Multi-GPU Technology

Visualize and Process at the same time on a Single System. NVIDIA® Multi-GPU Technology


As energy companies push the boundaries of technology to find oil and gas fields more cost effectively, the scope and complexity of seismic data processing and interpretation are growing exponentially. At stake is the ability to extract value from this large volume of seismic data to reduce uncertainties, improve the accuracy of reservoir predictions, and mitigate the risk associated with expensive drilling and production activities.

The speed and accuracy of seismic interpretation are critical in the exploration workflow. However, traditional interpretation methods are increasingly challenged by the volume of data, fewer experts in the industry, and the influx of new hires pushing innovation for personal productivity such as augmented reality and auto-extraction.

Multi-GPU Technology boosts scalability through the use of two or more professional GPUs for visualization and heavy computation. This improves real-time calculation of seismic trace attributes and visual analysis of complex regional basins right at the interpreter's desk. The result is dramatically reduced model processing cycle times and sharper images of region-of-interest datasets leading to more effective lease bidding, higher service revenues, and ultimately greater chances of striking oil.


NVIDIA engineers work closely with software vendors to ensure that multiple GPUs will function with all the speed, functionality, and reliability users demand.

Application Category Benefits of Multiple GPUs
Paradigm- VoxelGeo Interpretation and Modeling Faster computations in CUDA
TerraSpark- InsideEarth Interpretation and Modeling Faster computations in CUDA
ffA- GeoTeric Interpretation and Modeling Faster computations in OpenCL
Hue- Headwave Interpretation and Modeling Faster computations in CUDA


"Paradigm actively seeks to take advantage of new hardware technologies, such as NVIDIA Maximus technology, to improve our customers' performance and efficiency. By significantly accelerating the calculation of seismic trace attributes, interpreters can evaluate new workflows and practices to gain more from their seismic data investment."
Laura Evins
Product manager of seismic attributes at Paradigm

"aAFE delivers the most accurate fault interpretation results in the industry, but there is some inconvenience to users waiting on day-long processing tasks, even though they are saving weeks of tedious fault interpretation. GPU computing has taken away that hurdle, reducing processing times by a factor of more than 10x. Utilizing just a Quadro 6000 graphics card, the process already will execute in just a few hours; by adding NVIDIA Maximus technology that adds the NVIDIA Tesla co-processor, our customers will realize a further, dramatic reduction in compute times."
Philip Neri,
Vice President of Marketing at TerraSpark.

"Geological Expression is all about maximising the amount of geological information that you can rapidly extract from 3D seismic. We've been working across multiple Quadro and Tesla GPUs in our workstations to do this for some time. Now, with NVIDIA Maximus certification for GeoTeric, and the additional supporting technology that comes with it, it is much easier for our clients to procure the Geological Expression platforms that are going to take their interpretation workflows to new levels of productivity."
Steve Purves
Director of Technology at ffA

Multi-GPU Technology Resources


Kepler SMX processing

Higher performance and efficiency achieved with SMX by increasing processing cores while reducing control logic.

Dynamic Parallelism

Dynamic Parallelism on Kepler GPU dynamically spawns new threads by adapting to the data without going back to the CPU, greatly simplifying GPU programming and accelerating a broader set of popular algorithms.


With Dynamic Parallelism, the grid resolution could be determined dynamically at runtime. The simulation can "zoom in" on areas of interest and avoid unnecessary calculation in areas with little change.


Kepler's Hyper-Q increases GPU utilization by providing streams access to 32 independent hardware work queues or MPI ranks leading to advanced programmability and efficiency.


Hyper-Q enables multiple CPU cores to launch work on a single GPU simultaneously, thereby dramatically increasing GPU utilization and slashing CPU idle times.

Bindless Textures



Caption about visible aliasing and higher image quality