UCT HPC cluster

JOB DETAILS FOR JOB 1304375

captured Sat Sep 5 19:53:01 SAST 2026

MaxRAM=3.5G
MaxVMSize=0G
AveCPUFreq=800K
AveDiskRead=2945162611
AveDiskWrite=311506333

bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7810 Nice=0 Account=a100free QOS=a100free
   JobState=RUNNING Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:00:21 TimeLimit=00:08:00 TimeMin=N/A
   SubmitTime=2026-09-05T19:52:40 EligibleTime=2026-09-05T19:52:40
   AccrueTime=2026-09-05T19:52:40
   StartTime=2026-09-05T19:52:41 EndTime=2026-09-05T20:00:41 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-05T19:52:41 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc104:460157
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=4 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=32G,node=1,billing=8,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=4,mem=32G,node=1,billing=8,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=2-3,30-31 Mem=32768 GRES=gpu:ampere:1(IDX:2)
   MinCPUsNode=4 MinMemoryNode=32G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/ORION/baicai/l3_tahoe_a1_diagnosis_retention_20260905/scripts/smoke_ampere.sbatch
   WorkDir=/home/bxxjin001
   StdErr=/scratch/bxxjin001/ORION/baicai/l3_tahoe_a1_diagnosis_retention_20260905/logs/ampere_smoke_1304375.out
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/ORION/baicai/l3_tahoe_a1_diagnosis_retention_20260905/logs/ampere_smoke_1304375.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:4

UCT HPC clusterJOB DETAILS FOR JOB 1304375

captured Sat Sep 5 19:53:39 SAST 2026

bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7810 Nice=0 Account=a100free QOS=a100free
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:00:43 TimeLimit=00:08:00 TimeMin=N/A
   SubmitTime=2026-09-05T19:52:40 EligibleTime=2026-09-05T19:52:40
   AccrueTime=2026-09-05T19:52:40
   StartTime=2026-09-05T19:52:41 EndTime=2026-09-05T19:53:24 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-05T19:52:41 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc104:460157
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=4 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=32G,node=1,billing=8,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=4,mem=32G,node=1,billing=8,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=2-3,30-31 Mem=32768 GRES=
   MinCPUsNode=4 MinMemoryNode=32G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/ORION/baicai/l3_tahoe_a1_diagnosis_retention_20260905/scripts/smoke_ampere.sbatch
   WorkDir=/home/bxxjin001
   StdErr=/scratch/bxxjin001/ORION/baicai/l3_tahoe_a1_diagnosis_retention_20260905/logs/ampere_smoke_1304375.out
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/ORION/baicai/l3_tahoe_a1_diagnosis_retention_20260905/logs/ampere_smoke_1304375.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:4

UCT HPC clusterJOB DETAILS FOR JOB 1304375

captured Sat Sep 5 19:54:01 SAST 2026

bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7810 Nice=0 Account=a100free QOS=a100free
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:00:43 TimeLimit=00:08:00 TimeMin=N/A
   SubmitTime=2026-09-05T19:52:40 EligibleTime=2026-09-05T19:52:40
   AccrueTime=2026-09-05T19:52:40
   StartTime=2026-09-05T19:52:41 EndTime=2026-09-05T19:53:24 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-05T19:52:41 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc104:460157
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=4 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=32G,node=1,billing=8,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=4,mem=32G,node=1,billing=8,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=2-3,30-31 Mem=32768 GRES=
   MinCPUsNode=4 MinMemoryNode=32G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/ORION/baicai/l3_tahoe_a1_diagnosis_retention_20260905/scripts/smoke_ampere.sbatch
   WorkDir=/home/bxxjin001
   StdErr=/scratch/bxxjin001/ORION/baicai/l3_tahoe_a1_diagnosis_retention_20260905/logs/ampere_smoke_1304375.out
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/ORION/baicai/l3_tahoe_a1_diagnosis_retention_20260905/logs/ampere_smoke_1304375.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:4

UCT HPC clusterJOB DETAILS FOR JOB 1304375

captured Sat Sep 5 19:54:38 SAST 2026

bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7810 Nice=0 Account=a100free QOS=a100free
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:00:43 TimeLimit=00:08:00 TimeMin=N/A
   SubmitTime=2026-09-05T19:52:40 EligibleTime=2026-09-05T19:52:40
   AccrueTime=2026-09-05T19:52:40
   StartTime=2026-09-05T19:52:41 EndTime=2026-09-05T19:53:24 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-05T19:52:41 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc104:460157
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=4 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=32G,node=1,billing=8,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=4,mem=32G,node=1,billing=8,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=2-3,30-31 Mem=32768 GRES=
   MinCPUsNode=4 MinMemoryNode=32G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/ORION/baicai/l3_tahoe_a1_diagnosis_retention_20260905/scripts/smoke_ampere.sbatch
   WorkDir=/home/bxxjin001
   StdErr=/scratch/bxxjin001/ORION/baicai/l3_tahoe_a1_diagnosis_retention_20260905/logs/ampere_smoke_1304375.out
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/ORION/baicai/l3_tahoe_a1_diagnosis_retention_20260905/logs/ampere_smoke_1304375.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:4

UCT HPC clusterJOB DETAILS FOR JOB 1304375

captured Sat Sep 5 19:55:01 SAST 2026

bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7810 Nice=0 Account=a100free QOS=a100free
   JobState=COMPLETED Reason=None Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:00:43 TimeLimit=00:08:00 TimeMin=N/A
   SubmitTime=2026-09-05T19:52:40 EligibleTime=2026-09-05T19:52:40
   AccrueTime=2026-09-05T19:52:40
   StartTime=2026-09-05T19:52:41 EndTime=2026-09-05T19:53:24 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-09-05T19:52:41 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc104:460157
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=4 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=32G,node=1,billing=8,gres/gpu=1,gres/gpu:ampere=1
   AllocTRES=cpu=4,mem=32G,node=1,billing=8,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=2-3,30-31 Mem=32768 GRES=
   MinCPUsNode=4 MinMemoryNode=32G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/bxxjin001/ORION/baicai/l3_tahoe_a1_diagnosis_retention_20260905/scripts/smoke_ampere.sbatch
   WorkDir=/home/bxxjin001
   StdErr=/scratch/bxxjin001/ORION/baicai/l3_tahoe_a1_diagnosis_retention_20260905/logs/ampere_smoke_1304375.out
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/ORION/baicai/l3_tahoe_a1_diagnosis_retention_20260905/logs/ampere_smoke_1304375.out
   Power=
   TresPerNode=gres/gpu:ampere:1
   TresPerTask=cpu:4