Choosing a computing resource - Revision history

Pmallik22 at 19:40, 9 November 2025

2025-11-09T19:40:37Z

← Older revision		Revision as of 19:40, 9 November 2025
Line 43:		Line 43:
	A GPU can perform some specific computations, such as vector arithmetic, extremely quickly relative to a CPU. This is important in (for example) rendering video game animations. Many problems in the natural and computational sciences also require such calculations, hence the development of GPGPUs. Demand for their use may increase as data science and machine learning continue to grow.		A GPU can perform some specific computations, such as vector arithmetic, extremely quickly relative to a CPU. This is important in (for example) rendering video game animations. Many problems in the natural and computational sciences also require such calculations, hence the development of GPGPUs. Demand for their use may increase as data science and machine learning continue to grow.

	Our NVIDIA GPGPUs (and associated drivers) are installed to the Faraday cluster. To program using ~~GPGPU's~~, load CUDA ([[CUDA\|read more about CUDA here]]) on the Farday cluster. Happy coding.		Our NVIDIA GPGPUs (and associated drivers) are installed to the Faraday cluster. To program using GPGPUs, load CUDA ([[CUDA\|read more about CUDA here]]) on the Farday cluster. Happy coding.

			You can also code on Jupyter notebooks on Faraday through [https://jupyter.cluster.earlham.edu jupyter.cluster.earlham.edu], which is distinct from [https://jupyter.cs.earlham.edu jupyter.cs.earlham.edu], which does not have GPGPUs.

	=== High-performance computing, including scientific and research computing ===		=== High-performance computing, including scientific and research computing ===
Line 81:		Line 83:
	On [https://code.cs.earlham.edu GitLab], you will find a series of bits of example code, mostly 'hello world' code to verify that you have successfully submitted and run a job on the correct resources.		On [https://code.cs.earlham.edu GitLab], you will find a series of bits of example code, mostly 'hello world' code to verify that you have successfully submitted and run a job on the correct resources.

	Tested and working ~~2022~~		Tested and working November 2025.

Pmallik22 at 23:08, 28 October 2025

2025-10-28T23:08:28Z

Pmallik22 at 00:26, 23 October 2025

2025-10-23T00:26:33Z

Ttphan21 at 19:05, 1 January 2023

2023-01-01T19:05:37Z

← Older revision		Revision as of 19:05, 1 January 2023
Line 1:		Line 1:
	Writeup on choosing which computing resources to use for what work		Writeup on choosing which computing resources to use for what work

			= Computer Resources =

			[https://wiki.cs.earlham.edu/index.php/Sysadmin:Computer_Resources All information related to our machines and VMs]

	= Short version =		= Short version =

Ttphan21 at 18:51, 26 November 2022

2022-11-26T18:51:28Z

← Older revision		Revision as of 18:51, 26 November 2022
Line 76:		Line 76:

	On [https://code.cs.earlham.edu GitLab], you will find a series of bits of example code, mostly �hello world� code to verify that you have successfully submitted and run a job on the correct resources.		On [https://code.cs.earlham.edu GitLab], you will find a series of bits of example code, mostly �hello world� code to verify that you have successfully submitted and run a job on the correct resources.

			Tested and working 2022

Ttphan21 at 18:49, 26 November 2022

2022-11-26T18:49:55Z

← Older revision		Revision as of 18:49, 26 November 2022
Line 75:		Line 75:
	= Examples =		= Examples =

	On [https://~~gitlab~~.~~cluster~~		On [https://code.cs

Ttphan21 at 18:59, 18 November 2022

2022-11-18T18:59:16Z

← Older revision		Revision as of 18:59, 18 November 2022
Line 49:		Line 49:
	==== Jumbo servers ====		==== Jumbo servers ====

	~~tl;dr~~
	* Jumbo server: one big machine, lots of RAM and storage compared to CPU		* Jumbo server: one big machine, lots of RAM and storage compared to CPU
	* Best for shared memory parallelism		* Best for shared memory parallelism
Line 61:		Line 60:
	==== Clusters ====		==== Clusters ====

	~~tl;dr~~
	* Cluster: several less powerful machines linked together to perform operations in parallel		* Cluster: several less powerful machines linked together to perform operations in parallel
	* Best for distributed memory parallelism		* Best for distributed memory parallelism

Pelibby16 at 19:10, 21 September 2022

2022-09-21T19:10:54Z

← Older revision		Revision as of 19:10, 21 September 2022
Line 73:		Line 73:
	The use of multiple nodes requires a lot of communications overhead. As such, a cluster is well-suited to problems where data can be distributed across many places, at each of which CPU�s (and/or GPU�s) can work on it.		The use of multiple nodes requires a lot of communications overhead. As such, a cluster is well-suited to problems where data can be distributed across many places, at each of which CPU�s (and/or GPU�s) can work on it.

	~~= Detailed Specs =~~
	This section includes detailed information on each machine/cluster. This will likely be more information than you need, but it can come in handy for research or other applications where you need to provide information about how your code was run.

	~~== Whedon Specs (cluster) ==~~
	{\|
	~~\|- style="vertical-align:top;"~~
	\|
	~~; Memory Details~~
	~~: Total Width: 72 bits~~
	~~: Data Width: 64 bits~~
	~~: Size: 256GB (8x32 GB)~~
	~~: Form Factor: DIMM~~
	~~: Set: None~~
	~~: Type: DDR4~~
	~~: Type Detail: Synchronous~~
	~~: Speed: 2133 MT/s~~
	~~: Manufacturer: Samsung~~
	~~: Serial Number: 315FBBB7~~
	~~: Configured Memory Speed: 1866 MT/s~~
	\|
	~~; CPU Details~~
	~~: Architecture: x86_64~~
	~~: CPU op-mode(s): 32-bit, 64-bit~~
	~~: Byte Order: Little Endian~~
	~~: CPU(s): 32~~
	~~: On-line CPU(s) list: 0-31~~
	~~: Thread(s) per core: 2~~
	~~: Core(s) per socket: 8~~
	~~: Socket(s): 2~~
	~~: NUMA node(s): 2~~
	~~: Vendor ID: GenuineIntel~~
	~~: CPU family: 6~~
	~~: Model: 63~~
	~~: Model name: Intel(R) Xeon(R) CPU E5-2630 v3 @ 2.40GHz~~
	~~: Stepping: 2~~
	~~: CPU MHz: 2599.951~~
	~~: CPU max MHz: 3200.0000~~
	~~: CPU min MHz: 1200.0000~~
	~~: BogoMIPS: 4799.75~~
	~~: Virtualization: VT-x~~
	~~: L1d cache: 32K~~
	~~: L1i cache: 32K~~
	~~: L2 cache: 256K~~
	~~: L3 cache: 20480K~~
	~~: NUMA node0 CPU(s): 0-7,16-23~~
	~~: NUMA node1 CPU(s): 8-15,24-31~~
	\|}
	~~== Hamilton (cluster) ==~~

	~~== Layout (cluster) ==~~

Pelibby16 at 19:09, 21 September 2022

2022-09-21T19:09:53Z

@@ Line 72: / Line 72: @@
 The use of multiple nodes requires a lot of communications overhead. As such, a cluster is well-suited to problems where data can be distributed across many places, at each of which CPU�s (and/or GPU�s) can work on it.
 = Examples =
 On [https://gitlab.cluster.earlham.edu GitLab], you will find a series of bits of example code, mostly �hello world� code to verify that you have successfully submitted and run a job on the correct resources.

Craigje: /* Anything requiring a GPGPU */

2020-05-04T16:54:18Z

Anything requiring a GPGPU

← Older revision		Revision as of 16:54, 4 May 2020
Line 34:		Line 34:

	The layout cluster. This is an easy answer because our other machines do not contain GPGPU�s. :)		The layout cluster. This is an easy answer because our other machines do not contain GPGPU�s. :)

			If you're new to the term, a GPGPU (general-purpose graphics processing unit) is a GPU that performs computations in problem spaces other than rendering computer graphics.

			A GPU can perform some specific computations, such as vector arithmetic, extremely quickly relative to a CPU. This is important in (for example) rendering video game animations. Many problems in the natural and computational sciences also require such calculations, hence the development of GPGPUs. Demand for their use may increase as data science and machine learning continue to grow.



	=== High-performance computing, including scientific and research computing ===		=== High-performance computing, including scientific and research computing ===

← Older revision		Revision as of 23:08, 28 October 2025
Line 11:		Line 11:
	* hosting a website or web app: One of our web servers (web.cs most likely)		* hosting a website or web app: One of our web servers (web.cs most likely)
	* controlling a complete OS: a VM, send email to admins about this one		* controlling a complete OS: a VM, send email to admins about this one
	* GPGPU's: ~~Layout~~		* GPGPU's: Faraday
	* running jobs that need lots of RAM and/or storage: a phat node (lovelace or pollock)		* running jobs that need lots of RAM and/or storage: a phat node (lovelace or pollock)
	* running jobs you want to split across many machines: a cluster (~~layout~~ or whedon)		* running jobs you want to split across many machines: a cluster (faraday or whedon)

	Check out the rest of this document for the more detailed version.		Check out the rest of this document for the more detailed version.
Line 37:		Line 37:
	=== Anything requiring a GPGPU ===		=== Anything requiring a GPGPU ===

	The ~~layout~~ cluster. This is an easy answer because our other machines do not contain GPGPU's. :)		The Faraday cluster. This is an easy answer because our other machines do not contain GPGPU's. :)

	If you're new to the term, a GPGPU (general-purpose graphics processing unit) is a GPU that performs computations in problem spaces other than rendering computer graphics.		If you're new to the term, a GPGPU (general-purpose graphics processing unit) is a GPU that performs computations in problem spaces other than rendering computer graphics.
Line 43:		Line 43:
	A GPU can perform some specific computations, such as vector arithmetic, extremely quickly relative to a CPU. This is important in (for example) rendering video game animations. Many problems in the natural and computational sciences also require such calculations, hence the development of GPGPUs. Demand for their use may increase as data science and machine learning continue to grow.		A GPU can perform some specific computations, such as vector arithmetic, extremely quickly relative to a CPU. This is important in (for example) rendering video game animations. Many problems in the natural and computational sciences also require such calculations, hence the development of GPGPUs. Demand for their use may increase as data science and machine learning continue to grow.

	Our NVIDIA GPGPUs (and associated drivers) are installed to the ~~Layout~~ cluster. To program using GPGPU's, load CUDA ([[CUDA\|read more about CUDA here]]) on the ~~Layout~~ cluster. Happy coding.		Our NVIDIA GPGPUs (and associated drivers) are installed to the Faraday cluster. To program using GPGPU's, load CUDA ([[CUDA\|read more about CUDA here]]) on the Farday cluster. Happy coding.

	=== High-performance computing, including scientific and research computing ===		=== High-performance computing, including scientific and research computing ===

← Older revision		Revision as of 00:26, 23 October 2025
Line 37:		Line 37:
	=== Anything requiring a GPGPU ===		=== Anything requiring a GPGPU ===

	The layout cluster. This is an easy answer because our other machines do not contain . :)		The layout cluster. This is an easy answer because our other machines do not contain GPGPU's. :)

	If you're new to the term, a GPGPU (general-purpose graphics processing unit) is a GPU that performs computations in problem spaces other than rendering computer graphics.		If you're new to the term, a GPGPU (general-purpose graphics processing unit) is a GPU that performs computations in problem spaces other than rendering computer graphics.
Line 43:		Line 43:
	A GPU can perform some specific computations, such as vector arithmetic, extremely quickly relative to a CPU. This is important in (for example) rendering video game animations. Many problems in the natural and computational sciences also require such calculations, hence the development of GPGPUs. Demand for their use may increase as data science and machine learning continue to grow.		A GPU can perform some specific computations, such as vector arithmetic, extremely quickly relative to a CPU. This is important in (for example) rendering video game animations. Many problems in the natural and computational sciences also require such calculations, hence the development of GPGPUs. Demand for their use may increase as data science and machine learning continue to grow.

	Our NVIDIA GPGPUs (and associated drivers) are installed to the Layout cluster. To program using , load CUDA ([[CUDA\|read more about CUDA here]]) on the Layout cluster. Happy coding.		Our NVIDIA GPGPUs (and associated drivers) are installed to the Layout cluster. To program using GPGPU's, load CUDA ([[CUDA\|read more about CUDA here]]) on the Layout cluster. Happy coding.

	=== High-performance computing, including scientific and research computing ===		=== High-performance computing, including scientific and research computing ===
Line 58:		Line 58:
	* Hostnames: lovelace, pollock		* Hostnames: lovelace, pollock

	Jumbo servers (nee phat nodes) are in many respects just bigger versions of the computers accustomed to running. They have one or two , lots of RAM, and lots of disk.		Jumbo servers (nee phat nodes) are in many respects just bigger versions of the computers you're accustomed to running. They have one or two CPU's, lots of RAM, and lots of disk.

	A jumbo server is the best solution for problems that require a lot of data to be loaded into memory and handled all at once, with minimal communications overhead.		A jumbo server is the best solution for problems that require a lot of data to be loaded into memory and handled all at once, with minimal communications overhead.
Line 73:		Line 73:
	3. a network switch to link all the nodes together		3. a network switch to link all the nodes together

	The use of multiple nodes requires a lot of communications overhead. As such, a cluster is well-suited to problems where data can be distributed across many places, at each of which (and/or ) can work on it.		The use of multiple nodes requires a lot of communications overhead. As such, a cluster is well-suited to problems where data can be distributed across many places, at each of which CPU's (and/or GPU's) can work on it.


Line 79:		Line 79:
	= Examples =		= Examples =

	On [https://code.cs.earlham.edu GitLab], you will find a series of bits of example code, mostly code to verify that you have successfully submitted and run a job on the correct resources.		On [https://code.cs.earlham.edu GitLab], you will find a series of bits of example code, mostly 'hello world' code to verify that you have successfully submitted and run a job on the correct resources.

	Tested and working 2022		Tested and working 2022