Register for ICDCN 2025:   Link

Note
This workshop is a part of ICDCN (International Conference on Distributed Computing and Networking) hosted in IIT , Hyderabad. Registration to the conference gives access to this workshop and all workshops part of the conference.

Keynote 1: Evolution of Ethernet Transport for AI and HPC Networking

Exploration of challenges in networking for AI/ML workloads, future protocol developments, and advancements such as Ultra Ethernet and Google's Falcon protocol. Includes a discussion on simulation tools and community efforts from IIIT-D.

Speakers:

Dr. Rinku Shah

Dr. Rinku Shah is currently an Assistant Professor in the CSE department at Indraprastha Institute of Information Technology, Delhi (IIITD). She earned her PhD from IIT Bombay in February 2021. Her research interests lie in the broad area of networked systems with applications in security and machine learning. She has published her research at reputed conference venues such as ACM SOSR, IEEE ICNP, IEEE/IFIP Networking, ACM SIGCOMM FFSPIN, and ACM APNet.

Satananda Burla

Satananda Burla is a Senior Principal Engineer at Marvell, specializing in the research and development of cutting-edge networking and storage infrastructure solutions tailored for AI, cloud, and enterprise markets. He actively represents Marvell in technical forums, including the OPI Technical Steering Committee (TSC), OASIS VIRTIO, and the Ultra Ethernet Consortium (UEC), where he has contributed to the development of key specifications.

Keynote 2: The need to re-imagine networking for AI:
                     Why we need a clean slate approach

Shrijeet Mukherjee will talk through the various stages that interconnects have taken in the lead-up to the current designs for networking for AI/ML and high performance systems. The talk will cover what aspects are important and how to evaluate the efficacy of various methods and delve into the unique solutions that are presented by the Enfabrica ACF-S super-nic.

Speakers:

Shrijeet Mukherjee

Shrijeet Mukherjee, Co-Founder and Chief Development Officer at Enfabrica, leads innovations in software and system/hardware interconnects for modern data centers. With 30+ years of experience, he has developed high-performance systems, including NUMA graphics at SGI, the first SmartNIC at Cisco UCS, and advancements in Open Networking at Cumulus Networks. He also contributed to Google’s networking architectures. A Linux NetDev Society Board member and Enfabrica’s representative on the Ultra Ethernet Consortium’s Technical Advisory Committee, Shrijeet Mukherjee holds 50+ patents and an MS in Computer Science from the University of Oregon.

Keynote 3: FHE – System for Universal Computation on Encrypted Data

An in-depth discussion on fully homomorphic encryption (FHE) and its applications in secure private computation and inference on encrypted data.

Speakers:

Rohit Khera

Rohit Khera is a Distinguished Engineer at Marvell Technologies with a strong background in applied cryptography, protocols, numerical physics, and software. He has worked extensively on lattice cryptography, fully homomorphic encryption (FHE), multiparty computation, and succinct zero-knowledge arguments. His work focuses on optimizing sub-operations in FHE schemes, such as rescaling/re-linearization of tensored ciphertexts, boosted key switching, automorphisms on packed ciphertexts, and the representation of non-linear functions in encrypted domains for ML inference.

Keynote 4: Understanding system optimizations for GenAI workloads

The talk will provide a brief of current infrastructure for GenAI workloads and efficient utilization of the infrastructure. We will also discuss research efforts around orchestrating these workloads on a cloud infrastructure and other research opportunities from a system perspective.

Speakers:

Dr Priyanka Naik

Priyanka is a Research Scientist at IBM India Research Lab and is part of the GenAI platform team. Priyanka's prior research explored the space of cloud deployment, networking and observability of microservices such as network functions and extending the same for multi cloud deployments. Prior to joining IBM, she received her Ph.D. from IIT Bombay, India. She has been a speaker for multiple tutorials and a co-author to a cloud networking book.

Hands-on Session 1: Introducing AI/ML Inferencing Accelerators

• ML Acceleration in Marvell OCTEON Processors
• Marvell’s ML Software Ecosystem
• DAO SW Tools and Libraries for ML
• Hands-on Examples:
• Image Classification with Resnet50
• DDoS Attack Detection with LUCID
• Demo: DDoS Attack Detection on Live Network

Trainer:
Srikanth Yalavarthi – Principal Engineer, Machine Learning Team, Marvell Technology
Expertise: ML drivers, DPDK’s Machine Learning library, and ML in networking.

Hands-on Session 2: Introducing Programmable Packet and Crypto Accelerators

Packet and Protocol Accelerations
• Overview: VPP, DPDK, OVS, and XDP
• Overview: P4 Programming Language and Programmable Dataplanes
• Hands-on: VPP – A high-speed protocol stack using HW workload accelerations
• Hands-on: Design plugin to extend the VPP Protocol stack for next-gen protocols

Cryptographic and Protocol Accelerations
• Classical and Quantum-resistant cryptographic algorithms
• Overview: OCTEON CPT: Cryptographic and Protocol Accelerator Block
• Hands-on: Using Accelerated OpenSSL for Cryptographic Protocols
• Hands-on: Programming CPT for custom algorithms and protocols

Trainer:
Venkata Ravichandra Mynidi – Senior Principal Engineer, Accelerated Solutions Group, Marvell Technology
Expertise: Network security stacks, OpenSSL, VPP, DPDK, and TCP/UDP transport stacks.