AMD today announced the new AMD FirePro S9170 server GPU, a 32GB single-GPU server card for DGEMM heavy double-precision workloads, with support for OpenCL 2.0. Based on the second-generation AMD Graphics Core Next (GCN) GPU architecture, this new addition to the AMD FirePro server GPU family is equipped with 32GB GDDR5 on-board memory and features a 512-bit memory interface for 320 GB/s of memory bandwidth. It is capable of delivering up to 5.24 TFLOPS of peak single precision compute performance while enabling full throughput double precision performance, providing up to 2.62 TFLOPS of peak double precision performance.

With up to 2.62 TFLOPS of peak double precision performance, the AMD FirePro S9170 is the fastest single-GPU server card available for DGEMM heavy workloads, delivering up to 40% more performance than the Nvidia's Tesla K40 (1.43 TFLOPS peak double precision performance) Nvidia's highest performing dual-GPU server card in the market as of May 2015 is the Tesla K80, with up to 1.87 TFLOPS of peak double precision performance.

AMD also claims that the AMD FirePro S9170 support a 40% better double precision performance, while using 10% less power than the competition. The FirePro S9170 max power is 275W. Nvidia's highest performing single-GPU server card in the market as of May 2015 is the Tesla K40, max power of 235W, with up to 1.43 TFLOPS peak double precision performance. Nvidia's highest performing dual-GPU server card in the market as of May 2015 is the Tesla K80, max power of 300W, with up to 1.87 TFLOPS of peak double precision performance.

To address future needs for HPC development, AMD FirePro S9170 server GPU supports the latest version of OpenCL while ready for the OpenMP and OpenACC developer tools with planned availability in Q3 2015.

Specifications

Cooling/Power/Form Factor

• Max Power: 275W
• Bus Interface: PCIe x16
• Slots: Two
• Form Factor: Full height/ Full length
• Cooling: Passive heat sink