Fast execution of functions is an inevitable challenge in the serverless computing
landscape. Inefficient dispatching, fluctuations in invocation rates, burstiness of workloads …

Serverless data analytics generate a large amount of intermediate data during computation
stages. However, serverless functions, which are short-lived and lack direct communication …

Today, all computers have some degree of usable parallelism. Modern computers are
explicitly equipped with hardware support for parallelism, such as multiple nodes …

Online data services have stringent performance requirement and must tolerate workload
fluctuation. This paper introduces PitStop, a new query language runtime design built on the …

Serverless computing promises to significantly simplify cloud computing by providing
Functions-as-a-Service where invocations of functions, triggered by events, are …

With their high parallelism and resource needs, many scientific applications benefit from
cloud deployments. Today, scientific applications are executed on dedicated pools of VMs …

A major challenge in writing applications that execute across hosts, such as distributed
online services, is to reconcile (a) parallelism (ie, allowing components to execute …

A distributed system is made of interacting components. The current manual, ad-hoc
approach to composing them cannot ensure that the composition is correct, and makes it …

Large distributed systems are often built by assembling off-the-shelf (OTS) components, eg,
components, services, processes, etc., developed independently. The current approach is to …

Microservice-based architectures have become ubiquitous in large-scale software systems.
Experimental distributed systems researchers constantly propose enhanced resource …