The hpc6a.48xlarge pairs 96 vCPU with 384 GiB of RAM, the 4.00 GiB-per-vCPU ratio that marks a compute-optimized instance. In the name, "hpc" is high performance computing, "6" is the generation, "a" marks AMD processors and "48xlarge" is the size within the hpc6a family. It runs on AMD EPYC 7R13 Processor at 2.95 GHz, and AWS introduced it in January 2022. AWS has since shipped hpc7a and hpc8a; hpc7a.48xlarge is the direct replacement at this size, scoring 3,240,324 CoreMark/s against this instance's 2,704,225 — roughly 20% more throughput for the same vCPU count. Spot's node ladder tops out below this size, so hpc6a.48xlarge becomes 11 × ch.vs1.2xlarge (176 vCPU, 352 GiB combined), about 88% below the Asia Pacific (Sydney) on-demand rate. Spot delivers compute as managed Kubernetes, so a node pool of that size is the native shape of the answer rather than a workaround — provided the workload scales horizontally.
Match qualityScale-out match
hpc6a.48xlarge gives you 96 vCPU and 384 GiB in a single machine. The largest comparable Spot node, ch.vs1.2xlarge, is 16 vCPU and 32 GiB, so the equivalent here is 11 nodes rather than one.
Spot runs as managed Kubernetes, so a 11-node pool is the normal way to run things rather than a workaround. If your workload already sits behind a load balancer, a queue or a scheduler, it spreads across them without changes. If it needs all 96 cores and 384 GiB in one process, it does not.
