AMD has just announced another monster graphics card. The new FirePro S9300 X2 is AMD's second-fastest graphics card and it is targeted at servers and supercomputers. The FirePro S9300 X2 is the latest entry into the FirePro S series lineup, and packs two Fiji 28nm GPUs. The 300W card is clocked at 850MHz, giving the card a theoretical 13.9 TFLOPs of FP32 compute performance. That's shy of the 16 teraflop performance provided by the recently announced Radeon Pro Duo, a gaming GPU that AMD claims offers the highest performance of any single graphics card. It has 8GB of HBM (High-Bandwidth Memory), which is significantly faster than the older GDDR5 memory. Each GPU is getting 512GB/sec of memory bandwidth, for an aggregate 1TB/sec of bandwidth.

The FirePro is AMD's latest salvo on Nvidia, whose Titan X, with a single GPU, delivers peak performance of 7 teraflops.

The importance GPUs has grown in supercomputing. GPUs typically take code and break it down in parallel over thousands of cores to process a task or calculate an equation more quickly. Nvidia's success in high performance computing (HPC) has come partly with its proprietary CUDA parallel programming framework, which has locked supercomputers to the company's GPUs.

AMD has been relying on the open-source OpenCL parallel programming framework, and hopes to make HPC coding easier with GPUOpen.

The S9300 X2 will be shipping this quarter with an MSRP of $5999.

AMD also plans to ship the S9100 series cards this year. This one will be based on AMD?s Hawaii GPU and will also offer HPC-centric features such as ECC memory and high performance FP64.

Later this year, AMD will also announce graphics improvements of its own with GPUs based on its upcoming Polaris architecture, which will further intensify the graphics battle.

Nvidia is expected to announce faster GPU technologies at its GPU Technology Conference next week. The technology enhancements could include a new GPU architecture, advanced memory and faster throughput mechanisms.