Stack Overflow
Stack Overflow

Questions tagged [cuda-gdb]

CUDA-GDB is the NVIDIA tool for debugging CUDA applications running on Linux and Mac. CUDA-GDB is an extension to the x86-64 port of GDB, the GNU Project debugger.

From the CUDA-GDB documentation:

CUDA-GDB is the NVIDIA tool for debugging CUDA applications running on Linux and Mac. CUDA-GDB is an extension to the x86-64 port of GDB, the GNU Project debugger. The tool provides developers with a mechanism for debugging CUDA applications running on actual hardware. This enables developers to debug applications without the potential variations introduced by simulation and emulation environments.

CUDA-GDB runs on Linux and Mac OS X, 32-bit and 64-bit. CUDA-GDB is based on GDB 7.2 on both Linux and Mac OS X.

88 questions
1
vote
3 answers

Optimizing the solution of the 2D diffusion (heat) equation in CUDA

I have already checked earlier questions on SO about this issue but not able to see how it relates here. I am solving 2d diffusion equation with CUDA and it turns out that my GPU code is slower than its CPU counterpart. Here is my code: //kernel…
chatur
  • 2,365
  • 4
  • 24
  • 38
0
votes
0 answers

CUDA GDB not giving correct value at the end of large array

Trying to use CUDA-GDB instead of brutal printfs in the code, I found it does not give proper values at the end of a large array. The following is a simple code that creates and fills some values to the array of size 200,000. It contains some brutal…
Sangjun Lee
  • 406
  • 2
  • 12
0
votes
0 answers

cuda update from 9.2 in AMI amazon web services to solve debuger "LZMA support disabled at compile time"

I am using this Amazon Linux 2 AMI with NVIDIA TESLA GPU Driver $ cat /etc/*-release NAME="Amazon Linux" VERSION="2" ID="amzn" ID_LIKE="centos rhel fedora" VERSION_ID="2" PRETTY_NAME="Amazon Linux…
BugBreeder
  • 1
  • 2
0
votes
1 answer

CUDA-GDB: Setting Up the Debugger Environment

I'm following the CUDA-GDB guide (page 10, getting started) on Ubuntu Linux and got this: antonio@antonio-desktop:~$ export PATH=/usr/local/cuda/bin:$PATH antonio@antonio-desktop:~$ export…
andandandand
  • 21,946
  • 60
  • 170
  • 271
0
votes
0 answers

Cuda verification cannot find -lglut

I am trying to install cuda on my computer and according to nvidia's official guide,it is recommended to verify installation with this repo. However, when I am trying to build it, it gives me some error and the process exits. Error message I…
Ming Chen
  • 11
  • 4
0
votes
0 answers

Is there a Liveness guarantee in CUDA?

I am trying to implement a GPU application which requires the use of a MUTEX. I know this isn't ideal, but for correctness it is required. When the MUTEX is retrieved, which isn't often, all other threads will halt, and then only the single thread…
Daan W
  • 419
  • 4
  • 10
0
votes
2 answers

How to compute the achieved FLOPS of a MPI program which calls cuBlas function

I am accelerating a MPI program using cuBlas function. To evaluate the application's efficiency, I want to know the FLOPS, memory usage and other stuff of GPU after the program has ran, especially FLOPS. I have read the relevant question:How to…
TherLF
  • 13
  • 5
0
votes
1 answer

How to write the CMakeLists.txt file when use cuda-gdb？

my CMakeLists.txt: cmake_minimum_required(VERSION 3.16) project(cmake_and_cuda CUDA CXX C) find_package(CUDA REQUIRED) set(CMAKE_CUDA_COMPILER /usr/local/cuda-11.4/bin/nvcc) set(CMAKE_CUDA_FLAGS ${CMAKE_CUDA_FLAGS} " -g -G ") # enable…
HONG MAO
  • 1
  • 3
0
votes
1 answer

Cuda-gdb in vscode, Cannot find user-level thread for LWP 4077: generic error

I am trying to set up cuda programming in vs code and ran into this problem where cuda-gdb just returns an error. I tried running it with regular gdb and that works. I am using wsl. running the "CUDA C++: Launch" outputs this in the debug…
William Hofsøy
  • 3
  • 3
0
votes
1 answer

How to set filter in cuda-memcheck (or compute-sanitizer)

I am developing a fairly big project (have around 1200 kernels so far). I have 1 kernel that possibly has some memory race which is why it's giving different answers every time. I want to find it by performing cuda-memcheck on that specific kernel.…
sam3376
  • 33
  • 6
0
votes
2 answers

Cuda gdb print constant

I am in cuda-gdb, I can use ((@global float *)array)[0] but how to use constant memory in gdb ? I try ((@parameter float *)const_array) I declared const_array like this : __constant__ float const_array[1 << 14] I tried with 1 << 5, and it's the same…
Vadim Kashtanov
  • 23
  • 6
0
votes
1 answer

Questions about CUDA macro __CUDA_ARCH__

I have a simple cuda code in ttt.cu #include __global__ void example(){ printf("__CUDA_ARCH__: %d \n", __CUDA_ARCH__); } int main(){ example<<<1,1>>>(); } with CMakeLists.txt: cmake_minimum_required(VERSION…
picklesmithy129
  • 81
  • 8
0
votes
1 answer

Cuda Error (209): cudaLaunchKernel returned cudaErrorNoKernelImageForDevice

Operating System: CentOS 7 Cuda Toolkit Version: 11.0 Nvidia Driver and GPU Info: NVIDIA-SMI 450.51.05 Driver Version: 450.51.05 CUDA Version: 11.0 GPU: Quadro M2000M screenshot of nvidia-smi details I'm very new to cuda programming so any guidance…
cuda newb
  • 91
  • 2
  • 3
0
votes
1 answer

cuda-gdb giving error "warning: Cuda API error detected: cudaLaunchKernel returned (0x7)"

I am trying to debug a program in cuda-gdb. I am able to successfully set breakpoints in code that runs on the host (CPU), but whenever I try to set a breakpoint in code that runs on the GPU, the debugger skips over the breakpoints and gives me the…
DankMasterDan
  • 1,900
  • 4
  • 23
  • 35
0
votes
1 answer

Using CUDA-gdb with NVRTC

I have an application which generates CUDA C++ source code, compiles it into PTX at runtime using NVRTC, and then creates CUDA modules from it using the CUDA driver API. If I debug this application using cuda-gdb, it displays the kernel (where an…
tmlen
  • 8,533
  • 5
  • 31
  • 84
1 2 3
4
5 6