Scaling - Revision history

Robert-schade-e757@uni-paderborn.de at 11:30, 19 July 2024

2024-07-19T11:30:52Z

Sebastian-potthoff-3c73@uni-muenster.de: Sebastian-potthoff-3c73@uni-muenster.de moved page Scaling tutorial to Scaling

2022-06-03T08:49:36Z

Sebastian-potthoff-3c73@uni-muenster.de moved page Scaling to Scaling

Sebastian-potthoff-3c73@uni-muenster.de: Remove from tutorials category

2022-06-03T08:48:13Z

Remove from tutorials category

Mukund-pondkule-6a11@uni-paderborn.de at 14:38, 1 December 2021

2021-12-01T14:38:22Z

Mukund-pondkule-6a11@uni-paderborn.de at 14:37, 1 December 2021

2021-12-01T14:37:24Z

Robert-schade-e757@uni-paderborn.de at 20:08, 21 October 2020

2020-10-21T20:08:47Z

Mukund-pondkule-6a11@uni-paderborn.de at 15:53, 23 September 2020

2020-09-23T15:53:11Z

Mukund-pondkule-6a11@uni-paderborn.de: /* Weak Scaling */

2020-09-21T16:53:32Z

Weak Scaling

Mukund-pondkule-6a11@uni-paderborn.de: /* Strong Scaling */

2020-09-21T16:53:07Z

Strong Scaling

Mukund-pondkule-6a11@uni-paderborn.de: /* Weak Scaling */

2020-09-21T16:52:41Z

Weak Scaling

@@ Line 1: / Line 1: @@
 [[Category:HPC-User]]
 In the most general sense, '''scalability''' is defined as the ability to handle more work as the size of the computer or application grows. '''scalability''' or '''scaling''' is widely used to indicate the ability of hardware and software to deliver greater computational power when the amount of resources is increased. For HPC clusters, it is important that they are '''scalable''', in other words the capacity of the whole system can be proportionally increased by adding more hardware. For software, '''scalability''' is sometimes referred to as parallelization efficiency — the ratio between the actual speedup and the ideal speedup obtained when using a certain number of processors. For this tutorial, we focus on software scalability and discuss two common types of scaling. The speedup in parallel computing can be straightforwardly defined as
                                                                           {{Box|<math> Speedup = t(1) / t(N) </math>}}

← Older revision		Revision as of 08:48, 3 June 2022
Line 1:		Line 1:
−	~~[[Category:Tutorials]] [[Category:Basics]]~~
−	~~[[Category:Tutorials \| Scaling Tutorial]]~~
	[[Category:HPC-User]]		[[Category:HPC-User]]
	In the most general sense, '''scalability''' is defined as the ability to handle more work as the size of the computer or application grows. '''scalability''' or '''scaling''' is widely used to indicate the ability of hardware and software to deliver greater computational power when the amount of resources is increased. For HPC clusters, it is important that they are '''scalable''', in other words the capacity of the whole system can be proportionally increased by adding more hardware. For software, '''scalability''' is sometimes referred to as parallelization efficiency — the ratio between the actual speedup and the ideal speedup obtained when using a certain number of processors. For this tutorial, we focus on software scalability and discuss two common types of scaling. The speedup in parallel computing can be straightforwardly defined as		In the most general sense, '''scalability''' is defined as the ability to handle more work as the size of the computer or application grows. '''scalability''' or '''scaling''' is widely used to indicate the ability of hardware and software to deliver greater computational power when the amount of resources is increased. For HPC clusters, it is important that they are '''scalable''', in other words the capacity of the whole system can be proportionally increased by adding more hardware. For software, '''scalability''' is sometimes referred to as parallelization efficiency — the ratio between the actual speedup and the ideal speedup obtained when using a certain number of processors. For this tutorial, we focus on software scalability and discuss two common types of scaling. The speedup in parallel computing can be straightforwardly defined as

@@ Line 3: / Line 3: @@
 [[Category:HPC-User]]
 In the most general sense, '''scalability''' is defined as the ability to handle more work as the size of the computer or application grows. '''scalability''' or '''scaling''' is widely used to indicate the ability of hardware and software to deliver greater computational power when the amount of resources is increased. For HPC clusters, it is important that they are '''scalable''', in other words the capacity of the whole system can be proportionally increased by adding more hardware. For software, '''scalability''' is sometimes referred to as parallelization efficiency — the ratio between the actual speedup and the ideal speedup obtained when using a certain number of processors. For this tutorial, we focus on software scalability and discuss two common types of scaling. The speedup in parallel computing can be straightforwardly defined as
-                                                                          {{Box|<math>Speedup = t(1) / t(N)</math>}}
+                                                                          {{Box|<math> Speedup = t(1) / t(N) </math>}}
 where '''t(1)''' is the computational time for running the software using one processor, and '''t(N)''' is the computational time running the same software with N processors. Ideally, we would like software to have a linear speedup that is equal to the number of processors (speedup = N), as that would mean that every processor would be contributing 100% of its computational power. Unfortunately, this is a very challenging goal for real world applications to attain.

@@ Line 3: / Line 3: @@
 [[Category:HPC-User]]
 In the most general sense, '''scalability''' is defined as the ability to handle more work as the size of the computer or application grows. '''scalability''' or '''scaling''' is widely used to indicate the ability of hardware and software to deliver greater computational power when the amount of resources is increased. For HPC clusters, it is important that they are '''scalable''', in other words the capacity of the whole system can be proportionally increased by adding more hardware. For software, '''scalability''' is sometimes referred to as parallelization efficiency — the ratio between the actual speedup and the ideal speedup obtained when using a certain number of processors. For this tutorial, we focus on software scalability and discuss two common types of scaling. The speedup in parallel computing can be straightforwardly defined as
-                                                                          {{Box|<math> Speedup = t(1) / t(N) </math>}}
+                                                                          {{Box|<math>Speedup = t(1) / t(N)</math>}}
 where '''t(1)''' is the computational time for running the software using one processor, and '''t(N)''' is the computational time running the same software with N processors. Ideally, we would like software to have a linear speedup that is equal to the number of processors (speedup = N), as that would mean that every processor would be contributing 100% of its computational power. Unfortunately, this is a very challenging goal for real world applications to attain.

← Older revision		Revision as of 20:08, 21 October 2020
Line 1:		Line 1:
		+	[[Category:Tutorials]] [[Category:Basics]]
		+	[[Category:Tutorials \| Scaling Tutorial]]
	[[Category:HPC-User]]		[[Category:HPC-User]]
	In the most general sense, '''scalability''' is defined as the ability to handle more work as the size of the computer or application grows. '''scalability''' or '''scaling''' is widely used to indicate the ability of hardware and software to deliver greater computational power when the amount of resources is increased. For HPC clusters, it is important that they are '''scalable''', in other words the capacity of the whole system can be proportionally increased by adding more hardware. For software, '''scalability''' is sometimes referred to as parallelization efficiency — the ratio between the actual speedup and the ideal speedup obtained when using a certain number of processors. For this tutorial, we focus on software scalability and discuss two common types of scaling. The speedup in parallel computing can be straightforwardly defined as		In the most general sense, '''scalability''' is defined as the ability to handle more work as the size of the computer or application grows. '''scalability''' or '''scaling''' is widely used to indicate the ability of hardware and software to deliver greater computational power when the amount of resources is increased. For HPC clusters, it is important that they are '''scalable''', in other words the capacity of the whole system can be proportionally increased by adding more hardware. For software, '''scalability''' is sometimes referred to as parallelization efficiency — the ratio between the actual speedup and the ideal speedup obtained when using a certain number of processors. For this tutorial, we focus on software scalability and discuss two common types of scaling. The speedup in parallel computing can be straightforwardly defined as

← Older revision	Revision as of 08:49, 3 June 2022
(No difference)

← Older revision		Revision as of 16:53, 21 September 2020
Line 189:		Line 189:


−	<span style="color:red"> '''Note: Due to low Efficiency we haven’t plotted the row with 2048 processors but it is given for your reference to indicate the trend of decreasing efficiency.''' </span>	+	<span style="color:red"> '''Note: Due to low Efficiency we haven’t plotted the row with 2048 processors but it is given for your reference to indicate the trend of decreasing efficiency.''' </span>

	<gallery mode="packed" heights="400" perrow="1">		<gallery mode="packed" heights="400" perrow="1">

← Older revision		Revision as of 16:53, 21 September 2020
Line 138:		Line 138:


−	<span style="color:red"> '''Note: Due to bad Speedup we haven’t plotted the row with 2048 processors but it is given for your reference to indicate the trend of decreasing speedup.''' </span>	+	<span style="color:red"> '''Note: Due to bad Speedup we haven’t plotted the row with 2048 processors but it is given for your reference to indicate the trend of decreasing speedup.''' </span>

	<gallery mode="packed" heights="400" perrow="1">		<gallery mode="packed" heights="400" perrow="1">

← Older revision		Revision as of 16:52, 21 September 2020
Line 189:		Line 189:


−	<span style="color:red"> '''Note: Due to low Efficiency we haven’t plotted the row with 2048 processors but it is given for your reference to indicate the trend of decreasing efficiency.''' </span>	+	<span style="color:red"> '''Note: Due to low Efficiency we haven’t plotted the row with 2048 processors but it is given for your reference to indicate the trend of decreasing efficiency.''' </span>

	<gallery mode="packed" heights="400" perrow="1">		<gallery mode="packed" heights="400" perrow="1">