Tolerating hardware faults in modern architectures is becoming a prominent problem due to
the miniaturization of the hardware components, their increasing complexity, and the …

Machine learning inference is becoming a core building block for interactive web
applications. As a result, the underlying model serving systems on which these applications …

We are accustomed to thinking of computers as fail-stop, especially the cores that execute
instructions, and most system software implicitly relies on that assumption. During most of …

The performance of compute hardware varies: software run repeatedly on the same server
(or a different server with supposedly identical parts) can produce performance results that …

Silent Data Corruption (SDC) in processors can lead to various application-level issues,
such as incorrect calculations and even data loss. Since traditional techniques are not …

Research on flash devices almost exclusively focuses on conventional SSDs, which expose
a block interface. Industry, however, has standardized and is adopting Zoned Namespaces …

This discussion paper highlights the potential of display holograms in the storage of
information about objects' shape. The images recorded and reconstructed from holograms …

We present AGGREGATHOR, a framework that implements state-of-the-art robust
(Byzantine-resilient) distributed stochastic gradient descent. Following the standard …

The newly-emerging''fail-slow''failures plague both software and hardware where the victim
components are still functioning yet with degraded performance. To address this problem …

Modern computer systems are highly configurable, with the total variability space sometimes
larger than the number of atoms in the universe. Understanding and reasoning about the …