https://wiki.egi.eu/w/api.php?action=feedcontributions&user=Walshj1&feedformat=atomEGIWiki - User contributions [en]2024-03-28T14:38:41ZUser contributionsMediaWiki 1.37.1https://wiki.egi.eu/w/index.php?title=GPGPU-WG_ExperimentalTestingSetup_-_MatchMakingJS&diff=68623GPGPU-WG ExperimentalTestingSetup - MatchMakingJS2014-07-19T16:06:06Z<p>Walshj1: </p>
<hr />
<div>Because many of the new GLUE 2.0 attributes published by the GPU information providers are not used by the UMD WMS, an alternative method has been devised to allow the user to locate GPGPU resources using the familar JDL CLASSAD expression. The jobsubmission is therefore currently a two phased approach:<br />
* The GPU classad helps find suitable Resource Centre CEs that match the GPU classad,<br />
* This list of matching CEs is passed into a template JDL, which is then submitted to the WMS.<br />
<br />
It is expected that this two phase method can be combined into a single match-making or submission command in the future.<br />
<br />
<br />
[[ GPGPU-WG:ExperimentalTestingSetup | Parent Page ]]</div>Walshj1https://wiki.egi.eu/w/index.php?title=GPGPU-WG_ExperimentalTestingSetup_-_MatchMakingJS&diff=68622GPGPU-WG ExperimentalTestingSetup - MatchMakingJS2014-07-19T16:05:24Z<p>Walshj1: </p>
<hr />
<div>Because many of the new GLUE 2.0 attributes published by the GPU information providers are not used by the UMD WMS, an alternative method has been devised to allow the user to locate GPGPU resources using the familar JDL CLASSAD expression. The jobsubmission is therefore currently a two phased approach:<br />
* The GPU classad helps find suitable Resource Centre CEs that match the GPU classad,<br />
* This list of matching CEs is passed into a template JDL, which is then submitted to the WMS.<br />
<br />
It is expected that this two phase method can be combined into a single match-making or submission command in the future.</div>Walshj1https://wiki.egi.eu/w/index.php?title=GPGPU-WG_ExperimentalTestingSetup_-_MatchMakingJS&diff=68621GPGPU-WG ExperimentalTestingSetup - MatchMakingJS2014-07-19T16:04:22Z<p>Walshj1: Created page with " Because many of the new GLUE 2.0 attributes published by the GPU information providers are not used by the UMD WMS, an alternative method has been devised to allow the user to l..."</p>
<hr />
<div><br />
Because many of the new GLUE 2.0 attributes published by the GPU information providers are not used by the UMD WMS, an alternative method has been devised to allow the user to locate GPGPU resources based on a CLASSAD expression. The jobsubmission is therefore currently a two phased approach:<br />
* The GPU classad helps find suitable Resource Centre CEs that match the GPU classad,<br />
* This list of matching CEs is passed into a template JDL, which is then submitted to the WMS.<br />
<br />
It is expected that this two phase method can be combined into a single match-making or submission command in the future.</div>Walshj1https://wiki.egi.eu/w/index.php?title=GPGPU-WG_ExperimentalTestingSetup_BatchSystemIntegration&diff=68620GPGPU-WG ExperimentalTestingSetup BatchSystemIntegration2014-07-19T15:44:22Z<p>Walshj1: </p>
<hr />
<div>This section discusses the method used to pass JDL GPGPU Attribute value pairs and convert these into local batch system directives. In principle, the method developed here can be used to pass/convert many new key-value pairs into appropriate batch system directives. For our GPGPU experiment we shall pass the GPU GPUSPerNode='X'<br />
<br />
<br />
* CE changes:<br />
** yum install glite-ce-cream-cli (used in LRMS_local_submit_attributes.sh)<br />
** install parsejdl_gpu (used in LRMS_local_submit_attributes.sh to validate the data)<br />
** create /usr/libexec/LRMS_local_submit_attributes.sh script (or place this code into another executable file, and call it from an existing local script)</div>Walshj1https://wiki.egi.eu/w/index.php?title=GPGPU-WG_ExperimentalTestingSetup_BatchSystemIntegration&diff=68619GPGPU-WG ExperimentalTestingSetup BatchSystemIntegration2014-07-19T15:20:04Z<p>Walshj1: Created page with "This section discusses the method used to pass JDL GPGPU Attribute value pairs and convert these into local batch system directives. In principle, the method developed here can b..."</p>
<hr />
<div>This section discusses the method used to pass JDL GPGPU Attribute value pairs and convert these into local batch system directives.<br />
In principle, the method developed here can be used to pass/convert many new key-value pairs into appropriate batch system directives.<br />
<br />
<br />
* CE changes:<br />
** yum install glite-ce-cream-cli<br />
** parsejdl_gpu <br />
** create /usr/libexec/LRMS_local_submit_attributes.sh script (or add addition code if this script already exists on your CE)</div>Walshj1https://wiki.egi.eu/w/index.php?title=GPGPU-WG_ExperimentalTestingSetup_ServiceDiscovery&diff=68596GPGPU-WG ExperimentalTestingSetup ServiceDiscovery2014-07-17T17:14:22Z<p>Walshj1: </p>
<hr />
<div>The objective is to allow GPGPU related resources and their state to be discovered by user commands such as glite-wms-job-list-match. In this experimental work, we would like to publish sufficient details about the GPGPU software and hardware within a GLUE2 based environment.<br />
The experimental work concentrates on using a basic GLUE2 ApplicationEnvironment to publish details about both the CUDA software environment and hardware details about the GPGPU resources and any node properties.<br />
<br />
'''This work is experimental is is likely to change in the future'''.<br />
<br />
The UMD GIP usr/libexec/glite-ce-glue2-applicationenvironment-dynamic is currently used generate GLUE2 ApplicationEnvironment entities.<br />
A small modification to this GIP <br />
<br />
<br />
[[GPGPU-WG:ExperimentalTestingSetup | Parent Page]]</div>Walshj1https://wiki.egi.eu/w/index.php?title=GPGPU-WG_ExperimentalTestingSetup_ServiceDiscovery&diff=68591GPGPU-WG ExperimentalTestingSetup ServiceDiscovery2014-07-17T16:35:55Z<p>Walshj1: </p>
<hr />
<div>The objective is to allow GPGPU related resources and their state to be discovered by user commands such as glite-wms-job-list-match. In this experimental work, we would like to publish sufficient details about the GPGPU software and hardware within a GLUE2 based environment.<br />
The experimental work concentrates on using a basic GLUE2 ApplicationEnvironment to publish details about both the CUDA software environment and hardware details about the GPGPU resources and any node properties.<br />
<br />
'''This work is experimental is is likely to change in the future'''.<br />
<br />
[[GPGPU-WG:ExperimentalTestingSetup | Parent Page]]</div>Walshj1https://wiki.egi.eu/w/index.php?title=GPGPU-WG_ExperimentalTestingSetup_ServiceDiscovery&diff=68590GPGPU-WG ExperimentalTestingSetup ServiceDiscovery2014-07-17T16:35:12Z<p>Walshj1: </p>
<hr />
<div>The objective is to allow GPGPU related resources and their state to be discovered by user commands such as glite-wms-job-list-match. In this experimental work, we would like to publish sufficient details about the GPGPU software and hardware within a GLUE2 based environment.<br />
The experimental work concentrates on using a basic GLUE2 ApplicationEnvironment to publish details about both the CUDA software environment and hardware details about the GPGPU resources and any node properties.<br />
<br />
'''This work is experimental is is likely to change in the future'''.</div>Walshj1https://wiki.egi.eu/w/index.php?title=GPGPU-WG_ExperimentalTestingSetup_ServiceDiscovery&diff=68589GPGPU-WG ExperimentalTestingSetup ServiceDiscovery2014-07-17T16:33:56Z<p>Walshj1: </p>
<hr />
<div><br />
The objective is to allow GPGPU related resources and their state to be discovered by user commands such as glite-wms-job-list-match. In this experimental work, we would like to publish sufficient details about the GPGPU software and hardware within a GLUE2 based environment.<br />
The experimental work concentrates on using a basic GLUE2 ApplicationEnvironment to publish details about both the CUDA software environment and hardware details about the GPGPU resources and any node properties.<br />
<br />
''This work is experimental is is likely to change in the future''.</div>Walshj1https://wiki.egi.eu/w/index.php?title=GPGPU-WG_ExperimentalTestingSetup_JDL&diff=68575GPGPU-WG ExperimentalTestingSetup JDL2014-07-17T15:35:19Z<p>Walshj1: </p>
<hr />
<div>A core objective is to allow the user to specify additional key-value pairs that:<br />
* place a restriction on the resource centres that the job should be targeted at<br />
* Provide addition specification to the LRMS<br />
<br />
This page describes the usage of some experimental key-values pairs:<br />
{| class="wikitable"<br />
!colspan="5"| '''GPGPU LRMS directives'''<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
|'''Key'''<br />
|colspan=3 | '''Value'''<br />
|'''Description'''<br />
|- <br />
| GPUPerNode <br />
| colspan="3" | Positive Integer > 0<br />
| The number of GPGPUs required for the job to run on the allocated node(s). Eg. GPUPerNode=2;<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
|}<br />
<br />
[[GPGPU-WG:ExperimentalTestingSetup | Parent Page]]</div>Walshj1https://wiki.egi.eu/w/index.php?title=GPGPU-WG_ExperimentalTestingSetup_JDL&diff=68574GPGPU-WG ExperimentalTestingSetup JDL2014-07-17T15:34:25Z<p>Walshj1: </p>
<hr />
<div>A core objective is to allow the user to specify additional key-value pairs that:<br />
* place a restriction on the resource centres that the job should be targeted at<br />
* Provide addition specification to the LRMS<br />
<br />
This page describes the usage of some experimental key-values pairs:<br />
{| class="wikitable"<br />
!colspan="5"| '''GPGPU LRMS attributes'''<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
|'''Key'''<br />
|colspan=3 | '''Value'''<br />
|'''Description'''<br />
|- <br />
| GPUPerNode <br />
| colspan="3" | Positive Integer > 0<br />
| The number of GPGPUs required for the job to run on the allocated node(s). Eg. GPUPerNode=2;<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
|}<br />
<br />
[[GPGPU-WG:ExperimentalTestingSetup | Parent Page]]</div>Walshj1https://wiki.egi.eu/w/index.php?title=GPGPU-WG_ExperimentalTestingSetup_JDL&diff=68573GPGPU-WG ExperimentalTestingSetup JDL2014-07-17T15:33:37Z<p>Walshj1: </p>
<hr />
<div>A core objective is to allow the user to specify additional key-value pairs that:<br />
* place a restriction on the resource centres that the job should be targeted at<br />
* Provide addition specification to the LRMS<br />
<br />
This page describes the usage of some experimental key-values pairs:<br />
{| class="wikitable"<br />
!colspan="5"| '''GPGPU LRMS attributes'''<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
|'''Key'''<br />
|colspan=3 | '''Value'''<br />
|'''Description'''<br />
|- <br />
| GPUPerNode <br />
| colspan="3" | Positive Integer > 0<br />
| The number of GPGPUs required for the job to run on a specific node.<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
|}<br />
<br />
[[GPGPU-WG:ExperimentalTestingSetup | Parent Page]]</div>Walshj1https://wiki.egi.eu/w/index.php?title=GPGPU-WG_ExperimentalTestingSetup_JDL&diff=68572GPGPU-WG ExperimentalTestingSetup JDL2014-07-17T15:26:35Z<p>Walshj1: </p>
<hr />
<div>A core objective is to allow the user to specify additional key-value pairs that:<br />
* place a restriction on the resource centres that the job should be targeted at<br />
* Provide addition specification to the LRMS<br />
<br />
This page describes the usage of some experimental key-values pairs:<br />
{| class="wikitable"<br />
!colspan="5"| '''GPGPU LRMS attributes'''<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
|'''Entity'''<br />
|colspan=3 | '''Key'''<br />
|'''Value'''<br />
|- <br />
| Description <br />
| colspan="3" | GPUPerNode<br />
| A type of environment available to and requestable by a Grid job when submitted to a<br />
ComputingService via a Computing Endpoint; the type of environment is described in terms of hardware, operating system and network characteristics. Information about the total/available/used instances of this type of execution environment are also included.<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
|}<br />
<br />
[[GPGPU-WG:ExperimentalTestingSetup | Parent Page]]</div>Walshj1https://wiki.egi.eu/w/index.php?title=GPGPU-WG_ExperimentalTestingSetup_JDL&diff=68571GPGPU-WG ExperimentalTestingSetup JDL2014-07-17T15:24:59Z<p>Walshj1: </p>
<hr />
<div>A core objective is to allow the user to specify additional key-value pairs that:<br />
* place a restriction on the resource centres that the job should be targeted at<br />
* Provide addition specification to the LRMS<br />
<br />
This page describes the usage of some experimental key-values pairs:<br />
{| class="wikitable"<br />
!colspan="5"| '''GPGPU LRMS attributes'''<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
|'''Entity'''<br />
|colspan=3 | '''Inherits from'''<br />
|'''Description'''<br />
|- <br />
| ExecutionEnvironment <br />
| colspan="3" | Resource<br />
| A type of environment available to and requestable by a Grid job when submitted to a<br />
ComputingService via a Computing Endpoint; the type of environment is described in terms of hardware, operating system and network characteristics. Information about the total/available/used instances of this type of execution environment are also included.<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
|}<br />
<br />
[[GPGPU-WG:ExperimentalTestingSetup | Parent Page]]</div>Walshj1https://wiki.egi.eu/w/index.php?title=GPGPU-WG_ExperimentalTestingSetup_JDL&diff=68569GPGPU-WG ExperimentalTestingSetup JDL2014-07-17T15:22:14Z<p>Walshj1: </p>
<hr />
<div>A core objective is to allow the user to specify additional key-value pairs that:<br />
* place a restriction on the resource centres that the job should be targeted at<br />
* Provide addition specification to the LRMS<br />
<br />
This page describes the usage of some experimental key-values pairs:<br />
<br />
[[GPGPU-WG:ExperimentalTestingSetup | Parent Page]]</div>Walshj1https://wiki.egi.eu/w/index.php?title=GPGPU-WG_ExperimentalTestingSetup_JDL&diff=68568GPGPU-WG ExperimentalTestingSetup JDL2014-07-17T15:21:22Z<p>Walshj1: Created page with " A core objective is to allow the user to specify additional key-value pairs that: * place a restriction on the resource centres that the job should be targeted at * Provide addi..."</p>
<hr />
<div><br />
A core objective is to allow the user to specify additional key-value pairs that:<br />
* place a restriction on the resource centres that the job should be targeted at<br />
* Provide addition specification to the LRMS<br />
<br />
This page describes the usage of some experimental key-values pairs:</div>Walshj1https://wiki.egi.eu/w/index.php?title=GPGPU-WG_ExperimentalTestingSetup&diff=68563GPGPU-WG ExperimentalTestingSetup2014-07-17T15:02:55Z<p>Walshj1: </p>
<hr />
<div>An experimental system for advertising GPGPUs, passing parameters to the native LRMS and basic service discovery/match-making is described:<br />
<br />
* [[GPGPU-WG:ExperimentalTestingSetup:ServiceDiscovery | Service Discovery]]<br />
* [[GPGPU-WG:ExperimentalTestingSetup:JDL | JDL Specification]]<br />
* [[GPGPU-WG:ExperimentalTestingSetup:BatchSystemIntegration | Batch System Integration]]<br />
* [[GPGPU-WG:ExperimentalTestingSetup:MatchMakingJS | MatchMaking and Job Submission]]</div>Walshj1https://wiki.egi.eu/w/index.php?title=GPGPU-WG_ExperimentalTestingSetup&diff=68561GPGPU-WG ExperimentalTestingSetup2014-07-17T15:00:31Z<p>Walshj1: </p>
<hr />
<div>An experimental system for advertising GPGPUs, passing parameters to the native LRMS and basic service discovery/match-making is described:<br />
<br />
* [[GPGPU-WG:ExperimentalTestingSetup:ServiceDiscovery | Service Discovery]]<br />
* JDL Specification<br />
* Batch System Integration<br />
* MatchMaking and Job Submission</div>Walshj1https://wiki.egi.eu/w/index.php?title=GPGPU_Working_Group&diff=68558GPGPU Working Group2014-07-17T14:54:36Z<p>Walshj1: /* Useful Links */</p>
<hr />
<div>{{Template:Op menubar}} {{TOC_right}} <br />
[[Category:Task_forces]]<br />
<br />
'''Coordinator''': Miroslav Ruda/CESNET, John Walsh/TCD <br />
<br />
'''Meetings page''': [https://indico.egi.eu/indico/categoryDisplay.py?categId=116 Agendas] <br />
<br />
'''Mailing list''': vt-gpgpu (at) mailman.egi.eu <br />
<br />
'''Duration''': Sep 2013 <br />
<br />
'''Members:''' <br />
<br />
= Introduction<br> =<br />
<br />
Over the summer of 2012, [[VT_GPGPU | the EGI GPGPU Virtual Team]] developed and distributed two surveys - a Grid User oriented survey and a Resource Centre (RC) oriented survey - on the current and future use of General Purpose Graphics Processing Units (GPGPU) on the European Grid Infrastructure (EGI). The key results of the surveys, which were presented at the EGI Technical Forum 2013, showed that:<br />
* many Resource Centres had already deployed GPGPUs or had planned to do so<br />
* Users would be interested in using these resources. <br />
However, currently there is no coherent or standardised means for discovering or accessing GPGPU resources on the EGI or similarly related grid infrastructures. Integration of such resources is a non-trivial task. <br />
These include: <br />
* Batch System integration best practices; <br />
* the evaluation and adoption of an appropriate GlueSchema; <br />
* GPGPU resource usage accounting; <br />
* GPGPU resource availability and reliability testing.<br />
<br />
<br />
= Objectives =<br />
EGI Technical Group/Working Group will study <br />
* Batch System integration best practices <br />
* the proposal and evaluation of an appropriate GlueSchema suitable for describing generalised “Computational Accelerators”. <br />
<br />
=Membership=<br />
Membership of the Group is open to Resource Centre representatives who can contribute directly to either of these objectives. User Community representation and expertise from GlueSchema developers is required to aid with the development and evaluation of the GlueSchema definition. <br />
<br />
= Milestones =<br />
<br />
= Testbed = <br />
Testbed Contacts: <br />
* Derek Ross/STFC, [http://www.einfrastructuresouth.ac.uk/cfi/emerald/ Emerald GPU Cluster] with 372 Nvidia M2090<br />
* Andrea Sartirana/GRIF, 4 servers, each one with 2 accelerators (4 nvidia K20 and 4 Xeon Phi) <br />
* Oleksandr Savytskyi/moldyngrid.org, gromacs 4.6.3 testing (native GPU support) on GPU\Xeon Phi clusters<br />
* Miguel Cardenas/CIEMAT (applications: DES - Dark Energy Survey, artificial intelligence)<br />
* Mariusz Sterzel,Lukasz Flis/Cyfronet: Application Area - Computational Chemistry amd Biology (Nodes with 2 or 8 GPGPU cards)<br />
* Emanouil Atanassov/BG01-IPP: 16 NVIDIA M2090<br />
<br />
= User Communities =<br />
* WeNMR (MD simulations via GROMACS)<br />
* MoldynGrid (MD simulations)<br />
* AstroPhysics (Contact Miguel Cárdenas)<br />
<br />
= Actions =<br />
<div><br></div><br />
<br />
= Results =<br />
<br />
= Use Cases =<br />
Information about GPGPU use cases was collected in a survey back in 2012 organized by the GPGPU virtual team: go to [[VT_GPGPU/Use_Case|Use Cases]]<br />
<br />
= Useful Links =<br />
* [[GPGPU-WG:GPGPU_Working_Group_KnowlegeBase | GPGPU Knowledge-base]]<br />
* [[GPGPU-WG:ResorceCentres | GPGPU Resource Centres]]<br />
* [[GPGPU-WG:ExperimentalTestingSetup | Advanced Experimental Testing]]<br />
* [[VT_GPGPU|GPGPU Virtual Team]] (closed)</div>Walshj1https://wiki.egi.eu/w/index.php?title=GPGPU-WG_ExperimentalTestingSetup_ServiceDiscovery&diff=68556GPGPU-WG ExperimentalTestingSetup ServiceDiscovery2014-07-17T14:51:06Z<p>Walshj1: Created page with "Service Discovery"</p>
<hr />
<div>Service Discovery</div>Walshj1https://wiki.egi.eu/w/index.php?title=GPGPU_Working_Group&diff=68555GPGPU Working Group2014-07-17T14:46:38Z<p>Walshj1: /* User Communities */</p>
<hr />
<div>{{Template:Op menubar}} {{TOC_right}} <br />
[[Category:Task_forces]]<br />
<br />
'''Coordinator''': Miroslav Ruda/CESNET, John Walsh/TCD <br />
<br />
'''Meetings page''': [https://indico.egi.eu/indico/categoryDisplay.py?categId=116 Agendas] <br />
<br />
'''Mailing list''': vt-gpgpu (at) mailman.egi.eu <br />
<br />
'''Duration''': Sep 2013 <br />
<br />
'''Members:''' <br />
<br />
= Introduction<br> =<br />
<br />
Over the summer of 2012, [[VT_GPGPU | the EGI GPGPU Virtual Team]] developed and distributed two surveys - a Grid User oriented survey and a Resource Centre (RC) oriented survey - on the current and future use of General Purpose Graphics Processing Units (GPGPU) on the European Grid Infrastructure (EGI). The key results of the surveys, which were presented at the EGI Technical Forum 2013, showed that:<br />
* many Resource Centres had already deployed GPGPUs or had planned to do so<br />
* Users would be interested in using these resources. <br />
However, currently there is no coherent or standardised means for discovering or accessing GPGPU resources on the EGI or similarly related grid infrastructures. Integration of such resources is a non-trivial task. <br />
These include: <br />
* Batch System integration best practices; <br />
* the evaluation and adoption of an appropriate GlueSchema; <br />
* GPGPU resource usage accounting; <br />
* GPGPU resource availability and reliability testing.<br />
<br />
<br />
= Objectives =<br />
EGI Technical Group/Working Group will study <br />
* Batch System integration best practices <br />
* the proposal and evaluation of an appropriate GlueSchema suitable for describing generalised “Computational Accelerators”. <br />
<br />
=Membership=<br />
Membership of the Group is open to Resource Centre representatives who can contribute directly to either of these objectives. User Community representation and expertise from GlueSchema developers is required to aid with the development and evaluation of the GlueSchema definition. <br />
<br />
= Milestones =<br />
<br />
= Testbed = <br />
Testbed Contacts: <br />
* Derek Ross/STFC, [http://www.einfrastructuresouth.ac.uk/cfi/emerald/ Emerald GPU Cluster] with 372 Nvidia M2090<br />
* Andrea Sartirana/GRIF, 4 servers, each one with 2 accelerators (4 nvidia K20 and 4 Xeon Phi) <br />
* Oleksandr Savytskyi/moldyngrid.org, gromacs 4.6.3 testing (native GPU support) on GPU\Xeon Phi clusters<br />
* Miguel Cardenas/CIEMAT (applications: DES - Dark Energy Survey, artificial intelligence)<br />
* Mariusz Sterzel,Lukasz Flis/Cyfronet: Application Area - Computational Chemistry amd Biology (Nodes with 2 or 8 GPGPU cards)<br />
* Emanouil Atanassov/BG01-IPP: 16 NVIDIA M2090<br />
<br />
= User Communities =<br />
* WeNMR (MD simulations via GROMACS)<br />
* MoldynGrid (MD simulations)<br />
* AstroPhysics (Contact Miguel Cárdenas)<br />
<br />
= Actions =<br />
<div><br></div><br />
<br />
= Results =<br />
<br />
= Use Cases =<br />
Information about GPGPU use cases was collected in a survey back in 2012 organized by the GPGPU virtual team: go to [[VT_GPGPU/Use_Case|Use Cases]]<br />
<br />
= Useful Links =<br />
* [[GPGPU-WG:GPGPU_Working_Group_KnowlegeBase | GPGPU Knowledge-base]]<br />
* [[GPGPU-WG:ResorceCentres | GPGPU Resource Centres]]<br />
* [[VT_GPGPU|GPGPU Virtual Team]] (closed)</div>Walshj1https://wiki.egi.eu/w/index.php?title=GPGPU-WG_KnowledgeBase_-_Batch_Schedulers_-_SchedulerScenarios_-_GPUOnlyQueue&diff=68552GPGPU-WG KnowledgeBase - Batch Schedulers - SchedulerScenarios - GPUOnlyQueue2014-07-17T14:28:45Z<p>Walshj1: /* JDL Example 1 */</p>
<hr />
<div>== Single GPGPU per node ==<br />
A simple batch setup that assumes a physical node and its componenent GPGPU card expose a single '''Job Slot''' would simplify Resource Centre setup. Each GPGPU node could be partitioned from the non-GPGPU nodes using an access-control-list. However, most modern physical nodes contain and expose multiple CPU-cores to the batch system. If the physical system supports '''Virtualisation''', a CPU-core could be allocated to the GPU on the phsical node, and a single virtual machine could expose the remainder of the job slots. For example: Assume the physical host (wn1) has 8-cores, we can configure the node to declare (in torque) "np=1" to the batch system. If we create a VM with "np=7", then all cores can be allocated to the batch system.<br />
<br />
<br />
The major drawback of taking the gpgpu queue approach is that:<br />
* There is a direct relationship between the number of available CPU cores to the number of GPGPUs.<br />
** This hinders jobs that require more CPUs than there are GPGPUs<br />
** It cannot deal with jobs requiring a mixture of just CPU and CPU/GPU pairs "-lnodes=1+nodes=2:ppn=2:gpus=2" without the risk or wasting/blocking resources.<br />
<br />
<br />
=== Options for RC ===<br />
* Define a queue with name tagged '''gpgpu'''<br />
* Apply the usual VO restrictions on the queue<br />
* Define an ACL that partitions these nodes from non-GPGPU nodes<br />
* Publish basic SoftwareEnvironment (eg. CUDA, CUDA-5, CUDA-5.5)<br />
* Ensure the WN environment is configured with all relevant GPGPU Software development kit installed.<br />
<br />
=== JDL Example 1 ===<br />
This example simply requests 1 job slots from any queue matching '''"*gpgpu$"'''. This is equivalent to the PBS '''-l nodes=1'''<br />
<br />
<pre><br />
[<br />
Type="Job";<br />
<br />
JobType="Normal";<br />
Executable = "myScript.sh";<br />
StdOutput = "std.out";<br />
StdError = "std.err";<br />
InputSandbox = {"myScript.sh"};<br />
Requirements = ( RegExp(".*gpgpu$", other.GlueCEUniqueID) && Member("CUDA", other.GlueHostApplicationSoftwareRunTimeEnvironment);<br />
]<br />
</pre><br />
<br />
=== JDL Example 2 ===<br />
<br />
This example simply requests 2 job slots from any queue matching '''"*gpgpu$"'''. The allocated cores may be on distinct hosts, so we cannot assume that the the GPGPU application will see or can enumerate both GPGPU cards. This is equivalent to the PBS '''-l nodes=2'''<br />
<br />
<pre><br />
[<br />
Type="Job";<br />
JobType="Normal";<br />
CPUnumber=2;<br />
# myScript.sh must take responsibility for executing the GPGPU application on both the allocated core/GPGPU pairs!<br />
Executable = "myScript.sh"; <br />
StdOutput = "std.out";<br />
StdError = "std.err";<br />
InputSandbox = {"myScript.sh"};<br />
Requirements = ( RegExp(".*gpgpu$", other.GlueCEUniqueID) && Member("CUDA", other.GlueHostApplicationSoftwareRunTimeEnvironment);<br />
]<br />
</pre><br />
<br />
== Multiple GPGPUs per Physical Node ==<br />
Similar to the Virtualisation example above, a physical node with '''N'''-gpgpu cards could be configured with: <br />
<br />
''np=#NUM_OF_GPGPUS''<br />
<br />
A virtual machine could the remaining number of cores:<br />
<br />
''np=#NUM_OF_CORES-#NUM_OF_GPGPUS'' job slots<br />
<br />
<br />
The drawback of this scheme is that we need to develop a scheme to ensure that jobs from distinct users cannot interfere with each other. User code could try to enumerate and use all the GPGPUs on the node. This will have (potentially job-catastrophic) unintended side-effects, so we need some mechanism to ensure that a user-job does not consume more than its allocation. <br />
<br />
The VT '''must''' investigate ways of mitigating cross-job contamination, such as linux cgroups and cpusets.<br />
<br />
<br />
<br />
=== JDL Example 3 JDL - multiple GPGPU per node ===<br />
<br />
This example should ensure 2 GPGPUs on the same host. Again, if there are more than 2 GPGPUs on the node, we need to ensure that other user processes do no interfere with each other. This is equivalent to the PBS '''-l nodes=1:ppn=2'''. In reality 2 cores are actually allocated to the job, so there is a potential waste of resources.<br />
<br />
<pre><br />
[<br />
Type="Job";<br />
JobType="Normal";<br />
CPUnumber=2;<br />
SMPgranularity=2;<br />
# We assume that the GPGPU application will take responsibilty for enumerating both GPGPU devices<br />
Executable = "myScript.sh"; <br />
StdOutput = "std.out";<br />
StdError = "std.err";<br />
InputSandbox = {"myScript.sh"};<br />
Requirements = ( RegExp(".*gpgpu$", other.GlueCEUniqueID) && Member("CUDA", other.GlueHostApplicationSoftwareRunTimeEnvironment);<br />
]<br />
</pre></div>Walshj1https://wiki.egi.eu/w/index.php?title=GPGPU-WG_ExperimentalTestingSetup&diff=68526GPGPU-WG ExperimentalTestingSetup2014-07-16T16:56:11Z<p>Walshj1: Created page with "An experimental system for advertising GPGPUs, passing parameters to the native LRMS and basic service discovery/match-making is described: * Service Discovery * JDL Specificati..."</p>
<hr />
<div>An experimental system for advertising GPGPUs, passing parameters to the native LRMS and basic service discovery/match-making is described:<br />
<br />
* Service Discovery<br />
* JDL Specification<br />
* Batch System Integration<br />
* MatchMaking and Job Submission</div>Walshj1https://wiki.egi.eu/w/index.php?title=GPGPU-WG_KnowledgeBase_Batch_Schedulers&diff=68524GPGPU-WG KnowledgeBase Batch Schedulers2014-07-16T15:11:22Z<p>Walshj1: </p>
<hr />
<div>This section contains links to the current knowlege base of Scheduler Support for GPGPUs.<br />
<br />
* [[GPGPU-WG:GPGPU_Working_Group_KnowledgeBase:Batch_Schedulers:Torque | Torque (Without Maui)]]<br />
* [[GPGPU-WG:GPGPU_Working_Group_KnowledgeBase:Batch_Schedulers:Torque_MAUI | Torque/MAUI]]<br />
* [[GPGPU-WG:GPGPU_Working_Group_KnowledgeBase:Batch_Schedulers:SLURM | SLURM]]<br />
* [[GPGPU-WG:GPGPU_Working_Group_KnowledgeBase:Batch_Schedulers:Condor | Condor]]<br />
* [[GPGPU-WG:GPGPU_Working_Group_KnowledgeBase:Batch_Schedulers:LSF | LSF]]<br />
* [[GPGPU-WG:GPGPU_Working_Group_KnowledgeBase:Batch_Schedulers:SGE | SGE]]</div>Walshj1https://wiki.egi.eu/w/index.php?title=GPGPU_Working_Group_KnowledgeBase_-_Batch_Schedulers_-_Condor&diff=68523GPGPU Working Group KnowledgeBase - Batch Schedulers - Condor2014-07-16T15:08:45Z<p>Walshj1: Created page with "The HTCondor batch system has support for both ATI and Nvidia GPGPUs. Further details can be found at https://htcondor-wiki.cs.wisc.edu/index.cgi/wiki?p=HowToManageGpus"</p>
<hr />
<div>The HTCondor batch system has support for both ATI and Nvidia GPGPUs. Further details can be found at https://htcondor-wiki.cs.wisc.edu/index.cgi/wiki?p=HowToManageGpus</div>Walshj1https://wiki.egi.eu/w/index.php?title=GPGPU_WG_KnowledgeBase_-Batch_Schedulers_-_SLURM&diff=67260GPGPU WG KnowledgeBase -Batch Schedulers - SLURM2014-05-09T14:09:28Z<p>Walshj1: </p>
<hr />
<div>SLURM has increased in popularity as the LRMS of choice at many large resource centres.<br />
This document does not <br />
<br />
<br />
GPGPU resources are handled as a '''Generic Resource''' under SLURM.<br />
To add support for GPGPU generic resources, the following value must be declared in slurm.conf:<br />
<pre><br />
GresTypes=gpu<br />
# cons_res seems to be necessary to stop all cores being allocated on the workernode for the job <br />
SelectType=select/cons_res<br />
</pre><br />
<br />
<br />
To declare that a workernode supports GPGPUs, the resource must be declared through the NodeName/NodeAddr statement.<br />
<pre><br />
#Declare a range of nodes wn0 -> wn9<br />
#Each of these nodes has 2 GPGPUs and 8 job slots<br />
NodeName=wn[0-9].example.com Gres=gpu:2 CPUs=8<br />
</pre><br />
<br />
A '''Partition''' defined a set of related nodes, and is somewhat equivalent to a PBS queue.<br />
<pre><br />
PartitionName=gpgpu Nodes=wn[0-9].example.com Default=YES MaxTime=INFINITE State=UP Shared=YES<br />
</pre><br />
<br />
<br />
<br />
<br />
<br />
To view which nodes support GPU resources:<br />
<pre><br />
NodeName=wn0 Arch=x86_64 CoresPerSocket=1<br />
CPUAlloc=0 CPUErr=0 CPUTot=8 CPULoad=0.00 Features=(null)<br />
Gres=gpu:2<br />
NodeAddr=wn0.example.com NodeHostName=wn0.example.com<br />
OS=Linux RealMemory=1 AllocMem=0 Sockets=8 Boards=1<br />
State=IDLE ThreadsPerCore=1 TmpDisk=0 Weight=1<br />
BootTime=2014-01-27T22:30:02 SlurmdStartTime=2014-01-30T15:58:43<br />
CurrentWatts=0 LowestJoules=0 ConsumedJoules=0<br />
ExtSensorsJoules=n/s ExtSensorsWatts=0 ExtSensorsTemp=n/s<br />
</pre><br />
<br />
<br />
The above configuration will prevent more than two jobs requiring a single GPU from running simultaneously<br />
<pre><br />
srun -p gpgpu --gres=gpu:1 sleep 20 &<br />
srun -p gpgpu --gres=gpu:1 sleep 20 &<br />
srun -p gpgpu --gres=gpu:1 sleep 20 & # This job should wait until a GPGPU is available<br />
srun -p gpgpu sleep 20 # This job will run immediately is a job slot is available<br />
</pre><br />
<br />
<br />
SLURM can also handle CUDA_VISIBILE_DEVICES correctly:<br />
<pre><br />
# Acquire 2 GPU on same node<br />
srun -p gpgpu --gres=gpu:2 env | grep -i cuda<br />
CUDA_VISIBLE_DEVICES=0,1<br />
<br />
#Acquire 1 GPU on Node<br />
srun -p gpgpu --gres=gpu:1 env | grep -i cuda<br />
CUDA_VISIBLE_DEVICES=0<br />
</pre></div>Walshj1https://wiki.egi.eu/w/index.php?title=GPGPU-WG_KnowledgeBase_GLUE2_Profile_ExecutionEnvironment&diff=65271GPGPU-WG KnowledgeBase GLUE2 Profile ExecutionEnvironment2014-03-03T13:22:26Z<p>Walshj1: </p>
<hr />
<div>== Introduction ==<br />
<br />
The ExecutionEnvironment class describes the hardware and operating system environment in which a job will run. It represents a set of homogeneous Worker Nodes, so if a computing system contains nodes with significantly different properties there MAY be several ExecutionEnvironment instances. This implies that it should be possible to request a specific environment when a job is submitted. The ExecutionEnvironment MAY refer to virtual rather than physical machines.<br />
<br />
As well as attributes describing a typical node, the class gives summary information about the size and usage of the set of nodes which posess those properties. However, there is no way to relate these to the information in other entities, e.g. it is not possible to know which jobs in a given ComputingShare are running on which ExecutionEnvironment.<br />
<br />
<br />
== Discussion Points ==<br />
The ExecutionEnvironment attributes (listed below) describe the properties of a CPU environment. The question as to whether this is an appropriate environment for decribing Accelerators is an issue that this Working Group should either recommend or advise against. Arguments for both cases are listed below:<br />
<br />
* Pro<br />
** Can describe basic properties of GPGPU/Accelerator (e.g. Vendor, Model, Quantity, Speed, Memory)<br />
** Can associate/assign multiple Benchmarks to the ExecutionEnvironment<br />
** Can use the OpenCL platform/device classification to easily agree a common description for salient attributes<br />
* Contra <br />
** Does not describe Num of Streaming Cores/Parallel Threads.<br />
<br />
<br />
{| class="wikitable"<br />
!colspan="5"| '''ExecutionEnvironment'''<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
|'''Entity'''<br />
|colspan=3 | '''Inherits from'''<br />
|'''Description'''<br />
|- <br />
| ExecutionEnvironment <br />
| colspan="3" | Resource<br />
| A type of environment available to and requestable by a Grid job when submitted to a<br />
ComputingService via a Computing Endpoint; the type of environment is described in terms of hardware, operating system and network characteristics. Information about the total/available/used instances of this type of execution environment are also included.<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
| '''Inherited Attribute '''<br />
| '''Type'''<br />
| '''Mult'''<br />
| '''Unit'''<br />
| '''Description'''<br />
|-<br />
| ''Creation Time''<br />
| ''DateTime_t''<br />
| ''0..1''<br />
|<br />
| ''Timestamp describing when the entity instance was created''<br />
|-<br />
| ''Validity''<br />
| ''Unit64''<br />
| ''0..1''<br />
| ''s''<br />
| '' The duration after CreationTime that the information presented in the Entity SHOULD be considered relevant. After that period has elapsed, the information SHOULD NOT be consideredrelevant''<br />
|-<br />
| ''ID [key]''<br />
| ''URI''<br />
| ''1''<br />
|<br />
| ''A global unique ID''<br />
|-<br />
| ''Name''<br />
| ''String''<br />
| ''0..1''<br />
|<br />
| ''Human Readable name''<br />
|-<br />
| ''OtherInfo''<br />
| ''String''<br />
| ''*''<br />
|<br />
| ''Placeholder to publish info that does not fit in any other attribute. Free-form string, comma-separated tags, (name, value ) pair are all examples of valid syntax.''<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
| '''Attribute '''<br />
| '''Type'''<br />
| '''Mult'''<br />
| '''Unit'''<br />
| '''Description'''<br />
|-<br />
| Platform<br />
| Platform_t<br />
| 1<br />
|<br />
| The platform of this Execution Environment.<br />
|-<br />
| VirtualMachine<br />
| ExtendedBoolean_t<br />
| 0..1<br />
|<br />
| True if the Execution Environment is hosted within a virtual machine; in this case, the values of the other attributes are related to the virtualized environment and not to the hosting environment.<br />
|-<br />
| TotalInstances<br />
| UInt32<br />
| 0..1<br />
|<br />
| The total number of Execution Environment instances. This SHOULD reflect the total installed capacity, i.e. including resources which are temporarily unavailable.<br />
|-<br />
| UsedInstances <br />
| UInt32 <br />
| 0..1<br />
|<br />
| The number of Execution Environment instances which are considered to be fully used; an instance is used when, according to the policies of the Computing Manager (i.e., LRMS), it cannot accept new jobs because it already runs the maximum number of allowed jobs.<br />
|-<br />
| UnavailableInstances<br />
| UInt32<br />
| 0..1<br />
|<br />
| The number of Execution Environment instances which are currently unavailable, e.g. because of failures or maintenance.<br />
|-<br />
| PhysicalCPUs <br />
| UInt32<br />
| 0..1<br />
|<br />
| The number of physical CPUs in one ExecutionEnvironment instance, i.e. the number of sockets per Worker Node.<br />
|-<br />
| LogicalCPUs<br />
| UInt32<br />
| 0..1<br />
|<br />
| The number of logical CPUs in one ExecutionEnvironment instance, i.e. typically the number of cores per Worker Node.<br />
|-<br />
| CPUMultiplicity<br />
| CPUMultiplicity_t<br />
| 0..1<br />
|<br />
| Condensed information about the multiplicity of both physical CPUs and cores available in an execution environment instance..<br />
|-<br />
| CPUVendor<br />
| String<br />
| 0..1<br />
|<br />
| The name of the physical CPU vendor. Free format, but it SHOULD correspond to the name by which the vendor is generally known.<br />
|-<br />
| CPUModel<br />
| String<br />
| 0..1<br />
|<br />
| The name of the physical CPU model, as defined by the vendor.<br />
|-<br />
| CPUVersion<br />
| String<br />
| 0..1<br />
|<br />
| The specific version of the Physical CPU model, as defined by the vendor<br />
|-<br />
| CPUClockSpeed<br />
| UInt32<br />
| 0..1<br />
| MHz<br />
| The nominal clock speed of the physical CPU.<br />
|-<br />
| CPUTimeScalingFactor<br />
| Real32<br />
| 0..1<br />
|<br />
| The factor used by the Computing Manager (i.e., LRMS) to scale the CPU time limit (the CPU Time is divided by the CPUTimeScalingFactor); for the reference execution environment, this attribute is equal to 1. See the description of the ComputingShare for further information.<br />
|-<br />
| WallTimeScalingFactor<br />
| Real32<br />
| 0..1<br />
|<br />
| The factor used by the Computing Manager (i.e., LRMS) to scale the Wallclock time limit (the Wallclock Time is divided by the WallTimeScalingFactor). See the description of the ComputingShare for further information.<br />
|-<br />
| MainMemorySize<br />
| UInt64 <br />
| 1<br />
| MB<br />
| The total amount of physical RAM in one Execution Environment instance; if many jobs run in the same instance they compete for the total RAM.<br />
|-<br />
| VirtualMemorySize<br />
| UInt64<br />
| 0..1<br />
| MB<br />
| The total amount of virtual memory (RAM plus swap space) in one ExecutionEnvironment instance.<br />
|-<br />
| OSFamily<br />
| OSFamily_t<br />
| 1<br />
|<br />
| The general family to which the ExecutionEnvironment operating system belongs.<br />
|-<br />
| OSName<br />
| OSName_t<br />
| 0..1<br />
|<br />
| The specific name of the operating system.<br />
|-<br />
| OSVersion <br />
| String <br />
| 0..1<br />
|<br />
| The version of the operating system, as defined by the vendor. <br />
|-<br />
| ConnectivityIn<br />
| ExtendedBoolean_t <br />
| 1<br />
|<br />
| True if direct inbound network connectivity is available to a running job, even if limited, e.g. by firewall rules.<br />
|-<br />
| ConnectivityOut<br />
| ExtendedBoolean_t<br />
| 1<br />
|<br />
| True if direct outbound network connectivity is available from a running job, even if limited, e.g. by firewall rules.<br />
|-<br />
| NetworkInfo<br />
| NetworkInfo_t<br />
| *<br />
|<br />
| The type of internal network connection available among the Execution Environment instances.<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
| colspan="2" | '''Association End'''<br />
| '''Mult.'''<br />
| colspan=2 | '''Description'''<br />
|- <br />
| colspan="2" | ComputingManager.ID (Redefines Manager.ID)<br />
| 1<br />
| colspan="2" | An execution environment is managed by a computing manager.<br />
|-<br />
| colspan="2" | ComputingShare.ID (Redefines Share.ID)<br />
| *<br />
| colspan="2" | An execution environment provides capacity in terms of computing shares.<br />
|-<br />
| colspan="2" | ComputingActivity.ID<br />
| *<br />
| colspan="2" | An execution environment runs zero or more computing activities.<br />
|-<br />
| colspan="2" | ApplicationEnvironment.ID<br />
| *<br />
| colspan="2" | An execution environment offers zero or more application environments.<br />
|-<br />
| colspan="2" | Benchmark.ID<br />
| *<br />
| colspan="2" | An execution environment has zero or more associated benchmarks.<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
| colspan="2" | '''Inherited Association End'''<br />
| '''Mult.'''<br />
| colspan="2" | '''Description'''<br />
|-<br />
| colspan="2" |Extension.Key<br />
| *<br />
| colspan="2" | The entity MAY be extended via key-value pairs<br />
|}</div>Walshj1https://wiki.egi.eu/w/index.php?title=GPGPU-WG_KnowledgeBase_GLUE2_Profile_ExecutionEnvironment&diff=65252GPGPU-WG KnowledgeBase GLUE2 Profile ExecutionEnvironment2014-03-02T22:47:25Z<p>Walshj1: </p>
<hr />
<div>The ExecutionEnvironment class describes the hardware and operating system environment in which a job will run. It represents a set of homogeneous Worker Nodes, so if a computing system contains nodes with significantly different properties there MAY be several ExecutionEnvironment instances. This implies that it should be possible to request a specific environment when a job is submitted. The ExecutionEnvironment MAY refer to virtual rather than physical machines.<br />
<br />
As well as attributes describing a typical node, the class gives summary information about the size and usage of the set of nodes which posess those properties. However, there is no way to relate these to the information in other entities, e.g. it is not possible to know which jobs in a given ComputingShare are running on which ExecutionEnvironment.<br />
<br />
<br />
<br />
{| class="wikitable"<br />
!colspan="5"| '''ExecutionEnvironment'''<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
|'''Entity'''<br />
|colspan=3 | '''Inherits from'''<br />
|'''Description'''<br />
|- <br />
| ExecutionEnvironment <br />
| colspan="3" | Resource<br />
| A type of environment available to and requestable by a Grid job when submitted to a<br />
ComputingService via a Computing Endpoint; the type of environment is described in terms of hardware, operating system and network characteristics. Information about the total/available/used instances of this type of execution environment are also included.<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
| '''Inherited Attribute '''<br />
| '''Type'''<br />
| '''Mult'''<br />
| '''Unit'''<br />
| '''Description'''<br />
|-<br />
| ''Creation Time''<br />
| ''DateTime_t''<br />
| ''0..1''<br />
|<br />
| ''Timestamp describing when the entity instance was created''<br />
|-<br />
| ''Validity''<br />
| ''Unit64''<br />
| ''0..1''<br />
| ''s''<br />
| '' The duration after CreationTime that the information presented in the Entity SHOULD be considered relevant. After that period has elapsed, the information SHOULD NOT be consideredrelevant''<br />
|-<br />
| ''ID [key]''<br />
| ''URI''<br />
| ''1''<br />
|<br />
| ''A global unique ID''<br />
|-<br />
| ''Name''<br />
| ''String''<br />
| ''0..1''<br />
|<br />
| ''Human Readable name''<br />
|-<br />
| ''OtherInfo''<br />
| ''String''<br />
| ''*''<br />
|<br />
| ''Placeholder to publish info that does not fit in any other attribute. Free-form string, comma-separated tags, (name, value ) pair are all examples of valid syntax.''<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
| '''Attribute '''<br />
| '''Type'''<br />
| '''Mult'''<br />
| '''Unit'''<br />
| '''Description'''<br />
|-<br />
| Platform<br />
| Platform_t<br />
| 1<br />
|<br />
| The platform of this Execution Environment.<br />
|-<br />
| VirtualMachine<br />
| ExtendedBoolean_t<br />
| 0..1<br />
|<br />
| True if the Execution Environment is hosted within a virtual machine; in this case, the values of the other attributes are related to the virtualized environment and not to the hosting environment.<br />
|-<br />
| TotalInstances<br />
| UInt32<br />
| 0..1<br />
|<br />
| The total number of Execution Environment instances. This SHOULD reflect the total installed capacity, i.e. including resources which are temporarily unavailable.<br />
|-<br />
| UsedInstances <br />
| UInt32 <br />
| 0..1<br />
|<br />
| The number of Execution Environment instances which are considered to be fully used; an instance is used when, according to the policies of the Computing Manager (i.e., LRMS), it cannot accept new jobs because it already runs the maximum number of allowed jobs.<br />
|-<br />
| UnavailableInstances<br />
| UInt32<br />
| 0..1<br />
|<br />
| The number of Execution Environment instances which are currently unavailable, e.g. because of failures or maintenance.<br />
|-<br />
| PhysicalCPUs <br />
| UInt32<br />
| 0..1<br />
|<br />
| The number of physical CPUs in one ExecutionEnvironment instance, i.e. the number of sockets per Worker Node.<br />
|-<br />
| LogicalCPUs<br />
| UInt32<br />
| 0..1<br />
|<br />
| The number of logical CPUs in one ExecutionEnvironment instance, i.e. typically the number of cores per Worker Node.<br />
|-<br />
| CPUMultiplicity<br />
| CPUMultiplicity_t<br />
| 0..1<br />
|<br />
| Condensed information about the multiplicity of both physical CPUs and cores available in an execution environment instance..<br />
|-<br />
| CPUVendor<br />
| String<br />
| 0..1<br />
|<br />
| The name of the physical CPU vendor. Free format, but it SHOULD correspond to the name by which the vendor is generally known.<br />
|-<br />
| CPUModel<br />
| String<br />
| 0..1<br />
|<br />
| The name of the physical CPU model, as defined by the vendor.<br />
|-<br />
| CPUVersion<br />
| String<br />
| 0..1<br />
|<br />
| The specific version of the Physical CPU model, as defined by the vendor<br />
|-<br />
| CPUClockSpeed<br />
| UInt32<br />
| 0..1<br />
| MHz<br />
| The nominal clock speed of the physical CPU.<br />
|-<br />
| CPUTimeScalingFactor<br />
| Real32<br />
| 0..1<br />
|<br />
| The factor used by the Computing Manager (i.e., LRMS) to scale the CPU time limit (the CPU Time is divided by the CPUTimeScalingFactor); for the reference execution environment, this attribute is equal to 1. See the description of the ComputingShare for further information.<br />
|-<br />
| WallTimeScalingFactor<br />
| Real32<br />
| 0..1<br />
|<br />
| The factor used by the Computing Manager (i.e., LRMS) to scale the Wallclock time limit (the Wallclock Time is divided by the WallTimeScalingFactor). See the description of the ComputingShare for further information.<br />
|-<br />
| MainMemorySize<br />
| UInt64 <br />
| 1<br />
| MB<br />
| The total amount of physical RAM in one Execution Environment instance; if many jobs run in the same instance they compete for the total RAM.<br />
|-<br />
| VirtualMemorySize<br />
| UInt64<br />
| 0..1<br />
| MB<br />
| The total amount of virtual memory (RAM plus swap space) in one ExecutionEnvironment instance.<br />
|-<br />
| OSFamily<br />
| OSFamily_t<br />
| 1<br />
|<br />
| The general family to which the ExecutionEnvironment operating system belongs.<br />
|-<br />
| OSName<br />
| OSName_t<br />
| 0..1<br />
|<br />
| The specific name of the operating system.<br />
|-<br />
| OSVersion <br />
| String <br />
| 0..1<br />
|<br />
| The version of the operating system, as defined by the vendor. <br />
|-<br />
| ConnectivityIn<br />
| ExtendedBoolean_t <br />
| 1<br />
|<br />
| True if direct inbound network connectivity is available to a running job, even if limited, e.g. by firewall rules.<br />
|-<br />
| ConnectivityOut<br />
| ExtendedBoolean_t<br />
| 1<br />
|<br />
| True if direct outbound network connectivity is available from a running job, even if limited, e.g. by firewall rules.<br />
|-<br />
| NetworkInfo<br />
| NetworkInfo_t<br />
| *<br />
|<br />
| The type of internal network connection available among the Execution Environment instances.<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
| colspan="2" | '''Association End'''<br />
| '''Mult.'''<br />
| colspan=2 | '''Description'''<br />
|- <br />
| colspan="2" | ComputingManager.ID (Redefines Manager.ID)<br />
| 1<br />
| colspan="2" | An execution environment is managed by a computing manager.<br />
|-<br />
| colspan="2" | ComputingShare.ID (Redefines Share.ID)<br />
| *<br />
| colspan="2" | An execution environment provides capacity in terms of computing shares.<br />
|-<br />
| colspan="2" | ComputingActivity.ID<br />
| *<br />
| colspan="2" | An execution environment runs zero or more computing activities.<br />
|-<br />
| colspan="2" | ApplicationEnvironment.ID<br />
| *<br />
| colspan="2" | An execution environment offers zero or more application environments.<br />
|-<br />
| colspan="2" | Benchmark.ID<br />
| *<br />
| colspan="2" | An execution environment has zero or more associated benchmarks.<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
| colspan="2" | '''Inherited Association End'''<br />
| '''Mult.'''<br />
| colspan="2" | '''Description'''<br />
|-<br />
| colspan="2" |Extension.Key<br />
| *<br />
| colspan="2" | The entity MAY be extended via key-value pairs<br />
|}</div>Walshj1https://wiki.egi.eu/w/index.php?title=GPGPU-WG_KnowledgeBase_GLUE2_Profile_ExecutionEnvironment&diff=65251GPGPU-WG KnowledgeBase GLUE2 Profile ExecutionEnvironment2014-03-02T22:40:11Z<p>Walshj1: </p>
<hr />
<div>The ExecutionEnvironment class describes the hardware and operating system environment in which a job will run. It represents a set of homogeneous Worker Nodes, so if a computing system contains nodes with significantly different properties there MAY be several ExecutionEnvironment instances. This implies that it should be possible to request a specific environment when a job is submitted. The ExecutionEnvironment MAY refer to virtual rather than physical machines.<br />
<br />
As well as attributes describing a typical node, the class gives summary information about the size and usage of the set of nodes which posess those properties. However, there is no way to relate these to the information in other entities, e.g. it is not possible to know which jobs in a given ComputingShare are running on which ExecutionEnvironment.<br />
<br />
<br />
<br />
{| class="wikitable"<br />
!colspan="5"| '''ExecutionEnvironment'''<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
|'''Entity'''<br />
|colspan=3 | '''Inherits from'''<br />
|'''Description'''<br />
|- <br />
| ExecutionEnvironment <br />
| colspan="3" | Resource<br />
| A type of environment available to and requestable by a Grid job when submitted to a<br />
ComputingService via a Computing Endpoint; the type of environment is described in terms of hardware, operating system and network characteristics. Information about the total/available/used instances of this type of execution environment are also included.<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
| '''Inherited Attribute '''<br />
| '''Type'''<br />
| '''Mult'''<br />
| '''Unit'''<br />
| '''Description'''<br />
|-<br />
| ''Creation Time''<br />
| ''DateTime_t''<br />
| ''0..1''<br />
|<br />
| ''Timestamp describing when the entity instance was created''<br />
|-<br />
| ''Validity''<br />
| ''Unit64''<br />
| ''0..1''<br />
| ''s''<br />
| '' The duration after CreationTime that the information presented in the Entity SHOULD be considered relevant. After that period has elapsed, the information SHOULD NOT be consideredrelevant''<br />
|-<br />
| ''ID [key]''<br />
| ''URI''<br />
| ''1''<br />
|<br />
| ''A global unique ID''<br />
|-<br />
| ''Name''<br />
| ''String''<br />
| ''0..1''<br />
|<br />
| ''Human Readable name''<br />
|-<br />
| ''OtherInfo''<br />
| ''String''<br />
| ''*''<br />
|<br />
| ''Placeholder to publish info that does not fit in any other attribute. Free-form string, comma-separated tags, (name, value ) pair are all examples of valid syntax.''<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
| '''Attribute '''<br />
| '''Type'''<br />
| '''Mult'''<br />
| '''Unit'''<br />
| '''Description'''<br />
|-<br />
| Platform<br />
| Platform_t<br />
| 1<br />
|<br />
| The platform of this Execution Environment.<br />
|-<br />
| VirtualMachine<br />
| ExtendedBoolean_t<br />
| 0..1<br />
|<br />
| True if the Execution Environment is hosted within a virtual machine; in this case, the values of the other attributes are related to the virtualized environment and not to the hosting environment.<br />
|-<br />
| TotalInstances<br />
| UInt32<br />
| 0..1<br />
|<br />
| The total number of Execution Environment instances. This SHOULD reflect the total installed capacity, i.e. including resources which are temporarily unavailable.<br />
|-<br />
| UsedInstances <br />
| UInt32 <br />
| 0..1<br />
|<br />
| The number of Execution Environment instances which are considered to be fully used; an instance is used when, according to the policies of the Computing Manager (i.e., LRMS), it cannot accept new jobs because it already runs the maximum number of allowed jobs.<br />
|-<br />
| UnavailableInstances<br />
| UInt32<br />
| 0..1<br />
|<br />
| The number of Execution Environment instances which are currently unavailable, e.g. because of failures or maintenance.<br />
|-<br />
| PhysicalCPUs <br />
| UInt32<br />
| 0..1<br />
|<br />
| The number of physical CPUs in one ExecutionEnvironment instance, i.e. the number of sockets per Worker Node.<br />
|-<br />
| LogicalCPUs<br />
| UInt32<br />
| 0..1<br />
|<br />
| The number of logical CPUs in one ExecutionEnvironment instance, i.e. typically the number of cores per Worker Node.<br />
|-<br />
| CPUMultiplicity<br />
| CPUMultiplicity_t<br />
| 0..1<br />
|<br />
| Condensed information about the multiplicity of both physical CPUs and cores available in an execution environment instance..<br />
|-<br />
| CPUVendor<br />
| String<br />
| 0..1<br />
|<br />
| The name of the physical CPU vendor. Free format, but it SHOULD correspond to the name by which the vendor is generally known.<br />
|-<br />
| CPUModel<br />
| String<br />
| 0..1<br />
|<br />
| The name of the physical CPU model, as defined by the vendor.<br />
|-<br />
| CPUVersion<br />
| String<br />
| 0..1<br />
|<br />
| The specific version of the Physical CPU model, as defined by the vendor<br />
|-<br />
| CPUClockSpeed<br />
| UInt32<br />
| 0..1<br />
| MHz<br />
| The nominal clock speed of the physical CPU.<br />
|-<br />
| CPUTimeScalingFactor<br />
| Real32<br />
| 0..1<br />
|<br />
| The factor used by the Computing Manager (i.e., LRMS) to scale the CPU time limit (the CPU Time is divided by the CPUTimeScalingFactor); for the reference execution environment, this attribute is equal to 1. See the description of the ComputingShare for further information.<br />
|-<br />
| WallTimeScalingFactor<br />
| Real32<br />
| 0..1<br />
|<br />
| The factor used by the Computing Manager (i.e., LRMS) to scale the Wallclock time limit (the Wallclock Time is divided by the WallTimeScalingFactor). See the description of the ComputingShare for further information.<br />
|-<br />
| MainMemorySize<br />
| UInt64 <br />
| 1<br />
| MB<br />
| The total amount of physical RAM in one Execution Environment instance; if many jobs run in the same instance they compete for the total RAM.<br />
|-<br />
| VirtualMemorySize<br />
| UInt64<br />
| 0..1<br />
| MB<br />
| The total amount of virtual memory (RAM plus swap space) in one ExecutionEnvironment instance.<br />
|-<br />
| OSFamily<br />
| OSFamily_t<br />
| 1<br />
|<br />
| The general family to which the ExecutionEnvironment operating system belongs.<br />
|-<br />
| OSName<br />
| OSName_t<br />
| 0..1<br />
|<br />
| The specific name of the operating system.<br />
|-<br />
| OSVersion <br />
| String <br />
| 0..1<br />
|<br />
| The version of the operating system, as defined by the vendor. <br />
|-<br />
| ConnectivityIn<br />
| ExtendedBoolean_t <br />
| 1<br />
|<br />
| True if direct inbound network connectivity is available to a running job, even if limited, e.g. by firewall rules.<br />
|-<br />
| ConnectivityOut<br />
| ExtendedBoolean_t<br />
| 1<br />
|<br />
| True if direct outbound network connectivity is available from a running job, even if limited, e.g. by firewall rules.<br />
|-<br />
| NetworkInfo<br />
| NetworkInfo_t<br />
| *<br />
|<br />
| The type of internal network connection available among the Execution Environment instances.<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
| colspan="2" | '''Association End'''<br />
| '''Mult.'''<br />
| colspan=2 | '''Description'''<br />
|- <br />
| colspan="2" | ComputingManager.ID (Redefines Manager.ID)<br />
| 1<br />
| colspan="2" | An execution environment is managed by a computing manager.<br />
|-<br />
| colspan="2" | ComputingShare.ID (Redefines Share.ID)<br />
| *<br />
| colspan="2" | An execution environment provides capacity in terms of computing shares.<br />
|-<br />
| colspan="2" | ComputingActivity.ID<br />
| *<br />
| colspan="2" | An execution environment runs zero or more computing activities.<br />
|-<br />
| colspan="2" | ApplicationEnvironment.ID<br />
| *<br />
| colspan="2" | An execution environment runs zero or more computing activities.<br />
|-<br />
| colspan="2" | Benchmark.ID<br />
| *<br />
| colspan="2" | An execution environment runs zero or more computing activities.<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
| colspan="2" | '''Inherited Association End'''<br />
| '''Mult.'''<br />
| colspan="2" | '''Description'''<br />
|-<br />
| colspan="2" |Extension.Key<br />
| *<br />
| colspan="2" | The entity MAY be extended via key-value pairs<br />
|}</div>Walshj1https://wiki.egi.eu/w/index.php?title=GPGPU-WG_KnowledgeBase_GLUE2_Profile_ExecutionEnvironment&diff=65250GPGPU-WG KnowledgeBase GLUE2 Profile ExecutionEnvironment2014-03-02T22:07:24Z<p>Walshj1: </p>
<hr />
<div>The ExecutionEnvironment class describes the hardware and operating system environment in which a job will run. It represents a set of homogeneous Worker Nodes, so if a computing system contains nodes with significantly different properties there MAY be several ExecutionEnvironment instances. This implies that it should be possible to request a specific environment when a job is submitted. The ExecutionEnvironment MAY refer to virtual rather than physical machines.<br />
<br />
As well as attributes describing a typical node, the class gives summary information about the size and usage of the set of nodes which posess those properties. However, there is no way to relate these to the information in other entities, e.g. it is not possible to know which jobs in a given ComputingShare are running on which ExecutionEnvironment.<br />
<br />
<br />
<br />
{| class="wikitable"<br />
!colspan="5"| '''ExecutionEnvironment'''<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
|'''Entity'''<br />
|colspan=3 | '''Inherits from'''<br />
|'''Description'''<br />
|- <br />
| ExecutionEnvironment <br />
| colspan="3" | Resource<br />
| A type of environment available to and requestable by a Grid job when submitted to a<br />
ComputingService via a Computing Endpoint; the type of environment is described in terms of hardware, operating system and network characteristics. Information about the total/available/used instances of this type of execution environment are also included.<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
| '''Inherited Attribute '''<br />
| '''Type'''<br />
| '''Mult'''<br />
| '''Unit'''<br />
| '''Description'''<br />
|-<br />
| ''Creation Time''<br />
| ''DateTime_t''<br />
| ''0..1''<br />
|<br />
| ''Timestamp describing when the entity instance was created''<br />
|-<br />
| ''Validity''<br />
| ''Unit64''<br />
| ''0..1''<br />
| ''s''<br />
| '' The duration after CreationTime that the information presented in the Entity SHOULD be considered relevant. After that period has elapsed, the information SHOULD NOT be consideredrelevant''<br />
|-<br />
| ''ID [key]''<br />
| ''URI''<br />
| ''1''<br />
|<br />
| ''A global unique ID''<br />
|-<br />
| ''Name''<br />
| ''String''<br />
| ''0..1''<br />
|<br />
| ''Human Readable name''<br />
|-<br />
| ''OtherInfo''<br />
| ''String''<br />
| ''*''<br />
|<br />
| ''Placeholder to publish info that does not fit in any other attribute. Free-form string, comma-separated tags, (name, value ) pair are all examples of valid syntax.''<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
| '''Attribute '''<br />
| '''Type'''<br />
| '''Mult'''<br />
| '''Unit'''<br />
| '''Description'''<br />
|-<br />
| Platform<br />
| Platform_t<br />
| 1<br />
|<br />
| The platform of this Execution Environment.<br />
|-<br />
| VirtualMachine<br />
| ExtendedBoolean_t<br />
| 0..1<br />
|<br />
| True if the Execution Environment is hosted within a virtual machine; in this case, the values of the other attributes are related to the virtualized environment and not to the hosting environment.<br />
|-<br />
| TotalInstances<br />
| UInt32<br />
| 0..1<br />
|<br />
| The total number of Execution Environment instances. This SHOULD reflect the total installed capacity, i.e. including resources which are temporarily unavailable.<br />
|-<br />
| UsedInstances <br />
| UInt32 <br />
| 0..1<br />
|<br />
| The number of Execution Environment instances which are considered to be fully used; an instance is used when, according to the policies of the Computing Manager (i.e., LRMS), it cannot accept new jobs because it already runs the maximum number of allowed jobs.<br />
|-<br />
| UnavailableInstances<br />
| UInt32<br />
| 0..1<br />
|<br />
| The number of Execution Environment instances which are currently unavailable, e.g. because of failures or maintenance.<br />
|-<br />
| PhysicalCPUs <br />
| UInt32<br />
| 0..1<br />
|<br />
| The number of physical CPUs in one ExecutionEnvironment instance, i.e. the number of sockets per Worker Node.<br />
|-<br />
| LogicalCPUs<br />
| UInt32<br />
| 0..1<br />
|<br />
| The number of logical CPUs in one ExecutionEnvironment instance, i.e. typically the number of cores per Worker Node.<br />
|-<br />
| CPUMultiplicity<br />
| CPUMultiplicity_t<br />
| 0..1<br />
|<br />
| Condensed information about the multiplicity of both physical CPUs and cores available in an execution environment instance..<br />
|-<br />
| CPUVendor<br />
| String<br />
| 0..1<br />
|<br />
| The name of the physical CPU vendor. Free format, but it SHOULD correspond to the name by which the vendor is generally known.<br />
|-<br />
| CPUModel<br />
| String<br />
| 0..1<br />
|<br />
| The name of the physical CPU model, as defined by the vendor.<br />
|-<br />
| CPUVersion<br />
| String<br />
| 0..1<br />
|<br />
| The specific version of the Physical CPU model, as defined by the vendor<br />
|-<br />
| CPUClockSpeed<br />
| UInt32<br />
| 0..1<br />
| MHz<br />
| The nominal clock speed of the physical CPU.<br />
|-<br />
| CPUTimeScalingFactor<br />
| Real32<br />
| 0..1<br />
|<br />
| The factor used by the Computing Manager (i.e., LRMS) to scale the CPU time limit (the CPU Time is divided by the CPUTimeScalingFactor); for the reference execution environment, this attribute is equal to 1. See the description of the ComputingShare for further information.<br />
|-<br />
| WallTimeScalingFactor<br />
| Real32<br />
| 0..1<br />
|<br />
| The factor used by the Computing Manager (i.e., LRMS) to scale the Wallclock time limit (the Wallclock Time is divided by the WallTimeScalingFactor). See the description of the ComputingShare for further information.<br />
|-<br />
| MainMemorySize<br />
| UInt64 <br />
| 1<br />
| MB<br />
| The total amount of physical RAM in one Execution Environment instance; if many jobs run in the same instance they compete for the total RAM.<br />
|-<br />
| VirtualMemorySize<br />
| UInt64<br />
| 0..1<br />
| MB<br />
| The total amount of virtual memory (RAM plus swap space) in one ExecutionEnvironment instance.<br />
|-<br />
| OSFamily<br />
| OSFamily_t<br />
| 1<br />
|<br />
| The general family to which the ExecutionEnvironment operating system belongs.<br />
|-<br />
| OSName<br />
| OSName_t<br />
| 0..1<br />
|<br />
| The specific name of the operating system.<br />
|-<br />
| OSVersion <br />
| String <br />
| 0..1<br />
|<br />
| The version of the operating system, as defined by the vendor. <br />
|-<br />
| ConnectivityIn<br />
| ExtendedBoolean_t <br />
| 1<br />
|<br />
| True if direct inbound network connectivity is available to a running job, even if limited, e.g. by firewall rules.<br />
|-<br />
| ConnectivityOut<br />
| ExtendedBoolean_t<br />
| 1<br />
|<br />
|<br />
|-<br />
| NetworkInfo<br />
| NetworkInfo_t<br />
| *<br />
|<br />
|<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
| colspan="2" | '''Association End'''<br />
| '''Mult.'''<br />
| colspan=2 | '''Description'''<br />
|- <br />
| colspan="2" | ExecutionEnvironment.ID<br />
| *<br />
| colspan="2" | An application environment MAY be used in zero or more execution environments<br />
|-<br />
| colspan="2" | ComputingManager.ID<br />
| 1<br />
| colspan="2" | An application environment is part of a computing manager.<br />
|-<br />
| colspan="2" | ApplicationHandle.ID<br />
| *<br />
| colspan="2" | An application environment MAY be handled via zero or more application handles.<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
| colspan="2" | '''Inherited Association End'''<br />
| '''Mult.'''<br />
| colspan="2" | '''Description'''<br />
|-<br />
| colspan="2" |Extension.Key<br />
| *<br />
| colspan="2" | The entity MAY be extended via key-value pairs<br />
|}</div>Walshj1https://wiki.egi.eu/w/index.php?title=GPGPU-WG_KnowledgeBase_GLUE2_Profile_ExecutionEnvironment&diff=65249GPGPU-WG KnowledgeBase GLUE2 Profile ExecutionEnvironment2014-03-02T21:58:48Z<p>Walshj1: </p>
<hr />
<div>The ExecutionEnvironment class describes the hardware and operating system environment in which a job will run. It represents a set of homogeneous Worker Nodes, so if a computing system contains nodes with significantly different properties there MAY be several ExecutionEnvironment instances. This implies that it should be possible to request a specific environment when a job is submitted. The ExecutionEnvironment MAY refer to virtual rather than physical machines.<br />
<br />
As well as attributes describing a typical node, the class gives summary information about the size and usage of the set of nodes which posess those properties. However, there is no way to relate these to the information in other entities, e.g. it is not possible to know which jobs in a given ComputingShare are running on which ExecutionEnvironment.<br />
<br />
<br />
<br />
{| class="wikitable"<br />
!colspan="5"| '''ExecutionEnvironment'''<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
|'''Entity'''<br />
|colspan=3 | '''Inherits from'''<br />
|'''Description'''<br />
|- <br />
| ExecutionEnvironment <br />
| colspan="3" | Resource<br />
| A type of environment available to and requestable by a Grid job when submitted to a<br />
ComputingService via a Computing Endpoint; the type of environment is described in terms of hardware, operating system and network characteristics. Information about the total/available/used instances of this type of execution environment are also included.<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
| '''Inherited Attribute '''<br />
| '''Type'''<br />
| '''Mult'''<br />
| '''Unit'''<br />
| '''Description'''<br />
|-<br />
| ''Creation Time''<br />
| ''DateTime_t''<br />
| ''0..1''<br />
|<br />
| ''Timestamp describing when the entity instance was created''<br />
|-<br />
| ''Validity''<br />
| ''Unit64''<br />
| ''0..1''<br />
| ''s''<br />
| '' The duration after CreationTime that the information presented in the Entity SHOULD be considered relevant. After that period has elapsed, the information SHOULD NOT be consideredrelevant''<br />
|-<br />
| ''ID [key]''<br />
| ''URI''<br />
| ''1''<br />
|<br />
| ''A global unique ID''<br />
|-<br />
| ''Name''<br />
| ''String''<br />
| ''0..1''<br />
|<br />
| ''Human Readable name''<br />
|-<br />
| ''OtherInfo''<br />
| ''String''<br />
| ''*''<br />
|<br />
| ''Placeholder to publish info that does not fit in any other attribute. Free-form string, comma-separated tags, (name, value ) pair are all examples of valid syntax.''<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
| '''Attribute '''<br />
| '''Type'''<br />
| '''Mult'''<br />
| '''Unit'''<br />
| '''Description'''<br />
|-<br />
| Platform<br />
| Platform_t<br />
| 1<br />
|<br />
| The platform of this Execution Environment.<br />
|-<br />
| VirtualMachine<br />
| ExtendedBoolean_t<br />
| 0..1<br />
|<br />
| True if the Execution Environment is hosted within a virtual machine; in this case, the values of the other attributes are related to the virtualized environment and not to the hosting environment.<br />
|-<br />
| TotalInstances<br />
| UInt32<br />
| 0..1<br />
|<br />
| The total number of Execution Environment instances. This SHOULD reflect the total installed capacity, i.e. including resources which are temporarily unavailable.<br />
|-<br />
| UsedInstances <br />
| UInt32 <br />
| 0..1<br />
|<br />
| The number of Execution Environment instances which are considered to be fully used; an instance is used when, according to the policies of the Computing Manager (i.e., LRMS), it cannot accept new jobs because it already runs the maximum number of allowed jobs.<br />
|-<br />
| UnavailableInstances<br />
| UInt32<br />
| 0..1<br />
|<br />
| The number of Execution Environment instances which are currently unavailable, e.g. because of failures or maintenance.<br />
|-<br />
| PhysicalCPUs <br />
| UInt32<br />
| 0..1<br />
|<br />
| The number of physical CPUs in one ExecutionEnvironment instance, i.e. the number of sockets per Worker Node.<br />
|-<br />
| LogicalCPUs<br />
| UInt32<br />
| 0..1<br />
|<br />
| The number of logical CPUs in one ExecutionEnvironment instance, i.e. typically the number of cores per Worker Node.<br />
|-<br />
| CPUMultiplicity<br />
| CPUMultiplicity_t<br />
| 0..1<br />
|<br />
| Condensed information about the multiplicity of both physical CPUs and cores available in an execution environment instance..<br />
|-<br />
| CPUVendor<br />
| String<br />
| 0..1<br />
|<br />
| The name of the physical CPU vendor. Free format, but it SHOULD correspond to the name by which the vendor is generally known.<br />
|-<br />
| CPUModel<br />
| String<br />
| 0..1<br />
|<br />
| The name of the physical CPU model, as defined by the vendor.<br />
|-<br />
| CPUVersion<br />
| String<br />
| 0..1<br />
|<br />
| The specific version of the Physical CPU model, as defined by the vendor<br />
|-<br />
| CPUClockSpeed<br />
| UInt32<br />
| 0..1<br />
| MHz<br />
| The nominal clock speed of the physical CPU.<br />
|-<br />
| CPUTimeScalingFactor<br />
| Real32<br />
| 0..1<br />
|<br />
| The factor used by the Computing Manager (i.e., LRMS) to scale the CPU time limit (the CPU Time is divided by the CPUTimeScalingFactor); for the reference execution environment, this attribute is equal to 1. See the description of the ComputingShare for further information.<br />
|-<br />
| WallTimeScalingFactor<br />
| Real32<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| MainMemorySize<br />
| UInt64 <br />
| 1<br />
| MB<br />
|<br />
|-<br />
| VirtualMemorySize<br />
| UInt64<br />
| 0..1<br />
| MB<br />
|<br />
|-<br />
| OSFamily<br />
| OSFamily_t<br />
| 1<br />
|<br />
|<br />
|-<br />
| OSName<br />
| OSName_t<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| OSVersion <br />
| String <br />
| 0..1<br />
|<br />
|<br />
|-<br />
| ConnectivityIn<br />
| ExtendedBoolean_t <br />
| 1<br />
|<br />
|<br />
|-<br />
| ConnectivityOut<br />
| ExtendedBoolean_t<br />
| 1<br />
|<br />
|<br />
|-<br />
| NetworkInfo<br />
| NetworkInfo_t<br />
| *<br />
|<br />
|<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
| colspan="2" | '''Association End'''<br />
| '''Mult.'''<br />
| colspan=2 | '''Description'''<br />
|- <br />
| colspan="2" | ExecutionEnvironment.ID<br />
| *<br />
| colspan="2" | An application environment MAY be used in zero or more execution environments<br />
|-<br />
| colspan="2" | ComputingManager.ID<br />
| 1<br />
| colspan="2" | An application environment is part of a computing manager.<br />
|-<br />
| colspan="2" | ApplicationHandle.ID<br />
| *<br />
| colspan="2" | An application environment MAY be handled via zero or more application handles.<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
| colspan="2" | '''Inherited Association End'''<br />
| '''Mult.'''<br />
| colspan="2" | '''Description'''<br />
|-<br />
| colspan="2" |Extension.Key<br />
| *<br />
| colspan="2" | The entity MAY be extended via key-value pairs<br />
|}</div>Walshj1https://wiki.egi.eu/w/index.php?title=GPGPU-WG_KnowledgeBase_GLUE2_Profile_ExecutionEnvironment&diff=65248GPGPU-WG KnowledgeBase GLUE2 Profile ExecutionEnvironment2014-03-02T21:52:51Z<p>Walshj1: </p>
<hr />
<div>The ExecutionEnvironment class describes the hardware and operating system environment in which a job will run. It represents a set of homogeneous Worker Nodes, so if a computing system contains nodes with significantly different properties there MAY be several ExecutionEnvironment instances. This implies that it should be possible to request a specific environment when a job is submitted. The ExecutionEnvironment MAY refer to virtual rather than physical machines.<br />
<br />
As well as attributes describing a typical node, the class gives summary information about the size and usage of the set of nodes which posess those properties. However, there is no way to relate these to the information in other entities, e.g. it is not possible to know which jobs in a given ComputingShare are running on which ExecutionEnvironment.<br />
<br />
<br />
<br />
{| class="wikitable"<br />
!colspan="5"| '''ExecutionEnvironment'''<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
|'''Entity'''<br />
|colspan=3 | '''Inherits from'''<br />
|'''Description'''<br />
|- <br />
| ExecutionEnvironment <br />
| colspan="3" | Resource<br />
| A type of environment available to and requestable by a Grid job when submitted to a<br />
ComputingService via a Computing Endpoint; the type of environment is described in terms of hardware, operating system and network characteristics. Information about the total/available/used instances of this type of execution environment are also included.<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
| '''Inherited Attribute '''<br />
| '''Type'''<br />
| '''Mult'''<br />
| '''Unit'''<br />
| '''Description'''<br />
|-<br />
| ''Creation Time''<br />
| ''DateTime_t''<br />
| ''0..1''<br />
|<br />
| ''Timestamp describing when the entity instance was created''<br />
|-<br />
| ''Validity''<br />
| ''Unit64''<br />
| ''0..1''<br />
| ''s''<br />
| '' The duration after CreationTime that the information presented in the Entity SHOULD be considered relevant. After that period has elapsed, the information SHOULD NOT be consideredrelevant''<br />
|-<br />
| ''ID [key]''<br />
| ''URI''<br />
| ''1''<br />
|<br />
| ''A global unique ID''<br />
|-<br />
| ''Name''<br />
| ''String''<br />
| ''0..1''<br />
|<br />
| ''Human Readable name''<br />
|-<br />
| ''OtherInfo''<br />
| ''String''<br />
| ''*''<br />
|<br />
| ''Placeholder to publish info that does not fit in any other attribute. Free-form string, comma-separated tags, (name, value ) pair are all examples of valid syntax.''<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
| '''Attribute '''<br />
| '''Type'''<br />
| '''Mult'''<br />
| '''Unit'''<br />
| '''Description'''<br />
|-<br />
| Platform<br />
| Platform_t<br />
| 1<br />
|<br />
| The platform of this Execution Environment.<br />
|-<br />
| VirtualMachine<br />
| ExtendedBoolean_t<br />
| 0..1<br />
|<br />
| True if the Execution Environment is hosted within a virtual machine; in this case, the values of the other attributes are related to the virtualized environment and not to the hosting environment.<br />
|-<br />
| TotalInstances<br />
| UInt32<br />
| 0..1<br />
|<br />
| The total number of Execution Environment instances. This SHOULD reflect the total installed capacity, i.e. including resources which are temporarily unavailable.<br />
|-<br />
| UsedInstances <br />
| UInt32 <br />
| 0..1<br />
|<br />
| The number of Execution Environment instances which are considered to be fully used; an instance is used when, according to the policies of the Computing Manager (i.e., LRMS), it cannot accept new jobs because it already runs the maximum number of allowed jobs.<br />
|-<br />
| UnavailableInstances<br />
| UInt32<br />
| 0..1<br />
|<br />
| The number of Execution Environment instances which are currently unavailable, e.g. because of failures or maintenance.<br />
|-<br />
| PhysicalCPUs <br />
| UInt32<br />
| 0..1<br />
|<br />
| The number of physical CPUs in one ExecutionEnvironment instance, i.e. the number of sockets per Worker Node.<br />
|-<br />
| LogicalCPUs<br />
| UInt32<br />
| 0..1<br />
|<br />
| The number of logical CPUs in one ExecutionEnvironment instance, i.e. typically the number of cores per Worker Node.<br />
|-<br />
| CPUMultiplicity<br />
| CPUMultiplicity_t<br />
| 0..1<br />
|<br />
| Condensed information about the multiplicity of both physical CPUs and cores available in an execution environment instance..<br />
|-<br />
| CPUVendor<br />
| String<br />
| 0..1<br />
|<br />
| The name of the physical CPU vendor. Free format, but it SHOULD correspond to the name by which the vendor is generally known.<br />
|-<br />
| CPUModel<br />
| String<br />
| 0..1<br />
|<br />
| The name of the physical CPU model, as defined by the vendor.<br />
|-<br />
| CPUVersion<br />
| String<br />
| 0..1<br />
|<br />
| The specific version of the Physical CPU model, as defined by the vendor<br />
|-<br />
| CPUClockSpeed<br />
| UInt32<br />
| 0..1<br />
| MHz<br />
| The nominal clock speed of the physical CPU.<br />
|-<br />
| CPUTimeScalingFactor<br />
| Real32<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| WallTimeScalingFactor<br />
| Real32<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| MainMemorySize<br />
| UInt64 <br />
| 1<br />
| MB<br />
|<br />
|-<br />
| VirtualMemorySize<br />
| UInt64<br />
| 0..1<br />
| MB<br />
|<br />
|-<br />
| OSFamily<br />
| OSFamily_t<br />
| 1<br />
|<br />
|<br />
|-<br />
| OSName<br />
| OSName_t<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| OSVersion <br />
| String <br />
| 0..1<br />
|<br />
|<br />
|-<br />
| ConnectivityIn<br />
| ExtendedBoolean_t <br />
| 1<br />
|<br />
|<br />
|-<br />
| ConnectivityOut<br />
| ExtendedBoolean_t<br />
| 1<br />
|<br />
|<br />
|-<br />
| NetworkInfo<br />
| NetworkInfo_t<br />
| *<br />
|<br />
|<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
| colspan="2" | '''Association End'''<br />
| '''Mult.'''<br />
| colspan=2 | '''Description'''<br />
|- <br />
| colspan="2" | ExecutionEnvironment.ID<br />
| *<br />
| colspan="2" | An application environment MAY be used in zero or more execution environments<br />
|-<br />
| colspan="2" | ComputingManager.ID<br />
| 1<br />
| colspan="2" | An application environment is part of a computing manager.<br />
|-<br />
| colspan="2" | ApplicationHandle.ID<br />
| *<br />
| colspan="2" | An application environment MAY be handled via zero or more application handles.<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
| colspan="2" | '''Inherited Association End'''<br />
| '''Mult.'''<br />
| colspan="2" | '''Description'''<br />
|-<br />
| colspan="2" |Extension.Key<br />
| *<br />
| colspan="2" | The entity MAY be extended via key-value pairs<br />
|}</div>Walshj1https://wiki.egi.eu/w/index.php?title=GPGPU-WG_KnowledgeBase_GLUE2_Profile_ExecutionEnvironment&diff=65247GPGPU-WG KnowledgeBase GLUE2 Profile ExecutionEnvironment2014-03-02T21:42:49Z<p>Walshj1: </p>
<hr />
<div>The ExecutionEnvironment class describes the hardware and operating system environment in which a job will run. It represents a set of homogeneous Worker Nodes, so if a computing system contains nodes with significantly different properties there MAY be several ExecutionEnvironment instances. This implies that it should be possible to request a specific environment when a job is submitted. The ExecutionEnvironment MAY refer to virtual rather than physical machines.<br />
<br />
As well as attributes describing a typical node, the class gives summary information about the size and usage of the set of nodes which posess those properties. However, there is no way to relate these to the information in other entities, e.g. it is not possible to know which jobs in a given ComputingShare are running on which ExecutionEnvironment.<br />
<br />
<br />
<br />
{| class="wikitable"<br />
!colspan="5"| '''ExecutionEnvironment'''<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
|'''Entity'''<br />
|colspan=3 | '''Inherits from'''<br />
|'''Description'''<br />
|- <br />
| ExecutionEnvironment <br />
| colspan="3" | Resource<br />
| A type of environment available to and requestable by a Grid job when submitted to a<br />
ComputingService via a Computing Endpoint; the type of environment is described in terms of hardware, operating system and network characteristics. Information about the total/available/used instances of this type of execution environment are also included.<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
| '''Inherited Attribute '''<br />
| '''Type'''<br />
| '''Mult'''<br />
| '''Unit'''<br />
| '''Description'''<br />
|-<br />
| ''Creation Time''<br />
| ''DateTime_t''<br />
| ''0..1''<br />
|<br />
| ''Timestamp describing when the entity instance was created''<br />
|-<br />
| ''Validity''<br />
| ''Unit64''<br />
| ''0..1''<br />
| ''s''<br />
| '' The duration after CreationTime that the information presented in the Entity SHOULD be considered relevant. After that period has elapsed, the information SHOULD NOT be consideredrelevant''<br />
|-<br />
| ''ID [key]''<br />
| ''URI''<br />
| ''1''<br />
|<br />
| ''A global unique ID''<br />
|-<br />
| ''Name''<br />
| ''String''<br />
| ''0..1''<br />
|<br />
| ''Human Readable name''<br />
|-<br />
| ''OtherInfo''<br />
| ''String''<br />
| ''*''<br />
|<br />
| ''Placeholder to publish info that does not fit in any other attribute. Free-form string, comma-separated tags, (name, value ) pair are all examples of valid syntax.''<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
| '''Attribute '''<br />
| '''Type'''<br />
| '''Mult'''<br />
| '''Unit'''<br />
| '''Description'''<br />
|-<br />
| Platform<br />
| Platform_t<br />
| 1<br />
|<br />
| The platform of this Execution Environment.<br />
|-<br />
| VirtualMachine<br />
| ExtendedBoolean_t<br />
| 0..1<br />
|<br />
| True if the Execution Environment is hosted within a virtual machine; in this case, the values of the other attributes are related to the virtualized environment and not to the hosting environment.<br />
|-<br />
| TotalInstances<br />
| UInt32<br />
| 0..1<br />
|<br />
| The total number of Execution Environment instances. This SHOULD reflect the total installed capacity, i.e. including resources which are temporarily unavailable.<br />
|-<br />
| UsedInstances <br />
| UInt32 <br />
| 0..1<br />
|<br />
| The number of Execution Environment instances which are considered to be fully used; an instance is used when, according to the policies of the Computing Manager (i.e., LRMS), it cannot accept new jobs because it already runs the maximum number of allowed jobs.<br />
|-<br />
| UnavailableInstances<br />
| UInt32<br />
| 0..1<br />
|<br />
| The number of Execution Environment instances which are currently unavailable, e.g. because of failures or maintenance.<br />
|-<br />
| PhysicalCPUs <br />
| UInt32<br />
| 0..1<br />
|<br />
| The number of physical CPUs in one ExecutionEnvironment instance, i.e. the number of sockets per Worker Node.<br />
|-<br />
| LogicalCPUs<br />
| UInt32<br />
| 0..1<br />
|<br />
| The number of logical CPUs in one ExecutionEnvironment instance, i.e. typically the number of cores per Worker Node.<br />
|-<br />
| CPUMultiplicity<br />
| CPUMultiplicity_t<br />
| 0..1<br />
|<br />
| Condensed information about the multiplicity of both physical CPUs and cores available in an execution environment instance..<br />
|-<br />
| CPUVendor<br />
| String<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| CPUModel<br />
| String<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| CPUVersion<br />
| String<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| CPUClockSpeed<br />
| UInt32<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| CPUTimeScalingFactor<br />
| Real32<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| WallTimeScalingFactor<br />
| Real32<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| MainMemorySize<br />
| UInt64 <br />
| 1<br />
| MB<br />
|<br />
|-<br />
| VirtualMemorySize<br />
| UInt64<br />
| 0..1<br />
| MB<br />
|<br />
|-<br />
| OSFamily<br />
| OSFamily_t<br />
| 1<br />
|<br />
|<br />
|-<br />
| OSName<br />
| OSName_t<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| OSVersion <br />
| String <br />
| 0..1<br />
|<br />
|<br />
|-<br />
| ConnectivityIn<br />
| ExtendedBoolean_t <br />
| 1<br />
|<br />
|<br />
|-<br />
| ConnectivityOut<br />
| ExtendedBoolean_t<br />
| 1<br />
|<br />
|<br />
|-<br />
| NetworkInfo<br />
| NetworkInfo_t<br />
| *<br />
|<br />
|<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
| colspan="2" | '''Association End'''<br />
| '''Mult.'''<br />
| colspan=2 | '''Description'''<br />
|- <br />
| colspan="2" | ExecutionEnvironment.ID<br />
| *<br />
| colspan="2" | An application environment MAY be used in zero or more execution environments<br />
|-<br />
| colspan="2" | ComputingManager.ID<br />
| 1<br />
| colspan="2" | An application environment is part of a computing manager.<br />
|-<br />
| colspan="2" | ApplicationHandle.ID<br />
| *<br />
| colspan="2" | An application environment MAY be handled via zero or more application handles.<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
| colspan="2" | '''Inherited Association End'''<br />
| '''Mult.'''<br />
| colspan="2" | '''Description'''<br />
|-<br />
| colspan="2" |Extension.Key<br />
| *<br />
| colspan="2" | The entity MAY be extended via key-value pairs<br />
|}</div>Walshj1https://wiki.egi.eu/w/index.php?title=GPGPU-WG_KnowledgeBase_GLUE2_Profile_ExecutionEnvironment&diff=65246GPGPU-WG KnowledgeBase GLUE2 Profile ExecutionEnvironment2014-03-02T21:34:27Z<p>Walshj1: </p>
<hr />
<div>The ExecutionEnvironment class describes the hardware and operating system environment in which a job will run. It represents a set of homogeneous Worker Nodes, so if a computing system contains nodes with significantly different properties there MAY be several ExecutionEnvironment instances. This implies that it should be possible to request a specific environment when a job is submitted. The ExecutionEnvironment MAY refer to virtual rather than physical machines.<br />
<br />
As well as attributes describing a typical node, the class gives summary information about the size and usage of the set of nodes which posess those properties. However, there is no way to relate these to the information in other entities, e.g. it is not possible to know which jobs in a given ComputingShare are running on which ExecutionEnvironment.<br />
<br />
<br />
<br />
{| class="wikitable"<br />
!colspan="5"| '''ExecutionEnvironment'''<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
|'''Entity'''<br />
|colspan=3 | '''Inherits from'''<br />
|'''Description'''<br />
|- <br />
| ExecutionEnvironment <br />
| colspan="3" | Resource<br />
| A type of environment available to and requestable by a Grid job when submitted to a<br />
ComputingService via a Computing Endpoint; the type of environment is described in terms of hardware, operating system and network characteristics. Information about the total/available/used instances of this type of execution environment are also included.<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
| '''Inherited Attribute '''<br />
| '''Type'''<br />
| '''Mult'''<br />
| '''Unit'''<br />
| '''Description'''<br />
|-<br />
| ''Creation Time''<br />
| ''DateTime_t''<br />
| ''0..1''<br />
|<br />
| ''Timestamp describing when the entity instance was created''<br />
|-<br />
| ''Validity''<br />
| ''Unit64''<br />
| ''0..1''<br />
| ''s''<br />
| '' The duration after CreationTime that the information presented in the Entity SHOULD be considered relevant. After that period has elapsed, the information SHOULD NOT be consideredrelevant''<br />
|-<br />
| ''ID [key]''<br />
| ''URI''<br />
| ''1''<br />
|<br />
| ''A global unique ID''<br />
|-<br />
| ''Name''<br />
| ''String''<br />
| ''0..1''<br />
|<br />
| ''Human Readable name''<br />
|-<br />
| ''OtherInfo''<br />
| ''String''<br />
| ''*''<br />
|<br />
| ''Placeholder to publish info that does not fit in any other attribute. Free-form string, comma-separated tags, (name, value ) pair are all examples of valid syntax.''<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
| '''Attribute '''<br />
| '''Type'''<br />
| '''Mult'''<br />
| '''Unit'''<br />
| '''Description'''<br />
|-<br />
| Platform<br />
| Platform_t<br />
| 1<br />
|<br />
| The platform of this Execution Environment.<br />
|-<br />
| VirtualMachine<br />
| ExtendedBoolean_t<br />
| 0..1<br />
|<br />
| True if the Execution Environment is hosted within a virtual machine; in this case, the values of the other attributes are related to the virtualized environment and not to the hosting environment.<br />
|-<br />
| TotalInstances<br />
| UInt32<br />
| 0..1<br />
|<br />
| The total number of Execution Environment instances. This SHOULD reflect the total installed capacity, i.e. including resources which are temporarily unavailable.<br />
|-<br />
| UsedInstances <br />
| UInt32 <br />
| 0..1<br />
|<br />
| <br />
|-<br />
| UnavailableInstances<br />
| UInt32<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| PhysicalCPUs <br />
| UInt32<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| LogicalCPUs<br />
| UInt32<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| CPUMultiplicity<br />
| CPUMultiplicity_t<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| CPUVendor<br />
| String<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| CPUModel<br />
| String<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| CPUVersion<br />
| String<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| CPUClockSpeed<br />
| UInt32<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| CPUTimeScalingFactor<br />
| Real32<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| WallTimeScalingFactor<br />
| Real32<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| MainMemorySize<br />
| UInt64 <br />
| 1<br />
| MB<br />
|<br />
|-<br />
| VirtualMemorySize<br />
| UInt64<br />
| 0..1<br />
| MB<br />
|<br />
|-<br />
| OSFamily<br />
| OSFamily_t<br />
| 1<br />
|<br />
|<br />
|-<br />
| OSName<br />
| OSName_t<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| OSVersion <br />
| String <br />
| 0..1<br />
|<br />
|<br />
|-<br />
| ConnectivityIn<br />
| ExtendedBoolean_t <br />
| 1<br />
|<br />
|<br />
|-<br />
| ConnectivityOut<br />
| ExtendedBoolean_t<br />
| 1<br />
|<br />
|<br />
|-<br />
| NetworkInfo<br />
| NetworkInfo_t<br />
| *<br />
|<br />
|<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
| colspan="2" | '''Association End'''<br />
| '''Mult.'''<br />
| colspan=2 | '''Description'''<br />
|- <br />
| colspan="2" | ExecutionEnvironment.ID<br />
| *<br />
| colspan="2" | An application environment MAY be used in zero or more execution environments<br />
|-<br />
| colspan="2" | ComputingManager.ID<br />
| 1<br />
| colspan="2" | An application environment is part of a computing manager.<br />
|-<br />
| colspan="2" | ApplicationHandle.ID<br />
| *<br />
| colspan="2" | An application environment MAY be handled via zero or more application handles.<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
| colspan="2" | '''Inherited Association End'''<br />
| '''Mult.'''<br />
| colspan="2" | '''Description'''<br />
|-<br />
| colspan="2" |Extension.Key<br />
| *<br />
| colspan="2" | The entity MAY be extended via key-value pairs<br />
|}</div>Walshj1https://wiki.egi.eu/w/index.php?title=GPGPU-WG_KnowledgeBase_GLUE2_Profile_ExecutionEnvironment&diff=65245GPGPU-WG KnowledgeBase GLUE2 Profile ExecutionEnvironment2014-03-02T21:33:12Z<p>Walshj1: Undo revision 65244 by Walshj1 (talk)</p>
<hr />
<div>The ExecutionEnvironment class describes the hardware and operating system environment in which a job will run. It represents a set of homogeneous Worker Nodes, so if a computing system contains nodes with significantly different properties there MAY be several ExecutionEnvironment instances. This implies that it should be possible to request a specific environment when a job is submitted. The ExecutionEnvironment MAY refer to virtual rather than physical machines.<br />
<br />
As well as attributes describing a typical node, the class gives summary information about the size and usage of the set of nodes which posess those properties. However, there is no way to relate these to the information in other entities, e.g. it is not possible to know which jobs in a given ComputingShare are running on which ExecutionEnvironment.<br />
<br />
<br />
<br />
{|!colspan="5"| '''ExecutionEnvironment'''<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
|'''Entity'''<br />
|colspan=3 | '''Inherits from'''<br />
|'''Description'''<br />
|- <br />
| ExecutionEnvironment <br />
| colspan="3" | Resource<br />
| A type of environment available to and requestable by a Grid job when submitted to a<br />
ComputingService via a Computing Endpoint; the type of environment is described in terms of hardware, operating system and network characteristics. Information about the total/available/used instances of this type of execution environment are also included.<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
| '''Inherited Attribute '''<br />
| '''Type'''<br />
| '''Mult'''<br />
| '''Unit'''<br />
| '''Description'''<br />
|-<br />
| ''Creation Time''<br />
| ''DateTime_t''<br />
| ''0..1''<br />
|<br />
| ''Timestamp describing when the entity instance was created''<br />
|-<br />
| ''Validity''<br />
| ''Unit64''<br />
| ''0..1''<br />
| ''s''<br />
| '' The duration after CreationTime that the information presented in the Entity SHOULD be considered relevant. After that period has elapsed, the information SHOULD NOT be consideredrelevant''<br />
|-<br />
| ''ID [key]''<br />
| ''URI''<br />
| ''1''<br />
|<br />
| ''A global unique ID''<br />
|-<br />
| ''Name''<br />
| ''String''<br />
| ''0..1''<br />
|<br />
| ''Human Readable name''<br />
|-<br />
| ''OtherInfo''<br />
| ''String''<br />
| ''*''<br />
|<br />
| ''Placeholder to publish info that does not fit in any other attribute. Free-form string, comma-separated tags, (name, value ) pair are all examples of valid syntax.''<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
| '''Attribute '''<br />
| '''Type'''<br />
| '''Mult'''<br />
| '''Unit'''<br />
| '''Description'''<br />
|-<br />
| Platform<br />
| Platform_t<br />
| 1<br />
|<br />
| The platform of this Execution Environment.<br />
|-<br />
| VirtualMachine<br />
| ExtendedBoolean_t<br />
| 0..1<br />
|<br />
| True if the Execution Environment is hosted within a virtual machine; in this case, the values of the other attributes are related to the virtualized environment and not to the hosting environment.<br />
|-<br />
| TotalInstances<br />
| UInt32<br />
| 0..1<br />
|<br />
| The total number of Execution Environment instances. This SHOULD reflect the total installed capacity, i.e. including resources which are temporarily unavailable.<br />
|-<br />
| UsedInstances <br />
| UInt32 <br />
| 0..1<br />
|<br />
| <br />
|-<br />
| UnavailableInstances<br />
| UInt32<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| PhysicalCPUs <br />
| UInt32<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| LogicalCPUs<br />
| UInt32<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| CPUMultiplicity<br />
| CPUMultiplicity_t<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| CPUVendor<br />
| String<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| CPUModel<br />
| String<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| CPUVersion<br />
| String<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| CPUClockSpeed<br />
| UInt32<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| CPUTimeScalingFactor<br />
| Real32<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| WallTimeScalingFactor<br />
| Real32<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| MainMemorySize<br />
| UInt64 <br />
| 1<br />
| MB<br />
|<br />
|-<br />
| VirtualMemorySize<br />
| UInt64<br />
| 0..1<br />
| MB<br />
|<br />
|-<br />
| OSFamily<br />
| OSFamily_t<br />
| 1<br />
|<br />
|<br />
|-<br />
| OSName<br />
| OSName_t<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| OSVersion <br />
| String <br />
| 0..1<br />
|<br />
|<br />
|-<br />
| ConnectivityIn<br />
| ExtendedBoolean_t <br />
| 1<br />
|<br />
|<br />
|-<br />
| ConnectivityOut<br />
| ExtendedBoolean_t<br />
| 1<br />
|<br />
|<br />
|-<br />
| NetworkInfo<br />
| NetworkInfo_t<br />
| *<br />
|<br />
|<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
| colspan="2" | '''Association End'''<br />
| '''Mult.'''<br />
| colspan=2 | '''Description'''<br />
|- <br />
| colspan="2" | ExecutionEnvironment.ID<br />
| *<br />
| colspan="2" | An application environment MAY be used in zero or more execution environments<br />
|-<br />
| colspan="2" | ComputingManager.ID<br />
| 1<br />
| colspan="2" | An application environment is part of a computing manager.<br />
|-<br />
| colspan="2" | ApplicationHandle.ID<br />
| *<br />
| colspan="2" | An application environment MAY be handled via zero or more application handles.<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
| colspan="2" | '''Inherited Association End'''<br />
| '''Mult.'''<br />
| colspan="2" | '''Description'''<br />
|-<br />
| colspan="2" |Extension.Key<br />
| *<br />
| colspan="2" | The entity MAY be extended via key-value pairs<br />
|}</div>Walshj1https://wiki.egi.eu/w/index.php?title=GPGPU-WG_KnowledgeBase_GLUE2_Profile_ExecutionEnvironment&diff=65244GPGPU-WG KnowledgeBase GLUE2 Profile ExecutionEnvironment2014-03-02T21:31:11Z<p>Walshj1: </p>
<hr />
<div>The ExecutionEnvironment class describes the hardware and operating system environment in which a job will run. It represents a set of homogeneous Worker Nodes, so if a computing system contains nodes with significantly different properties there MAY be several ExecutionEnvironment instances. This implies that it should be possible to request a specific environment when a job is submitted. The ExecutionEnvironment MAY refer to virtual rather than physical machines.<br />
<br />
As well as attributes describing a typical node, the class gives summary information about the size and usage of the set of nodes which posess those properties. However, there is no way to relate these to the information in other entities, e.g. it is not possible to know which jobs in a given ComputingShare are running on which ExecutionEnvironment.<br />
<br />
<br />
<br />
{|!colspan="5"| '''ExecutionEnvironment'''<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
|'''Entity'''<br />
|colspan=3 | '''Inherits from'''<br />
|'''Description'''<br />
|- <br />
| ExecutionEnvironment <br />
| colspan="3" | Resource<br />
| A type of environment available to and requestable by a Grid job when submitted to a<br />
ComputingService via a Computing Endpoint; the type of environment is described in terms of hardware, operating system and network characteristics. Information about the total/available/used instances of this type of execution environment are also included.<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
| '''Inherited Attribute '''<br />
| '''Type'''<br />
| '''Mult'''<br />
| '''Unit'''<br />
| '''Description'''<br />
|-<br />
| ''Creation Time''<br />
| ''DateTime_t''<br />
| ''0..1''<br />
|<br />
| ''Timestamp describing when the entity instance was created''<br />
|-<br />
| ''Validity''<br />
| ''Unit64''<br />
| ''0..1''<br />
| ''s''<br />
| '' The duration after CreationTime that the information presented in the Entity SHOULD be considered relevant. After that period has elapsed, the information SHOULD NOT be consideredrelevant''<br />
|-<br />
| ''ID [key]''<br />
| ''URI''<br />
| ''1''<br />
|<br />
| ''A global unique ID''<br />
|-<br />
| ''Name''<br />
| ''String''<br />
| ''0..1''<br />
|<br />
| ''Human Readable name''<br />
|-<br />
| ''OtherInfo''<br />
| ''String''<br />
| ''*''<br />
|<br />
| ''Placeholder to publish info that does not fit in any other attribute. Free-form string, comma-separated tags, (name, value ) pair are all examples of valid syntax.''<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
| '''Attribute '''<br />
| '''Type'''<br />
| '''Mult'''<br />
| '''Unit'''<br />
| '''Description'''<br />
|-<br />
| Platform<br />
| Platform_t<br />
| 1<br />
|<br />
| The platform of this Execution Environment.<br />
|-<br />
| VirtualMachine<br />
| ExtendedBoolean_t<br />
| 0..1<br />
|<br />
| True if the Execution Environment is hosted within a virtual machine; in this case, the values of the other attributes are related to the virtualized environment and not to the hosting environment.<br />
|-<br />
| TotalInstances<br />
| UInt32<br />
| 0..1<br />
|<br />
| The total number of Execution Environment instances. This SHOULD reflect the total installed capacity, i.e. including resources which are temporarily unavailable.<br />
|-<br />
| UsedInstances <br />
| UInt32 <br />
| 0..1<br />
|<br />
| <br />
|-<br />
| UnavailableInstances<br />
| UInt32<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| PhysicalCPUs <br />
| UInt32<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| LogicalCPUs<br />
| UInt32<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| CPUMultiplicity<br />
| CPUMultiplicity_t<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| CPUVendor<br />
| String<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| CPUModel<br />
| String<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| CPUVersion<br />
| String<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| CPUClockSpeed<br />
| UInt32<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| CPUTimeScalingFactor<br />
| Real32<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| WallTimeScalingFactor<br />
| Real32<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| MainMemorySize<br />
| UInt64 <br />
| 1<br />
| MB<br />
|<br />
|-<br />
| VirtualMemorySize<br />
| UInt64<br />
| 0..1<br />
| MB<br />
|<br />
|-<br />
| OSFamily<br />
| OSFamily_t<br />
| 1<br />
|<br />
|<br />
|-<br />
| OSName<br />
| OSName_t<br />
| 0..1<br />
|<br />
||- style="color:white; background-color:black;" cellpadding="3"<br />
| colspan="2" | '''Association End'''<br />
| '''Mult.'''<br />
| colspan=2 | '''Description'''<br />
|- <br />
| colspan="2" | ExecutionEnvironment.ID<br />
| *<br />
| colspan="2" | An application environment MAY be used in zero or more execution environments<br />
|-<br />
| colspan="2" | ComputingManager.ID<br />
| 1<br />
| colspan="2" | An application environment is part of a computing manager.<br />
|-<br />
| colspan="2" | ApplicationHandle.ID<br />
| *<br />
| colspan="2" | An application environment MAY be handled via zero or more application handles.<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
| colspan="2" | '''Inherited Association End'''<br />
| '''Mult.'''<br />
| colspan="2" | '''Description'''<br />
|-<br />
| colspan="2" |Extension.Key<br />
| *<br />
| colspan="2" | The entity MAY be extended via key-value pairs<br />
|-<br />
| OSVersion <br />
| String <br />
| 0..1<br />
|<br />
|<br />
|-<br />
| ConnectivityIn<br />
| ExtendedBoolean_t <br />
| 1<br />
|<br />
|<br />
|-<br />
| ConnectivityOut<br />
| ExtendedBoolean_t<br />
| 1<br />
|<br />
|<br />
|-<br />
| NetworkInfo<br />
| NetworkInfo_t<br />
| *<br />
|<br />
|<br />
|}</div>Walshj1https://wiki.egi.eu/w/index.php?title=GPGPU-WG_KnowledgeBase_GLUE2_Profile_ExecutionEnvironment&diff=65243GPGPU-WG KnowledgeBase GLUE2 Profile ExecutionEnvironment2014-03-02T21:25:09Z<p>Walshj1: </p>
<hr />
<div>The ExecutionEnvironment class describes the hardware and operating system environment in which a job will run. It represents a set of homogeneous Worker Nodes, so if a computing system contains nodes with significantly different properties there MAY be several ExecutionEnvironment instances. This implies that it should be possible to request a specific environment when a job is submitted. The ExecutionEnvironment MAY refer to virtual rather than physical machines.<br />
<br />
As well as attributes describing a typical node, the class gives summary information about the size and usage of the set of nodes which posess those properties. However, there is no way to relate these to the information in other entities, e.g. it is not possible to know which jobs in a given ComputingShare are running on which ExecutionEnvironment.<br />
<br />
<br />
<br />
{|!colspan="5"| '''ExecutionEnvironment'''<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
|'''Entity'''<br />
|colspan=3 | '''Inherits from'''<br />
|'''Description'''<br />
|- <br />
| ExecutionEnvironment <br />
| colspan="3" | Resource<br />
| A type of environment available to and requestable by a Grid job when submitted to a<br />
ComputingService via a Computing Endpoint; the type of environment is described in terms of hardware, operating system and network characteristics. Information about the total/available/used instances of this type of execution environment are also included.<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
| '''Inherited Attribute '''<br />
| '''Type'''<br />
| '''Mult'''<br />
| '''Unit'''<br />
| '''Description'''<br />
|-<br />
| ''Creation Time''<br />
| ''DateTime_t''<br />
| ''0..1''<br />
|<br />
| ''Timestamp describing when the entity instance was created''<br />
|-<br />
| ''Validity''<br />
| ''Unit64''<br />
| ''0..1''<br />
| ''s''<br />
| '' The duration after CreationTime that the information presented in the Entity SHOULD be considered relevant. After that period has elapsed, the information SHOULD NOT be consideredrelevant''<br />
|-<br />
| ''ID [key]''<br />
| ''URI''<br />
| ''1''<br />
|<br />
| ''A global unique ID''<br />
|-<br />
| ''Name''<br />
| ''String''<br />
| ''0..1''<br />
|<br />
| ''Human Readable name''<br />
|-<br />
| ''OtherInfo''<br />
| ''String''<br />
| ''*''<br />
|<br />
| ''Placeholder to publish info that does not fit in any other attribute. Free-form string, comma-separated tags, (name, value ) pair are all examples of valid syntax.''<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
| '''Attribute '''<br />
| '''Type'''<br />
| '''Mult'''<br />
| '''Unit'''<br />
| '''Description'''<br />
|-<br />
| Platform<br />
| Platform_t<br />
| 1<br />
|<br />
| The platform of this Execution Environment.<br />
|-<br />
| VirtualMachine<br />
| ExtendedBoolean_t<br />
| 0..1<br />
|<br />
| True if the Execution Environment is hosted within a virtual machine; in this case, the values of the other attributes are related to the virtualized environment and not to the hosting environment.<br />
|-<br />
| TotalInstances<br />
| UInt32<br />
| 0..1<br />
|<br />
| The total number of Execution Environment instances. This SHOULD reflect the total installed capacity, i.e. including resources which are temporarily unavailable.<br />
|-<br />
| UsedInstances <br />
| UInt32 <br />
| 0..1<br />
|<br />
| <br />
|-<br />
| UnavailableInstances<br />
| UInt32<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| PhysicalCPUs <br />
| UInt32<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| LogicalCPUs<br />
| UInt32<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| CPUMultiplicity<br />
| CPUMultiplicity_t<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| CPUVendor<br />
| String<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| CPUModel<br />
| String<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| CPUVersion<br />
| String<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| CPUClockSpeed<br />
| UInt32<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| CPUTimeScalingFactor<br />
| Real32<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| WallTimeScalingFactor<br />
| Real32<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| MainMemorySize<br />
| UInt64 <br />
| 1<br />
| MB<br />
|<br />
|-<br />
| VirtualMemorySize<br />
| UInt64<br />
| 0..1<br />
| MB<br />
|<br />
|-<br />
| OSFamily<br />
| OSFamily_t<br />
| 1<br />
|<br />
|<br />
|-<br />
| OSName<br />
| OSName_t<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| OSVersion <br />
| String <br />
| 0..1<br />
|<br />
|<br />
|-<br />
| ConnectivityIn<br />
| ExtendedBoolean_t <br />
| 1<br />
|<br />
|<br />
|-<br />
| ConnectivityOut<br />
| ExtendedBoolean_t<br />
| 1<br />
|<br />
|<br />
|-<br />
| NetworkInfo<br />
| NetworkInfo_t<br />
| *<br />
|<br />
|<br />
|}</div>Walshj1https://wiki.egi.eu/w/index.php?title=GPGPU-WG_KnowledgeBase_GLUE2_Profile_ExecutionEnvironment&diff=65242GPGPU-WG KnowledgeBase GLUE2 Profile ExecutionEnvironment2014-03-02T21:23:49Z<p>Walshj1: </p>
<hr />
<div>The ExecutionEnvironment class describes the hardware and operating system environment in which a job will run. It represents a set of homogeneous Worker Nodes, so if a computing system contains nodes with significantly different properties there MAY be several ExecutionEnvironment instances. This implies that it should be possible to request a specific environment when a job is submitted. The ExecutionEnvironment MAY refer to virtual rather than physical machines.<br />
<br />
As well as attributes describing a typical node, the class gives summary information about the size and usage of the set of nodes which posess those properties. However, there is no way to relate these to the information in other entities, e.g. it is not possible to know which jobs in a given ComputingShare are running on which ExecutionEnvironment.<br />
<br />
<br />
<br />
{|!colspan="5"| '''ExecutionEnvironment'''<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
|'''Entity'''<br />
|colspan=3 | '''Inherits from'''<br />
|'''Description'''<br />
|- <br />
| ExecutionEnvironment <br />
| colspan="3" | Resource<br />
| A type of environment available to and requestable by a Grid job when submitted to a<br />
ComputingService via a Computing Endpoint; the type of environment is described in terms of hardware, operating system and network characteristics. Information about the total/available/used instances of this type of execution environment are also included.<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
| '''Inherited Attribute '''<br />
| '''Type'''<br />
| '''Mult'''<br />
| '''Unit'''<br />
| '''Description'''<br />
|-<br />
| ''Creation Time''<br />
| ''DateTime_t''<br />
| ''0..1''<br />
|<br />
| ''Timestamp describing when the entity instance was created''<br />
|-<br />
| ''Validity''<br />
| ''Unit64''<br />
| ''0..1''<br />
| ''s''<br />
| '' The duration after CreationTime that the information presented in the Entity SHOULD be considered relevant. After that period has elapsed, the information SHOULD NOT be consideredrelevant''<br />
|-<br />
| ''ID [key]''<br />
| ''URI''<br />
| ''1''<br />
|<br />
| ''A global unique ID''<br />
|-<br />
| ''Name''<br />
| ''String''<br />
| ''0..1''<br />
|<br />
| ''Human Readable name''<br />
|-<br />
| ''OtherInfo''<br />
| ''String''<br />
| ''*''<br />
|<br />
| ''Placeholder to publish info that does not fit in any other attribute. Free-form string, comma-separated tags, (name, value ) pair are all examples of valid syntax.''<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
| '''Attribute '''<br />
| '''Type'''<br />
| '''Mult'''<br />
| '''Unit'''<br />
| '''Description'''<br />
|-<br />
| Platform<br />
| Platform_t<br />
| 1<br />
|<br />
| The platform of this Execution Environment.<br />
|-<br />
| VirtualMachine<br />
| ExtendedBoolean_t<br />
| 0..1<br />
|<br />
| True if the Execution Environment is hosted within a virtual machine; in this case, the values of the other attributes are related to the virtualized environment and not to the hosting environment.<br />
|-<br />
| TotalInstances<br />
| UInt32<br />
| 0..1<br />
|<br />
| The total number of Execution Environment instances. This SHOULD reflect the total installed capacity, i.e. including resources which are temporarily unavailable.<br />
|-<br />
| UsedInstances <br />
| UInt32 <br />
| 0..1<br />
|<br />
| <br />
|-<br />
| UnavailableInstances<br />
| UInt32<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| PhysicalCPUs <br />
| UInt32<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| LogicalCPUs<br />
| UInt32<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| CPUMultiplicity<br />
| CPUMultiplicity_t<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| CPUVendor<br />
| String<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| CPUModel<br />
| String<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| CPUVersion<br />
| String<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| CPUClockSpeed<br />
| UInt32<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| CPUTimeScalingFactor<br />
| Real32<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| WallTimeScalingFactor<br />
| Real32<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| MainMemorySize<br />
| UInt64 <br />
| 1<br />
| MB<br />
|<br />
|-<br />
| VirtualMemorySize<br />
| UInt64<br />
| 0..1<br />
| MB<br />
|<br />
|-<br />
| OSFamily<br />
| OSFamily_t<br />
| 1<br />
|<br />
|<br />
|-<br />
| OSName<br />
| OSName_t<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| OSVersion <br />
| String <br />
| 0..1<br />
|<br />
|<br />
|-<br />
| ConnectivityIn<br />
| ExtendedBoolean_t <br />
| 1<br />
|<br />
|<br />
| ConnectivityOut<br />
| ExtendedBoolean_t<br />
| 1<br />
|<br />
|<br />
|-<br />
| NetworkInfo<br />
| NetworkInfo_t<br />
| *<br />
|<br />
|<br />
|}</div>Walshj1https://wiki.egi.eu/w/index.php?title=GPGPU-WG_KnowledgeBase_GLUE2_Profile_ExecutionEnvironment&diff=65241GPGPU-WG KnowledgeBase GLUE2 Profile ExecutionEnvironment2014-03-02T21:10:08Z<p>Walshj1: </p>
<hr />
<div>The ExecutionEnvironment class describes the hardware and operating system environment in which a job will run. It represents a set of homogeneous Worker Nodes, so if a computing system contains nodes with significantly different properties there MAY be several ExecutionEnvironment instances. This implies that it should be possible to request a specific environment when a job is submitted. The ExecutionEnvironment MAY refer to virtual rather than physical machines.<br />
<br />
As well as attributes describing a typical node, the class gives summary information about the size and usage of the set of nodes which posess those properties. However, there is no way to relate these to the information in other entities, e.g. it is not possible to know which jobs in a given ComputingShare are running on which ExecutionEnvironment.<br />
<br />
<br />
<br />
{|!colspan="5"| '''ExecutionEnvironment'''<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
|'''Entity'''<br />
|colspan=3 | '''Inherits from'''<br />
|'''Description'''<br />
|- <br />
| ExecutionEnvironment <br />
| colspan="3" | Resource<br />
| A type of environment available to and requestable by a Grid job when submitted to a<br />
ComputingService via a Computing Endpoint; the type of environment is described in terms of hardware, operating system and network characteristics. Information about the total/available/used instances of this type of execution environment are also included.<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
| '''Inherited Attribute '''<br />
| '''Type'''<br />
| '''Mult'''<br />
| '''Unit'''<br />
| '''Description'''<br />
|-<br />
| ''Creation Time''<br />
| ''DateTime_t''<br />
| ''0..1''<br />
|<br />
| ''Timestamp describing when the entity instance was created''<br />
|-<br />
| ''Validity''<br />
| ''Unit64''<br />
| ''0..1''<br />
| ''s''<br />
| '' The duration after CreationTime that the information presented in the Entity SHOULD be considered relevant. After that period has elapsed, the information SHOULD NOT be consideredrelevant''<br />
|-<br />
| ''ID [key]''<br />
| ''URI''<br />
| ''1''<br />
|<br />
| ''A global unique ID''<br />
|-<br />
| ''Name''<br />
| ''String''<br />
| ''0..1''<br />
|<br />
| ''Human Readable name''<br />
|-<br />
| ''OtherInfo''<br />
| ''String''<br />
| ''*''<br />
|<br />
| ''Placeholder to publish info that does not fit in any other attribute. Free-form string, comma-separated tags, (name, value ) pair are all examples of valid syntax.''<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
| '''Attribute '''<br />
| '''Type'''<br />
| '''Mult'''<br />
| '''Unit'''<br />
| '''Description'''<br />
|-<br />
| Platform<br />
| Platform_t<br />
| 1<br />
|<br />
| The platform of this Execution Environment.<br />
|-<br />
| VirtualMachine<br />
| ExtendedBoolean_t<br />
| 0..1<br />
|<br />
| True if the Execution Environment is hosted within a virtual machine; in this case, the values of the other attributes are related to the virtualized environment and not to the hosting environment.<br />
|-<br />
| TotalInstances<br />
| UInt32<br />
| 0..1<br />
|<br />
| The total number of Execution Environment instances. This SHOULD reflect the total installed capacity, i.e. including resources which are temporarily unavailable.<br />
|-<br />
| UsedInstances <br />
| UInt32 <br />
| 0..1<br />
|<br />
| <br />
|-<br />
| UnavailableInstances<br />
| UInt32<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| PhysicalCPUs <br />
| UInt32<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| LogicalCPUs<br />
| UInt32<br />
| 0..1<br />
|<br />
|<br />
|-<br />
| CPUMultiplicity<br />
| CPUMultiplicity_t<br />
| 0..1<br />
|<br />
|<br />
|}</div>Walshj1https://wiki.egi.eu/w/index.php?title=GPGPU-WG_KnowledgeBase_GLUE2_Profile_ExecutionEnvironment&diff=65240GPGPU-WG KnowledgeBase GLUE2 Profile ExecutionEnvironment2014-03-02T21:01:08Z<p>Walshj1: </p>
<hr />
<div>The ExecutionEnvironment class describes the hardware and operating system environment in which a job will run. It represents a set of homogeneous Worker Nodes, so if a computing system contains nodes with significantly different properties there MAY be several ExecutionEnvironment instances. This implies that it should be possible to request a specific environment when a job is submitted. The ExecutionEnvironment MAY refer to virtual rather than physical machines.<br />
<br />
As well as attributes describing a typical node, the class gives summary information about the size and usage of the set of nodes which posess those properties. However, there is no way to relate these to the information in other entities, e.g. it is not possible to know which jobs in a given ComputingShare are running on which ExecutionEnvironment.<br />
<br />
<br />
<br />
{|!colspan="5"| '''ExecutionEnvironment'''<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
|'''Entity'''<br />
|colspan=3 | '''Inherits from'''<br />
|'''Description'''<br />
|- <br />
| ExecutionEnvironment <br />
| colspan="3" | Resource<br />
| A type of environment available to and requestable by a Grid job when submitted to a<br />
ComputingService via a Computing Endpoint; the type of environment is described in terms of hardware, operating system and network characteristics. Information about the total/available/used instances of this type of execution environment are also included.<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
| '''Inherited Attribute '''<br />
| '''Type'''<br />
| '''Mult'''<br />
| '''Unit'''<br />
| '''Description'''<br />
|-<br />
| ''Creation Time''<br />
| ''DateTime_t''<br />
| ''0..1''<br />
|<br />
| ''Timestamp describing when the entity instance was created''<br />
|-<br />
| ''Validity''<br />
| ''Unit64''<br />
| ''0..1''<br />
| ''s''<br />
| '' The duration after CreationTime that the information presented in the Entity SHOULD be considered relevant. After that period has elapsed, the information SHOULD NOT be consideredrelevant''<br />
|-<br />
| ''ID [key]''<br />
| ''URI''<br />
| ''1''<br />
|<br />
| ''A global unique ID''<br />
|-<br />
| ''Name''<br />
| ''String''<br />
| ''0..1''<br />
|<br />
| ''Human Readable name''<br />
|-<br />
| ''OtherInfo''<br />
| ''String''<br />
| ''*''<br />
|<br />
| ''Placeholder to publish info that does not fit in any other attribute. Free-form string, comma-separated tags, (name, value ) pair are all examples of valid syntax.''<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
| '''Attribute '''<br />
| '''Type'''<br />
| '''Mult'''<br />
| '''Unit'''<br />
| '''Description'''<br />
|-<br />
| Platform<br />
| Platform_t<br />
| 1<br />
|<br />
| The platform of this Execution Environment.<br />
|-<br />
| VirtualMachine<br />
| ExtendedBoolean_t<br />
| 0..1<br />
|<br />
| True if the Execution Environment is hosted within a virtual machine; in this case, the values of the other attributes are related to the virtualized environment and not to the hosting environment.<br />
|-<br />
| TotalInstances<br />
| UInt32<br />
| 0..1<br />
|<br />
| The total number of Execution Environment instances. This SHOULD reflect the total installed capacity, i.e. including resources which are temporarily unavailable.<br />
|}</div>Walshj1https://wiki.egi.eu/w/index.php?title=GPGPU-WG_KnowledgeBase_GLUE2_Profile_ExecutionEnvironment&diff=65236GPGPU-WG KnowledgeBase GLUE2 Profile ExecutionEnvironment2014-03-02T06:21:31Z<p>Walshj1: </p>
<hr />
<div>The ExecutionEnvironment class describes the hardware and operating system environment in which a job will run. It represents a set of homogeneous Worker Nodes, so if a computing system contains nodes with significantly different properties there MAY be several ExecutionEnvironment instances. This implies that it should be possible to request a specific environment when a job is submitted. The ExecutionEnvironment MAY refer to virtual rather than physical machines.<br />
<br />
As well as attributes describing a typical node, the class gives summary information about the size and usage of the set of nodes which posess those properties. However, there is no way to relate these to the information in other entities, e.g. it is not possible to know which jobs in a given ComputingShare are running on which ExecutionEnvironment.<br />
<br />
<br />
<br />
{|!colspan="5"| '''ExecutionEnvironment'''<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
|'''Entity'''<br />
|colspan=3 | '''Inherits from'''<br />
|'''Description'''<br />
|- <br />
| ExecutionEnvironment <br />
| colspan="3" | Resource<br />
| A type of environment available to and requestable by a Grid job when submitted to a<br />
ComputingService via a Computing Endpoint; the type of environment is described in terms of hardware, operating system and network characteristics. Information about the total/available/used instances of this type of execution environment are also included.<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
| '''Inherited Attribute '''<br />
| '''Type'''<br />
| '''Mult'''<br />
| '''Unit'''<br />
| '''Description'''<br />
|-<br />
| ''Creation Time''<br />
| ''DateTime_t''<br />
| ''0..1''<br />
|<br />
| ''Timestamp describing when the entity instance was created''<br />
|-<br />
| ''Validity''<br />
| ''Unit64''<br />
| ''0..1''<br />
| ''s''<br />
| '' The duration after CreationTime that the information presented in the Entity SHOULD be considered relevant. After that period has elapsed, the information SHOULD NOT be consideredrelevant''<br />
|-<br />
| ''ID [key]''<br />
| ''URI''<br />
| ''1''<br />
|<br />
| ''A global unique ID''<br />
|-<br />
| ''Name''<br />
| ''String''<br />
| ''0..1''<br />
|<br />
| ''Human Readable name''<br />
|-<br />
| ''OtherInfo''<br />
| ''String''<br />
| ''*''<br />
|<br />
| ''Placeholder to publish info that does not fit in any other attribute. Free-form string, comma-separated tags, (name, value ) pair are all examples of valid syntax.''<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
| '''Attribute '''<br />
| '''Type'''<br />
| '''Mult'''<br />
| '''Unit'''<br />
| '''Description'''<br />
|-<br />
| AppName<br />
| String<br />
| 1<br />
|<br />
| The name of the application or environment.<br />
|<br />
|}</div>Walshj1https://wiki.egi.eu/w/index.php?title=GPGPU-WG_KnowledgeBase_GLUE2_Profile_ExecutionEnvironment&diff=65235GPGPU-WG KnowledgeBase GLUE2 Profile ExecutionEnvironment2014-03-02T06:19:08Z<p>Walshj1: </p>
<hr />
<div>The ExecutionEnvironment class describes the hardware and operating system environment in which a job will run. It represents a set of homogeneous Worker Nodes, so if a computing system contains nodes with significantly different properties there MAY be several ExecutionEnvironment instances. This implies that it should be possible to request a specific environment when a job is submitted. The ExecutionEnvironment MAY refer to virtual rather than physical machines.<br />
<br />
As well as attributes describing a typical node, the class gives summary information about the size and usage of the set of nodes which posess those properties. However, there is no way to relate these to the information in other entities, e.g. it is not possible to know which jobs in a given ComputingShare are running on which ExecutionEnvironment.<br />
<br />
<br />
<br />
{|!colspan="5"| '''ExecutionEnvironment'''<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
|'''Entity'''<br />
|colspan=3 | '''Inherits from'''<br />
|'''Description'''<br />
|- <br />
| ExecutionEnvironment <br />
| colspan="3" | Entity<br />
| A description of the installed application software available or software environment characteristics available within one or more Execution Environments.<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
| '''Inherited Attribute '''<br />
| '''Type'''<br />
| '''Mult'''<br />
| '''Unit'''<br />
| '''Description'''<br />
|-<br />
| ''Creation Time''<br />
| ''DateTime_t''<br />
| ''0..1''<br />
|<br />
| ''Timestamp describing when the entity instance was created''<br />
|-<br />
| ''Validity''<br />
| ''Unit64''<br />
| ''0..1''<br />
| ''s''<br />
| '' The duration after CreationTime that the information presented in the Entity SHOULD be considered relevant. After that period has elapsed, the information SHOULD NOT be consideredrelevant''<br />
|-<br />
| ''ID [key]''<br />
| ''URI''<br />
| ''1''<br />
|<br />
| ''A global unique ID''<br />
|-<br />
| ''Name''<br />
| ''String''<br />
| ''0..1''<br />
|<br />
| ''Human Readable name''<br />
|-<br />
| ''OtherInfo''<br />
| ''String''<br />
| ''*''<br />
|<br />
| ''Placeholder to publish info that does not fit in any other attribute. Free-form string, comma-separated tags, (name, value ) pair are all examples of valid syntax.''<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
| '''Attribute '''<br />
| '''Type'''<br />
| '''Mult'''<br />
| '''Unit'''<br />
| '''Description'''<br />
|-<br />
| AppName<br />
| String<br />
| 1<br />
|<br />
| The name of the application or environment.<br />
|<br />
|}</div>Walshj1https://wiki.egi.eu/w/index.php?title=GPGPU-WG_KnowledgeBase_GLUE2_Profile_ExecutionEnvironment&diff=65234GPGPU-WG KnowledgeBase GLUE2 Profile ExecutionEnvironment2014-03-02T06:18:12Z<p>Walshj1: </p>
<hr />
<div>The ExecutionEnvironment class describes the hardware and operating system environment in which a job will run. It represents a set of homogeneous Worker Nodes, so if a computing system contains nodes with significantly different properties there MAY be several ExecutionEnvironment instances. This implies that it should be possible to request a specific environment when a job is submitted. The ExecutionEnvironment MAY refer to virtual rather than physical machines.<br />
<br />
As well as attributes describing a typical node, the class gives summary information about the size and usage of the set of nodes which posess those properties. However, there is no way to relate these to the information in other entities, e.g. it is not possible to know which jobs in a given ComputingShare are running on which ExecutionEnvironment.<br />
<br />
<br />
<br />
{|!colspan="5"| '''ApplicationEnvironment'''<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
|'''Entity'''<br />
|colspan=3 | '''Inherits from'''<br />
|'''Description'''<br />
|- <br />
| ApplicationEnvironment <br />
| colspan="3" | Entity<br />
| A description of the installed application software available or software environment characteristics available within one or more Execution Environments.<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
| '''Inherited Attribute '''<br />
| '''Type'''<br />
| '''Mult'''<br />
| '''Unit'''<br />
| '''Description'''<br />
|-<br />
| ''Creation Time''<br />
| ''DateTime_t''<br />
| ''0..1''<br />
|<br />
| ''Timestamp describing when the entity instance was created''<br />
|-<br />
| ''Validity''<br />
| ''Unit64''<br />
| ''0..1''<br />
| ''s''<br />
| '' The duration after CreationTime that the information presented in the Entity SHOULD be considered relevant. After that period has elapsed, the information SHOULD NOT be consideredrelevant''<br />
|-<br />
| ''ID [key]''<br />
| ''URI''<br />
| ''1''<br />
|<br />
| ''A global unique ID''<br />
|-<br />
| ''Name''<br />
| ''String''<br />
| ''0..1''<br />
|<br />
| ''Human Readable name''<br />
|-<br />
| ''OtherInfo''<br />
| ''String''<br />
| ''*''<br />
|<br />
| ''Placeholder to publish info that does not fit in any other attribute. Free-form string, comma-separated tags, (name, value ) pair are all examples of valid syntax.''<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
| '''Attribute '''<br />
| '''Type'''<br />
| '''Mult'''<br />
| '''Unit'''<br />
| '''Description'''<br />
|-<br />
| AppName<br />
| String<br />
| 1<br />
|<br />
| The name of the application or environment.<br />
|<br />
|}</div>Walshj1https://wiki.egi.eu/w/index.php?title=GPGPU-WG_KnowledgeBase_GLUE2_Profile_ExecutionEnvironment&diff=65233GPGPU-WG KnowledgeBase GLUE2 Profile ExecutionEnvironment2014-03-02T06:17:39Z<p>Walshj1: </p>
<hr />
<div>The ExecutionEnvironment class describes the hardware and operating system environment in which a job will run. It represents a set of homogeneous Worker Nodes, so if a computing system contains nodes with significantly different properties there MAY be several ExecutionEnvironment instances. This implies that it should be possible to request a specific environment when a job is submitted. The ExecutionEnvironment MAY refer to virtual rather than physical machines.<br />
<br />
As well as attributes describing a typical node, the class gives summary information about the size and usage of the set of nodes which posess those properties. However, there is no way to relate these to the information in other entities, e.g. it is not possible to know which jobs in a given ComputingShare are running on which ExecutionEnvironment.<br />
<br />
<br />
<br />
!colspan="5"| '''ApplicationEnvironment'''<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
|'''Entity'''<br />
|colspan=3 | '''Inherits from'''<br />
|'''Description'''<br />
|- <br />
| ApplicationEnvironment <br />
| colspan="3" | Entity<br />
| A description of the installed application software available or software environment characteristics available within one or more Execution Environments.<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
| '''Inherited Attribute '''<br />
| '''Type'''<br />
| '''Mult'''<br />
| '''Unit'''<br />
| '''Description'''<br />
|-<br />
| ''Creation Time''<br />
| ''DateTime_t''<br />
| ''0..1''<br />
|<br />
| ''Timestamp describing when the entity instance was created''<br />
|-<br />
| ''Validity''<br />
| ''Unit64''<br />
| ''0..1''<br />
| ''s''<br />
| '' The duration after CreationTime that the information presented in the Entity SHOULD be considered relevant. After that period has elapsed, the information SHOULD NOT be consideredrelevant''<br />
|-<br />
| ''ID [key]''<br />
| ''URI''<br />
| ''1''<br />
|<br />
| ''A global unique ID''<br />
|-<br />
| ''Name''<br />
| ''String''<br />
| ''0..1''<br />
|<br />
| ''Human Readable name''<br />
|-<br />
| ''OtherInfo''<br />
| ''String''<br />
| ''*''<br />
|<br />
| ''Placeholder to publish info that does not fit in any other attribute. Free-form string, comma-separated tags, (name, value ) pair are all examples of valid syntax.''<br />
|- style="color:white; background-color:black;" cellpadding="3"<br />
| '''Attribute '''<br />
| '''Type'''<br />
| '''Mult'''<br />
| '''Unit'''<br />
| '''Description'''<br />
|-<br />
| AppName<br />
| String<br />
| 1<br />
|<br />
| The name of the application or environment.<br />
|<br />
|}</div>Walshj1https://wiki.egi.eu/w/index.php?title=GPGPU-WG_KnowledgeBase_GLUE2_Profile_ExecutionEnvironment&diff=65232GPGPU-WG KnowledgeBase GLUE2 Profile ExecutionEnvironment2014-03-02T06:12:23Z<p>Walshj1: Created page with "The ExecutionEnvironment class describes the hardware and operating system environment in which a job will run. It represents a set of homogeneous Worker Nodes, so if a computing..."</p>
<hr />
<div>The ExecutionEnvironment class describes the hardware and operating system environment in which a job will run. It represents a set of homogeneous Worker Nodes, so if a computing system contains nodes with significantly different properties there MAY be several ExecutionEnvironment instances. This implies that it should be possible to request a specific environment when a job is submitted. The ExecutionEnvironment MAY refer to virtual rather than physical machines.<br />
<br />
As well as attributes describing a typical node, the class gives summary information about the size and usage of the set of nodes which posess those properties. However, there is no way to relate these to the information in other entities, e.g. it is not possible to know which jobs in a given ComputingShare are running on which ExecutionEnvironment.</div>Walshj1https://wiki.egi.eu/w/index.php?title=GPGPU-WG_KnowledgeBase&diff=65228GPGPU-WG KnowledgeBase2014-02-28T20:55:58Z<p>Walshj1: </p>
<hr />
<div>This page indexes the current knowledge-base on GPGPU integration into the EGI Grid Infrastructure.<br />
<br />
* [[GPGPU-WG:GPGPU_Working_Group_KnowledgeBase:Batch_Schedulers| Batch Schedulers]]<br />
** [[GPGPU-WG:GPGPU_Working_Group_KnowledgeBase:Batch_Schedulers:Torque | Torque (Without Maui)]]<br />
** [[GPGPU-WG:GPGPU_Working_Group_KnowledgeBase:Batch_Schedulers:Torque_MAUI | Torque/MAUI]]<br />
** [[GPGPU-WG:GPGPU_Working_Group_KnowledgeBase:Batch_Schedulers:SLURM | SLURM]]<br />
** [[GPGPU-WG:GPGPU_Working_Group_KnowledgeBase:Batch_Schedulers:SchedulerScenarios| Possible RC Setups]]<br />
<br />
* Glue 2.0<br />
** GLUE Documents<br />
*** [https://documents.egi.eu/public/ShowDocument?docid=1324 EGI GLUE2 Profile]<br />
*** [http://redmine.ogf.org/dmsf/glue-wg?folder_id=18 OGF Glue 2.0 Specification]<br />
*** [[GPGPU-WG:GPGPU_Working_Group_KnowledgeBase:GLUE2:Profile:Application | GLUE2 Application Software Profiles (draft)]]<br />
*** [[GPGPU-WG:GPGPU_Working_Group_KnowledgeBase:GLUE2:Profile:ExecutionEnvironment | Execution Environment ]]<br />
<br />
* Glue 1.3 Implementation<br />
** Based on ideas for supporting "Short Dealine Jobs" and MPI-WG<br />
** [[GPGPU-WG:GPGPU_Working_Group_KnowledgeBase:Batch_Schedulers:SchedulerScenarios:GPUOnlyQueue | Proposes establishing specific batch queue following a naming convention]], and uses SoftwareEnvironment tags to publish basic software support or hardware details.<br />
** Usage of resources not handled well, unless the GPGPUs are exposed through a distinct CE or SubCluster<br />
** WMS Ranking Support(?)<br />
<br />
[[GPGPU-WG | To Parent Page]]</div>Walshj1https://wiki.egi.eu/w/index.php?title=GPGPU-WG_KnowledgeBase&diff=65227GPGPU-WG KnowledgeBase2014-02-28T20:52:32Z<p>Walshj1: </p>
<hr />
<div>This page indexes the current knowledge-base on GPGPU integration into the EGI Grid Infrastructure.<br />
<br />
* [[GPGPU-WG:GPGPU_Working_Group_KnowledgeBase:Batch_Schedulers| Batch Schedulers]]<br />
** [[GPGPU-WG:GPGPU_Working_Group_KnowledgeBase:Batch_Schedulers:Torque | Torque (Without Maui)]]<br />
** [[GPGPU-WG:GPGPU_Working_Group_KnowledgeBase:Batch_Schedulers:Torque_MAUI | Torque/MAUI]]<br />
** [[GPGPU-WG:GPGPU_Working_Group_KnowledgeBase:Batch_Schedulers:SLURM | SLURM]]<br />
** [[GPGPU-WG:GPGPU_Working_Group_KnowledgeBase:Batch_Schedulers:SchedulerScenarios| Possible RC Setups]]<br />
<br />
* Glue 2.0<br />
** GLUE Documents<br />
*** [https://documents.egi.eu/public/ShowDocument?docid=1324 EGI GLUE2 Profile]<br />
*** [http://redmine.ogf.org/dmsf/glue-wg?folder_id=18 OGF Glue 2.0 Specification]<br />
*** [[GPGPU-WG:GPGPU_Working_Group_KnowledgeBase:GLUE2:Profile:Application | GLUE2 Application Software Profiles (draft)]]<br />
*** [[GPGPU-WG:GPGPU_Working_Group_KnowledgeBase:GLUE2:Profile:ExecutionEnvironment | Execution Environment ]]<br />
<br />
* Glue 1.3 Implementation<br />
** Based on ideas for supporting "Short Dealine Jobs" and MPI-WG<br />
** [[GPGPU-WG:GPGPU_Working_Group_KnowledgeBase:Batch_Schedulers:SchedulerScenarios | Proposes establishing specific batch queue following a naming convention]], and uses SoftwareEnvironment tags to publish basic software support or hardware details.<br />
** Usage of resources not handled well, unless the GPGPUs are exposed through a distinct CE or SubCluster<br />
** WMS Ranking Support(?)</div>Walshj1https://wiki.egi.eu/w/index.php?title=GPGPU-WG_KnowledgeBase&diff=65226GPGPU-WG KnowledgeBase2014-02-28T20:50:02Z<p>Walshj1: </p>
<hr />
<div>This page indexes the current knowledge-base on GPGPU integration into the EGI Grid Infrastructure.<br />
<br />
* [[GPGPU-WG:GPGPU_Working_Group_KnowledgeBase:Batch_Schedulers| Batch Schedulers]]<br />
** [[GPGPU-WG:GPGPU_Working_Group_KnowledgeBase:Batch_Schedulers:Torque | Torque (Without Maui)]]<br />
** [[GPGPU-WG:GPGPU_Working_Group_KnowledgeBase:Batch_Schedulers:Torque_MAUI | Torque/MAUI]]<br />
** [[GPGPU-WG:GPGPU_Working_Group_KnowledgeBase:Batch_Schedulers:SLURM | SLURM]]<br />
** [[GPGPU-WG:GPGPU_Working_Group_KnowledgeBase:Batch_Schedulers:SchedulerScenarios| Possible RC Setups]]<br />
<br />
* Glue 2.0<br />
** GLUE Documents<br />
*** [https://documents.egi.eu/public/ShowDocument?docid=1324 EGI GLUE2 Profile]<br />
*** [http://redmine.ogf.org/dmsf/glue-wg?folder_id=18 OGF Glue 2.0 Specification]<br />
*** [[GPGPU-WG:GPGPU_Working_Group_KnowledgeBase:GLUE2:Profile:Application | GLUE2 Application Software Profiles (draft)]]<br />
*** [[GPGPU-WG:GPGPU_Working_Group_KnowledgeBase:GLUE2:Profile:ExecutionEnvironment | Execution Environment ]]<br />
<br />
* Glue 1.3 Implementation<br />
** Based on ideas for supporting "Short Dealine Jobs" and MPI-WG<br />
** Proposes establishing specific batch queue following a naming convention, and uses SoftwareEnvironment tags to publish basic software support or hardware details.<br />
** Usage of resources not handled well, unless the GPGPUs are exposed through a distinct CE or SubCluster<br />
** WMS Ranking Support(?)</div>Walshj1https://wiki.egi.eu/w/index.php?title=GPGPU_Working_Group&diff=65225GPGPU Working Group2014-02-28T20:36:32Z<p>Walshj1: /* Useful Links */</p>
<hr />
<div>{{Template:Op menubar}} {{TOC_right}} <br />
[[Category:Task_forces]]<br />
<br />
'''Coordinator''': Miroslav Ruda/CESNET, John Walsh/TCD <br />
<br />
'''Meetings page''': [https://indico.egi.eu/indico/categoryDisplay.py?categId=116 Agendas] <br />
<br />
'''Mailing list''': vt-gpgpu (at) mailman.egi.eu <br />
<br />
'''Duration''': Sep 2013 <br />
<br />
'''Members:''' <br />
<br />
= Introduction<br> =<br />
<br />
Over the summer of 2012, [[VT_GPGPU | the EGI GPGPU Virtual Team]] developed and distributed two surveys - a Grid User oriented survey and a Resource Centre (RC) oriented survey - on the current and future use of General Purpose Graphics Processing Units (GPGPU) on the European Grid Infrastructure (EGI). The key results of the surveys, which were presented at the EGI Technical Forum 2013, showed that:<br />
* many Resource Centres had already deployed GPGPUs or had planned to do so<br />
* Users would be interested in using these resources. <br />
However, currently there is no coherent or standardised means for discovering or accessing GPGPU resources on the EGI or similarly related grid infrastructures. Integration of such resources is a non-trivial task. <br />
These include: <br />
* Batch System integration best practices; <br />
* the evaluation and adoption of an appropriate GlueSchema; <br />
* GPGPU resource usage accounting; <br />
* GPGPU resource availability and reliability testing.<br />
<br />
<br />
= Objectives =<br />
EGI Technical Group/Working Group will study <br />
* Batch System integration best practices <br />
* the proposal and evaluation of an appropriate GlueSchema suitable for describing generalised “Computational Accelerators”. <br />
<br />
=Membership=<br />
Membership of the Group is open to Resource Centre representatives who can contribute directly to either of these objectives. User Community representation and expertise from GlueSchema developers is required to aid with the development and evaluation of the GlueSchema definition. <br />
<br />
= Milestones =<br />
<br />
= Testbed = <br />
Testbed Contacts: <br />
* Derek Ross/STFC, [http://www.einfrastructuresouth.ac.uk/cfi/emerald/ Emerald GPU Cluster] with 372 Nvidia M2090<br />
* Andrea Sartirana/GRIF, 4 servers, each one with 2 accelerators (4 nvidia K20 and 4 Xeon Phi) <br />
* Oleksandr Savytskyi/moldyngrid.org, gromacs 4.6.3 testing (native GPU support) on GPU\Xeon Phi clusters<br />
* Miguel Cardenas/CIEMAT (applications: DES - Dark Energy Survey, artificial intelligence)<br />
* Mariusz Sterzel,Lukasz Flis/Cyfronet: Application Area - Computational Chemistry amd Biology (Nodes with 2 or 8 GPGPU cards)<br />
* Emanouil Atanassov/BG01-IPP: 9 NVIDIA M2090<br />
<br />
= User Communities =<br />
* WeNMR (MD simulations via GROMACS)<br />
<br />
= Actions =<br />
<br />
= Results =<br />
<br />
= Use Cases =<br />
Information about GPGPU use cases was collected in a survey back in 2012 organized by the GPGPU virtual team: go to [[VT_GPGPU/Use_Case|Use Cases]]<br />
<br />
= Useful Links =<br />
* [[GPGPU-WG:GPGPU_Working_Group_KnowlegeBase | GPGPU Knowledge-base]]<br />
* [[GPGPU-WG:ResorceCentres | GPGPU Resource Centres]]<br />
* [[VT_GPGPU|GPGPU Virtual Team]] (closed)</div>Walshj1https://wiki.egi.eu/w/index.php?title=GPGPU_Working_Group&diff=65224GPGPU Working Group2014-02-28T20:36:01Z<p>Walshj1: /* Useful Links */</p>
<hr />
<div>{{Template:Op menubar}} {{TOC_right}} <br />
[[Category:Task_forces]]<br />
<br />
'''Coordinator''': Miroslav Ruda/CESNET, John Walsh/TCD <br />
<br />
'''Meetings page''': [https://indico.egi.eu/indico/categoryDisplay.py?categId=116 Agendas] <br />
<br />
'''Mailing list''': vt-gpgpu (at) mailman.egi.eu <br />
<br />
'''Duration''': Sep 2013 <br />
<br />
'''Members:''' <br />
<br />
= Introduction<br> =<br />
<br />
Over the summer of 2012, [[VT_GPGPU | the EGI GPGPU Virtual Team]] developed and distributed two surveys - a Grid User oriented survey and a Resource Centre (RC) oriented survey - on the current and future use of General Purpose Graphics Processing Units (GPGPU) on the European Grid Infrastructure (EGI). The key results of the surveys, which were presented at the EGI Technical Forum 2013, showed that:<br />
* many Resource Centres had already deployed GPGPUs or had planned to do so<br />
* Users would be interested in using these resources. <br />
However, currently there is no coherent or standardised means for discovering or accessing GPGPU resources on the EGI or similarly related grid infrastructures. Integration of such resources is a non-trivial task. <br />
These include: <br />
* Batch System integration best practices; <br />
* the evaluation and adoption of an appropriate GlueSchema; <br />
* GPGPU resource usage accounting; <br />
* GPGPU resource availability and reliability testing.<br />
<br />
<br />
= Objectives =<br />
EGI Technical Group/Working Group will study <br />
* Batch System integration best practices <br />
* the proposal and evaluation of an appropriate GlueSchema suitable for describing generalised “Computational Accelerators”. <br />
<br />
=Membership=<br />
Membership of the Group is open to Resource Centre representatives who can contribute directly to either of these objectives. User Community representation and expertise from GlueSchema developers is required to aid with the development and evaluation of the GlueSchema definition. <br />
<br />
= Milestones =<br />
<br />
= Testbed = <br />
Testbed Contacts: <br />
* Derek Ross/STFC, [http://www.einfrastructuresouth.ac.uk/cfi/emerald/ Emerald GPU Cluster] with 372 Nvidia M2090<br />
* Andrea Sartirana/GRIF, 4 servers, each one with 2 accelerators (4 nvidia K20 and 4 Xeon Phi) <br />
* Oleksandr Savytskyi/moldyngrid.org, gromacs 4.6.3 testing (native GPU support) on GPU\Xeon Phi clusters<br />
* Miguel Cardenas/CIEMAT (applications: DES - Dark Energy Survey, artificial intelligence)<br />
* Mariusz Sterzel,Lukasz Flis/Cyfronet: Application Area - Computational Chemistry amd Biology (Nodes with 2 or 8 GPGPU cards)<br />
* Emanouil Atanassov/BG01-IPP: 9 NVIDIA M2090<br />
<br />
= User Communities =<br />
* WeNMR (MD simulations via GROMACS)<br />
<br />
= Actions =<br />
<br />
= Results =<br />
<br />
= Use Cases =<br />
Information about GPGPU use cases was collected in a survey back in 2012 organized by the GPGPU virtual team: go to [[VT_GPGPU/Use_Case|Use Cases]]<br />
<br />
= Useful Links =<br />
* [[GPGPU-WG:GPGPU_Working_Group_KnowlegeBase | GPGPU Knowlege-base]]<br />
* [[GPGPU-WG:ResorceCentres | GPGPU Resource Centres]]<br />
* [[VT_GPGPU|GPGPU Virtual Team]] (closed)</div>Walshj1