Designed for DGEMM heavy double-precision workloads the card supports OpenCL 2.0 and is based on the second-generation AMD Graphics Core Next (GCN) GPU architecture.

All this means the AMD FirePro server GPU family can manage 5.24 TFLOPS of peak single precision compute performance when it is going downhill and the wind is behind it.

With the double precision performance button switched on it can manage 2.62 TFLOPS.

Obviously this is not going to power games, and is designed with compute-intensive workflows in mind – data centre manages and those needing to calculate big numbers, like the amount of cash that Greece owes the rest of the world.

Sean Burke, corporate vice president and general manager, AMD Professional Graphics group said:

 "The AMD FirePro S9170 server GPU can accelerate complex workloads in scientific computing, data analytics, or seismic processing, wielding an industry-leading 32GB of memory. We designed the new offering for supercomputers to achieve massive compute performance while maximizing available power budgets."

The AMD FirePro S9170 is the industry's first server GPU with 32GB ultra-fast GDDR5 on-board memory and features a 512-bit memory interface for 320 GB/s of memory bandwidth,

It should be out sometime in the third quarter and no word on price yet.