UCT HPC cluster

JOB DETAILS FOR JOB 341031

captured Wed Nov 12 15:35:01 SAST 2025

MaxRAM=1.2G
MaxVMSize=0G
AveCPUFreq=801K
AveDiskRead=4196593192
AveDiskWrite=926745

mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7803 Nice=0 Account=a100free QOS=a100free
   JobState=RUNNING Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=01:05:42 TimeLimit=08:00:00 TimeMin=N/A
   SubmitTime=2025-11-12T14:29:19 EligibleTime=2025-11-12T14:29:19
   AccrueTime=2025-11-12T14:29:19
   StartTime=2025-11-12T14:29:19 EndTime=2025-11-12T22:29:19 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-11-12T14:29:19 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrocgpu010.uct.ac.za:86917
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=8 NumTasks=8 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=73136M,node=1,billing=16,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=8,mem=73136M,node=1,billing=16,gres/gpu=1,gres/gpu:ampere=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:1
     Nodes=srvrocgpu010 CPU_IDs=2-5,31-34 Mem=73136 GRES=gpu:ampere:1(IDX:2)
   MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/mrpcol001/Diffusion_job/eval_12nov/submit_evaluation.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/eval_12nov
   StdErr=/scratch/mrpcol001/Diffusion_job/eval_12nov/slurm-341031.err
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/eval_12nov/slurm-341031.out
   Power=
   TresPerNode=gres/gpu:ampere:1

UCT HPC clusterJOB DETAILS FOR JOB 341031

captured Wed Nov 12 15:35:38 SAST 2025

mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7803 Nice=0 Account=a100free QOS=a100free
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=01:05:57 TimeLimit=08:00:00 TimeMin=N/A
   SubmitTime=2025-11-12T14:29:19 EligibleTime=2025-11-12T14:29:19
   AccrueTime=2025-11-12T14:29:19
   StartTime=2025-11-12T14:29:19 EndTime=2025-11-12T15:35:16 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-11-12T14:29:19 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrocgpu010.uct.ac.za:86917
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=8 NumTasks=8 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=73136M,node=1,billing=16,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=8,mem=73136M,node=1,billing=16,gres/gpu=1,gres/gpu:ampere=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:1
     Nodes=srvrocgpu010 CPU_IDs=2-5,31-34 Mem=73136 GRES=
   MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/mrpcol001/Diffusion_job/eval_12nov/submit_evaluation.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/eval_12nov
   StdErr=/scratch/mrpcol001/Diffusion_job/eval_12nov/slurm-341031.err
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/eval_12nov/slurm-341031.out
   Power=
   TresPerNode=gres/gpu:ampere:1

UCT HPC clusterJOB DETAILS FOR JOB 341031

captured Wed Nov 12 15:36:01 SAST 2025

mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7803 Nice=0 Account=a100free QOS=a100free
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=01:05:57 TimeLimit=08:00:00 TimeMin=N/A
   SubmitTime=2025-11-12T14:29:19 EligibleTime=2025-11-12T14:29:19
   AccrueTime=2025-11-12T14:29:19
   StartTime=2025-11-12T14:29:19 EndTime=2025-11-12T15:35:16 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-11-12T14:29:19 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrocgpu010.uct.ac.za:86917
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=8 NumTasks=8 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=73136M,node=1,billing=16,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=8,mem=73136M,node=1,billing=16,gres/gpu=1,gres/gpu:ampere=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:1
     Nodes=srvrocgpu010 CPU_IDs=2-5,31-34 Mem=73136 GRES=
   MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/mrpcol001/Diffusion_job/eval_12nov/submit_evaluation.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/eval_12nov
   StdErr=/scratch/mrpcol001/Diffusion_job/eval_12nov/slurm-341031.err
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/eval_12nov/slurm-341031.out
   Power=
   TresPerNode=gres/gpu:ampere:1

UCT HPC clusterJOB DETAILS FOR JOB 341031

captured Wed Nov 12 15:36:38 SAST 2025

mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7803 Nice=0 Account=a100free QOS=a100free
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=01:05:57 TimeLimit=08:00:00 TimeMin=N/A
   SubmitTime=2025-11-12T14:29:19 EligibleTime=2025-11-12T14:29:19
   AccrueTime=2025-11-12T14:29:19
   StartTime=2025-11-12T14:29:19 EndTime=2025-11-12T15:35:16 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-11-12T14:29:19 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrocgpu010.uct.ac.za:86917
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=8 NumTasks=8 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=73136M,node=1,billing=16,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=8,mem=73136M,node=1,billing=16,gres/gpu=1,gres/gpu:ampere=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:ampere:1
     Nodes=srvrocgpu010 CPU_IDs=2-5,31-34 Mem=73136 GRES=
   MinCPUsNode=1 MinMemoryCPU=9142M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/mrpcol001/Diffusion_job/eval_12nov/submit_evaluation.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/eval_12nov
   StdErr=/scratch/mrpcol001/Diffusion_job/eval_12nov/slurm-341031.err
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/eval_12nov/slurm-341031.out
   Power=
   TresPerNode=gres/gpu:ampere:1