Running Calculations: Difference between revisions
K Siegmund (talk | contribs) |
K Siegmund (talk | contribs) |
||
| (13 intermediate revisions by 3 users not shown) | |||
| Line 3: | Line 3: | ||
On your desktop computer, you start your calculations and they start immediately, run until they are finished, then your desktop does mostly nothing, until you start another calculation. A compute cluster has several hundred, maybe a thousand computers (compute nodes), all of them are busy most of the time and many people want to run a great number of calculations. So running your job has to include some extra steps: |
On your desktop computer, you start your calculations and they start immediately, run until they are finished, then your desktop does mostly nothing, until you start another calculation. A compute cluster has several hundred, maybe a thousand computers (compute nodes), all of them are busy most of the time and many people want to run a great number of calculations. So running your job has to include some extra steps: |
||
# prepare a |
# prepare a script (a set commands to run - usually as a shell script), with all the commands that are necessary to run your calculation from start to finish. In addition to the commands necessary to run the calculation, this ''[[batch script]]'' has a header section, in which you specify details like required compute cores (processing units witin a computer), estimated runtime, memory requirements, disk space needed, etc. |
||
# '' |
# ''Submit'' the script into a queue, where your ''job'' (calculation) |
||
# |
# is queued and waits in row with other compute jobs until the resources you requested in the header become available. |
||
# Execution: Once your job reaches the front of the queue, your script is executed on a compute node. Your calculation runs on that node until it is finished or reaches the specified time limit. |
# Execution: Once your job reaches the front of the queue, your script is executed on a compute node. Your calculation runs on that node until it is finished or reaches the specified time limit. |
||
# Save results: At the end of your script, include commands to save the calculation results back to your home directory. |
# Save results: At the end of your script, include commands to save the calculation results back to your home directory. |
||
There are two types of [[batch system]]s currently used on bwHPC clusters, called " |
There are two types of [[batch system]]s currently used on bwHPC clusters, called "Moab" (legacy installs) and "Slurm". |
||
== Example Jobs == |
|||
You are in luck, if you need to use a software that is installed on your bwHPC cluster as a software module (List of installed software via "module avail" on the cluster or also at https://www.bwhpc.de/software.html). |
|||
For most software that a bwHPC project installed on the cluster, we have prepared an example job script running some example calculation with that exact software. |
|||
How to access these examples is described in the "Software job examples" section of the [[Environment_Modules]] page - in short, after loading the module, the examples will be available in path available through the variable $SOFTWARENAME_EXA_DIR (e.g. for the module chem/lammps in $LAMMPS_EXA_DIR) |
|||
== Link to Batch System per Cluster == |
== Link to Batch System per Cluster == |
||
| Line 20: | Line 28: | ||
** [[Helix/Slurm | Slurm Helix]] |
** [[Helix/Slurm | Slurm Helix]] |
||
* Moab systems (legacy systems with deprecated queuing system) |
* Moab systems (legacy systems with deprecated queuing system) |
||
** [[NEMO/Moab|Moab NEMO |
** [[NEMO/Moab|Moab NEMO]] |
||
** [[BinAC/Moab|Moab BinAC |
** [[BinAC/Moab|Moab BinAC]] |
||
== Scaling == |
|||
| ⚫ | |||
| ⚫ | |||
* [[Scaling]] |
|||
== Energy Efficiency == |
|||
Please also see our advice for |
|||
* [[Energy Efficient Cluster Usage]] |
|||
== HPC Glossary == |
|||
A short definition of the typical elements of an HPC cluster. |
|||
;HPC |
|||
: short for '''H'''igh '''P'''erformance '''C'''omputing |
|||
;HPC Cluster |
|||
:Collection of compute nodes with (usually) high bandwidth and low latency communication. They can be accessed via login nodes. |
|||
;Node |
|||
:An individual computer with one or more sockets, part of an HPC cluster. |
|||
;Socket |
|||
:Physical socket where the CPU capsules are placed. |
|||
;Core |
|||
:The physical unit that can independently execute tasks on a CPU. Modern CPUs generally have multiple cores. |
|||
;Thread |
|||
:Logical unit that can be executed independently. |
|||
;Hyperthreading |
|||
: Modern computers can be configured so that one real compute-[[core]] appears like two "logical" cores on the system. These two "hyperthreads" can sometimes do computations in parallel, if the calculations use two different sub-units of the compute-core - but most of the time, two calculations on two hyperthreads run on the same physical hardware and both run half as fast as if one thread had a full core. Some programs (e.g. gromacs) can profit from running with twice as many threads on hyperthreads and finish 10-20% faster if run in that way. |
|||
;Multithreading |
|||
: Multithreading means that one computer program runs calculations on more than one compute-core using several logical "threads" of serial compute instructions to do so (eg. to work through different and independent data arrays in parallel). Specific types of multithreaded parallelization are [[OpenMP]] or [[MPI]]. |
|||
;CPU |
|||
:Central Processing Unit. It performs the actual computation in a compute node. A modern CPU is composed of numerous cores and layers of cache. |
|||
;GPU:Graphics Processing Unit. GPUs in HPC clusters are used as high-performance accelerators and are particularly useful to process workloads in Machine Learning (ML) and Artificial Intelligence (AI) more efficiently. The software has to be explicitly designed to use GPUs. CUDA and OpenACC are the most popular platforms in scientific computing with GPUs. |
|||
;RAM |
|||
:Random Access Memory. It is used as the working memory for the cores. |
|||
;Batch System |
|||
; Moab |
|||
; Script |
|||
; Slurm |
|||
{|style="background:#deffee; width:100%;" |
|||
; Shell Script / Bash |
|||
|style="padding:5px; background:#cef2e0; text-align:left"| |
|||
[[Image:Attention.svg|center|25px]] |
|||
|style="padding:5px; background:#cef2e0; text-align:left"| |
|||
Scientific software installed on the bwHPC Clusters often comes with simple example jobs (job script and input files). See [[Software Modules]] on how to load examples. |
|||
|} |
|||
== How to Use Computing Ressources Efficiently == |
|||
; Job |
|||
; Runtime |
|||
| ⚫ | |||
; Scaling |
|||
For this, your computational problem will have to be divided into pieces, which always causes some overhead. |
|||
| ⚫ | |||
; Scheduler |
|||
Information regarding the supported parallel programming paradigms and specific hints on their usage are summarized at '''[[Parallel Programming]]''' |
|||
; Submit |
|||
Running calculations on an HPC node consumes a lot of energy. To make the most of the available resources and keep cluster and energy use as efficient as possible please also see our advice for '''[[Energy Efficient Cluster Usage]] |
|||
; Parallelization |
|||
''' |
|||
Latest revision as of 11:52, 11 September 2024
Description
On your desktop computer, you start your calculations and they start immediately, run until they are finished, then your desktop does mostly nothing, until you start another calculation. A compute cluster has several hundred, maybe a thousand computers (compute nodes), all of them are busy most of the time and many people want to run a great number of calculations. So running your job has to include some extra steps:
- prepare a script (a set commands to run - usually as a shell script), with all the commands that are necessary to run your calculation from start to finish. In addition to the commands necessary to run the calculation, this batch script has a header section, in which you specify details like required compute cores (processing units witin a computer), estimated runtime, memory requirements, disk space needed, etc.
- Submit the script into a queue, where your job (calculation)
- is queued and waits in row with other compute jobs until the resources you requested in the header become available.
- Execution: Once your job reaches the front of the queue, your script is executed on a compute node. Your calculation runs on that node until it is finished or reaches the specified time limit.
- Save results: At the end of your script, include commands to save the calculation results back to your home directory.
There are two types of batch systems currently used on bwHPC clusters, called "Moab" (legacy installs) and "Slurm".
Example Jobs
You are in luck, if you need to use a software that is installed on your bwHPC cluster as a software module (List of installed software via "module avail" on the cluster or also at https://www.bwhpc.de/software.html).
For most software that a bwHPC project installed on the cluster, we have prepared an example job script running some example calculation with that exact software.
How to access these examples is described in the "Software job examples" section of the Environment_Modules page - in short, after loading the module, the examples will be available in path available through the variable $SOFTWARENAME_EXA_DIR (e.g. for the module chem/lammps in $LAMMPS_EXA_DIR)
Link to Batch System per Cluster
Because of differences in configuration (partly due to different available hardware), each cluster has their own batch system documention:
- Slurm systems
- Moab systems (legacy systems with deprecated queuing system)
 |
Scientific software installed on the bwHPC Clusters often comes with simple example jobs (job script and input files). See Software Modules on how to load examples. |
How to Use Computing Ressources Efficiently
When you are running your calculations, you will have to decide on how many compute-cores your calculation will be simultaneously calculated. For this, your computational problem will have to be divided into pieces, which always causes some overhead.
How to find a reasonable number of how many compute cores to use for your calculation can be found under Scaling
Information regarding the supported parallel programming paradigms and specific hints on their usage are summarized at Parallel Programming
Running calculations on an HPC node consumes a lot of energy. To make the most of the available resources and keep cluster and energy use as efficient as possible please also see our advice for Energy Efficient Cluster Usage