Huygens GPU acceleration options
This page gives an overview of NVIDIA cards that can be used in combination with the Small, Medium, Large or Extreme GPU option in the latest version of Huygens for GPU acceleration. Over time this page will be refreshed, for a category overview of cards working with older versions of Huygens, please contact support at svi.nl
For cards that are not included in this page: the option that is required in your license will depend on the amount of CUDA cores and amount of RAM that the card has according to the following specifications:
Small GPU option: for cards that have up to 1024 CUDA cores and up to 2 GB of RAM (included with every Huygens license Free of Charge)
Medium GPU option: for cards that have up to 3072 CUDA cores and up to 4 GB of RAM.
Large GPU option: for cards that have up to 8192 CUDA cores and up to 24 GB of RAM.
Extreme GPU option: for cards that have up to 24576 CUDA cores and up to 64 GB of RAM.
Small GPU cards
The Small GPU option is required in your Huygens license in order to use small GPU cards. The small GPU option is included in every Huygens base license from 15.10 and later. Download the latest Huygens now.GPU card | CUDA cores | RAM |
---|---|---|
GeForce GTX 1050 Ti | 768 | 4GB |
GeForce GTX 1050 (3GB) | 768 | 3GB |
GeForce GTX 1050 (2GB) | 640 | 2GB |
GeForce GTX 960 | 1024 | 2GB |
GeForce GTX 950 | 786 | 2GB |
GeForce GTX 770 | 1536 | 2GB |
GeForce GTX 760 | 1152 | 2GB |
GeForce GTX 750 Ti | 640 | 2 GB |
GeForce GTX 750 | 512 | 1GB or 2 GB |
GeForce GTX 745 | 384 | 2GB or 4 GB |
Quadro P1000 | 640 | 4GB |
Quadro M2000 | 768 | 4GB |
Quadro K4000 | 768 | 3GB |
Quadro K2200 | 640 | 4GB |
Quadro K2000 | 384 | 2GB |
Medium GPU cards
The Medium GPU option is required in your Huygens license in order to use medium GPU cards. Request QuoteGPU card | CUDA cores | RAM |
---|---|---|
GeForce RTX 2060 | 1920 | 6GB |
GeForce GTX 1060 6GB | 1280 | 6GB |
GeForce GTX 1060 3GB | 1280 | 3GB |
GeForce GTX 980 | 2048 | 4GB |
GeForce GTX 970 | 1664 | 4GB |
GeForce GTX 780 Ti | 2880 | 3GB |
GeForce GTX 780 | 2304 | 3GB |
Quadro P2000 | 1024 | 5GB |
Quadro K5000 | 1536 | 4GB |
Quadro K4200 | 1344 | 4GB |
Large GPU cards
Large GPU option is required in your license in order to use Large GPU cards. Request QuoteGPU card | CUDA cores | RAM |
---|---|---|
Titan RTX | 4608 | 24GB |
Titan V | 5120 | 12GB |
Titan-Xp (Pascal Generation) | 3584 | 12GB |
GeForce GTX Titan-X | 3072 | 12GB |
GeForce RTX 2080 Ti | 4352 | 11GB |
GeForce RTX 2080 | 2944 | 8GB |
GeForce RTX 2070 | 2304 | 8GB |
GeForce GTX 1080 Ti | 3584 | 11GB |
GeForce GTX 1080 | 2560 | 8GB |
GeForce GTX 1070 Ti | 2432 | 8GB |
GeForce GTX 1070 | 1920 | 8GB |
GeForce GTX 980 Ti | 2816 | 6GB |
Tesla V100 (16GB version) | 5120 | 16GB |
Tesla P100 | 3584 | 16GB |
Tesla P100 NVLINK | 3584 | 16GB |
Tesla P40 | 3840 | 24GB |
Tesla M60 | 4096 | 16 GB |
Tesla M40 | 3072 | 12GB or 24 GB |
Tesla K80 | 4992 | 2 x 12GB |
Tesla K40 | 2880 | 12GB |
Tesla K20 | 2496 | 5GB |
Quadro GP100 | 3584 | 16GB |
Quadro RTX 6000 | 4608 | 24GB |
Quadro RTX 5000 | 3072 | 16GB |
Quadro RTX 4000 | 2304 | 8GB |
Quadro P6000 | 3840 | 24GB |
Quadro P5000 | 2560 | 16GB |
Quadro P4000 | 1792 | 8GB |
Quadro M6000 24GB | 3072 | 24GB |
Quadro M6000 | 3072 | 12GB |
Quadro M5000 | 2048 | 8GB |
Quadro M4000 | 1664 | 8GB |
Quadro K6000 | 2880 | 12GB |
Quadro K5200 | 2304 | 8GB |
Extreme GPU cards
Extreme GPU option is required in your license in order to use the GPU cards below. Request QuoteGPU card | CUDA cores | RAM |
---|---|---|
Tesla V100 (32GB version) | 5120 | 32GB |
Quadro RTX 8000 | 4608 | 48GB |
Quadro GV100 | 5120 | 32GB |
Titan V CEO Edition | 5120 | 32GB |
Multi-GPU acceleration with Performance options
Besides the GPU options for Huygens, SVI also offers Performance options. For the use of multi-GPU acceleration the Performance Plus, Mega or Extreme option is needed. With Huygens version 16.10.0p8, multi-GPU support has been introduced in the Batch Processor and Huygens Core to perform deconvolution of a queue of images on multiple GPU devices simultaneously. With Huygens 17.10 (Linux) and Huygens 18.04 (Windows), support is added for running a single image deconvolution on multiple GPUs in Huygens Professional. We offer the following performance packages to get the most out of your workstation:Performance Option: Standard included in Huygens for using up to 6 CPU cores (12 logical when hyper-threaded) and 1 Small GPU card.
Performance Plus: Allows you to use up to 12 CPU cores (24 logical cores when hyper-threaded) and 2 Large GPU cards.
Performance Mega: Allows you to use up to 24 CPU cores (48 logical cores when hyper-threaded) and 4 Large GPU cards.
Performance Extreme: Allows you to use up to 48 CPU cores (96 logical cores when hyper-threaded) and 8 Large GPU cards.
Below is a table that shows which options and commands in Huygens can use single GPU acceleration or multi-GPU acceleration in batch mode.
Accelerated with GPU (CUDA) | |
---|---|
Deconvolution algorithms | |
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 |
Tikhonov-Miller deconvolution | |
Batch Processor | + Multi GPU support |
Deconvolution Wizard | |
Deconvolution Express | |
Batch Express | |
Registration & Deconvolution | |
Object Stabilizer | + Multi GPU support: Batch Processor |
Chromatic Aberration Corrector | + Multi GPU support: Batch Processor |
Stitching & Decon Wizard | |
Light-Sheet Decon & Fusion Wizard | |
Visualization & Analysis | |
2D slice renderers | |
Colocalization Analysis | Since v.18.10 + Multi GPU support: HuCore/HRM since v.18.10 |
Image processing commands | |
Image processing filters (min, max, variance, ppu, avg, gauss) | |
Image properties 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) | Since v.18.10 |