Week 5 involved working out the lots of technical details surrounding which AWS resources would be best suited to the task of running hashcat. Rather than opting for Elastic GPUs as originally planned, I chose EC2 g3.8xlarge. I did end up spending (read: wasting) time messing with Elastic GPUs; however, I realized that they are incompatible with OpenCL–a hashcat requirement. I also had to request a resource limit increase from AWS Billing, which took away some valuable time.

GPU Optimized Instance Specifications:

Model GPUs GPU Memory vCPUs Main Memory EBS Bandwidth
g3.4xlarge 1 8 GiB 16 122 GiB 3.5 Gbps
g3.8xlarge 2 16 GiB 32 244 GiB 7 Gbps
g3.16xlarge 4 32 GiB 64 488 GiB 14 Gbps

I got the go ahead from AWS so I will be building the environment during week 6.