Energy proportionality in near-threshold computing servers and cloud data centers: Consolidating or Not?

Pahlevan, Ali; Qureshi, Yasir Mahmood; Zapater, Marina; Bartolini, Andrea; Rossi, Davide; Benini, Luca; Atienza, David

doi:10.23919/date.2018.8341994

Cited by 12 publications

(12 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We utilize an Alexnet model in the ARM Compute Library framework (ACL), developed by ARM (2018), for our CNN experiments. • Power Model: To compute energy values, we use the power model for 28nm bulk CMOS A57 OoO cores proposed by Pahlevan et al (2018). For in-order cores, we use the energy ratio between A57 and A53 cores at different frequencies as proposed by Frumusanu and Smith (2015a), Frumusanu and Smith (2015b).…”

Section: Methodsmentioning

confidence: 99%

Gem5-X: A Gem5-Based System Level Simulation Framework to Optimize Many-Core Platforms

Qureshi

Simon

Zapater

et al. 2019

2019 Spring Simulation Conference (SpringSim)

Self Cite

View full text Add to dashboard Cite

The rapid expansion of online-based services requires novel energy and performance efficient architectures to meet power and latency constraints. Fast architectural exploration has become a key enabler in the proposal of architectural innovation. In this paper, we present gem5-X, a gem5-based system level simulation framework, and a methodology to optimize many-core systems for performance and power. As real-life case studies of many-core server workloads, we use real-time video transcoding and image classification using convolutional neural networks (CNNs). Gem5-X allows us to identify bottlenecks and evaluate the potential benefits of architectural extensions such as in-cache computing and 3D stacked High Bandwidth Memory. For real-time video transcoding, we achieve 15% speed-up using in-order cores with in-cache computing when compared to a baseline in-order system and 76% energy savings when compared to an Out-of-Order system. When using HBM, we further accelerate real-time transcoding and CNNs by up to 7% and 8% respectively.

show abstract

Section: Methodsmentioning

confidence: 99%

Gem5-X: A Gem5-Based System Level Simulation Framework to Optimize Many-Core Platforms

Qureshi

Simon

Zapater

et al. 2019

2019 Spring Simulation Conference (SpringSim)

Self Cite

View full text Add to dashboard Cite

show abstract

“…We formulate our optimization problem in equations (4)- (7). Let S H and S V represent the set of hosts and VMs of the data center, respectively, with N and M denoting their number of members during the time period (t 1 ,t 2 ) correspondingly.…”

Section: Problem Formulation Of Host and Vm Managementmentioning

confidence: 99%

“…In this sense, the low power modes of recent servers, more efficient in terms of energy and transition overheads [6], allow further savings when compared to traditional switch-off techniques. However, given the variable nature of VMs loads, and energy and delay overheads of both migration and Power Mode Transitions (PMTs), dynamic consolidation may degrade QoS (and even increase overall energy consumption) if not effectively applied [7].…”

Section: Introductionmentioning

confidence: 99%

MAGNETIC: Multi-Agent Machine Learning-Based Approach for Energy Efficient Dynamic Consolidation in Data Centers

Haghshenas

Pahlevan

Zapater

et al. 2022

IEEE Trans. Serv. Comput.

Self Cite

View full text Add to dashboard Cite

Improving the energy efficiency of data centers while guaranteeing Quality of Service (QoS), together with detecting performance variability of servers caused by either hardware or software failures, are two of the major challenges for efficient resource management of large-scale cloud infrastructures. Previous works in the area of dynamic Virtual Machine (VM) consolidation are mostly focused on addressing the energy challenge, but fall short in proposing comprehensive, scalable, and low-overhead approaches that jointly tackle energy efficiency and performance variability. Moreover, they usually assume over-simplistic power models, and fail to accurately consider all the delay and power costs associated with VM migration and host power mode transition. These assumptions are no longer valid in modern servers executing heterogeneous workloads and lead to unrealistic or inefficient results. In this paper, we propose a centralized-distributed low-overhead failure-aware dynamic VM consolidation strategy to minimize energy consumption in large-scale data centers. Our approach selects the most adequate power mode and frequency of each host during runtime using a distributed multi-agent Machine Learning (ML) based strategy, and migrates the VMs accordingly using a centralized heuristic. Our Multi-AGent machine learNing-based approach for Energy efficienT dynamIc Consolidation (MAGNETIC) is implemented in a modified version of the CloudSim simulator, and considers the energy and delay overheads associated with host power mode transition and VM migration, and is evaluated using power traces collected from various workloads running in real servers and resource utilization logs from cloud data center infrastructures. Results show how our strategy reduces data center energy consumption by up to 15% compared to other works in the state-of-the-art (SoA), guaranteeing the same QoS and reducing the number of VM migrations and host power mode transitions by up to 86% and 90%, respectively. Moreover, it shows better scalability than all other approaches, taking less than 0.7% time overhead to execute for a data center with 1500 VMs. Finally, our solution is capable of detecting host performance variability due to failures, automatically migrating VMs from failing hosts and draining them from workload.

show abstract

“…For the energy efficiency and power assessment of the proposed architecture, 28 nm FD-SOI power models for ARMv8 in-order cores were used, as proposed by [29] and [30]. The power models include active core power, Wait-For-Memory (WFM) power, and the static core power.…”

Section: Power Modelsmentioning

confidence: 99%

A Product Engine for Energy-Efficient Execution of Binary Neural Networks Using Resistive Memories

Vieira

Giacomin

Qureshi

et al. 2019

2019 IFIP/IEEE 27th International Conference on Very Large Scale Integration (VLSI-SoC)

Self Cite

View full text Add to dashboard Cite

The need for running complex Machine Learning (ML) algorithms, such as Convolutional Neural Networks (CNNs), in edge devices, which are highly constrained in terms of computing power and energy, makes it important to execute such applications efficiently. The situation has led to the popularization of Binary Neural Networks (BNNs), which significantly reduce execution time and memory requirements by representing the weights (and possibly the data being operated) using only one bit. Because approximately 90% of the operations executed by CNNs and BNNs are convolutions, a significant part of the memory transfers consists of fetching the convolutional kernels. Such kernels are usually small (e.g., 3×3 operands), and particularly in BNNs redundancy is expected. Therefore, equal kernels can be mapped to the same memory addresses, requiring significantly less memory to store them. In this context, this paper presents a custom Binary Dot Product Engine (BDPE) for BNNs that exploits the features of Resistive Random-Access Memories (RRAMs). This new engine allows accelerating the execution of the inference phase of BNNs. The novel BDPE locally stores the most used binary weights and performs binary convolution using computing capabilities enabled by the RRAMs. The system-level gem5 architectural simulator was used together with a C-based ML framework to evaluate the system's performance and obtain power results. Results show that this novel BDPE improves performance by 11.3%, energy efficiency by 7.4% and reduces the number of memory accesses by 10.7% at a cost of less than 0.3% additional die area, when integrated with a 28 nm Fully Depleted Silicon On Insulator ARMv8 in-order core, in comparison to a fully-optimized baseline of YoloV3 XNOR-Net running in a unmodified Central Processing Unit.

show abstract

Energy proportionality in near-threshold computing servers and cloud data centers: Consolidating or Not?

Cited by 12 publications

References 17 publications

Gem5-X: A Gem5-Based System Level Simulation Framework to Optimize Many-Core Platforms

Gem5-X: A Gem5-Based System Level Simulation Framework to Optimize Many-Core Platforms

MAGNETIC: Multi-Agent Machine Learning-Based Approach for Energy Efficient Dynamic Consolidation in Data Centers

A Product Engine for Energy-Efficient Execution of Binary Neural Networks Using Resistive Memories

Contact Info

Product

Resources

About