UCT HPC cluster

JOB DETAILS FOR JOB 792560

captured Sat May 2 13:25:35 SAST 2026

MaxRAM=13.6G
MaxVMSize=0G
AveCPUFreq=18K
AveDiskRead=1300408177
AveDiskWrite=21936

mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7632 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=RUNNING Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=1-23:59:38 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-04-30T13:25:56 EligibleTime=2026-04-30T13:25:56
   AccrueTime=2026-04-30T13:25:56
   StartTime=2026-04-30T13:25:57 EndTime=2026-05-02T13:25:57 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-04-30T13:25:57 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc110:2486976
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu014
   BatchHost=srvrocgpu014
   NumNodes=1 NumCPUs=8 NumTasks=8 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu014 CPU_IDs=0-3,24-27 Mem=80000 GRES=gpu:l40s:1(IDX:0)
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/mrpcol001/Diffusion_job/Models/scripts/run_posterior_inference.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/Models/scripts
   StdErr=/scratch/mrpcol001/Diffusion_job/Models/scripts/slurm-vlb-infer-792560.err
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/Models/scripts/slurm-vlb-infer-792560.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 792560

captured Sat May 2 13:26:01 SAST 2026

mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7632 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=TIMEOUT Reason=TimeLimit Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=2-00:00:02 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-04-30T13:25:56 EligibleTime=2026-04-30T13:25:56
   AccrueTime=2026-04-30T13:25:56
   StartTime=2026-04-30T13:25:57 EndTime=2026-05-02T13:25:59 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-04-30T13:25:57 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc110:2486976
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu014
   BatchHost=srvrocgpu014
   NumNodes=1 NumCPUs=8 NumTasks=8 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu014 CPU_IDs=0-3,24-27 Mem=80000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/mrpcol001/Diffusion_job/Models/scripts/run_posterior_inference.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/Models/scripts
   StdErr=/scratch/mrpcol001/Diffusion_job/Models/scripts/slurm-vlb-infer-792560.err
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/Models/scripts/slurm-vlb-infer-792560.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 792560

captured Sat May 2 13:26:33 SAST 2026

mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7632 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=TIMEOUT Reason=TimeLimit Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=2-00:00:02 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-04-30T13:25:56 EligibleTime=2026-04-30T13:25:56
   AccrueTime=2026-04-30T13:25:56
   StartTime=2026-04-30T13:25:57 EndTime=2026-05-02T13:25:59 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-04-30T13:25:57 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc110:2486976
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu014
   BatchHost=srvrocgpu014
   NumNodes=1 NumCPUs=8 NumTasks=8 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu014 CPU_IDs=0-3,24-27 Mem=80000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/mrpcol001/Diffusion_job/Models/scripts/run_posterior_inference.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/Models/scripts
   StdErr=/scratch/mrpcol001/Diffusion_job/Models/scripts/slurm-vlb-infer-792560.err
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/Models/scripts/slurm-vlb-infer-792560.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 792560

captured Sat May 2 13:27:01 SAST 2026

mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7632 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=TIMEOUT Reason=TimeLimit Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=2-00:00:02 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-04-30T13:25:56 EligibleTime=2026-04-30T13:25:56
   AccrueTime=2026-04-30T13:25:56
   StartTime=2026-04-30T13:25:57 EndTime=2026-05-02T13:25:59 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-04-30T13:25:57 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc110:2486976
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu014
   BatchHost=srvrocgpu014
   NumNodes=1 NumCPUs=8 NumTasks=8 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu014 CPU_IDs=0-3,24-27 Mem=80000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/mrpcol001/Diffusion_job/Models/scripts/run_posterior_inference.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/Models/scripts
   StdErr=/scratch/mrpcol001/Diffusion_job/Models/scripts/slurm-vlb-infer-792560.err
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/Models/scripts/slurm-vlb-infer-792560.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 792560

captured Sat May 2 13:27:33 SAST 2026

mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7632 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=TIMEOUT Reason=TimeLimit Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=2-00:00:02 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-04-30T13:25:56 EligibleTime=2026-04-30T13:25:56
   AccrueTime=2026-04-30T13:25:56
   StartTime=2026-04-30T13:25:57 EndTime=2026-05-02T13:25:59 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-04-30T13:25:57 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc110:2486976
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu014
   BatchHost=srvrocgpu014
   NumNodes=1 NumCPUs=8 NumTasks=8 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu014 CPU_IDs=0-3,24-27 Mem=80000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/mrpcol001/Diffusion_job/Models/scripts/run_posterior_inference.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/Models/scripts
   StdErr=/scratch/mrpcol001/Diffusion_job/Models/scripts/slurm-vlb-infer-792560.err
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/Models/scripts/slurm-vlb-infer-792560.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 792560

captured Sat May 2 13:28:01 SAST 2026

mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7632 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=TIMEOUT Reason=TimeLimit Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:15
   DerivedExitCode=0:0
   RunTime=2-00:00:02 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-04-30T13:25:56 EligibleTime=2026-04-30T13:25:56
   AccrueTime=2026-04-30T13:25:56
   StartTime=2026-04-30T13:25:57 EndTime=2026-05-02T13:25:59 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-04-30T13:25:57 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc110:2486976
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu014
   BatchHost=srvrocgpu014
   NumNodes=1 NumCPUs=8 NumTasks=8 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=8,mem=80000M,node=1,billing=15,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu014 CPU_IDs=0-3,24-27 Mem=80000 GRES=
   MinCPUsNode=1 MinMemoryCPU=10000M MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/mrpcol001/Diffusion_job/Models/scripts/run_posterior_inference.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/Models/scripts
   StdErr=/scratch/mrpcol001/Diffusion_job/Models/scripts/slurm-vlb-infer-792560.err
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/Models/scripts/slurm-vlb-infer-792560.out
   Power=
   TresPerNode=gres/gpu:l40s:1