# High Performance Computing

**URL:** https://community.unix.com/c/etc/high-performance-computing/92.md

[Latest](https://community.unix.com/latest.md) · [Categories](https://community.unix.com/categories.md)

---

## [About the High Performance Computing category](https://community.unix.com/t/about-the-high-performance-computing-category/138131)

<div class="topic-metadata">

**Author:** [@system](https://community.unix.com/u/system)\
**Replies:** 0

</div>

Message Passing Interface (MPI) programming and tuning, MPI library installation and management, parallel administration tools, cluster monitoring, cluster optimization, and more HPC topics.

---

## [Trends in supercomputer rankings](https://community.unix.com/t/trends-in-supercomputer-rankings/397242)

<div class="topic-metadata">

**Author:** [@technossomy](https://community.unix.com/u/technossomy)\
**Replies:** 0\
**Last updated:** [August 22, 2025, 1:41pm UTC](https://community.unix.com/t/trends-in-supercomputer-rankings/397242 "2025-08-22T13:41:43Z")

</div>

Collected a few data points of some supercomputers, each of which outside the top 10, to see how their ranking changes over time. Low variability: crossovers are rare. Data quality issues have been left in, such as the m…

---

## [SLURM job limits configuration](https://community.unix.com/t/slurm-job-limits-configuration/381422)

<div class="topic-metadata">

**Author:** [@shaohao](https://community.unix.com/u/shaohao)\
**Replies:** 0\
**Last updated:** [January 14, 2021, 10:12pm UTC](https://community.unix.com/t/slurm-job-limits-configuration/381422 "2021-01-14T22:12:51Z")

</div>

We use Slurm job scheduler on our HPC Linux cluster. Currently, we set the max to submit jobs per user to a fixed number on our cluster. The limit is for both array jobs and individual jobs. But we want to set the max su…

---

## [Encrypting interconnect](https://community.unix.com/t/encrypting-interconnect/367609)

<div class="topic-metadata">

**Author:** [@fiberkill](https://community.unix.com/u/fiberkill)\
**Replies:** 3\
**Last updated:** [July 26, 2017, 10:56am UTC](https://community.unix.com/t/encrypting-interconnect/367609 "2017-07-26T10:56:28Z")

</div>

Hi, i’ve got a qusetion regarding interconnect of compute nodes. In our company we are running a Simulation Cluster which is administrated by the Simulation department. Now our central IT requires to encrypt the interc…

---

## [Helpful Ressources for HPC Admin](https://community.unix.com/t/helpful-ressources-for-hpc-admin/366185)

<div class="topic-metadata">

**Author:** [@akchired](https://community.unix.com/u/akchired)\
**Replies:** 0\
**Last updated:** [April 19, 2017, 8:55am UTC](https://community.unix.com/t/helpful-ressources-for-hpc-admin/366185 "2017-04-19T08:55:18Z")

</div>

Hi Everyone I am new to this valuable forum and would like to ask members for some helpful resources to learn HPC administration and monitoring resources such as webinars, websites, forums, books, and moocs as I need th…

---

## [Python code runs on login node but not on cluster](https://community.unix.com/t/python-code-runs-on-login-node-but-not-on-cluster/363452)

<div class="topic-metadata">

**Author:** [@devinmgibson](https://community.unix.com/u/devinmgibson)\
**Replies:** 0\
**Last updated:** [November 8, 2016, 5:29pm UTC](https://community.unix.com/t/python-code-runs-on-login-node-but-not-on-cluster/363452 "2016-11-08T17:29:10Z")

</div>

I work for one of my professors and we are trying to run SU2 in parallel on a cluster owned by the university that uses slurm for its workload manager. The problem we are running into is that when we ssh into the cluster…

---

## [Building Linux cluster for mechanical engineering software](https://community.unix.com/t/building-linux-cluster-for-mechanical-engineering-software/346672)

<div class="topic-metadata">

**Author:** [@biro](https://community.unix.com/u/biro)\
**Replies:** 6\
**Last updated:** [October 8, 2014, 3:18pm UTC](https://community.unix.com/t/building-linux-cluster-for-mechanical-engineering-software/346672 "2014-10-08T15:18:17Z")

</div>

Hello everybody, I’m new here in the forum and first i will greet everybody. Also I’m new with the issue of HPC, but I have to inform my urgently. My issue: I’m a mechanical engineer, specialised on simulation like f…

---

## [How can an EE major looking to get into HPC bolster their CS foundation?](https://community.unix.com/t/how-can-an-ee-major-looking-to-get-into-hpc-bolster-their-cs-foundation/341441)

<div class="topic-metadata">

**Author:** [@Harmonic](https://community.unix.com/u/Harmonic)\
**Replies:** 2\
**Last updated:** [July 23, 2014, 3:44pm UTC](https://community.unix.com/t/how-can-an-ee-major-looking-to-get-into-hpc-bolster-their-cs-foundation/341441 "2014-07-23T15:44:54Z")

</div>

Im a soph. EE major with an interest in applied mathematics looking to get into HPC and am looking for suggestions on where to start in terms of reading up on some CS subjects in order to get relatively rigorous understa…

---

## [AVX for Linux (32-bit)](https://community.unix.com/t/avx-for-linux-32-bit/342583)

<div class="topic-metadata">

**Author:** [@GG2014](https://community.unix.com/u/GG2014)\
**Replies:** 2\
**Last updated:** [May 10, 2014, 2:33pm UTC](https://community.unix.com/t/avx-for-linux-32-bit/342583 "2014-05-10T14:33:26Z")

</div>

For Intel processors we’ve a lot of new instruction sets (AVX and AVX2 already exists, AVX512 is announced). Therefore an application has to check during run time which instruction sets are available. I’ve written for th…

---

## [Vectorization](https://community.unix.com/t/vectorization/341221)

<div class="topic-metadata">

**Author:** [@a3mlord](https://community.unix.com/u/a3mlord)\
**Replies:** 2\
**Last updated:** [March 29, 2014, 12:29pm UTC](https://community.unix.com/t/vectorization/341221 "2014-03-29T12:29:03Z")

</div>

Hi, I have the following vectorized code: long valor = 0, i=0; \_\_m128i vsum, vecPi, vecCi, vecQCi; vsum = \_mm\_set1\_epi32(0); int32\_t \* const pA = A-\>data; int32\_t \* const pB = B-\>data; int sumDot\[1\]; for( ; …

---

## [Job Schedular for Suse Enterprise SLES 11 SP2](https://community.unix.com/t/job-schedular-for-suse-enterprise-sles-11-sp2/336420)

<div class="topic-metadata">

**Author:** [@vaibhavvsk](https://community.unix.com/u/vaibhavvsk)\
**Replies:** 0\
**Last updated:** [November 8, 2013, 6:48am UTC](https://community.unix.com/t/job-schedular-for-suse-enterprise-sles-11-sp2/336420 "2013-11-08T06:48:48Z")

</div>

We have a server with 160 hyper-threaded cpu’s threads and 2Tb of RAM. I need to implement command line job queue and parallel thread usage for multiple user environment kindly suggest necessary tools to be installed. I…

---

## [IBM Hardware: Test speed of an execution core reliably.](https://community.unix.com/t/ibm-hardware-test-speed-of-an-execution-core-reliably/333397)

<div class="topic-metadata">

**Author:** [@Devyn](https://community.unix.com/u/Devyn)\
**Replies:** 2\
**Last updated:** [September 12, 2013, 3:12pm UTC](https://community.unix.com/t/ibm-hardware-test-speed-of-an-execution-core-reliably/333397 "2013-09-12T15:12:05Z")

</div>

Hey Folks, Doing simple floating point or integer arithmetic is limited since if another execution core is not busy, the system will (presumably?) assign CPU resources to where they are needed so I could be getting the …

---

## [Accelerated computing / GPUs](https://community.unix.com/t/accelerated-computing-gpus/327060)

<div class="topic-metadata">

**Author:** [@figaro](https://community.unix.com/u/figaro)\
**Replies:** 0\
**Last updated:** [April 13, 2013, 12:08pm UTC](https://community.unix.com/t/accelerated-computing-gpus/327060 "2013-04-13T12:08:02Z")

</div>

There are plenty of sources that explain the performance per watt of a computer. However, I wanted to investigate how accelerated computer components (notably GPUs) have become more efficient at a lower price over the ye…

---

## [Programming parallel for C++ and Python application](https://community.unix.com/t/programming-parallel-for-c-and-python-application/325209)

<div class="topic-metadata">

**Author:** [@figaro](https://community.unix.com/u/figaro)\
**Replies:** 3\
**Last updated:** [April 7, 2013, 4:42pm UTC](https://community.unix.com/t/programming-parallel-for-c-and-python-application/325209 "2013-04-07T16:42:51Z")

</div>

I am looking to have a C++ and Python application developed using the processing power of at least one GPU. We are already using Boost, so Boost.MPI comes to mind. We already have some experience in developing C++ appl…

---

## [FFTW - ./configure --enable-mpi error.](https://community.unix.com/t/fftw-configure-enable-mpi-error/324551)

<div class="topic-metadata">

**Author:** [@abhi34101](https://community.unix.com/u/abhi34101)\
**Replies:** 3\
**Last updated:** [February 20, 2013, 2:46pm UTC](https://community.unix.com/t/fftw-configure-enable-mpi-error/324551 "2013-02-20T14:46:04Z")

</div>

Hello I am trying to install fftw3.3.3 on an HPC system. The system has openmpi installed ( though we can choose between a variety of mpi distributions). However, while ./configure step of fftw, there is an error. The r…

---

## [Postgresql Database Corrupt](https://community.unix.com/t/postgresql-database-corrupt/324209)

<div class="topic-metadata">

**Author:** [@ahsanpmd](https://community.unix.com/u/ahsanpmd)\
**Replies:** 2\
**Last updated:** [February 12, 2013, 9:54pm UTC](https://community.unix.com/t/postgresql-database-corrupt/324209 "2013-02-12T21:54:55Z")

</div>

I am managing a linux cluster which has been build on Platform Cluster Manager PCM 1.2.1) from IBM Platform Computing. Unfortunately somebody deteled data files of postgresql from /var/lib directory. I somehow managed to…

---

## [VCS install error](https://community.unix.com/t/vcs-install-error/322066)

<div class="topic-metadata">

**Author:** [@samiulla](https://community.unix.com/u/samiulla)\
**Replies:** 0\
**Last updated:** [January 2, 2013, 12:19pm UTC](https://community.unix.com/t/vcs-install-error/322066 "2013-01-02T12:19:23Z")

</div>

hai this is samiulla i am installing vcs 6.0 in vmware solaris 10 (64bit) i got error while i am going to install vcs in 2 nodes even i add rhost files on both nodes and ssh autho login still i got error. But i install …

---

## [HPC Linpack test](https://community.unix.com/t/hpc-linpack-test/317367)

<div class="topic-metadata">

**Author:** [@PtaQ](https://community.unix.com/u/PtaQ)\
**Replies:** 2\
**Last updated:** [October 6, 2012, 7:12am UTC](https://community.unix.com/t/hpc-linpack-test/317367 "2012-10-06T07:12:37Z")

</div>

Hi, I compiled Linpack with ATLAS for test. What other libraries except ATLAS can be used to test?

---

## [I/O bound computing clusters](https://community.unix.com/t/i-o-bound-computing-clusters/315716)

<div class="topic-metadata">

**Author:** [@figaro](https://community.unix.com/u/figaro)\
**Replies:** 4\
**Last updated:** [August 27, 2012, 4:39pm UTC](https://community.unix.com/t/i-o-bound-computing-clusters/315716 "2012-08-27T16:39:13Z")

</div>

I want to build a computing cluster and have been looking into grid solutions. My understanding from grid solutions is that participating nodes have to actually sign up to participate in a computation and that an isolate…

---

## [SSI or not??](https://community.unix.com/t/ssi-or-not/312881)

<div class="topic-metadata">

**Author:** [@navic](https://community.unix.com/u/navic)\
**Replies:** 1\
**Last updated:** [July 26, 2012, 9:00am UTC](https://community.unix.com/t/ssi-or-not/312881 "2012-07-26T09:00:56Z")

</div>

I’m new to HPC so forgive me if this question is extremely simple. I have a cluster and each node has multiple NICs. I need the master to be able to see the nodes NICs as if they were it’s own. The vision is being abl…

---

## [How to check performance of your HPC cluster?](https://community.unix.com/t/how-to-check-performance-of-your-hpc-cluster/310465)

<div class="topic-metadata">

**Author:** [@albertspade](https://community.unix.com/u/albertspade)\
**Replies:** 4\
**Last updated:** [May 21, 2012, 5:46pm UTC](https://community.unix.com/t/how-to-check-performance-of-your-hpc-cluster/310465 "2012-05-21T17:46:52Z")

</div>

Hello Everybody, I have few queries : Do you have any idea how to check the performance of HPC cluster having mpich on top of centos 6.2? Are there any standard programs (like FFT, graphics rendering etc) to check the…

---

## [High Performance Linpack Compiling Issue](https://community.unix.com/t/high-performance-linpack-compiling-issue/301965)

<div class="topic-metadata">

**Author:** [@JPJPJPJP](https://community.unix.com/u/JPJPJPJP)\
**Replies:** 0\
**Last updated:** [December 31, 2011, 8:12am UTC](https://community.unix.com/t/high-performance-linpack-compiling-issue/301965 "2011-12-31T08:12:25Z")

</div>

I’m trying to compile Linpack on a Ubuntu cluster. I’m running MPI. I’ve modified the following values to fit my system TOPdir MPdir LAlib CC LINKER. When compiling I get the following error: (the error is at the end, t…

---

## [showq shows less active nodes as normal](https://community.unix.com/t/showq-shows-less-active-nodes-as-normal/297757)

<div class="topic-metadata">

**Author:** [@armando\_2011](https://community.unix.com/u/armando_2011)\
**Replies:** 1\
**Last updated:** [October 22, 2011, 4:20am UTC](https://community.unix.com/t/showq-shows-less-active-nodes-as-normal/297757 "2011-10-22T04:20:47Z")

</div>

Hi, I am new in system administration. I observe that some nodes in our cluster are not considered as active by showq: 22 active jobs 217 of 257 processors in use by local jobs (84.44%) 15 of 17 nodes active…

---

## [request more nodes](https://community.unix.com/t/request-more-nodes/297557)

<div class="topic-metadata">

**Author:** [@theawknewbie](https://community.unix.com/u/theawknewbie)\
**Replies:** 0\
**Last updated:** [October 19, 2011, 12:15pm UTC](https://community.unix.com/t/request-more-nodes/297557 "2011-10-19T12:15:38Z")

</div>

I am new to cluster commands. But I have tried utilizing: -pe, but I do not know my parallel computing environment. We are running SGE, is there a simpler command to request more nodes? also: qsub -N auto -M name@emai…

---

## [Guides for new HPC admins](https://community.unix.com/t/guides-for-new-hpc-admins/290616)

<div class="topic-metadata">

**Author:** [@DBryan](https://community.unix.com/u/DBryan)\
**Replies:** 0\
**Last updated:** [June 28, 2011, 2:40pm UTC](https://community.unix.com/t/guides-for-new-hpc-admins/290616 "2011-06-28T14:40:45Z")

</div>

In my company, it’s fallen on me to serve as the admin of our new HPC cluster, a task that’s very new to me. It’s very important to me to lay a solid foundation and avoid any unnecessary pitfalls. So, can anyone recommen…

---

## [PBS - restrict total number of processors per user](https://community.unix.com/t/pbs-restrict-total-number-of-processors-per-user/285757)

<div class="topic-metadata">

**Author:** [@gnuplot](https://community.unix.com/u/gnuplot)\
**Replies:** 0\
**Last updated:** [April 4, 2011, 9:35pm UTC](https://community.unix.com/t/pbs-restrict-total-number-of-processors-per-user/285757 "2011-04-04T21:35:30Z")

</div>

Hello everyone! I am a bit inexperienced with administering queueing programs. I installed Torque (a PBS derivative) on a Linux cluster and it is running well. There is one annoying problem though: users can run massive…

---

## [Alternative to Sun Grid Engine](https://community.unix.com/t/alternative-to-sun-grid-engine/280238)

<div class="topic-metadata">

**Author:** [@ccj4467](https://community.unix.com/u/ccj4467)\
**Replies:** 0\
**Last updated:** [January 5, 2011, 11:36am UTC](https://community.unix.com/t/alternative-to-sun-grid-engine/280238 "2011-01-05T11:36:30Z")

</div>

Does anybody know of a good alternative to Sun Grid Engine? It seems that Oracle is now charging for this software. I am running a HPC cluster that has Solaris 10 machines and I am adding some nodes that will be running …

---

## [Graphics cards](https://community.unix.com/t/graphics-cards/280116)

<div class="topic-metadata">

**Author:** [@figaro](https://community.unix.com/u/figaro)\
**Replies:** 2\
**Last updated:** [January 4, 2011, 12:28pm UTC](https://community.unix.com/t/graphics-cards/280116 "2011-01-04T12:28:14Z")

</div>

More and more applications which consist of computationally intensive tasks rely on the graphics card’s capabilities in order to speed up the calculations. The question is how can one know whether the graphics card will …

---

## [HPL on Rocks 5.3](https://community.unix.com/t/hpl-on-rocks-5-3/275650)

<div class="topic-metadata">

**Author:** [@futamill](https://community.unix.com/u/futamill)\
**Replies:** 0\
**Last updated:** [October 19, 2010, 4:57pm UTC](https://community.unix.com/t/hpl-on-rocks-5-3/275650 "2010-10-19T16:57:53Z")

</div>

Hey I am new to cluster benchmarking wondering if there was any guide available that I missed in my google searchs for HPL.

---

## [How to interpret Papi output](https://community.unix.com/t/how-to-interpret-papi-output/270583)

<div class="topic-metadata">

**Author:** [@vishwamitra](https://community.unix.com/u/vishwamitra)\
**Replies:** 0\
**Last updated:** [July 30, 2010, 4:56pm UTC](https://community.unix.com/t/how-to-interpret-papi-output/270583 "2010-07-30T16:56:28Z")

</div>

I have collected data of Number of L2 cache misses using PAPI. I had run an MPI application with 4 threads (mpirun -np 4) and each thread reads the cache misses in L2. Each thread outputs data for every timestamp. eg: …

[Next page](https://community.unix.com/c/etc/high-performance-computing/92.md?page=1)
