Docker --gpus all but nvidia-smi indicated me NVIDIA-SMI couldn't find...
Hey fellas , OS is centOS7.9 I was deploying a pytorch docker on it. while executing nvidia-smi,I got the correct result. BUT,when I use "docker run -it --gpus all In the docker i executed...
View ArticleTensorRT-8.0.1.6.Windows10.x86_64.cuda-10.2.cudnn8.2 python folder missing
Hi, there~ I was trying to install the tensorrt8.0.1.6 onto my windows10 computer with cuda 10.2 <to meet the jetson nano tensorrt version with 8.0.1.6 + cuda1.2> I was following the instruction...
View ArticleSuggest to add PC of kernel launch
Hi, I found that when I subscribe callbacks for kernel launch, the callback data Sanitizer_LaunchData doesn’t include the PC of the kernel. How can I get the current launched kernel’s start PC? If it...
View ArticleHow i find stopped vehicle label in deepstream python apps
Embeded device:jetson Nano 4gb jetpack version:4.5.1 cuda version:10.2.89 SDK:deepstream-5.1 python code:deepstream python apps video analytics ubuntu 18.04 LTS TensorRT:7.1.3.1 In deepstream python...
View ArticleCuda memory pool not thread safe?
Hi forum, I suspect that this is a bug or am I using it wrong? I’m trying to use the cudaMemPool in a multithreaded setup. #include <pthread.h> #include <iostream> #include <string>...
View ArticleGpu dynamic array coping back to host
hey guys I’m pretty new to cuda I expect this code to copy the first row from gpu into my host pointer I’m looking for a way to copy a 2d dynamic gpu array back to host array ps : i already know if i...
View ArticleSpark
Hi, I would like to use spark with Rapids. however, I didn’t found guide for how to measure on a single node. when I try to measure it on EMR using aws guide here: docs.aws.amazon.com Use the Nvidia...
View ArticleMultiple streams on 1 GPU and out of memory error
I’m running multiple streams across multiple GPUs. I have more streams (dozens) than devices (4). I assign the streams to the devices round robin style. The streams run concurrently on the GPUs as...
View ArticleCompute-sanitizer not quite a drop-in replacement of cuda-memcheck
Hi, Given the deprecation notice of cuda-memcheck, we are trying to port over to compute-sanitizer. However we notice that it’s not at all a drop-in replacement: On default launch, we get this error:...
View ArticleGpio and input
Hello dear: How can i use the pins of 3,5,27,28, to use for gpio and input and are not use for i2c ??? 3 posts - 2 participants Read full topic
View ArticleCUDA compute-sanitizer internal error: CUDA initialized before the Sanitizer
I’m trying to run compute-sanitizer on two systems: a docker with CUDA 11.2 and a cluster with CUDA 11.7. On both systems, whenever I’m running compute-sanitizer (with any arguments, although I’m...
View ArticleCompute-sanitizer consumes too much GPU memory, causing it unusable
I’m running a pytorch+tensorrt program on Tesla T4 GPU, with cuda 11.3, driver 460. It seems compute-sanitizer consumes an extra about 8GB memory, and making me encountering OOM problem every time....
View ArticleCompute sanitizer unable to attach to MPI processes
Hello, I have been working on a project that uses Intel MPI to spread work out over multi-gpu Azure nodes. Usually, the executable is run like this in a PBS file: mpiexec -s all -np 8 -machinefile...
View ArticleInconsistent results from cuda-memcheck and compute-sanitizer --tool memcheck
As I ran compute-sanitizer --tool memcheck ./TestRtcmReader.x86-64 ../jobs/mixed/24, I got ========= ERROR SUMMARY: 0 errors. On the other hand, as I ran cuda-memcheck ./TestRtcmReader.x86-64...
View ArticleRunning compute-sanitizer within a docker container
I couldn’t find any information on running compute-sanitizer from within a docker container. The following works fine outside of the container. Within the container sample executes correctly and...
View ArticleCompute Sanitizer for OpenAcc and OpenMPI
We wrote a program with OpenAcc and OpenMPI, and wanted to check possible GPU memory leak. In this program, CUDA functions like cuMemAlloc, cuPointerGetAttribute etc are loaded dynamically with...
View ArticleCompute Sanitizer not able to detect memory leak when using cuMemAlloc and...
I found a bug from CUDA-memcheck and Compute Sanitizer, that they can’t detect memory leak when using cuMemAlloc and OpenACC. compiler: nvhpc/22.5 MPI: OpenMPI/4.1.4 source code #include...
View ArticleCompute sanitizer hangs indefinitely while cuda-memcheck works as is
Compute sanitizer hangs indefinitely when a runtime conditional (graph->seq) is true and a cudaMemcpy is performed (unless cudaDeviceSynchronize added), while cuda-memcheck works as is whether the...
View ArticleCompute-sanitizer error : Target application terminated before first...
Hi, I am trying to use compute-sanitizer on my app (CUDA12.1 - windows 10 ): .\compute-sanitizer.exe --launch-timeout 0 --target-processes all --print-level info --tool memcheck app.exe That’s what...
View ArticleThe leak-check tool does not show the information of source code and line number
I tried to use the following samples. GitHub GitHub - NVIDIA/compute-sanitizer-samples: Samples demonstrating how to use... Samples demonstrating how to use the Compute Sanitizer Tools and Public API...
View Article
More Pages to Explore .....