Toward Dark Silicon in Servers

By Nikolaos Hardavellas, Michael Ferdman, Babak Falsafi, A. Ailamaki. IEEE Micro, 2011

335 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Electrical and Electronic Engineering, Hardware and Architecture

View Paper: https://www.semanticscholar.org/paper/8bf5afa21a0bd74551b261a7399eac4ffe2494e5

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

In Electrical and Electronic Engineering

In Hardware and Architecture

Citations in the corpus

Graviton: Trusted Execution Environments on GPUs (2018, background): “Recent trends such as the explosion in volume of data being collected and processed, declining yields from Moore’s Law [16], growing use of cloud computing, and applications, such as deep learning have fueled the widespread use of accelerators such as GPUs, FPGAs [37], and TPUs [20].”
Planaria: Dynamic Architecture Fission for Spatial Multi-Tenant Acceleration of Deep Neural Networks (2020, background): “The end of Dennard scaling [5] and diminishing beneﬁts from transistor scaling [6–8] has propelled an era of Domain-Speciﬁc Architectures [9].”
Trends in big data analytics (2014, background): “[42] populate the dice with a large, diverse array of application-specific heterogeneous cores that can achieve peak performance and energy efficiency by dynamically disabling all but the most application specific cores (resulting in dark silicon spots).”
Neural Acceleration for General-Purpose Approximate Programs (2012, background): “The cessation of Dennard scaling has limited recent improvements in transistor speed and energy efﬁciency, resulting in slowed general-purpose processor improvements.”
Shredder: Learning Noise Distributions to Protect Inference Privacy (2019, background): “The increasing processing demand of learningmodels [4, 5] has naturally pushed most of the computation to the cloud [6].”
LINQits: big data on little clients (2013, methodology): “Due to stringent energy demands coupled with the recent failure of Dennard Scaling [10, 18, 14, 42, 9], today’s client devices are”
Is dark silicon useful? Harnessing the four horsemen of the coming dark silicon apocalypse (2012, background): “(For subsequent work to [9, 27] on dark silicon and multicore scaling that explores more sophisticated models that incorporate factors such as application space and cache size, see [6, 13, 16].”
Sustainability of bitcoin and blockchains (2017, background): “Some applications can beneﬁt from specialized, heterogeneous cores that can be dynamically powered up for a given workload as in servers [26], or energy-efﬁcient cores for computationally intensive applications [23].”
ASIC Clouds: Specializing the Datacenter (2016, background): “The second change is the rise of dark silicon [1, 2, 3, 4] and dark silicon aware design techniques [5, 6, 7, 8, 9, 10] such as specialization and near-threshold computation, each of which help overcome threshold scaling limitations that prevent the full utilization of transistors on a silicon die.”
Shredder: Learning Noise to Protect Privacy with Partial DNN Inference on the Edge (2019, background): “The limited computation capability of edge devices [6] and the increasing processing demand of learning models [7, 8] has naturally pushed most of the computation to the cloud [9].”
From high-level deep neural models to FPGAs (2016, background): “With diminishing benefits from technology scaling [10, 11], the research community is increasingly turning to specialized accelerators for deep networks [12–15] and other workloads [16–22].”
Heracles: Improving resource efficiency at scale (2015, background): “However, with several imminent challenges in technology scaling [21, 25], alternate approaches are needed.”