NVIDIA have announced that the second generation of their innovative Maximus platform will be up and running in December. Powered by NVIDIA’s new Kepler-based GPUs, the Quadro K5000 and the Tesla K20, Maximus promises faster, better graphics performance for anyone from mograph artists to prospective oil barons.
How does Maximus work?
Maximus technology allows a Tesla and Quadro card to work in parallel to crunch numbers and simulate or render graphics at the same time, reducing the workload of both the cards and your CPU and resulting in faster graphics performance.
The new GPUs
Over to Jigsaw24 3D consultant and resident Maximus expert, Ben Kitching, to explain why we should be getting excited about the Tesla K20 and the Quadro K5000. “The new Kepler-based cards have up to 3000+ CUDA cores – that’s six times as many as the previous high-end cards like the Quadro 6000 and Tesla C2075. The new cards also have SMX and dynamic parallelism, two new technologies that allow them to make more efficient use of those cores,” he explains.
“On top of this, there is the pioneering GPU virtualisation, which brings the long awaited dream of remote working to those needing to use high performace apps like Autodesk Maya or the Adobe suites. Imagine being able to remote into your high performance workstation from a MacBook Air and access your production data at full speed and quality as if you were sat in front of it.”
Other key features of the Quadro K5000 include:
- Bindless Textures that give users the ability to reference over 1 million textures directly in memory while reducing CPU overhead.
- FXAA/TXAA film-style anti-aliasing technologies for outstanding image quality.
- Increased frame buffer capacity of 4GB, plus a next-generation PCIe-3 bus interconnect that accelerates data movement by 2x compared with PCIe-2.
- An all-new display engine capable of driving up to four displays simultaneously with a single K5000.
- Display Port 1.2 support for resolutions up to 3840×2160 at 60Hz.
The Tesla K20 is no slouch either, adding SMX streaming technology that promises to deliver up to three times as much performance per watt, dynamic parallelism and Hyper-Q technology (we should probably point out that all these stats came from NVIDIA, and we haven’t been able to verify them independently).
When can I have one?
The Quadro K5000 will be available as a standalone desktop GPU from October (we’re trying to wrangle a demo unit before then, so keep your eyes peeled for benchmarks). The Tesla K20 and qualified Maximus-capable workstations are set to follow in December.