nsight

问题 I have written a code on Nsight that compiles and can be executed but the first launch can't be completed. The strange thing is that when I run it in debug mode, it works perfectly but it is too slow. Here is the part of the code before entering the function that access the GPU (where i think there is an error I can't find) : void parallelAction (int * dataReturned, char * data, unsigned char * descBase, int range, int cardBase, int streamIdx) { size_t inputBytes = range*128*sizeof(unsigned

问题 I am trying to setup a remote Nsight v2.2 debugger for GPU debugging only(no CUDA). I have followed this Nvidia pdf for setting up the remote target machine and the development machine. All are up and running, but the communication between the two is not proper. I am getting errors like MSVSMON.exe not running on remote machine etc. I am not sure about the exact settings required. What should be the, VS2010 project settings Nsight Monitor(remote machine) settings Nsight Settings in VS2010 and

问题 I am trying to achieve " 3 -way overlapping" using 3 streams as in the examples in CUDA streams and concurrency webinar. But I couldn't achieve it. I have Geforce GT 550M (Fermi Architecture with one copy engine) and I am using Windows 7 (64 bit). Here is the code that I have written. #include <iostream> #include "cuda_runtime.h" #include "device_launch_parameters.h" // includes, project #include "helper_cuda.h" #include "helper_functions.h" // helper utility functions #include <stdio.h>

问题 I'we been writing some simple cuda program (I'm student so I need to practice), and the thing is I can compile it with nvcc from terminal (using Kubuntu 12.04LTS) and then execute it with optirun ./a.out (hardver is geforce gt 525m on dell inspiron) and everything works fine. The major problem is that I can't do anything from Nsight. When I try to start debug version of code the message is "Launch failed! Binaries not found!". I think it's about running command with optirun but I'm not sure.

问题 I am trying to learn NSIGHT. Can some one tell me what are these red marks indicating in the following screenshot taken from the User Guide ? There are two red marks in Occupancy per SM and two in warps section as you can see. Similarly what are those black lines which are varying in length, indicating? Another example from same page: 回答1: Here is the basic explanation: Grey bars represent the available amount of resources your particular device has (due to both its hardware and its compute

问题 I want to try gst_inst_128bit instruction. In the same program, nvvp give a lot of gst_inst_128bit command executed. While in nsight's profiler, 4 times gst_inst_32bit instructions is obtained. They should be a same program. How could this situation happen? The experiment was tried on Linux, CUDA 5.0, GTX 580. The program is only copying data from one array to another in kernel function: In main: cudaMalloc((void**)&dev_a, NUM * sizeof(float)); cudaMalloc((void**)&dev_b, NUM * sizeof(float));

问题 Disclaimer: I know that this question has been asked numerous times, but before Nsight 5.5 the answer simply was "You can't." I'm trying to debug a CUDA program with Nsight 5.5 on Ubuntu. The remote machine is also an Ubuntu with CUDA Toolkit 5.5. I setup debugging in NSight using the "Debug an application on a remote system". Whenever I try to run the application I get a "Could not start gdbserver on the remote host" error. This is what I get on the console: Last login: Thu Aug 1 16:09:26

问题 I have a UWP cppwinrt app that is using directx12 to render a cube with a basic shader. I would like to use a graphics debugger to inspect the data being sent to this shader. First I am trying to use the Nvidia Nsight debugger for visual studio 2017. The problem is that when I go to "Start Graphics Debugging" from the Nsight menu, the app immediately stop with an error saying: "Failed to launch UWP app (Could not terminate existing process)". I am able to launch the Nsight debugger on a

问题 I am using nsight eclipse edition for mac to debug my cuda code. I was able to run cuda-gdb all fine from a terminal but was not able to use the debug function in Nsight. Whenever I started to debug, an error window pops up saying "Error in final launch sequence Connection is shut down". My OS is Mac Lion (10.7.4). I understand the big thing in Cuda 5.0 is the interactive debugging with eclipse but sadly I won't be able to use it unless I switch to Windows or Linux. If anybody has seen this

问题 I have strange thing happened to my CUDA Toolkit 5.0. Few days ago both XCode and NSight Eclipse plugin lost ability to build even simplest CUDA related projects. XCode successfully building projects with custom build rule for C++ source files: nvcc "INPUT_FILE_NAME" But console output shows that run failed error: executable doesn't exist: '/Users/geraldus/Library/Developer/Xcode/DerivedData/CUDA_Hello_World-gzfzqivvsmeamfghnovopxapkdsz/Build/Products/Debug/CUDA Hello World' error: failed to