Tommaso Bonato
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Tommaso Bonato has a total of 47 co-authors. Here are the top co-authors by number of shared publications:
- Torsten Hoefler
ETH Zurich, Zurich, Switzerland
7 shared publications - Daniele De Sensi
Sapienza University of Rome, Rome, Italy
4 shared publications - Abdul Kabbani
Microsoft Corporation, Redmond, USA
2 shared publications - Ahmad Ghalayini
Microsoft, Redmond, USA
2 shared publications - Tiancheng Chen
ETH Zurich, Zurich, Switzerland
2 shared publications Abdulla Bataineh
HPE, Palo Alto, CA, USA
1 shared publication
Latest Publications
- Open Access
- 11 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 1973-1980
Ampel: Scheduling at the Network Cut in ML Training
- 11 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 1973-1980
Open AccessAmpel: Scheduling at the Network Cut in ML Training
- Open Access
- 26 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Network Design for Wafer-Scale Systems with Wafer-on-Wafer Hybrid Bonding
- 26 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Open AccessNetwork Design for Wafer-Scale Systems with Wafer-on-Wafer Hybrid Bonding
- Top Cited PapersOpen Access
- 26 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 225-246
REPS: Recycled Entropy Packet Spraying for Adaptive Load Balancing and Failure Mitigation
- 26 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 225-246
Top Cited PapersOpen AccessREPS: Recycled Entropy Packet Spraying for Adaptive Load Balancing and Failure Mitigation
- 12 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Networking
- Vol. 34, 1974-1987
Flowcut Switching: High-Performance Adaptive Routing With In-Order Delivery Guarantees
Network latency severely impacts the performance of applications running on supercomputers. Adaptive routing algorithms route packets over different available paths to reduce latency and improve network utilization. However, if a switch routes packets belonging to the same network flow on different paths, they might arrive at the destination out-of-order due to differences in the latency of these paths. For some transport protocols like TCP, QUIC, and RoCE, out-of-order (OOO) packets might cause large performance drops or significantly increase CPU utilization. In this work, we propose Flowcut switching, a new adaptive routing algorithm that provides high-performance in-order packet delivery. Differently from existing solutions like Flowlet switching, which are based on the assumption of bursty traffic and that might still reorder packets, Flowcut switching guarantees in-order delivery under any network conditions, and is effective also for non-bursty traffic, as it is often the case for RDMA. On top of this, Flowcut can be implemented either at the switch or NIC level providing flexibility and different tradeoffs.
- 12 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Networking
- Vol. 34, 1974-1987
Flowcut Switching: High-Performance Adaptive Routing With In-Order Delivery Guarantees
Network latency severely impacts the performance of applications running on supercomputers. Adaptive routing algorithms route packets over different available paths to reduce latency and improve network utilization. However, if a switch routes packets belonging to the same network flow on different paths, they might arrive at the destination out-of-order due to differences in the latency of these paths. For some transport protocols like TCP, QUIC, and RoCE, out-of-order (OOO) packets might cause large performance drops or significantly increase CPU utilization. In this work, we propose Flowcut switching, a new adaptive routing algorithm that provides high-performance in-order packet delivery. Differently from existing solutions like Flowlet switching, which are based on the assumption of bursty traffic and that might still reorder packets, Flowcut switching guarantees in-order delivery under any network conditions, and is effective also for non-bursty traffic, as it is often the case for RDMA. On top of this, Flowcut can be implemented either at the switch or NIC level providing flexibility and different tradeoffs.
- Open Access
- 15 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 349-367
ATLAHS: An Application-centric Network Simulator Toolchain for AI, HPC, and Distributed Storage
- 15 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 349-367
Open AccessATLAHS: An Application-centric Network Simulator Toolchain for AI, HPC, and Distributed Storage
- Open Access
- 15 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1195-1210
Uno: A One-Stop Solution for Inter- and Intra-Data Center Congestion Control and Reliable Connectivity
- 15 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1195-1210
Open AccessUno: A One-Stop Solution for Inter- and Intra-Data Center Congestion Control and Reliable Connectivity
- Open Access
- 15 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1901-1916
Bine Trees: Enhancing Collective Operations by Optimizing Communication Locality
- 15 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1901-1916
Open AccessBine Trees: Enhancing Collective Operations by Optimizing Communication Locality
- Open Access
HammingMesh: A Network Topology for Large-Scale Deep Learning
Numerous microarchitectural optimizations unlocked tremendous processing power for deep neural networks that in turn fueled the AI revolution. With the exhaustion of such optimizations, the growth of modern AI is now gated by the performance of training systems, especially their data movement. Instead of focusing on single accelerators, we investigate data-movement characteristics of large-scale training at full system scale. Based on our workload analysis, we design HammingMesh, a novel network topology that provides high bandwidth at low cost with high job scheduling flexibility. Specifically, HammingMesh can support full bandwidth and isolation to deep learning training jobs with two dimensions of parallelism. Furthermore, it also supports high global bandwidth for generic traffic. Thus, HammingMesh will power future large-scale deep learning systems with extreme bandwidth requirements.
Open AccessHammingMesh: A Network Topology for Large-Scale Deep Learning
Numerous microarchitectural optimizations unlocked tremendous processing power for deep neural networks that in turn fueled the AI revolution. With the exhaustion of such optimizations, the growth of modern AI is now gated by the performance of training systems, especially their data movement. Instead of focusing on single accelerators, we investigate data-movement characteristics of large-scale training at full system scale. Based on our workload analysis, we design HammingMesh, a novel network topology that provides high bandwidth at low cost with high job scheduling flexibility. Specifically, HammingMesh can support full bandwidth and isolation to deep learning training jobs with two dimensions of parallelism. Furthermore, it also supports high global bandwidth for generic traffic. Thus, HammingMesh will power future large-scale deep learning systems with extreme bandwidth requirements.