Spectrum LSF

Showing 292

Ability to browse LSF documentation via version/point-in-time

LSF documentation is not versioned — the documentation you see is essentially the latest version. We often want to know when a particular configuration parameter was first introduced, e.g. if you are running LSF 10.1.0.8, is configuration paramete...

about 2 months ago in Spectrum LSF / Documentation 1 Not under consideration

1 VOTE

install libnsl automatically during LSF installation

In RHEL8, I found the follows error. [root@rhel86 lsf]# lsadmin limstartup lsadmin: error while loading shared libraries: libnsl.so.1: cannot open shared object file: No such file or directory And I found "Known issues" part in LSF guide ment...

3 months ago in Spectrum LSF / Administration 1 Not under consideration

1 VOTE

Enabling the Batch processing based on Compute Express Link CXL 3.0 or CXL 4.0 Fabrics

CXL 3.0 is built upon the IBM OpenCAPI, but CXL3 and CXL 4 have more speeds and will achieve the following: 1- Enabling the Interconnection between IBM LinuxONE and Exa scale AI Data Centers based on Nvidia DGX H100 based on Nvidia H100 GPUs and I...

3 months ago in Spectrum LSF / Other 1 Not under consideration

1 VOTE

Adding heterogeneous processing CPUs, GPUs and FPGA Accelerator for Spectrum LSF

In the near future we will need more advanced distributed heterogeneous processing , We think it is better to take into consideration the Intel oneAPI and other tools like oneDNN, oneDAL ,...etc. It may need joining openPOWER foundation and IBM wi...

3 months ago in Spectrum LSF / Other 1 Not under consideration

1 VOTE

Allow preemption of shared gpu jobs (j_exclusive=no) by higher priority job queues.

We need the LSF support for preemption of shared gpu jobs. Currently GPU preemption is supported only for jobs in mode j_exclusive=yes This is a very big problem as we have a significant waste of gpu memory resource. because if a lower priority jo...

4 months ago in Spectrum LSF / Scheduling 1 Not under consideration

2 VOTE

Enable option for hardcoding GPU memory request like its available for CPU memory request

At this moment IBM offers features of hardcoding CPU memory. We have implemented this feature in our cluster with esub scripting. Similarly we want to have same feature available for GPU memmory (gmem) to be hardcoded. I have raised ticket to our ...

4 months ago in Spectrum LSF / Scheduling 2 Not under consideration

1 VOTE

Improving job status problem due to defunct process

Sometimes, defunct can occur in job processes for a variety of reasons. For example, 29460 below is one of the processes of some job. ps -ef | grep bg92 bg92.pa+ 29460 1 1 2022 ? 08:03:02 [Novas] <defunct> And if a defunct process occurs, L...

5 months ago in Spectrum LSF / Administration 2 Not under consideration

1 VOTE

LSF should support output/error file path that exists only in a container

As of now LSF cannot handle a scenario where the output/error file path exists only in the container and does not exist on the underlying host where the container is running .For example:bsub -o <path_in_container_only> --app <my_bapp>...

6 months ago in Spectrum LSF / Other 1 Not under consideration

1 VOTE

Dynamic priority based on jobarray length

We exclusively work with jobarrays at our company. We have a queue reserved for jobs that take no more than 3 minutes. A general rule of thumb is that small jobarrays at our company can be considered as interactive jobs where the user waits for th...

8 months ago in Spectrum LSF / Scheduling 0 Not under consideration

4 VOTE

bsub should accept a cpu_efficiency parameter to allow cpu over-commiting in the pool

It's rare for a job to achieve close to 100% cpu efficiency. Often, jobs have a peak cpu requirement during its execution lifetime but use less cpus in average. If bsub could be told that a job is expected to run with a given cpu efficiency, LSF c...

10 months ago in Spectrum LSF / Simulation & Prediction 2 Not under consideration

Please enter your email address

FILTER BY CATEGORY