Cloud vendors push ambitious in-network processing (e.g., crypto, telemetry) onto the NIC to offload servers even as link rates climb to terabit speeds. Vendors have responded with heterogeneous SmartNICs. For example, NVIDIA BlueField-3 interposes---between the wire and the host CPUs---a line-rate eSwitch, a multithre...
Robert Chang, Teng Jiang, Wonsup Yoon et al.· arXiv.org· 0 citations
This work presents Leto, a fault-tolerant training system that leverages surviving hardware to enable efficient in-place recovery and devise two-tier erasure protection and chunk-level transactional updates to keep the retained model state recoverable and consistent.
Geon-Woo Kim, Joonseok Kim, Daehyeok Kim· 0 citations
Vulcan is proposed, a framework that identifies LLM-friendly interfaces that isolate core decision logic from the rest of the implementation and demonstrates up to 4.9% higher savings for spot-VM scheduling, up to 2% lower miss ratios for cache eviction, and up to 14% higher application performance for tiered-memory sy...
Rohit Dwivedula, Divyanshu Saxena, Sujay Yadalam et al.· 1 citation
PacketExpress is presented, a packet processing architecture that enables networks to leverage large MTUs for Internet traffic without requiring modifications to neighboring networks and introduces F-PMTUD, which determines the path MTU within a single round-trip time without relying on ICMP.
Junghan Yoon, Youngmin Choi, Juyoung Park et al.· Conference on Applications,...· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.