A company has hired a technician to build a cloud infrastructure for a massively parallel application. Which of the following should the technician consider doing FIRST?

Question

Options

• AAdd a GPU to the VMs
• BConfigure the VMs to scale up automatically
• CAllocate maximum bandwidth to the VMs
• DSelect the most compute cores for the VMs

• A
  4% (2)
• B
  78% (43)
• C
  13% (7)
• D
  5% (3)

Explanation

For a massively parallel application, auto-scaling is the foundational architectural decision that must be made first. Massively parallel workloads are defined by dynamic, burst-heavy compute demand-the whole point is that the number of parallel tasks fluctuates. Configuring auto-scaling first ensures the infrastructure is architected to expand and contract as the workload demands, which is the core requirement. Adding GPUs, maximum bandwidth, or maximum compute cores are hardware tuning decisions that come after the scaling architecture is established. Provisioning max resources upfront without auto-scaling would be wasteful and would not actually address the parallel nature of the workload.

No community discussion yet for this question.