Advances in ML have motivated the design of video analytics systems that...
Sequence-based deep learning recommendation models (DLRMs) are an emergi...
We propose TROD, a novel transaction-oriented framework for debugging mo...
We present RecD (Recommendation Deduplication), a suite of end-to-end
in...
Developers are increasingly using function-as-a-service (FaaS) platforms...
Cloud platforms run many software agents on each server node. These agen...
We propose RecShard, a fine-grained embedding table (EMB) partitioning a...
Serverless computing has seen rapid growth due to the ease-of-use and
co...
The data ingestion pipeline, responsible for storing and preprocessing
t...
Function-as-a-Service (FaaS) has become an increasingly popular way for ...
FPGAs are now used in public clouds to accelerate a wide range of
applic...
The proliferation of camera-enabled devices and large video repositories...
Low-latency online services have strict Service Level Objectives (SLOs) ...
Current operating systems are complex systems that were designed before
...
The number of applications relying on inference from machine learning mo...
The trade-off between pull-based and push-based graph processing engines...
Operating a distributed data stream processing workload efficiently at s...
Many DNN accelerators have been proposed and built using different
micro...
The explosion in workload complexity and the recent slow-down in Moore's...
Networked applications traditionally derive their identity from the iden...