UCT HPC cluster

JOB DETAILS FOR JOB 1488397

captured Thu Oct 15 11:46:38 SAST 2026

01481067(465061756 Stefano Cacciatore) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7733 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=PENDING Reason=Priority Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:00:00 TimeLimit=01:00:00 TimeMin=N/A
   SubmitTime=2026-10-15T11:46:23 EligibleTime=2026-10-15T11:46:23
   AccrueTime=2026-10-15T11:46:23
   StartTime=Unknown EndTime=Unknown Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-10-15T11:46:24 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc001:2278899
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=
   NumNodes=1-1 NumCPUs=1 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=1,mem=16G,node=1,billing=2,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=(null)
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   MinCPUsNode=2 MinMemoryNode=16G 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_preflight_cuda.sh
   WorkDir=/scratch/firenze/NN
   StdErr=/scratch/firenze/NN/benchmark_logs/feR_JSS_pre_gpu_1488397.err
   StdIn=/dev/null
   StdOut=/scratch/firenze/NN/benchmark_logs/feR_JSS_pre_gpu_1488397.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   TresPerTask=cpu:1

UCT HPC clusterJOB DETAILS FOR JOB 1488397

captured Thu Oct 15 11:47:01 SAST 2026

01481067(465061756 Stefano Cacciatore) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7733 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=00:00:01 TimeLimit=01:00:00 TimeMin=N/A
   SubmitTime=2026-10-15T11:46:23 EligibleTime=2026-10-15T11:46:23
   AccrueTime=2026-10-15T11:46:23
   StartTime=2026-10-15T11:46:50 EndTime=2026-10-15T11:46:51 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-10-15T11:46:50 Scheduler=Backfill
   Partition=l40s AllocNode:Sid=srvrochpc001:2278899
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu016
   BatchHost=srvrocgpu016
   NumNodes=1 NumCPUs=1 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=1,mem=16G,node=1,billing=2,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=1,mem=16G,node=1,billing=2,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=24 Mem=16384 GRES=
   MinCPUsNode=2 MinMemoryNode=16G 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_preflight_cuda.sh
   WorkDir=/scratch/firenze/NN
   StdErr=/scratch/firenze/NN/benchmark_logs/feR_JSS_pre_gpu_1488397.err
   StdIn=/dev/null
   StdOut=/scratch/firenze/NN/benchmark_logs/feR_JSS_pre_gpu_1488397.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   TresPerTask=cpu:1

UCT HPC clusterJOB DETAILS FOR JOB 1488397

captured Thu Oct 15 11:47:37 SAST 2026

01481067(465061756 Stefano Cacciatore) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7733 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=00:00:01 TimeLimit=01:00:00 TimeMin=N/A
   SubmitTime=2026-10-15T11:46:23 EligibleTime=2026-10-15T11:46:23
   AccrueTime=2026-10-15T11:46:23
   StartTime=2026-10-15T11:46:50 EndTime=2026-10-15T11:46:51 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-10-15T11:46:50 Scheduler=Backfill
   Partition=l40s AllocNode:Sid=srvrochpc001:2278899
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu016
   BatchHost=srvrocgpu016
   NumNodes=1 NumCPUs=1 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=1,mem=16G,node=1,billing=2,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=1,mem=16G,node=1,billing=2,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=24 Mem=16384 GRES=
   MinCPUsNode=2 MinMemoryNode=16G 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_preflight_cuda.sh
   WorkDir=/scratch/firenze/NN
   StdErr=/scratch/firenze/NN/benchmark_logs/feR_JSS_pre_gpu_1488397.err
   StdIn=/dev/null
   StdOut=/scratch/firenze/NN/benchmark_logs/feR_JSS_pre_gpu_1488397.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   TresPerTask=cpu:1

UCT HPC clusterJOB DETAILS FOR JOB 1488397

captured Thu Oct 15 11:48:02 SAST 2026

01481067(465061756 Stefano Cacciatore) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7733 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=00:00:01 TimeLimit=01:00:00 TimeMin=N/A
   SubmitTime=2026-10-15T11:46:23 EligibleTime=2026-10-15T11:46:23
   AccrueTime=2026-10-15T11:46:23
   StartTime=2026-10-15T11:46:50 EndTime=2026-10-15T11:46:51 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-10-15T11:46:50 Scheduler=Backfill
   Partition=l40s AllocNode:Sid=srvrochpc001:2278899
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu016
   BatchHost=srvrocgpu016
   NumNodes=1 NumCPUs=1 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=1,mem=16G,node=1,billing=2,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=1,mem=16G,node=1,billing=2,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=24 Mem=16384 GRES=
   MinCPUsNode=2 MinMemoryNode=16G 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_preflight_cuda.sh
   WorkDir=/scratch/firenze/NN
   StdErr=/scratch/firenze/NN/benchmark_logs/feR_JSS_pre_gpu_1488397.err
   StdIn=/dev/null
   StdOut=/scratch/firenze/NN/benchmark_logs/feR_JSS_pre_gpu_1488397.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   TresPerTask=cpu:1

UCT HPC clusterJOB DETAILS FOR JOB 1488397

captured Thu Oct 15 11:48:38 SAST 2026

01481067(465061756 Stefano Cacciatore) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7733 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=00:00:01 TimeLimit=01:00:00 TimeMin=N/A
   SubmitTime=2026-10-15T11:46:23 EligibleTime=2026-10-15T11:46:23
   AccrueTime=2026-10-15T11:46:23
   StartTime=2026-10-15T11:46:50 EndTime=2026-10-15T11:46:51 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-10-15T11:46:50 Scheduler=Backfill
   Partition=l40s AllocNode:Sid=srvrochpc001:2278899
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu016
   BatchHost=srvrocgpu016
   NumNodes=1 NumCPUs=1 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=1,mem=16G,node=1,billing=2,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=1,mem=16G,node=1,billing=2,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=24 Mem=16384 GRES=
   MinCPUsNode=2 MinMemoryNode=16G 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_preflight_cuda.sh
   WorkDir=/scratch/firenze/NN
   StdErr=/scratch/firenze/NN/benchmark_logs/feR_JSS_pre_gpu_1488397.err
   StdIn=/dev/null
   StdOut=/scratch/firenze/NN/benchmark_logs/feR_JSS_pre_gpu_1488397.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   TresPerTask=cpu:1

UCT HPC clusterJOB DETAILS FOR JOB 1488397

captured Thu Oct 15 11:49:01 SAST 2026

01481067(465061756 Stefano Cacciatore) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7733 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=00:00:01 TimeLimit=01:00:00 TimeMin=N/A
   SubmitTime=2026-10-15T11:46:23 EligibleTime=2026-10-15T11:46:23
   AccrueTime=2026-10-15T11:46:23
   StartTime=2026-10-15T11:46:50 EndTime=2026-10-15T11:46:51 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-10-15T11:46:50 Scheduler=Backfill
   Partition=l40s AllocNode:Sid=srvrochpc001:2278899
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=srvrocgpu016
   BatchHost=srvrocgpu016
   NumNodes=1 NumCPUs=1 NumTasks=1 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=1,mem=16G,node=1,billing=2,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=1,mem=16G,node=1,billing=2,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=24 Mem=16384 GRES=
   MinCPUsNode=2 MinMemoryNode=16G 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_preflight_cuda.sh
   WorkDir=/scratch/firenze/NN
   StdErr=/scratch/firenze/NN/benchmark_logs/feR_JSS_pre_gpu_1488397.err
   StdIn=/dev/null
   StdOut=/scratch/firenze/NN/benchmark_logs/feR_JSS_pre_gpu_1488397.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   TresPerTask=cpu:1