Nvidia targets users of simulation software with new double precision Quadro GP100 GPU

170 0

Nvidia has launched the Quadro GP100, a ‘Pascal’-based workstation GPU designed specifically for compute tasks, big news for users of simulation software, including Ansys and Abaqus.

This is the first compute focused workstation GPU that Nvidia has launched since the Kepler-based Quadro K6000 in 2013, with the Maxwell-based Quadro M6000 not tuned for double precision operations that are needed for Finite Element Analysis (FEA) or Computational Fluid Dynamics (CFD).

The Quadro GP100 features 3,584 CUDA FP 32 cores and 1,792 CUDA FP 32 cores, boasting peak single precision performance (FP 32) of 10.3 TFLOPS and peak double precision performance (FP 64) of 5.2 TFLOPs, which is more than double that of the Quadro K6000.
In addition to offering significantly bigger compute resources than the Quadro K6000, the Quadro GP100 features bigger and faster memory. With 16 GB of High Bandwidth Memory (HBM2), the GPU can read data at a rate up to 717 GB/sec, which should make it much faster to load complex engineering datasets.

While 16GB is an improvement over the Quadro K6000, the Quadro GP100’s memory footprint is not as big as the Quadro P6000 (24GB), which is tuned for graphics and not double precision floating point operations.

Those interested in larger memory capacities for handling more complex CAE problems will likely be interested in NVLink, a technology built into the Quadro GP100, which effectively allows two cards to be connected together for shared GPU resources and memory (up to 32GB).

However, software developers will need to optimise their code to take advantage of this technology.

Advertisement
Advertisement

The Quadro GP100 can also be used for interactive graphics, Virtual Reality and single precision compute tasks, such as physically-based rendering. It features four DisplayPort 1.4 connections and one DVI-D.

“Customers count on Dassault Systèmes’ simulation tools to easily create often massively detailed models, while minimizing cost and inefficiencies.

“We have seen significant acceleration of our Abaqus FEA software simulations on the new Quadro GP100, which helps unify traditional design and simulation workflows, and are eager for our customers tap into its power to gain a competitive advantage,” said Sumanth Kumar, VP growth, Simulia, Dassault Systèmes.

NVLink allows two Nvidia Quadro GP100 cards to be used together and share memory and compute resources.