Patrick Stuedi bio photo

Patrick Stuedi

Buidling distributed systems for modern hardware.

  G. Scholar LinkedIn Github e-Mail

About

I’m a researcher and system’s builder in the area of distributed systems, networking and operating systems. From 2010 to 2019 I was a member of the research staff at IBM Research Zurich. I’m holding a PhD in Compuer Science from ETH Zurich. From 2008 to 2019 I spent two years as a Postdoc at Microsoft Research Silicon Valley. Starting Dec 2019 I will be joining the data infrastructure team at Linkedin.

The general theme of my work is to explore how modern networking and storage hardware can be exploited in distributed systems. Over the last years, I’ve been working on Crail, a fast distributed data store designed from ground up for fast storage (DRAM, NVMe, PCM) and networking hardware (100Gb/s RDMA, NVMf). Crail is built upon principles of user-level I/O and primarily targets fast sharing of ephemeral data in distributed data processing workloads (Spark, Tensforflow, serverless workloads, etc.).

Currently, I’m working on a new storage platform for efficient ML training on disaggregated storage.

Earlier, I developed DiSNI, a zero-copy RDMA-based network stack for the JVM, DaRPC, a ultra-low latency RPC library also for the JVM, and jVerbs, an RDMA-based network stack and precurser of DiSNI, which is part of the IBM JDK since May 2014.

News

Recent Talks

Program Committes

USENIX ATC’20, ASPLOS’20 (ERC), USENIX ATC’19, ASPLOS’19 (ERC), USENIX ATC’18, SoCC’18, SoCC’17, Systor’17, ICDCS’14, ICDCS’11, ICDCS’10

Teaching

I have been co-teaching the following courses: