| executable = /bin/bash |
| error = ./output/condor_logs/{errorfile}_$(ClusterId).$(ProcId).err |
| output = ./output/condor_logs/{outfile}_$(ClusterId).$(ProcId).out |
| log = ./output/condor_logs/{logfile}_$(ClusterId).$(ProcId).log |
| request_memory = 32768 |
| request_cpus = 6 |
| request_gpus = {gpus} |
| +WantGPUStats = true |
| requirements = (TARGET.CUDADeviceName=="{gpu_name}") |
| |
| on_exit_hold = (ExitCode =?= 3) |
| on_exit_hold_reason = "Checkpointed, will resume" |
| on_exit_hold_subcode = 2 |
| periodic_release = ( (JobStatus =?= 5) && (HoldReasonCode =?= 3) && (HoldReasonSubCode =?= 2) ) |
| +RunningPriceExceededAction = "kill" |
| queue |
|
|
