As modern GPU workloads grow in size and complexity, there is an ever-increasing demand
for GPU computational power. Emerging workloads contain hundreds or thousands of GPU …

DNN inference accelerators executing online services exhibit low average loads because of
service demand variability, leading to poor resource utilization. Unfortunately, reclaiming …

Resource-constrained system-on-chips (SoCs) are increasingly heterogeneous with
specialized accelerators for various tasks. Acceleration taxes due to control and data …

Storage and memory technologies are experiencing unprecedented transformation. Storage-
class memory (SCM) delivers near-DRAM performance in non-volatile storage media and …

In this work, we tackle the problem of estimating the security of iterated symmetric ciphers in
an efficient manner, with tests that do not require a deep analysis of the internal structure of …

In this paper, we present to the embedded research community an Embedded Platform as a
Service facility named SLePaaS that allows researchers remote access to experimental …

DNN infrastructure has observed an explosion in investment due to the increasing popularity
of DNNs in online services [16, 18, 22]. Unfortunately, a significant fraction of this investment …

As modern GPU workloads become larger and more complex, there is an ever-increasing
demand for GPU computational power. Traditionally, GPUs have lacked generalized data …

Abstract Network function virtualization (NFV)[50] is increasingly used to implement network
operations traditionally implemented in customized ASICs. NFV employs commodity …

In this work, we tackle the problem of estimating the security of iterated symmetric ciphers in
an efficient manner, with tests that do not require a deep analysis of the internal structure of …