The Flux HPC cluster has 40 NVIDIA K20x GPUs and 24 NVIDIA K40 GPUs available for researchers who have applications that can benefit from the acceleration provided by GPU co-processors. In addition, the software library on Flux has several programs that can benefit from these accelerators.

Flux has 40 K20x GPUs connected to 5 compute nodes. Each GPU allocation comes with 2 compute cores and 8GB of CPU RAM.

NVIDIA Tesla K20x specifications

Number and Type of GPU one Kepler GK110
Peak double precision floating point perf. 1.31 Tflops
Peak single precision floating point perf. 3.95 Tflops
Memory bandwidth (ECC off) 250 GB/sec
Memory size (GDDR5) 6 GB
CUDA cores 2688

If you have questions, please send email to

Order Service

Email with the following information:

  • number of cores needed (for help on determining the size of a Flux allocation, please see our pages on How Flux Works and Managing a Flux Project).
  • U-M shortcode for billing
  • start and end dates
  • list of users who should have access to the allocation
  • list of people who can change dates or approved users of the allocation.

For information on costs, visit our Rates page.