AMD aims GPU-based server at supercomputers
The FirePro S9150 server card is AMD’s first server card to support enhanced double precision and break the 2.0 TFLOPS double precision barrier.
It has 16Gbyte of GDDR5 memory and a maximum power consumption of 235W.
It is typical for a supercomputer to be designed on a processing platform incorporating GPUs and co-processors as well as CPUs.
The software ecosystem includes support for OpenCL and will support OpenCL 2.0 planned later this year.
Microelectronics Research Group at the University of Bristol is testing the FirePro S9150 server card as an HPC GPU accelerator.
“We’re even more excited by the prospects of combining its raw compute performance with OpenCL 2.0 later this year,” said Simon McIntosh-Smith, head of the Microelectronics Research Group at the University of Bristol. “Our research benefits from an open and royalty-free API, and we’re committed to OpenCL to accelerate our computations. New features such as Shared Virtual Memory and Nested Parallelism will allow us to make even better use of GPUs to increase performance and efficiency.”
Tags: AMD, GPU, processors, supercomputers