I started Literature Watch, a list of recent papers that are relevant to computing reliability. It began as a way to keep up with the field myself; this page makes the list public.
What it covers. Papers that help understand faults, their effects on the systems and programs, detection through testing or uarch/arch features, and the ideas behind test coverage. Each paper is tagged with one or more categories (subject to change, this system is WIP, I will share some details later):
- hardware: devices and computer architecture;
- cluster: fleets and datacenters;
- workload: software and applications.
Current state. For now, I start with papers published in HPCA 2024. ISCA, MICRO, and ASPLOS, followed by other architecture, systems, dependability, and test venues from 2024 onward.
The list is not meant to be a complete picture of reliability research. It reflects how I see the field through the lens of my own work, so it leaves out directions that others would consider central, and it will miss some relevant papers. If you think something is missing or does not belong, I would be glad to hear about it, and paper suggestions, so please reach out!