Methods and Metrics for Fair Server Assessment under Real-Time Financial Workloads

Giorgis Georgakoudis, Charles J. Gillan, Ahmed Sayed, Ivor Spence, Richard Faloon, Dimitrios S. Nikolopoulos

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

We present a rigorous methodology and new metrics for fair comparison of server and microserver platforms. Deploying our methodology and metrics, we compare a microserver with ARM cores against two servers with ×86 cores running the same real-time financial analytics workload. We define workload-specific but platform-independent performance metrics for platform comparison, targeting both datacenter operators and end users. Our methodology establishes that a server based on the Xeon Phi co-processor delivers the highest performance and energy efficiency. However, by scaling out energy-efficient microservers, we achieve competitive or better energy efficiency than a power-equivalent server with two Sandy Bridge sockets, despite the microserver's slower cores. Using a new iso-QoS metric, we find that the ARM microserver scales enough to meet market throughput demand, that is, a 100% QoS in terms of timely option pricing, with as little as 55% of the energy consumed by the Sandy Bridge server.
LanguageEnglish
Pages916-928
Number of pages13
JournalConcurrency and Computation: Practice and Experience
Volume28
Issue number3
Early online date13 Oct 2015
DOIs
Publication statusPublished - 10 Mar 2016

Fingerprint

Workload
Servers
Server
Real-time
Metric
Energy Efficiency
Energy efficiency
Methodology
Quality of service
Option Pricing
Performance Metrics
Energy Efficient
High Energy
Throughput
High Performance
Scaling
Operator
Energy
Costs

Cite this

@article{ad1bd24c4dae4c8ca9d708fdee1b2079,
title = "Methods and Metrics for Fair Server Assessment under Real-Time Financial Workloads",
abstract = "We present a rigorous methodology and new metrics for fair comparison of server and microserver platforms. Deploying our methodology and metrics, we compare a microserver with ARM cores against two servers with ×86 cores running the same real-time financial analytics workload. We define workload-specific but platform-independent performance metrics for platform comparison, targeting both datacenter operators and end users. Our methodology establishes that a server based on the Xeon Phi co-processor delivers the highest performance and energy efficiency. However, by scaling out energy-efficient microservers, we achieve competitive or better energy efficiency than a power-equivalent server with two Sandy Bridge sockets, despite the microserver's slower cores. Using a new iso-QoS metric, we find that the ARM microserver scales enough to meet market throughput demand, that is, a 100{\%} QoS in terms of timely option pricing, with as little as 55{\%} of the energy consumed by the Sandy Bridge server.",
author = "Giorgis Georgakoudis and Gillan, {Charles J.} and Ahmed Sayed and Ivor Spence and Richard Faloon and Nikolopoulos, {Dimitrios S.}",
year = "2016",
month = "3",
day = "10",
doi = "10.1002/cpe.3704",
language = "English",
volume = "28",
pages = "916--928",
journal = "Concurrency and Computation: Practice and Experience",
issn = "1532-0626",
publisher = "John Wiley and Sons Ltd",
number = "3",

}

Methods and Metrics for Fair Server Assessment under Real-Time Financial Workloads. / Georgakoudis, Giorgis; Gillan, Charles J.; Sayed, Ahmed; Spence, Ivor; Faloon, Richard; Nikolopoulos, Dimitrios S.

In: Concurrency and Computation: Practice and Experience, Vol. 28, No. 3, 10.03.2016, p. 916-928.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Methods and Metrics for Fair Server Assessment under Real-Time Financial Workloads

AU - Georgakoudis, Giorgis

AU - Gillan, Charles J.

AU - Sayed, Ahmed

AU - Spence, Ivor

AU - Faloon, Richard

AU - Nikolopoulos, Dimitrios S.

PY - 2016/3/10

Y1 - 2016/3/10

N2 - We present a rigorous methodology and new metrics for fair comparison of server and microserver platforms. Deploying our methodology and metrics, we compare a microserver with ARM cores against two servers with ×86 cores running the same real-time financial analytics workload. We define workload-specific but platform-independent performance metrics for platform comparison, targeting both datacenter operators and end users. Our methodology establishes that a server based on the Xeon Phi co-processor delivers the highest performance and energy efficiency. However, by scaling out energy-efficient microservers, we achieve competitive or better energy efficiency than a power-equivalent server with two Sandy Bridge sockets, despite the microserver's slower cores. Using a new iso-QoS metric, we find that the ARM microserver scales enough to meet market throughput demand, that is, a 100% QoS in terms of timely option pricing, with as little as 55% of the energy consumed by the Sandy Bridge server.

AB - We present a rigorous methodology and new metrics for fair comparison of server and microserver platforms. Deploying our methodology and metrics, we compare a microserver with ARM cores against two servers with ×86 cores running the same real-time financial analytics workload. We define workload-specific but platform-independent performance metrics for platform comparison, targeting both datacenter operators and end users. Our methodology establishes that a server based on the Xeon Phi co-processor delivers the highest performance and energy efficiency. However, by scaling out energy-efficient microservers, we achieve competitive or better energy efficiency than a power-equivalent server with two Sandy Bridge sockets, despite the microserver's slower cores. Using a new iso-QoS metric, we find that the ARM microserver scales enough to meet market throughput demand, that is, a 100% QoS in terms of timely option pricing, with as little as 55% of the energy consumed by the Sandy Bridge server.

U2 - 10.1002/cpe.3704

DO - 10.1002/cpe.3704

M3 - Article

VL - 28

SP - 916

EP - 928

JO - Concurrency and Computation: Practice and Experience

T2 - Concurrency and Computation: Practice and Experience

JF - Concurrency and Computation: Practice and Experience

SN - 1532-0626

IS - 3

ER -