Grant: Subatomic Physics Envelope - Individual
University of Victoria
$22,000.00
Reducing the environmental impact and power requirements of SAP computing
EF 2024-25
Résumé
The high energy physics (HEP) community is facing daunting computing and storage challenges in this decade as new facilities such as the high-luminosity Large Hadron Collider (LHC) and the high-intensity B-factory at the KEK Laboratory in Japan will deliver unprecedented amounts of data. At the same time, there is an increasing need to reduce the environmental impact of our field in all areas including the accelerator complexes, the detectors, the computing and even the travel. Globally, computing has carbon emissions equivalent to the aviation industry and is increasingly becoming a visible source of C02. Hence, is it critical that we develop solutions that allows to us reduce our emissions.
Although reducing the carbon footprint of our computing is a key goal, reducing the overall power consumption is also important considering the current political instabilities in Eastern Europe that have significantly increased the cost of electricity and raised concerns about the reliability of existing power grids.
There are several ways to reduce the carbon emissions and the power consumption of our computing. This includes building new highly efficient data centers and using power from renewable energy sources. More recently, we have found that we can lower our power consumption by using the low-power computing technologies commonly used in cell phones and laptops, or by expanding our use of graphical processors units (GPUs). And, as it has been highlighted in recent publications, we also need to write energy-efficient software.
To utilize low-power computing technologies and GPUs or write more efficient software, we need to develop tools that will help us make measurements to identify the optimal solutions. Our group at the Univ of Victoria, as part of an international team, has developed a new CPU benchmark called HEPScore, that is based on particle physics applications and has become the new standard for pledges and accounting of LHC computing resources. The HEPScore benchmark was used to show that low-power processors have the same processing capabilities while using significantly less power. In addition, our team is planning to measure the power consumption of a server while it is running the HEPScore benchmark and estimate the carbon footprint of a particle physics application.
Our team has been asked by the Worldwide Large Hadron Collider Grid (WLCG) Management Board to create a CPU+GPU benchmark as these systems are increasingly being used in our experiments. It is being shown by many experiments that CPU+GPU systems can significantly reduce the computation (and environmental impact) for selected applications.
The outcome of our research will be a system that will measure the CPU performance, power consumption and energy footprint of servers and particle physics applications. This will help our community make informed decisions to reduce its environmental impact and support the transition to a more sustainable, low-carbon economy.
Programme
Subatomic Physics Envelope - Individual
Bénéficiaire
Emplacement
British Columbia, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
SAPIN-2024-00039
Name nom
Sobie, Randall
Department département
Physics and Astronomy - Physics and Astronomy
Organization id
7
Institution établissement
University of Victoria
Province en
British Columbia
Province fr
Colombie-Britannique
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2024
Competition year année de concours
2024
Award amount
22000
Program id
SAPIN
Program name en
Subatomic Physics Envelope - Individual
Program name fr
Enveloppe de physique subatomique - Individuelles
Group en
DISCOVERY RESEARCH
Group fr
RECHERCHE AXÉE SUR LA DÉCOUVERTE
Committee code
19
Committee name en
Subatomic Physics
Committee name fr
Physique subatomique
Area of application code
1202
Area of application group en
Advancement of knowledge
Area of application group fr
Avancement des connaissances
Area of application en
Physical sciences
Area of application fr
Sciences physiques
Research subject code
3100
Research subject group en
Physics
Research subject group fr
Physique
Research subject en
Physics
Research subject fr
Physique
Field of research list names en
Not available
Field of research list names fr
Non disponible
Socioeconomic objective list names en
Not available
Socioeconomic objective list names fr
Non disponible
Application title
Reducing the environmental impact and power requirements of SAP computing
Keywords
particle physics; computing; cloud computing; big data; software
Application summary
The high energy physics (HEP) community is facing daunting computing and storage challenges in this decade as new facilities such as the high-luminosity Large Hadron Collider (LHC) and the high-intensity B-factory at the KEK Laboratory in Japan will deliver unprecedented amounts of data. At the same time, there is an increasing need to reduce the environmental impact of our field in all areas including the accelerator complexes, the detectors, the computing and even the travel. Globally, computing has carbon emissions equivalent to the aviation industry and is increasingly becoming a visible source of C02. Hence, is it critical that we develop solutions that allows to us reduce our emissions.
Although reducing the carbon footprint of our computing is a key goal, reducing the overall power consumption is also important considering the current political instabilities in Eastern Europe that have significantly increased the cost of electricity and raised concerns about the reliability of existing power grids.
There are several ways to reduce the carbon emissions and the power consumption of our computing. This includes building new highly efficient data centers and using power from renewable energy sources. More recently, we have found that we can lower our power consumption by using the low-power computing technologies commonly used in cell phones and laptops, or by expanding our use of graphical processors units (GPUs). And, as it has been highlighted in recent publications, we also need to write energy-efficient software.
To utilize low-power computing technologies and GPUs or write more efficient software, we need to develop tools that will help us make measurements to identify the optimal solutions. Our group at the Univ of Victoria, as part of an international team, has developed a new CPU benchmark called HEPScore, that is based on particle physics applications and has become the new standard for pledges and accounting of LHC computing resources. The HEPScore benchmark was used to show that low-power processors have the same processing capabilities while using significantly less power. In addition, our team is planning to measure the power consumption of a server while it is running the HEPScore benchmark and estimate the carbon footprint of a particle physics application.
Our team has been asked by the Worldwide Large Hadron Collider Grid (WLCG) Management Board to create a CPU+GPU benchmark as these systems are increasingly being used in our experiments. It is being shown by many experiments that CPU+GPU systems can significantly reduce the computation (and environmental impact) for selected applications.
The outcome of our research will be a system that will measure the CPU performance, power consumption and energy footprint of servers and particle physics applications. This will help our community make informed decisions to reduce its environmental impact and support the transition to a more sustainable, low-carbon economy.