The College of Engineering provides Flux allocations that can be used by anyone in the College:
|Allocation name||Service||Overall allocation size||Individual usage limits
(maximums per person)
|engin_flux||Standard Flux||50 cores / 200 GB RAM||20 cores / 80 GB RAM
Runtime: 5 core*months remaining across all running jobs
|engin_fluxg||GPU Flux||2 GPUs / 4 cores / 16 GB RAM||2 GPUs / 4 cores / 16 GB RAM
Runtime: 24 hours per job
Uses of these allocations include, but is not limited to:
- Testing the Flux service to determine whether to purchase an allocation.
- Note that Principal Investigators (PIs) across campus can also request a one-time two week trial allocation, for each type of service, by contacting firstname.lastname@example.org. The trial allocation is limited to 16 cores for standard Flux or 1 GPU for GPU Flux. These allocations are for the exclusive use of the PI’s research group.
- Experimentation and exploration on a small-scale, ad hoc basis of questions not necessarily tied to any particular research project, without needing to obtain funding with which to purchase a Flux allocation first.
The College of Engineering shared Flux allocations are neither intended to replace nor supplement other Flux allocations. Research groups who need more computation than is provided under the above allocation usage limits, or who need their jobs to start running faster than they would under the shared allocations, should obtain their own Flux allocation. Allocations can also be obtained for use by multiple research groups across departments, centers, institutes, or other units. Graduate students in particular may want to use Rackham Graduate Student Research Grants to purchase their own, private Flux allocation.
The College of Engineering has set usage limits on its shared Flux allocations in order to prevent a single individual or small group from monopolizing the allocations for extended periods of time to the detriment of others.
An individual may use up to 20 cores or up to 80 GB of memory across all of their running jobs at any point in time on engin_flux. Additionally, individuals are limited to having no more than 5 core*months (3,600 core*hours) worth of jobs running at any one time. This limit is calculated by summing the product of the remaining walltime and number of cores for all of a given individual’s running jobs, as shown by the command showq -r -u $USER. 5 core*months are sufficient to run a 5 core job for 28 days, or a 10 core job for 15 days, or a 20 core job for 7 days, or two 10 core jobs for 7 days, or many other combinations.
Two GPUs, with 4 cores and 16 GB of RAM, are available in engin_fluxg. Jobs on engin_fluxg are limited to a walltime of 24 hours. No other limits are set, so the job may use both GPUs along with all 4 cores and 16GB of RAM. The limit of 24 hours per job is set because there are only two GPUs in the allocation. Both the GPUs in engin_fluxg may be used at the same time by an individual, either in the same job or in two separate jobs.
Send questions about the College of Engineering’s shared Flux allocations to: email@example.com