# How to overcome the huge increase of windows dlls - minimum cuda/cudnn builds that support Ampere? **URL:** \ **Category:** cuDNN\ **Created:** [June 14, 2022, 9:45am UTC](https://forums.developer.nvidia.com/t/how-to-overcome-the-huge-increase-of-windows-dlls-minimum-cuda-cudnn-builds-that-support-ampere/217580 "2022-06-14T09:45:52Z")\ **Posts on this page:** 8\ **Page:** 1
**Author:** ![\_PM](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/_pm/32/20210_2.png) [@\_PM](https://forums.developer.nvidia.com/u/_PM)\ **Post date:** [June 14, 2022, 9:45am UTC](https://forums.developer.nvidia.com/t/how-to-overcome-the-huge-increase-of-windows-dlls-minimum-cuda-cudnn-builds-that-support-ampere/217580/1 "2022-06-14T09:45:52Z")
I’m upgrading from Cuda 10.x to 11.x in order to support Ampere cards for a Windows application. However not only the required cublas/cublasLt dlls went through a x5 size increase and still grow by tens of megabytes with each update but the cuddn\*infer.dll also increased drastically in size. I suppose that the trend is to optimize by hardcoding thousands of specialized kernels but this has really gone out of control! ![image](https://global.discourse-cdn.com/nvidia/original/3X/e/4/e4783637b1dbaabc1d0a39c797d8fa808b35c7fc.png) ![image](https://global.discourse-cdn.com/nvidia/original/3X/7/5/7511b6b73a9acafb9ffc3b2ec1bbffaf9f731dd9.png) I plotted the total size of biggest files I need to redistribute for an OpenCV based application. It went from 152MB (7zipped) to 389MB! ![image](https://global.discourse-cdn.com/nvidia/original/3X/1/2/124a985cebbe852f4f0348f3c01638df1590e3c9.png) So I was wondering 1. what is the mimimum package that supports compute\_86? I was expecting support from Cuda 11.0 but nvcc rejects anything above compute\_80. Is Cuda 11.1 the minimum 2. are there any problems to expect when using older builds? say Cuda 11.2.2 w/ cudnn 8.1.1 ---
**Author:** ![\_PM](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/_pm/32/20210_2.png) [@\_PM](https://forums.developer.nvidia.com/u/_PM)\ **Post date:** [June 21, 2022, 8:22am UTC](https://forums.developer.nvidia.com/t/how-to-overcome-the-huge-increase-of-windows-dlls-minimum-cuda-cudnn-builds-that-support-ampere/217580/2 "2022-06-21T08:22:53Z")
Any change to get an official reply on support of Ampere in Cuda 11.0/11.1? @jhalabi maybe? ---
**Author:** ![spolisetty](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/spolisetty/32/14047_2.png) [@spolisetty](https://forums.developer.nvidia.com/u/spolisetty)\ **Post date:** [June 21, 2022, 9:04am UTC](https://forums.developer.nvidia.com/t/how-to-overcome-the-huge-increase-of-windows-dlls-minimum-cuda-cudnn-builds-that-support-ampere/217580/3 "2022-06-21T09:04:53Z")
Hi, From CUDA 11.0 onwards support Ampere. Please refer to the support matrix doc to get more info. > **[Support Matrix :: NVIDIA Deep Learning cuDNN Documentation](https://docs.nvidia.com/deeplearning/cudnn/support-matrix/index.html)** > > These support matrices provide a look into the supported versions of the OS, NVIDIA CUDA, the CUDA driver, and the hardware for the NVIDIA cuDNN 8.5.0 release. Could you please let us know which steps are you following to upgrade CUDA. Have you tried uninstalling the old version and installing the new version again. Did it solve the problem? ---
**Author:** ![\_PM](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/_pm/32/20210_2.png) [@\_PM](https://forums.developer.nvidia.com/u/_PM)\ **Post date:** [June 21, 2022, 10:19am UTC](https://forums.developer.nvidia.com/t/how-to-overcome-the-huge-increase-of-windows-dlls-minimum-cuda-cudnn-builds-that-support-ampere/217580/4 "2022-06-21T10:19:40Z")
@spolisetty thank you for your reply I have tried 11.0, 11.1 up to 11.7 With the latter: nvcc rejects compiling with sm\_86, looking at the help ![image](https://global.discourse-cdn.com/nvidia/original/3X/3/0/304944c9c6546f5c49549511873ee7471b063ac3.png) ---
**Author:** ![\_PM](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/_pm/32/20210_2.png) [@\_PM](https://forums.developer.nvidia.com/u/_PM)\ **Post date:** [June 27, 2022, 9:55am UTC](https://forums.developer.nvidia.com/t/how-to-overcome-the-huge-increase-of-windows-dlls-minimum-cuda-cudnn-builds-that-support-ampere/217580/5 "2022-06-27T09:55:45Z")
Have I done anything wrong @spolisetty ? ---
**Author:** ![spolisetty](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/spolisetty/32/14047_2.png) [@spolisetty](https://forums.developer.nvidia.com/u/spolisetty)\ **Post date:** [June 29, 2022, 10:12am UTC](https://forums.developer.nvidia.com/t/how-to-overcome-the-huge-increase-of-windows-dlls-minimum-cuda-cudnn-builds-that-support-ampere/217580/6 "2022-06-29T10:12:48Z")
Hi, Please make sure you’re following the correct installation steps by following the official doc and also please make sure CUDA is installed correctly. > **[Installation Guide :: NVIDIA Deep Learning cuDNN Documentation](https://docs.nvidia.com/deeplearning/cudnn/install-guide/index.html#install-windows)** > > This cuDNN 8.5.0 Installation Guide provides step-by-step instructions on how to install and check for correct operation of NVIDIA cuDNN on Linux and Microsoft Windows systems. Please uninstall the old package completely and try a fresh installation. Thank you. ---
**Author:** ![\_PM](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/_pm/32/20210_2.png) [@\_PM](https://forums.developer.nvidia.com/u/_PM)\ **Post date:** [June 29, 2022, 10:16pm UTC](https://forums.developer.nvidia.com/t/how-to-overcome-the-huge-increase-of-windows-dlls-minimum-cuda-cudnn-builds-that-support-ampere/217580/7 "2022-06-29T22:16:31Z")
@spolisetty I will try once again. Looking carefully at the release notes, cuda 11.0 adds partial Ampere compatibility (sm\_80) [Release Notes :: CUDA Toolkit Documentation](https://docs.nvidia.com/cuda/archive/11.0/cuda-toolkit-release-notes/index.html#cuda-general-new-features) > CUDA 11.0 adds support for the NVIDIA Ampere GPU microarchitecture (compute\_80 and sm\_80). sm\_86 requires at least cuda 11.1: [Release Notes :: CUDA Toolkit Documentation](https://docs.nvidia.com/cuda/archive/11.1.0/cuda-toolkit-release-notes/index.html#cuda-general-new-features) > Added support for NVIDIA Ampere GPU architecture based GA10x GPUs GPUs (compute capability 8.6), including the GeForce RTX-30 series. ---
**Author:** ![\_PM](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/_pm/32/20210_2.png) [@\_PM](https://forums.developer.nvidia.com/u/_PM)\ **Post date:** [December 2, 2022, 4:53pm UTC](https://forums.developer.nvidia.com/t/how-to-overcome-the-huge-increase-of-windows-dlls-minimum-cuda-cudnn-builds-that-support-ampere/217580/8 "2022-12-02T16:53:14Z")
@spolisetty Since my last message, I’ve seen in the release notes that Nvidia wanted to better split dlls in order to mitigate the size increase. I also so that release 8.5.0 had slightly smaller dlls. However today I gave a look at cuda 11.8 + cudnn8.7.0 and again it’s a huge increase over previous version. Is there any official word addressing that issue? Because redistributing programs with cuda supports becomes more and more difficult due to the size of the libraries ![image](https://global.discourse-cdn.com/nvidia/original/3X/8/2/82348f5a5af07d8ad2df0969c224e0aa9e0cebe3.png)