Difference between revisions of "Leonhard beta testing"

From ScientificComputing
Jump to: navigation, search
m (Wrong numbers.)
(Adds basic node info.)
Line 7: Line 7:
 
Leonhard uses the same LSF batch system as the [[Euler|Euler cluster]].
 
Leonhard uses the same LSF batch system as the [[Euler|Euler cluster]].
  
Use the “bsub” command to submit a job and specify resources needed to run your job. By default, a job will get 1 core and 1024 MB of RAM for 4 hours.
+
Use the “bsub” command to submit a job and specify resources needed to run your job. By default, a job will get 1 core and 1024 MB of RAM for 4 hours. Unless otherwise specified, jobs requesting more than 36 cores will run on a single node. Regular nodes have 36 cores and 128 or 512 GB of RAM (of which about 90 and 460 GB, respectively, are usable).
  
 
Unlike Euler, '''requested memory is strictly enforced as a memory limit.''' For example, if you do not specifically state a memory requirement, your program can not use more than 1 GB of RAM per core. What counts is is actually used memory, including page cache for your job. All processes from the same job on a node share the same pool. For example, with a job submitted as
 
Unlike Euler, '''requested memory is strictly enforced as a memory limit.''' For example, if you do not specifically state a memory requirement, your program can not use more than 1 GB of RAM per core. What counts is is actually used memory, including page cache for your job. All processes from the same job on a node share the same pool. For example, with a job submitted as
Line 13: Line 13:
 
all of the 8 MPI ranks on a single node can use up to 8 GB.
 
all of the 8 MPI ranks on a single node can use up to 8 GB.
  
=== Requesting GPUs ===
+
=== Submitting GPU jobs ===
  
All GPUs in Leonhard are configured in Exclusive Process mode.
+
All GPUs in Leonhard are configured in Exclusive Process mode. The GPU nodes have 20&nbsp;cores, 8&nbsp;GPUs, and 256&nbsp;GB of RAM (of which only about 210&nbsp;GB is usable). To run multi-node job, you will need to request <tt>span[ptile=20]</tt>.
  
 
The LSF batch system has partial integrated support for GPUs. To use the GPUs for a job node you need to request the '''ngpus_excl_p''' resource. It refers to the number of GPUs '''per node''', which is unlike other resources, which are requested '''per core'''.
 
The LSF batch system has partial integrated support for GPUs. To use the GPUs for a job node you need to request the '''ngpus_excl_p''' resource. It refers to the number of GPUs '''per node''', which is unlike other resources, which are requested '''per core'''.
Line 26: Line 26:
 
  bsub -n 40 -R "rusage[mem=4500,ngpus_excl_p=8] span[ptile=20]" ./my_cuda_program
 
  bsub -n 40 -R "rusage[mem=4500,ngpus_excl_p=8] span[ptile=20]" ./my_cuda_program
  
While your jobs will see all GPUs, LSF will set the CUDA_VISIBLE_DEVICES environment variable, which is honored by CUDA programs.
+
While your jobs will see all GPUs, LSF will set the [https://devblogs.nvidia.com/parallelforall/cuda-pro-tip-control-gpu-visibility-cuda_visible_devices/ CUDA_VISIBLE_DEVICES] environment variable, which is honored by CUDA programs.

Revision as of 10:39, 17 May 2017

The Leonhard cluster is available for early-access beta testing.

Please read through the following to get started.

Submitting jobs

Leonhard uses the same LSF batch system as the Euler cluster.

Use the “bsub” command to submit a job and specify resources needed to run your job. By default, a job will get 1 core and 1024 MB of RAM for 4 hours. Unless otherwise specified, jobs requesting more than 36 cores will run on a single node. Regular nodes have 36 cores and 128 or 512 GB of RAM (of which about 90 and 460 GB, respectively, are usable).

Unlike Euler, requested memory is strictly enforced as a memory limit. For example, if you do not specifically state a memory requirement, your program can not use more than 1 GB of RAM per core. What counts is is actually used memory, including page cache for your job. All processes from the same job on a node share the same pool. For example, with a job submitted as

bsub -n 16 -R "rusage[mem=1024] span[ptile=8]" mpirun ./my_job

all of the 8 MPI ranks on a single node can use up to 8 GB.

Submitting GPU jobs

All GPUs in Leonhard are configured in Exclusive Process mode. The GPU nodes have 20 cores, 8 GPUs, and 256 GB of RAM (of which only about 210 GB is usable). To run multi-node job, you will need to request span[ptile=20].

The LSF batch system has partial integrated support for GPUs. To use the GPUs for a job node you need to request the ngpus_excl_p resource. It refers to the number of GPUs per node, which is unlike other resources, which are requested per core.

For example, to run a serial job with one GPU,

bsub -R "rusage[ngpus_excl_p=1]" ./my_cuda_program

or on a full node with all eight GPUs and up to 90 GB of RAM,

bsub -n 20 -R "rusage[mem=4500,ngpus_excl_p=8]" ./my_cuda_program

or on two full nodes:

bsub -n 40 -R "rusage[mem=4500,ngpus_excl_p=8] span[ptile=20]" ./my_cuda_program

While your jobs will see all GPUs, LSF will set the CUDA_VISIBLE_DEVICES environment variable, which is honored by CUDA programs.