- Infos im HLRS Wiki sind nicht rechtsverbindlich und ohne Gewähr -
- Information contained in the HLRS Wiki is not legally binding and HLRS is not responsible for any damages that might result from its use -

HPE Hawk: Difference between revisions

From HLRS Platforms
Jump to navigationJump to search
No edit summary
No edit summary
 
(28 intermediate revisions by 6 users not shown)
Line 1: Line 1:
{{warning|text=HAWK is currently in the set up phase. For more details about about the timing please see the [https://kb.hlrs.de/platforms/index.php/Hawk_installation_schedule Hawk installation schedule].}}
 
{{warning|text=Please have in mind that the system is currently under construction. Hence, modifications might occur and the observed performance can vary.}}
{{Note
| text = Please be sure to read at least the [[10_minutes_before_the_first_job]] document and consult the [[General HWW Documentation]] before you start to work with any of our systems.
}}
 
{{Warning
| text = In prepartion of the next generation supercomputer [[ Hunter_(HPE) | Hunter ]], the hardware configuration has been reduced (from 5632 compute nodes to 4096 compute nodes). Workspace filesystem ws10 has been removed.
}}




Line 13: Line 19:
{| style="border: 0; margin: 0;" cellpadding="3"
{| style="border: 0; margin: 0;" cellpadding="3"
| valign="top" |   
| valign="top" |   
<!-- * [[Hawk_installation_schedule#Terms_of_Use | Terms of use ]] -->
* [[HPE_Hawk_access|Access]]
* [[HPE_Hawk_access|Access]]
* [[HPE_Hawk_Hardware_and_Architecture|Hardware and Architecture]]
* [[HPE_Hawk_Hardware_and_Architecture|Hardware and Architecture]]
Line 27: Line 34:
* [[HPE_Hawk_Support|Support (contact/staff)]]
* [[HPE_Hawk_Support|Support (contact/staff)]]
* [[HPE_Hawk_FAQ|FAQ]]
* [[HPE_Hawk_FAQ|FAQ]]
* [http://websrv.hlrs.de/cgi-bin/hwwweather?task=viewmachine&machine=hawk News,Status,Maintenance for hawk]
* [http://websrv.hlrs.de/cgi-bin/hwwweather?task=viewmachine&machine=hawk Status,Maintenance for hawk]
* [[HPE_Hawk_News|News]]
|}
|}
</div>
</div>
Line 36: Line 44:




== Hardware ==
=== Node/Processor ===


Compute nodes as well as login nodes are equipped with
  AMD EPYC 7742 64-Core Processor
detailed information will be provided later. Please check for additional infos [https://www.amd.com/de/products/cpu/amd-epyc-7742 AMD Rome 7742]
With respect to node and processor details cf. here.


<br>
{| style="border:0; margin: 0;" width="100%" cellspacing="10"


=== Interconnect ===
| valign="top" style="padding: 0; border: 1px solid #aaaaaa; margin-bottom: 0;" |
Hawk deploys an Infiniband HDR based interconnect with a 9-dimensional enhanced hypercube topology. Please refer to [https://kb.hlrs.de/platforms/upload/Interconnect_topology.pdf here] with respect to the latter. Infiniband HDR has a bandwidth of 200 Gbit/s and a MPI latency of ~1.3us per link. The full bandwidth of 200 Gbit/s can be used if communicating between the 16 nodes connected to the same node of the hypercube (cf. [https://kb.hlrs.de/platforms/upload/Interconnect_topology.pdf here]). Within the hypercube, the higher the dimension, the less bandwidth is available.
<div style="font-size: 105%; padding: 0.4em; background-color: #eeeeee; border-bottom: 1px solid #aaaaaa; text-align: center;">'''Documentation'''</div>
Topology aware scheduling is used to exclude major performance fluctuations. This means that larger jobs can only be requested with defined node numbers (64, 128, 256, 512, 1024, 2048 and 4096) in regular operation. This restriction ensures optimal system utilization while simultaneously exploiting the network topology. Jobs with a node number of < 128 nodes are processed in a special partition. Jobs over 4096 nodes are processed at special times.
<div style="background: #ffffff; padding:0.2em 0.4em;">
{| style="border: 0; margin: 0;" cellpadding="3"
| valign="top" | 
* [[Batch_System_PBSPro_(Hawk)|Batch System]]
* [[Module environment(Hawk)|Module Environment]]
* [[Storage_(Hawk)| Storage Description ]]
* [[Compiler(Hawk)|Compiler]]
* [[MPI(Hawk)|MPI]]
* [[Libraries(Hawk)|Libraries]]
* [[Manuals(Hawk)|Manuals]]
* [[Optimization|Optimization]]
* [[Hawk_PrePostProcessing|Pre- and Post-Processing]]
* [[Big_Data,_AI_Aplications_and_Frameworks|Big Data, AI Applications and Frameworks]]
* [[Performance Analysis Tools]]
* [[CPE|Cray Programming Environment (CPE)]]


<br>
|}
</div>


=== Filesystem ===


<br>


== Access ==
| valign="top" style="padding: 0; border: 1px solid #aaaaaa; margin-bottom: 0;" |
<div style="font-size: 105%; padding: 0.4em; background-color: #eeeeee; border-bottom: 1px solid #aaaaaa; text-align: center;">'''Utilities'''</div>
<div style="background: #ffffff; padding:0.2em 0.4em;">
{| style="border: 0; margin: 0;" cellpadding="3"
| valign="top" | 
* [[CAE_utilities|CAE Utilities]]
* [[CAE_howtos|CAE HOWTOs]]
* [[MKL | MKL Fortran Interfaces ]]
|}
</div>


'''Login-Node''': hawk-tds-login1.hww.hlrs.de
|}
{{note|text=Access to the Hawk TDS is possible now on request. In case you have early access, we ask you to provide us with your experience regarding usage and performance (approximately half a page) once a month.}}


<br>


== Module environment ==
----
cf. [[Module environment(Hawk)|here]]
[[Help | Help for Wiki Usage]]
 
<br>
 
== Compiler ==
cf. [[Compiler(Hawk)|here]]
 
<br>
 
== MPI ==
 
'''Tuned MPI''': In order to use the MPI implementation provided by HPE, please load the Message Passing Toolkit (MPT) module ''mpt'' (not ABI-compatible to other MPI implementations) or ''hmpt'' (ABI-compatible to MPICH-derivatives).
 
'''User Guide''': For detailed information cf. the [http://www.hpe.com/support/mpi-ug-036 HPE Message Passing Interface (MPI) User Guide].
 
'''Performance optimization''': With respect to MPI performance optimization by means of tuning environment variables please cf.
[https://kb.hlrs.de/platforms/upload/Tuning_of_MPT.pdf Tuning of MPT]
 
<br>
 
== Libraries ==
 
cf. [[Libraries(Hawk)|here]]
 
<br>
 
 
== Batch System ==
 
cf. [[Batch_System_PBSPro_(Hawk)|here]]
 
<br>
 
 
== Disk storage ==
 
Home directories as well as workspaces are handled in the same way as on Hazel Hen, so please cf. [[CRAY_XC40_Disk_Storage | Storage Description ]] regarding details.
 
<br>
 
== Pre- and post processing ==
 
Within HLRS simulation environment special nodes for pre- and post processing tasks are available. Such nodes could be requested via the batch system (follow this link for more info).
Available nodes are
  table...
    4 nodes 2 TB Memory 2 Socket AMD ...x TB local storage  shared usage model
    1 Node  4 TB Memory 2 Socket AMD    x TB local storage  shared usage model
 
 
more specialized nodes e.g. graphics, vector, DataAnalytics, ... are available in the [[NEC_Cluster_Hardware_and_Architecture_(vulcan)|Vulcan cluster]]
 
<br>
 
== Manuals ==
'''Processor''':
* [https://developer.amd.com/wp-content/resources/56305_SOG_3.00_PUB.pdf Software Optimization Guide for AMD EPYC Rome Processors]
* [https://developer.amd.com/wp-content/resources/56255_3_03.PDF Open-Source Register Reference for AMD EPYC Rome Processors] <br> (in particular describing available hardware performance counters)
* [https://www.amd.com/system/files/TechDocs/47414_15h_sw_opt_guide.pdf Software Optimization Guide for AMD Family 15h] <br> (although depicting an older family of AMD processors, the optimization approaches shown in this document are also applicable to the AMD EPYC Rome processor deployed in Hawk)
 
<br>
 
'''MPI''':
* [http://www.hpe.com/support/mpi-ug-036 HPE Message Passing Interface (MPI) User Guide]
 
<br>
 
'''Batch system''':
* [https://www.altair.com/pdfs/pbsworks/PBSUserGuide19.2.3.pdf User's Guide]
* [https://www.altair.com/pdfs/pbsworks/PBSReferenceGuide19.2.3.pdf Reference Guide] (cf. this with respect to a complete list of environment variables exported by PBS)

Latest revision as of 08:44, 25 October 2024

Note: Please be sure to read at least the 10_minutes_before_the_first_job document and consult the General HWW Documentation before you start to work with any of our systems.


Warning: In prepartion of the next generation supercomputer Hunter , the hardware configuration has been reduced (from 5632 compute nodes to 4096 compute nodes). Workspace filesystem ws10 has been removed.




Introduction


Troubleshooting




Documentation


Utilities



Help for Wiki Usage