⚙️ Code: github.com/spcl/xaas-containers
📚 Artifact: zenodo.org/records/1711...

Join us on Tuesday in room 275!

📄Paper: dl.acm.org/doi/10.1145/...
💬Presentation: Tuesday, November 18th, 3:30pm - 3:52pm CST, Room 275

XaaS containers are the result of a collaboration between SPCL, @cscsch.bsky.social, LLNL, ANL, and the University of Chicago.

#HPC #SC25 #HPCignites

We designed Source and Intermediate Representation (IR) containers. In IR containers, we implement a pipeline where containerized applications are compiled to LLVM IR, and adapted to the target architecture (e.g., vectorization) at deployment time, ensuring peak performance.

Traditional containers lock in compilation decisions too early, hurting performance on diverse HPC systems. We delay performance-critical decisions until the target system is known, avoiding the traditional container trade-off between portability and hardware-specific optimizations.

Cppless is open source and built on top of LLVM with less than 1k LoC changes. More details in the paper on serialization, C++ lambda extraction, and cross-compilation.

Paper 👉 arxiv.org/abs/2401.10834
Code 👉 github.com/spcl/cppless
Artifact 👉 zenodo.org/records/1577...

Our evaluation shows that C++ serverless functions can scale to 512 parallel workers with a double-digit millisecond overhead. Using the example of ray tracing, we demonstrate a speedup of up to 59x. From a 60-second execution time to 1 second with hundreds of functions and a minimal cost increase.

With Cppless, C++ is no longer a second-class citizen in serverless. We introduce alternative entry points and implement lambda reflection, making C++ functions as easy to deploy as Python.

Cold starts? Just 10-12 milliseconds and up to 60x faster than Python functions!

⭐Larissa Schmid will present at EuroSys her paper "SeBS-Flow: Benchmarking Serverless Cloud Function Workflows".
📅 Thursday, April 3, 2025 at 9.00. Session 7-1
📚 Paper: arxiv.org/abs/2410.03480

⭐At the EuroSys poster session, I will present our joint work on SeBS-Flow, a new extension of SeBS that provides automatic and cloud-agnostic benchmarking of serverless workflows.
📅 Monday, March 31, 2025 at 18:00 - 19:30

⭐ I will present a work-in-progress paper at the SESAME'25 workshop: "SeBS 2.0: Keeping up with the Clouds"
📅 Monday, March 31, 2025 at 11:00 - 12:10
📚 Paper: dl.acm.org/doi/10.1145/...

Reasoning Language Models: A Blueprint

📜 arxiv.org/abs/2501.11223
x1 on GitHub: github.com/spcl/x1

We introduce x1, a modular implementation for rapid RLM prototyping, provide key insights (multi-phase training for policy/value models, importance of familiar training distributions) and discuss scalable RLM cloud deployments and how RLMs fit into the broader LLM ecosystem.

We propose a blueprint that organizes RLM components into a modular framework, based on an analysis of all RLM works, which incorporates reasoning structures (chains, trees, graphs) and strategies (e.g., #MCTS), Reinforcement Learning and supervision schemes.

Interesting observation, I hope that you will join the discussion on Thursday :)

Happy to meet&chat at SC to discuss your experience and thoughts!