UCT HPC cluster

JOB DETAILS FOR JOB 1496285

captured Fri Oct 16 04:58:01 SAST 2026

01481067(465061756 Stefano Cacciatore) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7761 Nice=0 Account=l40sfree QOS=l40sfree
   JobState=PENDING Reason=QOSMaxGRESPerUser Dependency=(null)
   Requeue=0 Restarts=0 BatchFlag=1 Reboot=0 ExitCode=0:0
   DerivedExitCode=0:0
   RunTime=00:00:00 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-10-16T04:57:28 EligibleTime=2026-10-16T04:57:28
   AccrueTime=2026-10-16T04:57:28
   StartTime=2026-10-16T19:20:05 EndTime=2026-10-18T19:20:05 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-10-16T04:57:58 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc100:2441442
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=
   NumNodes=1-1 NumCPUs=4 NumTasks=1 CPUs/Task=4 ReqB:S:C:T=0:0:*:*
   ReqTRES=cpu=4,mem=64G,node=1,billing=10,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=(null)
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   MinCPUsNode=7 MinMemoryNode=64G 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_support_sweep_cuda.sh
   WorkDir=/scratch/firenze/NN
   StdErr=/scratch/firenze/NN/benchmark_logs/feR_JSS_supP_g_1496281_2.err
   StdIn=/dev/null
   StdOut=/scratch/firenze/NN/benchmark_logs/feR_JSS_supP_g_1496281_2.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   TresPerTask=cpu:4

UCT HPC clusterJOB DETAILS FOR JOB 1496285

captured Fri Oct 16 04:58:36 SAST 2026

01481067(465061756 Stefano Cacciatore) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7761 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=00:00:18 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-10-16T04:57:28 EligibleTime=2026-10-16T04:57:28
   AccrueTime=2026-10-16T04:57:28
   StartTime=2026-10-16T04:58:02 EndTime=2026-10-16T04:58:20 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-10-16T04:58:02 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc100:2441442
   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=64G,node=1,billing=10,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=64G,node=1,billing=10,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=65536 GRES=
   MinCPUsNode=7 MinMemoryNode=64G 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_support_sweep_cuda.sh
   WorkDir=/scratch/firenze/NN
   StdErr=/scratch/firenze/NN/benchmark_logs/feR_JSS_supP_g_1496281_2.err
   StdIn=/dev/null
   StdOut=/scratch/firenze/NN/benchmark_logs/feR_JSS_supP_g_1496281_2.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   TresPerTask=cpu:4

UCT HPC clusterJOB DETAILS FOR JOB 1496285

captured Fri Oct 16 04:59:01 SAST 2026

01481067(465061756 Stefano Cacciatore) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7761 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=00:00:18 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-10-16T04:57:28 EligibleTime=2026-10-16T04:57:28
   AccrueTime=2026-10-16T04:57:28
   StartTime=2026-10-16T04:58:02 EndTime=2026-10-16T04:58:20 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-10-16T04:58:02 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc100:2441442
   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=64G,node=1,billing=10,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=64G,node=1,billing=10,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=65536 GRES=
   MinCPUsNode=7 MinMemoryNode=64G 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_support_sweep_cuda.sh
   WorkDir=/scratch/firenze/NN
   StdErr=/scratch/firenze/NN/benchmark_logs/feR_JSS_supP_g_1496281_2.err
   StdIn=/dev/null
   StdOut=/scratch/firenze/NN/benchmark_logs/feR_JSS_supP_g_1496281_2.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   TresPerTask=cpu:4

UCT HPC clusterJOB DETAILS FOR JOB 1496285

captured Fri Oct 16 04:59:35 SAST 2026

01481067(465061756 Stefano Cacciatore) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7761 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=00:00:18 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-10-16T04:57:28 EligibleTime=2026-10-16T04:57:28
   AccrueTime=2026-10-16T04:57:28
   StartTime=2026-10-16T04:58:02 EndTime=2026-10-16T04:58:20 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-10-16T04:58:02 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc100:2441442
   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=64G,node=1,billing=10,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=64G,node=1,billing=10,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=65536 GRES=
   MinCPUsNode=7 MinMemoryNode=64G 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_support_sweep_cuda.sh
   WorkDir=/scratch/firenze/NN
   StdErr=/scratch/firenze/NN/benchmark_logs/feR_JSS_supP_g_1496281_2.err
   StdIn=/dev/null
   StdOut=/scratch/firenze/NN/benchmark_logs/feR_JSS_supP_g_1496281_2.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   TresPerTask=cpu:4

UCT HPC clusterJOB DETAILS FOR JOB 1496285

captured Fri Oct 16 05:00:01 SAST 2026

01481067(465061756 Stefano Cacciatore) GroupId=eresearch_hpc_users(1221947160) MCS_label=N/A
   Priority=7761 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=00:00:18 TimeLimit=2-00:00:00 TimeMin=N/A
   SubmitTime=2026-10-16T04:57:28 EligibleTime=2026-10-16T04:57:28
   AccrueTime=2026-10-16T04:57:28
   StartTime=2026-10-16T04:58:02 EndTime=2026-10-16T04:58:20 Deadline=N/A
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2026-10-16T04:58:02 Scheduler=Main
   Partition=l40s AllocNode:Sid=srvrochpc100:2441442
   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=64G,node=1,billing=10,gres/gpu=1,gres/gpu:l40s=1
   AllocTRES=cpu=4,mem=64G,node=1,billing=10,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=65536 GRES=
   MinCPUsNode=7 MinMemoryNode=64G 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_support_sweep_cuda.sh
   WorkDir=/scratch/firenze/NN
   StdErr=/scratch/firenze/NN/benchmark_logs/feR_JSS_supP_g_1496281_2.err
   StdIn=/dev/null
   StdOut=/scratch/firenze/NN/benchmark_logs/feR_JSS_supP_g_1496281_2.out
   Power=
   TresPerNode=gres/gpu:l40s:1
   TresPerTask=cpu:4