UCT HPC cluster

JOB DETAILS FOR JOB 407446

captured Sat Dec 13 11:58:01 SAST 2025

MaxRAM=8.7G
MaxVMSize=0G
AveCPUFreq=8K
AveDiskRead=11710510146
AveDiskWrite=407773

mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7035 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=23:59:43 TimeLimit=1-00:00:00 TimeMin=N/A
   SubmitTime=2025-12-12T11:58:17 EligibleTime=2025-12-12T11:58:17
   AccrueTime=2025-12-12T11:58:18
   StartTime=2025-12-12T11:58:18 EndTime=2025-12-13T11:58:18 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-12-12T11:58:18 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrocgpu010.uct.ac.za:1348446
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=4 NumTasks=4 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu012 CPU_IDs=6-7,30-31 Mem=40000 GRES=gpu:l40s:1(IDX:1)
   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/dec/11dec/run_evaluation.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/dec/11dec
   StdErr=/scratch/mrpcol001/Diffusion_job/dec/11dec/slurm-eval-diffusion-407446.err
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/dec/11dec/slurm-eval-diffusion-407446.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 407446

captured Sat Dec 13 11:58:40 SAST 2025

mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7035 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=1-00:00:12 TimeLimit=1-00:00:00 TimeMin=N/A
   SubmitTime=2025-12-12T11:58:17 EligibleTime=2025-12-12T11:58:17
   AccrueTime=2025-12-12T11:58:18
   StartTime=2025-12-12T11:58:18 EndTime=2025-12-13T11:58:30 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-12-12T11:58:18 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrocgpu010.uct.ac.za:1348446
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=4 NumTasks=4 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu012 CPU_IDs=6-7,30-31 Mem=40000 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/dec/11dec/run_evaluation.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/dec/11dec
   StdErr=/scratch/mrpcol001/Diffusion_job/dec/11dec/slurm-eval-diffusion-407446.err
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/dec/11dec/slurm-eval-diffusion-407446.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 407446

captured Sat Dec 13 11:59:01 SAST 2025

mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7035 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=1-00:00:12 TimeLimit=1-00:00:00 TimeMin=N/A
   SubmitTime=2025-12-12T11:58:17 EligibleTime=2025-12-12T11:58:17
   AccrueTime=2025-12-12T11:58:18
   StartTime=2025-12-12T11:58:18 EndTime=2025-12-13T11:58:30 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-12-12T11:58:18 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrocgpu010.uct.ac.za:1348446
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=4 NumTasks=4 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu012 CPU_IDs=6-7,30-31 Mem=40000 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/dec/11dec/run_evaluation.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/dec/11dec
   StdErr=/scratch/mrpcol001/Diffusion_job/dec/11dec/slurm-eval-diffusion-407446.err
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/dec/11dec/slurm-eval-diffusion-407446.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 407446

captured Sat Dec 13 11:59:40 SAST 2025

mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7035 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=1-00:00:12 TimeLimit=1-00:00:00 TimeMin=N/A
   SubmitTime=2025-12-12T11:58:17 EligibleTime=2025-12-12T11:58:17
   AccrueTime=2025-12-12T11:58:18
   StartTime=2025-12-12T11:58:18 EndTime=2025-12-13T11:58:30 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-12-12T11:58:18 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrocgpu010.uct.ac.za:1348446
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=4 NumTasks=4 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu012 CPU_IDs=6-7,30-31 Mem=40000 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/dec/11dec/run_evaluation.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/dec/11dec
   StdErr=/scratch/mrpcol001/Diffusion_job/dec/11dec/slurm-eval-diffusion-407446.err
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/dec/11dec/slurm-eval-diffusion-407446.out
   Power=
   TresPerNode=gres/gpu:l40s:1

UCT HPC clusterJOB DETAILS FOR JOB 407446

captured Sat Dec 13 12:00:01 SAST 2025

mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7035 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=1-00:00:12 TimeLimit=1-00:00:00 TimeMin=N/A
   SubmitTime=2025-12-12T11:58:17 EligibleTime=2025-12-12T11:58:17
   AccrueTime=2025-12-12T11:58:18
   StartTime=2025-12-12T11:58:18 EndTime=2025-12-13T11:58:30 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-12-12T11:58:18 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrocgpu010.uct.ac.za:1348446
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=4 NumTasks=4 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=40000M,node=1,billing=7,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu012 CPU_IDs=6-7,30-31 Mem=40000 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/dec/11dec/run_evaluation.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/dec/11dec
   StdErr=/scratch/mrpcol001/Diffusion_job/dec/11dec/slurm-eval-diffusion-407446.err
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/dec/11dec/slurm-eval-diffusion-407446.out
   Power=
   TresPerNode=gres/gpu:l40s:1