Job Submission
The system is managed by the scheduler.
Please refer to the parallel server user manual for basic submitting jobs.
Making a job script
To execute a compiled executable file as a batch job, you need a job script to submit to the job scheduler.
Job Script
Please refer to following link.
After logon to pcc, sample script files can be found in the path below. Please copy it to your own directory before using.
lmpcc: /Samples
Job submission
1. Submit the job script to the scheduler as below.
% qsub -q <Queue> <Script>
2. Job submission (with mail notification)
Notification of the starting / ending the job can be requested as below,
% qsub -q <Queue> -M <mail address> -m be <Script>
-M <contact email>
-m be # b -> begin(Job starting) , e -> end(Job ending)
3. Job deletion
Only the owner of the job can delete his already submitted jobs
% qdel <Job id>
Queue classes
For Single Node(Large Memory Cluster):
Queue | Node | Cores | Memory | walltime | Number of simultaneous jobs(per user) |
---|---|---|---|---|---|
SINGLE | ~0.25node | ~16core | ~384GB | 1week | 90(16)job |
SINGLE-4 | ~1node | ~64core | ~1.5TB | 1week | 20(16)job |
LONG | ~0.25node | ~16Core | ~384GB | 3week | 16(4)job |
For SuperLarge node (12TB, 6TB memory server) :
Queue | Cores | Memory | walltime | Number of simultaneous jobs(per user) |
---|---|---|---|---|
XLARGE-6T | ~72Core | 6TB | 1week | 2(1)job |
XLARGE-12T | ~144Core | 12TB | 1week | 4(1)job |
FLOAT (preemption:The queue might be started regardless of type of CPU):
Queue | Cores | Memory | walltime | Number of simultaneous jobs(per user) |
---|---|---|---|---|
TINY | ~64Core | ~1TB | 1hour | 32(-)job |
FLOAT | ~16Core | ~384GB | 1week | 90(16)job |
For Materials Studio:
Queue | Node | Core | Memory | walltime | Number of simultaneous jobs(per user) |
---|---|---|---|---|---|
MatStudio | 0.125node | ~8core | ~192GB | 1week | 40(40)job |
MS_Dmol3 | 0.125node | ~8core | ~192GB | 1week | 90(32)job |
MS_Castep | 0.125node | ~8core | ~192GB | 1week | 60(32)job |
MS_Forcite | 0.125node | ~8core | ~192GB | 1week | 2(2)job |
MS_Compass | 0.125node | ~8core | ~192GB | 1week | 1(1)job |
MS_Amorphous | 0.125node | ~8core | ~192GB | 1week | 1(1)job |
MS_Dftbplus | 0.125node | ~8core | ~192GB | 1week | 1(1)job |
- MatStudioキューのみMaterials Studio Gatewayユーザ専用キューとなります.
- その他のキューに投入されたジョブは,各ライセンスが利用可能になるまで実行を待機します.
For Multi Nodes:
- 通常,MPI等を利用しない場合はジョブのマルチノード化はできません
(ジョブは正常に開始しますが,実際の計算はシングルノード内のみで実行されます)
Queue | Node | Core | walltime | Number of simultaneous jobs(per user) |
---|---|---|---|---|
SMALL | 2~4node | ~256core | 1week | 8(4)job |
LARGE | 5~8node | ~512core | 48hour | 2(1)job |
Request only:
Queue | Node | Core | walltime |
---|---|---|---|
LONG-XL | ~node | - | (申請ベース) |