Modern computing systems are overwhelmingly designed to move data to computation. This
design choice goes directly against at least three key trends in computing that cause …

Today's systems are overwhelmingly designed to move data to computation. This design
choice goes directly against at least three key trends in systems that cause performance …

Deep learning training on a shared GPU cluster is becoming a common practice. However,
we observe severe sharing anomaly in production multi-tenant clusters where jobs in some …

We present CASSINI, a network-aware job scheduler for machine learning (ML) clusters.
CASSINI introduces a novel geometric abstraction to consider the communication pattern of …

We present Heimdall, a mobile GPU coordination platform for emerging Augmented Reality
(AR) applications. Future AR apps impose an explored challenging workload: i) concurrent …

The rapidly growing popularity and scale of data-parallel workloads demand a
corresponding increase in raw computational power of Graphics Processing Units (GPUs) …

While unified virtual memory and demand paging in modern GPUs provide convenient
abstractions to programmers for working with large-scale applications, they come at a …

Modern discrete GPUs support unified memory and demand paging. Automatic
management of data movement between CPU memory and GPU memory dramatically …

This paper argues that fair-sharing, the holy grail of congestion control algorithms for
decades, is not necessarily a desirable property in Machine Learning (ML) training clusters …

As memory capacity has outstripped TLB coverage, large data applications suffer from
frequent page table walks. We investigate two complementary techniques for addressing …