Page tree

The current default walltime and resource limits for Gadi jobs are summarised below. If higher limit on core count (PBS_NCPUS) and walltime is needed, please launch a ticket on NCI help desk with a short description of the reasons why the exception is requested. For example, what simulation uses which solver provided by which application that doesn't allow check-points or the current scalability study suggests linear speedup at the core count beyond the current PBS_NCPUS limit. We will see how we can help on a case-by-case basis.

 Queue  

 

Max queueing jobs per project

Charge rate per resource*hour ‡PBS_NCPUS

Max PBS_MEM/node †

Max PBS_JOBFS/node †

Default walltime limit

normalnormal(route§)10002 SU 

1-48 

multiple of 48

190 GB 400 GB

48 hours for 1-672 cores

24 hours for 720-1440 cores

10 hours for 1488-2976 cores

5 hours for  3024-20736 cores

normal-exec§300
expressexpress(route)10006 SU

1-48 

multiple of 48

190 GB400 GB

24 hours for 1-480 cores

5 hours for 528- 3168 cores

express-exec50

hugemem


hugemem(route)10003 SU

1-48 

multiple of 48

1470GB 1400 GB

48 hours for 1-48 cores

24 hours for 96 cores

5 hours for 144, 192 cores

hugmem-exec

50
megamemmegamem(route)3005 SU

1-48

multiple of 48

2990 GB1400 GB

48 hours for 1-48 cores

24 hours for 96 cores


megamem-exec50
gpuvoltagpuvolta(route)10003 SU multiple of 12382 GB400 GB

48 hours for 1-96 CPU cores

24 hours for 144-192 CPU cores

5 hours for 240-960 CPU cores

gpuvolta-exec50
normalbwnormalbw(route)10001.25 SU

1-28

multiple of 28

128GB, 256GB400 GB

48 hours for 1-336 cores

24 hours for 364-840 cores

10 hours for 868-1736 cores

5 hours for 1764- 10080 cores

normalbw-exec300
expressbwexpressbw(route)10003.75 SU 

1-28 

multiple of 28

128GB, 256GB400 GB

24 hours for 1-280 cores

5 hours for 308-1848 cores

expressbw-exec50
normalslnormalsl(route)10001.5 SU

1-32

multiple of 32

192 GB 400 GB

48 hours for 1-288 cores

24 hours for 320-608 cores

10 hours for 640-1984 cores

5 hours for 2016-3200 cores

normalsl-exec300
hugemembwhugemembw(route)5001.25 SU

7, 14, 21, 28

multiple of 28

1020 GB 390 GB

48 hours for 1-28 cores

12 hours for 56-140 cores

hugemembw-exec100

megamembw

megamembw(route)

300

1.25 SU

32, 64


3000 GB

800 GB

48 hours for 32 cores

12 hours for 64 cores

megamembw-exec50
copyqcopyq(route)10002 SU1190 GB400 GB10 hours
copyq-exec50

dgxa100

dgxa100(route)

50

4.5 SU

multiple of 16


2000 GB

28 TB

48 hours for 16-128 cores

5 hours for 144-256 cores

dgxa100-exec50

† To make sure your jobs can be handled properly when they are terminated because of usage exceeding the memory and/or the local disk limit, please request no more than the amount listed in the corresponding column.

‡ The number of `resource` is calculated as ncpus_request * max[ 1, (ncpus_per_node/mem_per_node)*(mem_request/ncpus_request)].

§ The route queue is where jobs stay before they go to the execution queue. Only jobs in the execution queues, whose names end with `-exec`, are considered to be run on compute and data mover nodes by PBS.