Huygens (Multi) GPU acceleration:
Why wait? Accelerate your research now by using the power of GPUs!
*Acceleration Factor with respect to an Intel Core i5-3330 CPU (which has an acceleration factor of 1). Full benchmark specifications can be found here.
Reliable and high-quality
Reliable high-quality results, including spherical aberration correction. Just like Huygens CPU processing, yet much faster!
Save precious time in your image post-processing workflow by accelerated deconvolution.
Large files & High Throughput
Deconvolve large files faster and enable rapid high-throughput Multi-GPU batch processing.
Huygens GPU deconvolution: Fast high-quality results!
The Huygens Software is well known for its fast processing and high-quality deconvolution results. With the new GPU acceleration option you obtain the same high-quality results, yet even faster! Realize amazing deconvolution results within seconds using high-end NVIDIA GPU cards and the powerful Huygens deconvolution algorithms. The unique brick-splitting possibility is also available in the GPU mode, enabling you to deconvolve very large files on the GPU, even with cards with limited video-RAM. In addition, the algorithm is able to accurately correct for spherical aberration in case of refractive index mismatch.
GPU cardsDownload Now!
CPU vs GPU: what's the difference?
The Central Processing Unit (CPU) often consists of multiple individual Cores (typical 2-10 cores per CPU). The different cores can process different tasks in parallel. By using multiple cores in parallel this can speed up processes, such as deconvolution. The Graphic Processing Unit (GPU) was primarily designed for handling graphics processing, notably in the gaming industry. The rapid development in GPUs over the past few years has led to powerful GPU cards that at present contain hundreds to thousands of individual cores per chip. In addition, current cards contain a significant amount of onboard video-RAM. In combination with the NVIDIA CUDA programming model, this has made the NVIDIA GPUs extremely suitable for performance increase in scientific computations. The Huygens deconvolution can combine the processing of NVIDIA CUDA GPUs with CPU processing to accelerate the Huygens deconvolution significantly.
GPU acceleration: How does GPU acceleration work?
With GPU acceleration, a small section of the application code that requires significant computation time is run on the GPU, while the remainder of the code is run on the CPU. The GPU consists of hundreds or even thousand of separate processing units (cores), thereby making it extremely efficient and fast to process compute intensive code. With Huygens 15.10, we have introduced the possibility to utilize these powerful NVIDIA CUDA enabled GPU's to accelerate the Huygens deconvolution.
Can I benefit from (multi-GPU) acceleration?: Accelerate your research!
GPU acceleration is supported for all our powerful Huygens MLE algorithms. In addition, (multi)GPU acceleration is now also supported in various other Huygens modules and processing commands, which can save a significant amount of image processing time in your entire image processing workflow. The table below shows an overview of which options and commands in Huygens currently support acceleration using a single GPU card, and which options can benifit from running multiple jobs in parallel in batch mode. A Performance option can be added to your Huygens license to make use of up to 8 GPU cards in parallel.
Accelerated with GPU (CUDA)
|CMLE deconvolution||+ Multi GPU support: Operation Window, Batch Processor & Scripting|
|QMLE deconvolution||+ Multi GPU support: Operation Window, Batch Processor & Scripting|
|GMLE deconvolution||+ Multi GPU support: Operation Window, Batch Processor & Scripting|
|Batch Processor||+ Multi GPU support|
|Localization algorithms for Huygens Localizer|
|MLE particle fitting|
|LSQ particle fitting|
|Center of mass particle fitting|
|Registration & Deconvolution|
|Object Stabilizer||+ Multi GPU support: Batch Processor|
|Drift correction||+ Multi GPU support: Batch Processor|
|Stitching & Decon Wizard||+ Multi GPU support: HuCore/HRM|
|Light-Sheet Decon & Fusion Wizard|
|Image processing commands|
|Image processing fitlers (min, max, variance ppu, avg, gauss)|
|Image properites functions (hist, stat, range)|
|Image processing commands 1 (estbg, phaseCorr)|
|Image processing commands 2 (getpix, setpix, cp, slice, multiMip, miniMip, sum)|
|Image processing commands 3 (shift, resample, mirror, hist2ch, label, perc, optrep)|
|Visualization & Analysis|
|2D slice renderers|
|3D SFP renderer||Since v.19.04|
|3D MIP renderer||Since v.19.04|
|3D Surface renderer||Since v.19.04|
|Colocalization Analysis||+ Multi GPU support: HuCore/HRM|
|Object Analyzer||GPU support for labeling and rendering|
Get started: Experience the acceleration yourself!
Why wait? Experience the significant performance increase yourself, and request a free trial license to try out the Huygens GPU acceleration option. We offer different options that can be added to your Huygens license, depending on the performance of your NVIDIA GPU card (compute capability 3.0 or higher is required):
In addition, we offer Performance options, which allow the use of multiple GPU cards in parallel in the batch processor, operation window, scripting and in Huygens Core/HRM. It is possible to license up license the use of 2, 4 or 8 GPU cards in parallel by adding a Performance option to your license. A list of cards that can be used for each of these options can be found here. Click here for detailed instructions on how to get started with the Huygens GPU acceleration. If you would like to run a benchmark yourself, please visit our GPU benchmarks page. You can find a GPU checklist at this webpage. You can also request a quote or contact us for more information about the option best suited for your hardware and image processing needs.
Request QuoteDownload Now!