FirePro S10000 delivers 1.48 TFLOPS of double-precision floating-point calculations
AMD has launched new server graphics card, FirePro S10000, which the company said is designed for high-performance computing (HPC) workloads and graphics intensive applications.
The new professional-grade card exceeds one teraFLOPS (TFLOPS) of double-precision floating-point performance, brings a 5.91 TFLOPS of peak single-precision and 1.48 TFLOPS of double-precision floating-point calculations, the company said.
Additionally, the FirePro S10000 is also suitable for virtual desktop infrastructure (VDI) and workstation graphics deployments.
FirePro S10000 comes equipped with AMD next-generation Graphics Core Next Architecture and brings high performance computing and visualisation to several disciplines such as finance, oil exploration, aeronautics, automotive design and engineering, geophysics, life sciences, medicine and defense.
With two powerful GPUs in one dual-slot card, the FirePro S10000 enables high GPU density in the data center for VDI and helps increase overall processing performance.
The two on-board GPUs can help IT managers with cost savings, replacing the need to purchase two single ultra-high-end graphics cards and also reduces total cost of ownership (TCO) due to lower power and cooling expenses.
AMD Professional Graphics senior director and general manager David Cummings said: "The AMD FirePro S10000, equipped with our Graphics Core Next Architecture, enables server graphics to play a dual role in providing both compute and graphics horsepower simultaneously."
The new dual-GPU server graphics card delivers up to 1.3 times the single precision and up to 7.8 times peak double-precision floating-point performance of the competition’s comparable dual-GPU product.
AMD FirePro S10000 delivers 3.94 gigaFLOPS of peak double-precision performance-per-watt, up to 1.5 times the memory bandwidth of the competing dual-GPU application and comes equipped with a 6GB GDDR5 frame buffer and a 384-bit interface.
It also features DirectGMA support to remove CPU bandwidth and latency bottlenecks, optimising communication between both GPUs and OpenCL support that offers the advantage of combined parallel processing capabilities of the FirePro S10000.