UCT HPC cluster

JOB DETAILS FOR JOB 1496348

captured Fri Oct 16 05:24:01 SAST 2026

MaxRAM=1G
MaxVMSize=0G
AveCPUFreq=3.17M
AveDiskRead=3883394533
AveDiskWrite=4205362194

01481067(465061756 Stefano Cacciatore) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7795 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=00:01:06 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-10-16T04:58:20 EligibleTime=2026-10-16T04:58:20
   AccrueTime=2026-10-16T05:04:45
   StartTime=2026-10-16T05:22:56 EndTime=2026-10-18T05:22:56 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-10-16T05:22:56 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc100:2446737
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu016
   BatchHost=srvrocgpu016
   NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=4 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=128G,node=1,billing=16,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=128G,node=1,billing=16,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu016 CPU_IDs=0,11,24,26 Mem=131072 GRES=gpu:l40s:1(IDX:0)
   MinCPUsNode=14 MinMemoryNode=128G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/firenze/NN/benchmark_scripts/jss-review-validation/slurm/run_recall_quality_cuda_compact.sh
   WorkDir=/scratch/firenze/NN
   StdErr=/scratch/firenze/NN/benchmark_logs/feR_JSS_rq_g_1496294_9.err
   StdIn=/dev/null
   StdOut=/scratch/firenze/NN/benchmark_logs/feR_JSS_rq_g_1496294_9.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   TresPerTask=cpu:4

UCT HPC clusterJOB DETAILS FOR JOB 1496348

captured Fri Oct 16 05:24:36 SAST 2026

01481067(465061756 Stefano Cacciatore) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7795 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=00:01:14 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-10-16T04:58:20 EligibleTime=2026-10-16T04:58:20
   AccrueTime=2026-10-16T05:04:45
   StartTime=2026-10-16T05:22:56 EndTime=2026-10-16T05:24:10 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-10-16T05:22:56 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc100:2446737
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu016
   BatchHost=srvrocgpu016
   NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=4 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=128G,node=1,billing=16,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=128G,node=1,billing=16,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu016 CPU_IDs=0,11,24,26 Mem=131072 GRES=
   MinCPUsNode=14 MinMemoryNode=128G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/firenze/NN/benchmark_scripts/jss-review-validation/slurm/run_recall_quality_cuda_compact.sh
   WorkDir=/scratch/firenze/NN
   StdErr=/scratch/firenze/NN/benchmark_logs/feR_JSS_rq_g_1496294_9.err
   StdIn=/dev/null
   StdOut=/scratch/firenze/NN/benchmark_logs/feR_JSS_rq_g_1496294_9.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   TresPerTask=cpu:4

UCT HPC clusterJOB DETAILS FOR JOB 1496348

captured Fri Oct 16 05:25:01 SAST 2026

01481067(465061756 Stefano Cacciatore) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7795 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=00:01:14 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-10-16T04:58:20 EligibleTime=2026-10-16T04:58:20
   AccrueTime=2026-10-16T05:04:45
   StartTime=2026-10-16T05:22:56 EndTime=2026-10-16T05:24:10 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-10-16T05:22:56 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc100:2446737
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu016
   BatchHost=srvrocgpu016
   NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=4 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=128G,node=1,billing=16,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=128G,node=1,billing=16,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu016 CPU_IDs=0,11,24,26 Mem=131072 GRES=
   MinCPUsNode=14 MinMemoryNode=128G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/firenze/NN/benchmark_scripts/jss-review-validation/slurm/run_recall_quality_cuda_compact.sh
   WorkDir=/scratch/firenze/NN
   StdErr=/scratch/firenze/NN/benchmark_logs/feR_JSS_rq_g_1496294_9.err
   StdIn=/dev/null
   StdOut=/scratch/firenze/NN/benchmark_logs/feR_JSS_rq_g_1496294_9.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   TresPerTask=cpu:4

UCT HPC clusterJOB DETAILS FOR JOB 1496348

captured Fri Oct 16 05:25:36 SAST 2026

01481067(465061756 Stefano Cacciatore) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7795 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=00:01:14 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-10-16T04:58:20 EligibleTime=2026-10-16T04:58:20
   AccrueTime=2026-10-16T05:04:45
   StartTime=2026-10-16T05:22:56 EndTime=2026-10-16T05:24:10 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-10-16T05:22:56 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc100:2446737
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu016
   BatchHost=srvrocgpu016
   NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=4 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=128G,node=1,billing=16,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=128G,node=1,billing=16,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu016 CPU_IDs=0,11,24,26 Mem=131072 GRES=
   MinCPUsNode=14 MinMemoryNode=128G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/firenze/NN/benchmark_scripts/jss-review-validation/slurm/run_recall_quality_cuda_compact.sh
   WorkDir=/scratch/firenze/NN
   StdErr=/scratch/firenze/NN/benchmark_logs/feR_JSS_rq_g_1496294_9.err
   StdIn=/dev/null
   StdOut=/scratch/firenze/NN/benchmark_logs/feR_JSS_rq_g_1496294_9.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   TresPerTask=cpu:4

UCT HPC clusterJOB DETAILS FOR JOB 1496348

captured Fri Oct 16 05:26:01 SAST 2026

01481067(465061756 Stefano Cacciatore) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7795 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=FAILED Reason=NonZeroExitCode Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=1:0
   DerivedExitCode=0:0
   RunTime=00:01:14 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-10-16T04:58:20 EligibleTime=2026-10-16T04:58:20
   AccrueTime=2026-10-16T05:04:45
   StartTime=2026-10-16T05:22:56 EndTime=2026-10-16T05:24:10 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-10-16T05:22:56 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc100:2446737
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu016
   BatchHost=srvrocgpu016
   NumNodes=1 NumCPUs=4 NumTasks=1 CPUs/Task=4 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=128G,node=1,billing=16,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=128G,node=1,billing=16,gres/gpu=1,gres/gpu:l40s=1
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   JOB_GRES=gpu:l40s:1
     Nodes=srvrocgpu016 CPU_IDs=0,11,24,26 Mem=131072 GRES=
   MinCPUsNode=14 MinMemoryNode=128G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=/scratch/firenze/NN/benchmark_scripts/jss-review-validation/slurm/run_recall_quality_cuda_compact.sh
   WorkDir=/scratch/firenze/NN
   StdErr=/scratch/firenze/NN/benchmark_logs/feR_JSS_rq_g_1496294_9.err
   StdIn=/dev/null
   StdOut=/scratch/firenze/NN/benchmark_logs/feR_JSS_rq_g_1496294_9.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   TresPerTask=cpu:4