UCT HPC cluster

JOB DETAILS FOR JOB 789709

captured Wed Apr 29 13:43:01 SAST 2026

MaxRAM=0.5G
MaxVMSize=0G
AveCPUFreq=1.56M
AveDiskRead=28307216
AveDiskWrite=804

bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8131 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=00:01:20 TimeLimit=00:15:00 TimeMin=N/A
   SubmitTime=2026-04-29T13:41:41 EligibleTime=2026-04-29T13:41:41
   AccrueTime=2026-04-29T13:41:41
   StartTime=2026-04-29T13:41:41 EndTime=2026-04-29T13:56:41 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-04-29T13:41:41 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc113:1364740
   ReqNodeList=srvrocgpu010 ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=4 NumTasks=4 CPUs/Task=1 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=0-1,36-37 Mem=32768 GRES=gpu:ampere:1(IDX:0)
   MinCPUsNode=4 MinMemoryNode=32G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/tmp/sub_mmd_bench.sh
   WorkDir=/scratch/bxxjin001/XPert/experiment/NM/paper/figure_drafts/ed10
   StdErr=/scratch/bxxjin001/XPert/experiment/NM/scripts/mmd_bench_789709.out
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/XPert/experiment/NM/scripts/mmd_bench_789709.out
   Power=
   TresPerNode=gres/gpu:ampere:1

UCT HPC clusterJOB DETAILS FOR JOB 789709

captured Wed Apr 29 13:43:36 SAST 2026

bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8131 Nice=0 Account=a100free QOS=a100free
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=00:01:49 TimeLimit=00:15:00 TimeMin=N/A
   SubmitTime=2026-04-29T13:41:41 EligibleTime=2026-04-29T13:41:41
   AccrueTime=2026-04-29T13:41:41
   StartTime=2026-04-29T13:41:41 EndTime=2026-04-29T13:43:30 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-04-29T13:41:41 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc113:1364740
   ReqNodeList=srvrocgpu010 ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=4 NumTasks=4 CPUs/Task=1 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=0-1,36-37 Mem=32768 GRES=
   MinCPUsNode=4 MinMemoryNode=32G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/tmp/sub_mmd_bench.sh
   WorkDir=/scratch/bxxjin001/XPert/experiment/NM/paper/figure_drafts/ed10
   StdErr=/scratch/bxxjin001/XPert/experiment/NM/scripts/mmd_bench_789709.out
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/XPert/experiment/NM/scripts/mmd_bench_789709.out
   Power=
   TresPerNode=gres/gpu:ampere:1

UCT HPC clusterJOB DETAILS FOR JOB 789709

captured Wed Apr 29 13:44:01 SAST 2026

bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8131 Nice=0 Account=a100free QOS=a100free
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=00:01:49 TimeLimit=00:15:00 TimeMin=N/A
   SubmitTime=2026-04-29T13:41:41 EligibleTime=2026-04-29T13:41:41
   AccrueTime=2026-04-29T13:41:41
   StartTime=2026-04-29T13:41:41 EndTime=2026-04-29T13:43:30 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-04-29T13:41:41 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc113:1364740
   ReqNodeList=srvrocgpu010 ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=4 NumTasks=4 CPUs/Task=1 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=0-1,36-37 Mem=32768 GRES=
   MinCPUsNode=4 MinMemoryNode=32G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/tmp/sub_mmd_bench.sh
   WorkDir=/scratch/bxxjin001/XPert/experiment/NM/paper/figure_drafts/ed10
   StdErr=/scratch/bxxjin001/XPert/experiment/NM/scripts/mmd_bench_789709.out
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/XPert/experiment/NM/scripts/mmd_bench_789709.out
   Power=
   TresPerNode=gres/gpu:ampere:1

UCT HPC clusterJOB DETAILS FOR JOB 789709

captured Wed Apr 29 13:44:36 SAST 2026

bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8131 Nice=0 Account=a100free QOS=a100free
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=00:01:49 TimeLimit=00:15:00 TimeMin=N/A
   SubmitTime=2026-04-29T13:41:41 EligibleTime=2026-04-29T13:41:41
   AccrueTime=2026-04-29T13:41:41
   StartTime=2026-04-29T13:41:41 EndTime=2026-04-29T13:43:30 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-04-29T13:41:41 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc113:1364740
   ReqNodeList=srvrocgpu010 ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=4 NumTasks=4 CPUs/Task=1 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=0-1,36-37 Mem=32768 GRES=
   MinCPUsNode=4 MinMemoryNode=32G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/tmp/sub_mmd_bench.sh
   WorkDir=/scratch/bxxjin001/XPert/experiment/NM/paper/figure_drafts/ed10
   StdErr=/scratch/bxxjin001/XPert/experiment/NM/scripts/mmd_bench_789709.out
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/XPert/experiment/NM/scripts/mmd_bench_789709.out
   Power=
   TresPerNode=gres/gpu:ampere:1

UCT HPC clusterJOB DETAILS FOR JOB 789709

captured Wed Apr 29 13:45:01 SAST 2026

bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8131 Nice=0 Account=a100free QOS=a100free
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=00:01:49 TimeLimit=00:15:00 TimeMin=N/A
   SubmitTime=2026-04-29T13:41:41 EligibleTime=2026-04-29T13:41:41
   AccrueTime=2026-04-29T13:41:41
   StartTime=2026-04-29T13:41:41 EndTime=2026-04-29T13:43:30 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-04-29T13:41:41 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc113:1364740
   ReqNodeList=srvrocgpu010 ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=4 NumTasks=4 CPUs/Task=1 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=0-1,36-37 Mem=32768 GRES=
   MinCPUsNode=4 MinMemoryNode=32G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/tmp/sub_mmd_bench.sh
   WorkDir=/scratch/bxxjin001/XPert/experiment/NM/paper/figure_drafts/ed10
   StdErr=/scratch/bxxjin001/XPert/experiment/NM/scripts/mmd_bench_789709.out
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/XPert/experiment/NM/scripts/mmd_bench_789709.out
   Power=
   TresPerNode=gres/gpu:ampere:1

UCT HPC clusterJOB DETAILS FOR JOB 789709

captured Wed Apr 29 13:45:36 SAST 2026

bxxjin001(465013408 Jinming Bai) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=8131 Nice=0 Account=a100free QOS=a100free
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=00:01:49 TimeLimit=00:15:00 TimeMin=N/A
   SubmitTime=2026-04-29T13:41:41 EligibleTime=2026-04-29T13:41:41
   AccrueTime=2026-04-29T13:41:41
   StartTime=2026-04-29T13:41:41 EndTime=2026-04-29T13:43:30 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-04-29T13:41:41 Scheduler=Main
   Partition=a100 AllocNode:Sid=srvrochpc113:1364740
   ReqNodeList=srvrocgpu010 ExcNodeList=(null)
   NodeList=srvrocgpu010
   BatchHost=srvrocgpu010
   NumNodes=1 NumCPUs=4 NumTasks=4 CPUs/Task=1 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=0-1,36-37 Mem=32768 GRES=
   MinCPUsNode=4 MinMemoryNode=32G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/tmp/sub_mmd_bench.sh
   WorkDir=/scratch/bxxjin001/XPert/experiment/NM/paper/figure_drafts/ed10
   StdErr=/scratch/bxxjin001/XPert/experiment/NM/scripts/mmd_bench_789709.out
   StdIn=/dev/null
   StdOut=/scratch/bxxjin001/XPert/experiment/NM/scripts/mmd_bench_789709.out
   Power=
   TresPerNode=gres/gpu:ampere:1