UCT HPC cluster

JOB DETAILS FOR JOB 151428

captured Thu May 29 12:50:01 SAST 2025

MaxRAM=2.6G
MaxVMSize=0G
AveCPUFreq=16K
AveDiskRead=2434515259
AveDiskWrite=1000595678

JobId=151428 JobName=relu_e400_192
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7349 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=RUNNING Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=05:25:42 TimeLimit=10:00:00 TimeMin=N/A
   SubmitTime=2025-05-29T07:24:19 EligibleTime=2025-05-29T07:24:19
   AccrueTime=2025-05-29T07:24:19
   StartTime=2025-05-29T07:24:19 EndTime=2025-05-29T17:24:19 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-05-29T07:24:19 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:3912479
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=6 NumTasks=6 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=6,mem=60000M,node=1,billing=11,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=6,mem=60000M,node=1,billing=11,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=1-3,25-27 Mem=60000 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/model_27may/job_model64.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/model_27may
   StdErr=/scratch/mrpcol001/Diffusion_job/model_27may/slurm-151428.out
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/model_27may/slurm-151428.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=mrpcol001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT

UCT HPC clusterJOB DETAILS FOR JOB 151428

captured Thu May 29 12:50:33 SAST 2025

JobId=151428 JobName=relu_e400_192
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7349 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=05:26:07 TimeLimit=10:00:00 TimeMin=N/A
   SubmitTime=2025-05-29T07:24:19 EligibleTime=2025-05-29T07:24:19
   AccrueTime=2025-05-29T07:24:19
   StartTime=2025-05-29T07:24:19 EndTime=2025-05-29T12:50:26 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-05-29T07:24:19 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:3912479
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=6 NumTasks=6 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=6,mem=60000M,node=1,billing=11,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=6,mem=60000M,node=1,billing=11,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=1-3,25-27 Mem=60000 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/model_27may/job_model64.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/model_27may
   StdErr=/scratch/mrpcol001/Diffusion_job/model_27may/slurm-151428.out
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/model_27may/slurm-151428.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=mrpcol001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT

UCT HPC clusterJOB DETAILS FOR JOB 151428

captured Thu May 29 12:51:02 SAST 2025

JobId=151428 JobName=relu_e400_192
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7349 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=05:26:07 TimeLimit=10:00:00 TimeMin=N/A
   SubmitTime=2025-05-29T07:24:19 EligibleTime=2025-05-29T07:24:19
   AccrueTime=2025-05-29T07:24:19
   StartTime=2025-05-29T07:24:19 EndTime=2025-05-29T12:50:26 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-05-29T07:24:19 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:3912479
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=6 NumTasks=6 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=6,mem=60000M,node=1,billing=11,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=6,mem=60000M,node=1,billing=11,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=1-3,25-27 Mem=60000 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/model_27may/job_model64.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/model_27may
   StdErr=/scratch/mrpcol001/Diffusion_job/model_27may/slurm-151428.out
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/model_27may/slurm-151428.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=mrpcol001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT

UCT HPC clusterJOB DETAILS FOR JOB 151428

captured Thu May 29 12:51:33 SAST 2025

JobId=151428 JobName=relu_e400_192
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7349 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=05:26:07 TimeLimit=10:00:00 TimeMin=N/A
   SubmitTime=2025-05-29T07:24:19 EligibleTime=2025-05-29T07:24:19
   AccrueTime=2025-05-29T07:24:19
   StartTime=2025-05-29T07:24:19 EndTime=2025-05-29T12:50:26 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-05-29T07:24:19 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:3912479
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=6 NumTasks=6 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=6,mem=60000M,node=1,billing=11,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=6,mem=60000M,node=1,billing=11,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=1-3,25-27 Mem=60000 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/model_27may/job_model64.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/model_27may
   StdErr=/scratch/mrpcol001/Diffusion_job/model_27may/slurm-151428.out
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/model_27may/slurm-151428.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=mrpcol001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT

UCT HPC clusterJOB DETAILS FOR JOB 151428

captured Thu May 29 12:52:01 SAST 2025

JobId=151428 JobName=relu_e400_192
   UserId=mrpcol001(1221910514 Collins Maripane) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7349 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=05:26:07 TimeLimit=10:00:00 TimeMin=N/A
   SubmitTime=2025-05-29T07:24:19 EligibleTime=2025-05-29T07:24:19
   AccrueTime=2025-05-29T07:24:19
   StartTime=2025-05-29T07:24:19 EndTime=2025-05-29T12:50:26 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2025-05-29T07:24:19 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001.uct.ac.za:3912479
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu012
   BatchHost=srvrocgpu012
   NumNodes=1 NumCPUs=6 NumTasks=6 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=6,mem=60000M,node=1,billing=11,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=6,mem=60000M,node=1,billing=11,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=1-3,25-27 Mem=60000 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/model_27may/job_model64.sh
   WorkDir=/scratch/mrpcol001/Diffusion_job/model_27may
   StdErr=/scratch/mrpcol001/Diffusion_job/model_27may/slurm-151428.out
   StdIn=/dev/null
   StdOut=/scratch/mrpcol001/Diffusion_job/model_27may/slurm-151428.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   MailUser=mrpcol001@myuct.ac.za MailType=INVALID_DEPEND,BEGIN,END,FAIL,REQUEUE,STAGE_OUT