Energy Efficient Cluster Usage - Revision history

A Flachmueller: /* What do I want to do and why do I need an HPC Cluster for it? */

2026-04-22T10:35:53Z

What do I want to do and why do I need an HPC Cluster for it?

← Older revision		Revision as of 12:35, 22 April 2026
Line 24:		Line 24:
	Please consider testing new setups and their output for validity prior to submitting jobs that require lots of resources. This also includes projects where a lot of (smaller) similar jobs are submitted.		Please consider testing new setups and their output for validity prior to submitting jobs that require lots of resources. This also includes projects where a lot of (smaller) similar jobs are submitted.

	Make sure to double-check your jobs prior to the submission, having to discard the output data of an HPC project due to faulty input files is wasting a lot of computational resources.		Make sure to double-check your jobs prior to the submission, as having to discard the output data of an HPC project due to faulty input files is wasting a lot of computational resources.

⚫	Finally, identifying the specific resource requirements for a given job is important to allocate the optimal your compute job, and to decide if an HPC cluster is needed at all.

		⚫	Finally, identifying the specific resource requirements for a given job is important to allocate the optimal amount for your compute job, and to decide if an HPC cluster is needed at all.

	= How many and which kind of hardware resources do I require for it =		= How many and which kind of hardware resources do I require for it =

A Flachmueller: /* Introduction */

2026-04-22T10:30:03Z

Introduction

← Older revision		Revision as of 12:30, 22 April 2026
Line 6:		Line 6:
	Assuming that a typical bwHPC cluster has a few hundred compute nodes, this amounts to the energy consumption of a village for each cluster.		Assuming that a typical bwHPC cluster has a few hundred compute nodes, this amounts to the energy consumption of a village for each cluster.

	Although a large amount of this energy consumption is an intrinsic requirement of running large HPC clusters (even when ~~ist~~ processors are idle, a cluster uses a lot of energy), efficient use of the available resources is important. Using as many resources as possible does not make a power user. Using them wisely does.		Although a large amount of this energy consumption is an intrinsic requirement of running large HPC clusters (even when it's processors are idle, a cluster uses a lot of energy), efficient use of the available resources is important. Using as many resources as possible does not make a power user. Using them wisely does.
	In the following, a basic introduction to some of the most important aspects of energy-efficient HPC usage from a user perspective is given.		In the following, a basic introduction to some of the most important aspects of energy-efficient HPC usage from a user perspective is given.

H Schumacher: fixed link

2026-04-13T08:20:19Z

fixed link

← Older revision		Revision as of 10:20, 13 April 2026
Line 63:		Line 63:
	→ Handling via the scheduler is inefficient.		→ Handling via the scheduler is inefficient.

	→ Simple parallelization by hand is advisable. See: A basic introduction to [[Parallel Programming]].		→ Simple parallelization by hand is advisable. See: A basic introduction to [[Development/Parallel_Programming \| Parallel Programming]].

	= How do I optimize my code to use these resources most efficiently? =		= How do I optimize my code to use these resources most efficiently? =

J Steuer: /* How many and which kind of hardware resources do I require for it */

2023-08-21T11:58:23Z

How many and which kind of hardware resources do I require for it

← Older revision		Revision as of 13:58, 21 August 2023
Line 35:		Line 35:
	As this is dependent on both the job as well as the specific cluster hardware and architecture available.		As this is dependent on both the job as well as the specific cluster hardware and architecture available.

			'''

	A small number of jobs and few resources		A small number of jobs and few resources'''

	→ Submit to the scheduler. No extended testing and resource scaling analysis are needed.		→ Submit to the scheduler. No extended testing and resource scaling analysis are needed.

			'''

	Medium-sized projects		Medium-sized projects'''

	→ Run only necessary jobs: Please consider testing new setups and their output for validity prior to submitting a huge amount of similar jobs		→ Run only necessary jobs: Please consider testing new setups and their output for validity prior to submitting a huge amount of similar jobs
Line 52:		Line 52:


	Large projects		'''Large projects'''

	→ Same approach as for medium-sized projects.		→ Same approach as for medium-sized projects.
Line 59:		Line 59:


	Many short jobs		'''Many short jobs'''

	→ Handling via the scheduler is inefficient.		→ Handling via the scheduler is inefficient.

J Steuer: /* How many and which kind of hardware resources do I require for it */

2023-08-21T11:57:58Z

How many and which kind of hardware resources do I require for it

← Older revision		Revision as of 13:57, 21 August 2023
Line 34:		Line 34:
	Resource allocation is a crucial part when working on an HPC cluster.		Resource allocation is a crucial part when working on an HPC cluster.
	As this is dependent on both the job as well as the specific cluster hardware and architecture available.		As this is dependent on both the job as well as the specific cluster hardware and architecture available.


	A small number of jobs and few resources		A small number of jobs and few resources

	* Submit to the scheduler. No extended testing and resource scaling analysis are needed.		→ Submit to the scheduler. No extended testing and resource scaling analysis are needed.


	Medium-sized projects		Medium-sized projects

	* Run only necessary jobs: Please consider testing new setups and their output for validity prior to submitting a huge amount of similar jobs		→ Run only necessary jobs: Please consider testing new setups and their output for validity prior to submitting a huge amount of similar jobs
⚫	* Start small: Run your problem on a small set of resources first.

⚫	* Use the proper tools for development: If you develop your own code, please use the proper tools for debugging and parallel performance analysis. See: [[Development#Documentation_in_the_Wiki\|Development]].
		⚫	→ Start small: Run your problem on a small set of resources first.
⚫	* A look at the job feedback can help you determine if you are using the cluster efficiently

		⚫	→ Use the proper tools for development: If you develop your own code, please use the proper tools for debugging and parallel performance analysis. See: [[Development#Documentation_in_the_Wiki\|Development]].

		⚫	→ A look at the job feedback can help you determine if you are using the cluster efficiently


	Large projects		Large projects

	* Same approach as for medium-sized projects.		→ Same approach as for medium-sized projects.
⚫	* Run a scaling analysis for your project with regard to how many resources work best. See: [[Scaling]].

		⚫	→ Run a scaling analysis for your project with regard to how many resources work best. See: [[Scaling]].


	Many short jobs		Many short jobs

	* Handling via the scheduler is inefficient.		→ Handling via the scheduler is inefficient.
⚫	* Simple parallelization by hand is advisable. See: A basic introduction to [[Parallel Programming]].

		⚫	→ Simple parallelization by hand is advisable. See: A basic introduction to [[Parallel Programming]].

	= How do I optimize my code to use these resources most efficiently? =		= How do I optimize my code to use these resources most efficiently? =

J Steuer: /* How do I optimize my code to use these resources most efficiently? */

2023-08-21T11:57:20Z

How do I optimize my code to use these resources most efficiently?

← Older revision		Revision as of 13:57, 21 August 2023
Line 58:		Line 58:

	Here, we have gathered a few results based on other research:		Here, we have gathered a few results based on other research:
	* Use an efficient programming language such as Rust, C, and C++ -- well any compiled language. Do not use any interpreted language like Perl or Python. Since Machine Learning is a hot topic, this deserves a few words: Any ML-Python code using Tensorflow or other libraries will make heavy usage of NumPy and other math packages, which will use C-based implementations. Please make sure, you use the provided Python modules, which are optimized to use Intel MKL and other mathematical libraries.		→ Use an efficient programming language such as Rust, C, and C++ -- well any compiled language. Do not use any interpreted language like Perl or Python. Since Machine Learning is a hot topic, this deserves a few words: Any ML-Python code using Tensorflow or other libraries will make heavy usage of NumPy and other math packages, which will use C-based implementations. Please make sure, you use the provided Python modules, which are optimized to use Intel MKL and other mathematical libraries.

	Further reading:		Further reading:
	Rui Pereira, et al: "''Energy efficiency across programming languages: how do energy, time, and memory relate?''", SLE 2017: Proc. of the 10th ACM SIGPLAN Int. Conf. on SW Language Eng., Oct. 2017, pp. 256–267, [https://doi.org/10.1145/3136014.3136031 doi:10.1145/3136014.3136031]		Rui Pereira, et al: "''Energy efficiency across programming languages: how do energy, time, and memory relate?''", SLE 2017: Proc. of the 10th ACM SIGPLAN Int. Conf. on SW Language Eng., Oct. 2017, pp. 256–267, [https://doi.org/10.1145/3136014.3136031 doi:10.1145/3136014.3136031]

	* Analyse memory access patterns		→ Analyse memory access patterns

	* For small tight loops checking for locks, use the <code>pause</code> instruction.		→ For small tight loops checking for locks, use the <code>pause</code> instruction.

	= Summary: General Recommendations =		= Summary: General Recommendations =

J Steuer: /* Introduction */

2023-08-21T11:57:05Z

Introduction

← Older revision		Revision as of 13:57, 21 August 2023
Line 11:		Line 11:
	We can generally distinguish three tasks when optimizing for running HPC jobs efficiently.		We can generally distinguish three tasks when optimizing for running HPC jobs efficiently.

	* What do I want to do and why do I need an HPC Cluster for it?		→ What do I want to do and why do I need an HPC Cluster for it?

	* How many and which kind of hardware resources do I require for it?		→ How many and which kind of hardware resources do I require for it?
⚫	* How do I optimize my code to use these resources most efficiently?

		⚫	→ How do I optimize my code to use these resources most efficiently?

	= What do I want to do and why do I need an HPC Cluster for it? =		= What do I want to do and why do I need an HPC Cluster for it? =

J Steuer: /* Introduction */

2023-07-04T11:15:46Z

Introduction

← Older revision		Revision as of 13:15, 4 July 2023
Line 1:		Line 1:
	= Introduction =		= Introduction =


	Energy consumption of data centers has been increasing continuously throughout the last decade. In 2020, the energy consumption of all data centers in Germany amounted to around [https://www.bundestag.de/resource/blob/863850/423c11968fcb5c9995e9ef9090edf9e6/WD-8-070-21-pdf-data.pdf 3 percent] of the total electricity produced. Accompanying this large energy consumption are large-scale emissions of CO2 to the atmosphere and thus significant contributions to climate change.		Energy consumption of data centers has been increasing continuously throughout the last decade. In 2020, the energy consumption of all data centers in Germany amounted to around [https://www.bundestag.de/resource/blob/863850/423c11968fcb5c9995e9ef9090edf9e6/WD-8-070-21-pdf-data.pdf 3 percent] of the total electricity produced. Accompanying this large energy consumption are large-scale emissions of CO2 to the atmosphere and thus significant contributions to climate change.
	To illustrate this, an average compute job running on a single node for one day may easily consume 10 kWh or even more. That translates roughly to brewing 700 cups of coffee.		To illustrate this, an average compute job running on a single node for one day may easily consume 10 kWh or even more. That translates roughly to brewing 700 cups of coffee.

	Assuming that a typical bwHPC cluster has a few hundred compute nodes, this amounts to the energy consumption of a village for each cluster.		Assuming that a typical bwHPC cluster has a few hundred compute nodes, this amounts to the energy consumption of a village for each cluster.

	Using as many resources as possible does not make a power user. Using them wisely does~~. If in doubt, just ask~~.		Although a large amount of this energy consumption is an intrinsic requirement of running large HPC clusters (even when ist processors are idle, a cluster uses a lot of energy), efficient use of the available resources is important. Using as many resources as possible does not make a power user. Using them wisely does.

	Although a large amount of this energy consumption is an intrinsic requirement of running large HPC clusters (even when ist processors are idle, a cluster uses a lot of energy), efficient use of the available resources is important.
	In the following, a basic introduction to some of the most important aspects of energy-efficient HPC usage from a user perspective is given.		In the following, a basic introduction to some of the most important aspects of energy-efficient HPC usage from a user perspective is given.
	References to further reading are given as both, the range of scientific projects as well as the differences between the HPC clusters are too large to warrant an exhaustive discussion of this topic here.


	We can generally distinguish three tasks when optimizing for running HPC jobs efficiently.		We can generally distinguish three tasks when optimizing for running HPC jobs efficiently.
Line 18:		Line 14:
	* How many and which kind of hardware resources do I require for it?		* How many and which kind of hardware resources do I require for it?
	* How do I optimize my code to use these resources most efficiently?		* How do I optimize my code to use these resources most efficiently?

	In the following, a short summary of how these questions should typically be addressed is given.

	= What do I want to do and why do I need an HPC Cluster for it? =		= What do I want to do and why do I need an HPC Cluster for it? =

J Steuer: /* Introduction */

2023-06-06T08:19:16Z

Introduction

← Older revision		Revision as of 10:19, 6 June 2023
Line 2:		Line 2:

	Energy consumption of data centers has been increasing continuously throughout the last decade. In 2020, the energy consumption of all data centers in Germany amounted to around [https://www.bundestag.de/resource/blob/863850/423c11968fcb5c9995e9ef9090edf9e6/WD-8-070-21-pdf-data.pdf 3 percent] of the total electricity produced. Accompanying this large energy consumption are large-scale emissions of CO2 to the atmosphere and thus significant contributions to climate change.		Energy consumption of data centers has been increasing continuously throughout the last decade. In 2020, the energy consumption of all data centers in Germany amounted to around [https://www.bundestag.de/resource/blob/863850/423c11968fcb5c9995e9ef9090edf9e6/WD-8-070-21-pdf-data.pdf 3 percent] of the total electricity produced. Accompanying this large energy consumption are large-scale emissions of CO2 to the atmosphere and thus significant contributions to climate change.
	To illustrate this, an average compute job running on a single node for one day may easily consume 10 kWh or even more. That translates roughly to ~~one~~ of ~~the~~ ~~following activities:~~		To illustrate this, an average compute job running on a single node for one day may easily consume 10 kWh or even more. That translates roughly to brewing 700 cups of coffee.
	* toasting about 1330 slices of toast in a toaster
	* continuously blow-drying your hair for about 10 hours
	* actively working on a laptop for about 500 hours
	* brewing 700 cups of coffee

	Assuming that a typical bwHPC cluster has a few hundred compute nodes, this amounts to the energy consumption of a village for each cluster.		Assuming that a typical bwHPC cluster has a few hundred compute nodes, this amounts to the energy consumption of a village for each cluster.
Line 24:		Line 20:

	In the following, a short summary of how these questions should typically be addressed is given.		In the following, a short summary of how these questions should typically be addressed is given.


	= What do I want to do and why do I need an HPC Cluster for it? =		= What do I want to do and why do I need an HPC Cluster for it? =

K Siegmund: /* How many and which kind of hardware resources do I require for it */

2023-06-06T08:17:28Z

How many and which kind of hardware resources do I require for it

← Older revision		Revision as of 10:17, 6 June 2023
Line 50:		Line 50:
	* Run only necessary jobs: Please consider testing new setups and their output for validity prior to submitting a huge amount of similar jobs		* Run only necessary jobs: Please consider testing new setups and their output for validity prior to submitting a huge amount of similar jobs
	* Start small: Run your problem on a small set of resources first.		* Start small: Run your problem on a small set of resources first.
	* Use the proper tools for development: If you develop your own code, please use the proper tools for debugging and parallel performance analysis. ~~More information is available on the~~ [~~https://wiki.bwhpc.de/e/~~Development#Documentation_in_the_Wiki ~~bwHPC Wiki~~].		* Use the proper tools for development: If you develop your own code, please use the proper tools for debugging and parallel performance analysis. See: [[Development#Documentation_in_the_Wiki\|Development]].
	* A look at the job feedback can help you determine if you are using the cluster efficiently		* A look at the job feedback can help you determine if you are using the cluster efficiently

	Large projects		Large projects
	* Same approach as for medium-sized projects.		* Same approach as for medium-sized projects.
	* Run a scaling analysis for your project with regard to how many resources work best. ~~An introduction to how to do this can be found on the~~ [~~https://wiki.bwhpc.de/e/~~Scaling ~~bwHPC wiki~~].		* Run a scaling analysis for your project with regard to how many resources work best. See: [[Scaling]].

	Many short jobs		Many short jobs
	* Handling via the scheduler is inefficient.		* Handling via the scheduler is inefficient.
	* Simple parallelization by hand is advisable. A basic introduction to ~~how to parallelize your own code can be found on the~~ [~~https://wiki.bwhpc.de/e/Development/Parallel_Programming bwHPC~~ ~~wiki~~].		* Simple parallelization by hand is advisable. See: A basic introduction to [[Parallel Programming]].

	= How do I optimize my code to use these resources most efficiently? =		= How do I optimize my code to use these resources most efficiently? =