution that can be deployed on commodity NIC hardware. Toasty manages the packet buffer pool as a LIFO stack instead of a FIFO queue, and adapts the number of buffers populated into the NIC hardware RX ring based on incoming packet load and application processing rate. Together, these changes enable Toasty to recirculate a small working set of cache-warm buffers in steady state, while falling back to a larger pool of buffers during traffic bursts. We implement Toasty over the AF_XDP kernel bypass framework, and our evaluation shows that Toasty improves network throughput for a variety of network functions by up to 78% over the default buffer pool implementation of AF_XDP. We also show that Toasty matches the performance of a small buffer pool that fits in cache, while being more resilient to traffic bursts.
- Open Access
- 19 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 571-584
FLASH: Fast Linked AF_XDP Sockets for High Performance Network Function Chains
- 19 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 571-584
Open AccessFLASH: Fast Linked AF_XDP Sockets for High Performance Network Function Chains
- Open Access
- 3 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 156-162
Pyramis: Domain Specific Language for Developing Multi-tier Systems
Text-based specifications are the de-facto standard for specifying complex multi-tier systems. For example, 3GPP specifications define various interfaces, messages, and message processing at the multiple inter-connected nodes of a 5G system. These standards documents tend to be verbose, and may be ambiguous or inconsistent in places, increasing programmer effort to implement them in a general purpose language. This paper presents Pyramis, a Domain Specific Language (DSL) with suitable high-level abstractions for specifying the interfaces, messages, and processing in a multi-tier system. Pyramis allows programmers to specify multi-tier systems in a concise and precise manner, and enables easy development of software based on the specifications. We also develop a translator with Pyramis that automatically generates optimized, multi-threaded C++ code for the various components of the multi-tier system from the specification, and also generates eBPF-based measurement code for computing various performance metrics. We use Pyramis to build several components in the 5G mobile packet core. We show that the specifications written in Pyramis are 2–3 × smaller than the actual reference implementation, while the auto-generated C++ code performs on par with a hand-optimized implementation. We believe that Pyramis can eventually replace verbose text specifications like the 3GPP standards documents in telecom systems.
- 3 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 156-162
Open AccessPyramis: Domain Specific Language for Developing Multi-tier Systems
Text-based specifications are the de-facto standard for specifying complex multi-tier systems. For example, 3GPP specifications define various interfaces, messages, and message processing at the multiple inter-connected nodes of a 5G system. These standards documents tend to be verbose, and may be ambiguous or inconsistent in places, increasing programmer effort to implement them in a general purpose language. This paper presents Pyramis, a Domain Specific Language (DSL) with suitable high-level abstractions for specifying the interfaces, messages, and processing in a multi-tier system. Pyramis allows programmers to specify multi-tier systems in a concise and precise manner, and enables easy development of software based on the specifications. We also develop a translator with Pyramis that automatically generates optimized, multi-threaded C++ code for the various components of the multi-tier system from the specification, and also generates eBPF-based measurement code for computing various performance metrics. We use Pyramis to build several components in the 5G mobile packet core. We show that the specifications written in Pyramis are 2–3 × smaller than the actual reference implementation, while the auto-generated C++ code performs on par with a hand-optimized implementation. We believe that Pyramis can eventually replace verbose text specifications like the 3GPP standards documents in telecom systems.
- 1 November 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-7
Mobility-aware VNF placement in the LTE EPC
Traditional network infrastructure is facing significant challenges to support the growing bandwidth, coverage, and latency requirements of users, and to support new 4G and 5G use-cases. As a solution, telecom operators are looking to implement Network Function Virtualization (NFV) in future networks. The placement of Virtual Network Functions (VNFs) plays a critical role in reducing latency to serve users, while also helping in reducing the overall operational cost of the network. This work focuses on the VNF placement problem in the context of mobility and handovers, in scenarios such as mobile users travelling at high speeds, users served by small cells, and mobile IoT devices. We have modelled the VNF placement problem as an optimization problem that aims to reduce the latency in handovers resulting from mobility. We have compared our approach with other approaches, and we have demonstrated upto 60% reduction in the average time taken to serve handover requests in the network with no considerable increase in overall operational cost. We also provide a sub-graph based approach to solve for larger topologies and demonstrated its scalability.
- 1 November 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-7
Mobility-aware VNF placement in the LTE EPC
Traditional network infrastructure is facing significant challenges to support the growing bandwidth, coverage, and latency requirements of users, and to support new 4G and 5G use-cases. As a solution, telecom operators are looking to implement Network Function Virtualization (NFV) in future networks. The placement of Virtual Network Functions (VNFs) plays a critical role in reducing latency to serve users, while also helping in reducing the overall operational cost of the network. This work focuses on the VNF placement problem in the context of mobility and handovers, in scenarios such as mobile users travelling at high speeds, users served by small cells, and mobile IoT devices. We have modelled the VNF placement problem as an optimization problem that aims to reduce the latency in handovers resulting from mobility. We have compared our approach with other approaches, and we have demonstrated upto 60% reduction in the average time taken to serve handover requests in the network with no considerable increase in overall operational cost. We also provide a sub-graph based approach to solve for larger topologies and demonstrated its scalability.