AMS
Overview
"AMS" is an acronym for the High Performance Research Computing's Account Management System.
This system has been designed to provide you 24/7 comprehensive and easy access to your HPC resources at the Texas A&M High Performance Research Computing group.
AMS User Interfaces
AMS provides two different interfaces to users: web interface and command line.
Web Interface
The web interface provides a complete and historical view of your HPRC resources.
Command Line (myproject)
The command-line interface may be accessed by a command on the login nodes of a cluster. Also see on myproject page.
On an HPRC cluster command line, the command is "myproject -h" which provides the help information listed below:
myproject -h
Usage: myproject [option list...]
Options:
-d accountNo: Set accountNo as the default project account
-e YYYY-MM-DD: Specify end date (00:00 AM) for job records
(-j option must be specified.)
-h: Display this help and exit.
-j accountNo (or 'all'): Produce the job records in current fiscal year for
the selected project account or all project accounts when 'all' is given.
-l: List all the active local project accounts.
-p accountNo: List uncomplted jobs for accountNo.
-s YYYY-MM-DD: Specify start date (00:00 AM) for job recrods.
(-j option must be specified.)
-c: Display job records with line length <= 80 chars.
(-j option must be specified.)
Examples below show the most common usage of "myproject" command:
Example 1: List all accounts
The myproject command lists all projects for the user on the current cluster.
[user@cluster ~]$
myproject
==========================================================================================
List of user's Project Accounts
------------------------------------------------------------------------------------------
| Account | Default | Allocation |Used & Pending SUs| Balance | PI |
------------------------------------------------------------------------------------------
|1328000223136| N| 10000.00| 0.00| 10000.00|Doe, John |
------------------------------------------------------------------------------------------
|1328000243716| Y| 5000.00| -71.06| 4928.94|Doe, Jane |
------------------------------------------------------------------------------------------
|1358000247058| N| 5000.00| -0.91| 4999.09|Doe, Jane |
------------------------------------------------------------------------------------------
Example 2: Set Default Account
The "-d xxxxxxx" sets the project account xxxxxxx to be the default account to be charged when jobs are submitted by the user. The default project account can be overridden by "#SBATCH -A yyyyyy" in a job script for a particular job.
[user@terra ~]$
myproject -d 122858321140
Your default project account now is 122858321140.
Example 3: List Completed Jobs
The "-j" option lists jobs completed on Grace or Terra. If the extra "-s" and "-e" options are not specified, all jobs in current fiscal year (starting from 9/1 to 8/31 of the next year) are listed.
[user@grace ~]$
myproject -j 132858329759
------------------------------------------------------------ List of Jobs ---------------------------------------------------------------------
|ProjectAccount| JobID |JobArrayIndex| SubmitTime | StartTime | EndTime | Walltime | TotalSlots | UsedSUs |
-----------------------------------------------------------------------------------------------------------------------------------------------
|132858329759 |1739566 |0 |2015-09-14 15:18:16 |2015-09-14 15:18:16 |2015-09-14 15:18:27 | 11| 1| 0.00|
|132858329759 |1739567 |0 |2015-09-14 15:18:32 |2015-09-14 15:18:33 |2015-09-14 15:28:41 | 608| 1| 0.17|
|132858329759 |1739568 |0 |2015-09-14 15:18:42 |2015-09-14 15:18:42 |2015-09-14 15:19:09 | 27| 1| 0.01|
|132858329759 |1739569 |0 |2015-09-14 15:18:43 |2015-09-14 15:18:44 |2015-09-14 15:19:15 | 31| 1| 0.01|
|132858329759 |1739570 |0 |2015-09-14 15:18:44 |2015-09-14 15:18:45 |2015-09-14 15:18:55 | 10| 1| 0.00|
|132858329759 |1739578 |0 |2015-09-14 15:20:31 |2015-09-14 15:20:33 |2015-09-14 15:20:40 | 7| 1| 0.00|
|132858329759 |1739579 |0 |2015-09-14 15:20:42 |2015-09-14 15:20:43 |2015-09-14 15:22:01 | 78| 1| 0.02|
|132858329759 |1739580 |0 |2015-09-14 15:20:46 |2015-09-14 15:20:47 |2015-09-14 15:20:54 | 7| 1| 0.00|
|132858329759 |1739581 |0 |2015-09-14 15:20:47 |2015-09-14 15:20:48 |2015-09-14 15:20:55 | 7| 1| 0.00|
|132858329759 |1739582 |0 |2015-09-14 15:20:48 |2015-09-14 15:20:49 |2015-09-14 15:20:57 | 8| 1| 0.00|
|132858329759 |2259750 |0 |2016-03-07 12:46:13 |2016-03-07 12:46:15 |2016-03-07 13:28:55 | 2560| 1| 0.71|
|132858329759 |2259751 |0 |2016-03-07 12:46:15 |2016-03-07 12:46:16 |2016-03-07 13:28:54 | 2558| 1| 0.71|
|132858329759 |2259752 |0 |2016-03-07 12:46:17 |2016-03-07 12:46:18 |2016-03-07 12:56:01 | 583| 1| 0.16|
|132858329759 |2259753 |0 |2016-03-07 12:46:19 |2016-03-07 12:46:20 |2016-03-07 12:55:59 | 579| 1| 0.16|
|132858329759 |2259754 |0 |2016-03-07 12:46:21 |2016-03-07 12:46:22 |2016-03-07 12:49:27 | 185| 1| 0.05|
|132858329759 |2259755 |0 |2016-03-07 12:46:24 |2016-03-07 12:46:25 |2016-03-07 12:49:27 | 182| 1| 0.05|
|132858329759 |2259756 |0 |2016-03-07 12:46:26 |2016-03-07 12:46:26 |2016-03-07 12:47:38 | 72| 1| 0.02|
|132858329759 |2259757 |0 |2016-03-07 12:46:28 |2016-03-07 12:46:28 |2016-03-07 12:47:38 | 70| 1| 0.02|
|132858329759 |2261528 |0 |2016-03-08 11:05:32 |2016-03-08 11:05:33 |2016-03-08 11:05:36 | 3| 1| 0.00|
|132858329759 |2261530 |0 |2016-03-08 11:06:08 |2016-03-08 11:06:09 |2016-03-08 11:06:14 | 5| 1| 0.00|
|132858329759 |2261547 |0 |2016-03-08 11:07:34 |2016-03-08 11:07:35 |2016-03-08 11:08:15 | 40| 1| 0.01|
|132858329759 |2261550 |0 |2016-03-08 11:07:55 |2016-03-08 11:07:56 |2016-03-08 20:08:03 | 32407| 1| 9.00|
|132858329759 |2261694 |0 |2016-03-08 11:59:49 |2016-03-08 11:59:50 |2016-03-08 12:00:17 | 27| 1| 0.01|
------------------------------------------------------------------------------------------------------------------------------------------------
|Total Jobs: 1021 |Total Usage: 1220.41 |
------------------------------------------------------------------------------------------------------------------------------------------------
Example 4: List Incomplete Jobs
The "-p" option lists the pending (incomplete jobs) pre-charged to the project specified for this option. The pre-charged SUs listed in the output will be removed after the jobs are completed, and those completed jobs will be charged by their actual used SUs.
[user@terra ~]$
myproject -p 122858329759
--------------------------------------------------------------------
| Job Id |State|#Cores|#EffectiveCores|Walltime(H)|Pending SUs |
--------------------------------------------------------------------
|Total Jobs: 0 |Total Pending SUs: 0.00 |
--------------------------------------------------------------------
Functionality
Manage your accounts
Manage your granted computing time and report your usage with AMS. AMS allows you to flexibly manage the computing time you have been granted for each of the different machines of our Supercomputing Facility upon approval of your application.
Computing time is granted and measured in service units (SUs). Each SU corresponds to 1 hour of wall clock time elapsed on 1 cpu-core by your application. The amount of resources used by your jobs is deducted from a project account.
A personal project account is created for each machine requested in your application when you apply for the first time. A project account allows you to keep track of all the SUs granted to you and used by you on a given machine. It is usually assigned to you for the duration of your project, but it expires at the end of each accounting period. Currently, an accounting period spans an entire school year, running from September 1st to August 31st of the next year. For such reason, we will refer to it as fiscal year (FY).
For your convenience, project accounts are tied to the reason of your request of computing time. Therefore, you may assign to your project account a description related to your intended usage of the machine. For instance, you may use the title of a personal research project, or mention a class you are attending, etc.
If you reapply in the near future for the same research project, you may be allowed to continue to use the same project account number assigned to you for that project during the previous accounting period.
If you are a Principal Investigator (PI), and you manage a group of users working on a single research project, you may transfer SUs to your researchers' project accounts using your AMS personal web interface. You may also reclaim your transferred SUs and redistribute them later on according to your needs.
You should always select which one of your project accounts you wish to use.
For your convenience, however, you may designate a primary project account, which will be used as your default account when you don't specify any account number. Currently, you can set your primary account using either the command line interface (myproject -d accountnumber) or by selecting an account on the portal dashboard.
If you have only one project account, then this account is automatically set as primary and your usage is deducted from it by default.
Once you submit a job to our batch system, AMS computes an amount in SUs based on the amount of resources (wall clock time and number of cpu cores) requested by your batch job file. The balance of your selected project account is then checked to determine if you have enough SUs left to accommodate this amount (this check is done for each job step included in your job command file on eos). If your available balance is large enough, the amount is posted to the project account as pending. Once your job has exited the batch system, this pending amount is dismissed and a new amount reflecting the actual usage is deducted as final.
If your project account does not contain enough SUs to satisfy what is requested in your job command file, your job submission will be rejected by the batch system until your account is replenished.
For such reason, we strongly encourage you to request an amount of resources very close to what you estimate your job will actually need.
Also, you will not be allowed to use the batch system after your project account has expired. However, you may continue to login on the system and work on your files until your login id expires.
Currently, the expiration date of your login id is set by default to October 1st.
Service Unit
A 'Service Unit' (SU) is charged to a job when the job uses one 'effective_core' for one hour (walltime). The calculation of effective_core depends on whether a job is a exclusive job or not ('-x' specified or not).
SUs are allocated on a per-cluster basis and can not be transferred between clusters. Additionally, SUs expire each fiscal year and can not be extended to the new fiscal year.
Exclusive Job
When an exclusive job runs on a node with m cores, effective_core = m. Note that the effective_core for an exclusive job on a node is independent how many cores are requested by the job. Once the effective_core on a node is calculated, the effective_core for the job is simply the sum of the effective_core on all nodes where the job runs.
Non-Exclusive Job
The effective cores on a node is calculated by considering requested memory. When a job requests xxx memory by "--mem=xxx" and the node has m cores, then, for that requested memory, we have memory_equivalent_core = min(m, ceil(xxx/total_memory*m)) where total_memory is the total memory on a node available to users on that node.
Example 1
A compute node has 48 cores and around 351.5G memory available to users. When a job requests 13G memory and 2 cores, the job uses memory_equivalent_core of min(48, ceil(13/351.5625*48))=2 core.
Example 2
A compute node has 48 cores and around 351.5G memory available to users. When the job requests 20G memory and 2 cores, the job uses memory_equivalent_core of min(48, ceil(20/351.5625*48))=3 cores.
Example 3
A compute node has 48 cores and around 351.5G memory available to users. When the job requests 150G memory and 10 cores, the job uses memory_equivalent_core of min(48, ceil(150/351.5625*48))=21 cores.
Once the memory_equivalent_core is calculated, the effective_core on a node where a job request yyy cores can be calculated as below: effective_core = max(yyy, memory_equivalent_cores)
Finally, the effective_core for a job is the sum of the effective_core on all nodes where the job runs.
SUs for Jobs Requesting GPUs
SUs for GPU jobs are charged based on the number of CPUs requested and additional SUs per GPU type (see tables below).
Use the *** maxconfig *** tool to show how many SUs will be charged for your job script. See *** maxconfig -h *** for usage.
Grace
GPU jobs on grace are charged additional SUs per effective GPU requested:
Effective GPU | SU charge per one hour (wall_time) |
---|---|
A100 | 72 |
RTX 6000 | 48 |
T4 | 24 |
FASTER
GPU jobs on FASTER are charged in addition to SU charge for effective cores/hour:
Effective GPU | SU charge per one hour (wall_time) |
---|---|
A10 | 128 |
A30 | 128 |
A40 | 128 |
A100 | 128 |
T4 | 64 |
ACES
GPU or other coprocessor jobs on ACES are charged in addition to SU charge for effective cores/hour:
Effective GPU | SU charge per one hour (wall_time) |
---|---|
A30 | 60 |
H100 | 120 |
PVC | 60 |
Bittware FPGA | 100 |
D5005 FPGA | 50 |
NEC Vector Engine | 150 |
NextSilicon | 100 |
Optane Memory | 60 |
Graphcore IPU Classic | 90 |
Graphcore IPU Bow | 120 |
Add a Project Delegate
The PI of a Research or Startup project can add one delegate to transfer SUs to/from researchers of that project. A delegate of a project must be a researcher of that project. For example, a PI has a Research project 080123456789 with three researchers: Tom, Mary, and Gabriel. The PI can add one researcher (e.g. Mary) to be the delegate of this project. After Mary is added as the project delegate, Mary can transfer SUs from the PI's account to Tom's account and vice versa.
- PI needs to login at https://hprc.tamu.edu/ams
-
PI clicks the "Accounts" menu on the top
-
PI clicks the dropbox which lists all projects of the PI and select the project to add/remove delegate.
- PI goes to the "Your Researchers" section and clicks the 'Add' button in the same table row of the researcher to be added as the project delegate.
- Now PI should see the that the researcher is added as the project delegate.
Transfer SUs
A PI or a delegate of a Startup or Research allocation can transfer SUs to or from researchers after login at https://hprc.tamu.edu/ams. SUs CANNOT be transferred from a basic account.
-
Click the 'Transfer' menu on the top
-
Click the System (Cluster/Machine) to transfer SUs.
-
Click the Project/Account to transfer SUs
-
Click the Researcher Project/Account to transfer SUs, enter the amount of SUs to transfer, select the transfer is to or from the researcher, and then click the 'Submit' button'
-
Read the message after the 'Submit' button is clicked. If there are any error messages, please contact help@hprc.tamu.edu.
Project Reports
At the end of any Startup or Research allocation, a short summary report must be submitted to the allocation committee (see below for desired report content). Failure to submit this report may be used in the consideration of future allocations.
The report should be a maximum of 5 pages and should include the following information:
- Principal user information (PI's name, status, department, phone, email, and institution [if different from TAMU]).
- Summarize the TAMU-sponsored research in a non-technical fashion, suitable for public consumption (maximum two pages).
- Publications and other research products.
- Describe any potential applications of the research to industry or government.
- Describe any use of this allocation to encourage education in computational science, and particularly the level of student involvement and any HPRC elements incorporated into formal courses.
How to Submit a Report
1) Login to AMS.
2) On the grey navigation bar at the top of the page, select the 'Reports' tab. You should see your allocations which can have reports attached to them in the table below.
3) Click the 'Browse' button, and select your report file.
4) Your report is now ready to be submitted. Click the 'Submit' button to complete the process.
5) If the upload completed successfully, you will see the following message:
6) NOTE that submitting a new report does NOT automatically renew your account! You must still renew your account every fiscal year.
Support
AMS has been entirely designed and developed by HPRC.
Please email your questions, comments, and support requests to help@hprc.tamu.edu or call our Help Desk at 979-845-0219.