cuda-samples

cuda-samples copied to clipboard

Recently, I have done some performance optimization work. i used zero copy memory in my work. but i met a strange phenomenon. I have a custom struct array, and i...

GeneralJing

Does cuda support allocate meomory in one thread and use cuMemGetAddressRange to check that buffer range

2

changchengx

Is there any practical examples that uses L2 residency control or async copy introduced in CUDA 11?

xuantengh

I've run this sample on 2070super and 3090, the Naive kernel is always the fastest method for both GPUs. What's your purpose for this sample? A redundant and slow way...

JustLuoyu

Hello, I have a problem with installing OpenPose on my computer. After building files (using CMake), I entered a build folder in OpenPose documentation and wrote command in terminal: make...

STawor-coder

Shouldn't this be using GENERIC_ALL? According to https://www.khronos.org/registry/vulkan/specs/1.2-extensions/man/html/VkExportSemaphoreWin32HandleInfoKHR.html looks like those flags shouldn't be DXGI flags... https://github.com/NVIDIA/cuda-samples/blob/1f76a2d110b1d251896b7a4d20998328761ad168/Samples/simpleVulkanMMAP/VulkanBaseApp.cpp#L1461

jacereda

undefined reference to `cudaSignalExternalSemaphoresAsync_v2'

1

I am trying to build the `/NVIDIA_CUDA-11.4_Samples` and I have the following error. ``` >>> GCC Version is greater or equal to 5.1.0

fabrizioschiano

cudaGraph and cublas

1

how to add cublas sgemm to cudaGraph by cudaGraphAddKernelNode?

zkh2016

I'm sharing my experience including a small suggestion regarding buffer management and behavior of 'cuda-samples/Samples/bandwidthTest' under a GPU virtualization solution (Bitfusion, in my case). I hope this is useful for...

thatsdone

I have installed tensorflow 2.5.0 using pip command, installed cuda 11.2 and cudnn 8.1.1. GCC version -7.3.1 Bazel version - 3.7.2 Its a Linux server with RHEL 7.6 . I...

Poornni