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
1 answer

Printing dissasembly information in Cuda-gdb

I would like to print information from cuda disassembly. I am able to print registers in cuda using info registers R1 for example however I am not able to figure out how to print c[0x0][0x20] in (MOV R1, c[0x0][0x20]) or deferenced [R13+0x9f] in…
1
vote
1 answer

Checking currently residing entities in GPU memory

What would be the easiest way of checking which (and their size) entities that have been allocated with cudaMalloc (), reside currently on a GPU device? I want to find a memory leak inside a function, that if it's just called once and exit, there is…
nabber
  • 59
  • 8
1
vote
1 answer

NSight gdb error

I have a problem with the "pretty printer" option of IDE NSight (eclipse) when I try to debug. I have googled but I have not found a solution to my problem. When I start to debug, appears the next message: Traceback (most recent call last): File…
SolidusAbi
  • 43
  • 9
1
vote
1 answer

Invoke kernel failure through cuda-gdb?

Is there a way to invoke kernel failure using cuda-gdb? I've tried stepping through the kernel code and setting invalid index positions, odd values to variables, but I'm unable to trigger a "kernel Execution Failed" after continuing from an…
John
  • 652
  • 7
  • 22
1
vote
1 answer

CUDA kernel pointer arguments become NULL

My CUDA Kernel, needs a lot of arrays which need to be passed as pointers to the kernel. The problem is that just before the kernel launch, all the pointers have valid addresses, moreover the cudaMalloc and cudaMemcpy calls always return…
Swaroop
  • 1,219
  • 3
  • 16
  • 32
1
vote
1 answer

CUDA Illegal access to address strangeness

My question is: is the CUDA hardware faulty, or is there possibly another explanation? I have a kernel which has been in use for about a year without modification. Recently, I started getting segmentation faults at irregular intervals, i.e. it…
Tyson Hilmer
  • 741
  • 7
  • 25
1
vote
1 answer

CUDA cross-compiling error! cuda-gdb error message RSEG1058

I'm new in this CUDA and parallel computing staff and I have a recent problem. I have an Ubuntu 12.04 system which is host and Jetson TK1 as the target. I'm using Nsight Eclipse to write, edit and compile the algorithms. I'm using SSH protocol to…
bcaldir
  • 11
  • 1
1
vote
2 answers

CUDA 5.5 not working in Ubuntu 12.04 with GTX 750 Ti

I get the following error when trying to use a GTX 750 Ti with CUDA 5.5 in Ubuntu 12.04 64-bit: The driver installation is unable to locate the kernel source. Please make sure that the kernel source packages are installed and set up correctly. If…
mining
  • 3,557
  • 5
  • 39
  • 66
1
vote
1 answer

CUDA Constant Memory Error

I am trying to do a sample code with constant memory with CUDA 5.5. I have 2 constant arrays of size 3000 each. I have another global array X of size N. I want to compute Y[tid] = X[tid]*A[tid%3000] + B[tid%3000] Here is the code. #include…
mkuse
  • 2,250
  • 4
  • 32
  • 61
1
vote
2 answers

cuda-gdb remote debug error

I have a CentOS 6.0 x64 server with 2 Geforce 480GTX cards equipped and I am using it to debug my cuda programs. Today I tried to use cuda-gdb on my notebook to remote debug my program. So I tried like this: I opened my bash shell and use ssh to…
Xiangyu.Guo
  • 151
  • 1
  • 8
1
vote
0 answers

Nsight eclipse for linux remote debugging error

I'm using ubuntu12.10 x64 on my notebook and the nsight eclipse for linux to write cuda programs and I am trying to debug it on a server running CentOS6.0 x64 with 2 Geforce GTX 260 display cards. Both computers have installed the cuda toolkit 5.5,…
Xiangyu.Guo
  • 151
  • 1
  • 8
1
vote
1 answer

Can i debug openACC with cuda-gdb? Or other debugging tools?

I'm using CAPS OpenACC on CUDA. I'm trying debugging with cuda-gdb. And i can debug normally c/c++ code with cuda-gdb. In other words i couldn't debug codelet code. Is there a anybody who debugged openACC on cuda? or i couldn't put breakpoint in the…
grypp
  • 405
  • 2
  • 15
1
vote
2 answers

CUDA Nsight Eclipse debugger error (Mac OS X)

I am running Nsight Eclipse edition on my MacBook PRO (OS X 10.8.2, mountain lion, CUDA 5.0, GT650M) and I am getting a strange error each time I try to start the debugger in Nsight. In the console I get: Coalescing of the CUDA commands output is…
Sterbic
  • 213
  • 5
  • 15
1
vote
3 answers

cuda-gdb not working in nsight on linux

I installed cuda 5 in my Ubuntu 12.10 and it is working well, I can compile and debug through cuda-gdb in terminal as well. I'm trying to use nsight, it compiles and executes my code with no issues, but when I try to debug I got the following…
Frederico Schardong
  • 1,946
  • 6
  • 38
  • 62
1
vote
1 answer

CUDA 5.0 cuda-gdb on Linux Needs dedicated CPU?

With a fresh CUDA 5.0 Linux install on CentOS 5.5, I am not able to gdb. So I am wondering if you still need a dedicated GPU for the Linux cuda-gdb? I tried it with the Vesa device driver for X11, but get the same result. Profiling works, running…
TMB
  • 31
  • 3