Hello every one,
I have installed CUDA and started working with it (successfully launched several .cu files, tested nvcc and nvprof).
I am now at the step where I would like to debug my work in CUDA (access to kernels).
I have tried several attempts, but with always the same output:CUDA grid launch failed.
Let me detail this on one example, the MatrixMul CUDA sample, which is detailed in the Nsight VIsual Studio User Guide :
https://docs.nvidia.com/nsight-visual-studio-edition/2019.3/Nsight_Visual_Studio_Edition_User_Guide.htm#Debugging_CUDA_Application.htm%3FTocPath%3DCUDA%2520Debugger|_____1
My system (as detailed in the Nsight ->Windows->System Info) is:
| Name | Intel(R) Core™ i7-4700MQ CPU @ 2.40GHz |
|---|---|
| Architecture | x64 |
| Frequency | 2 394 MHz |
| Number of Cores | 8 |
| Page Size | 4 096 |
| Total Physical Memory | 7 993.00 MB |
| Available Physical Memory | 2 091.00 MB |
| Hybrid Graphics Enabled | False |
| Version Name | Windows 10 Enterprise |
| Version Number | 10.0.19041 |
| Nsight Version | 2019.1.0.19017 |
| Nsight Edition | Standard |
| Visual Studio Version | 14.0 |
For further information on my equipment, the deviceQuery CUDA sample returns:
CUDA Device Query (Runtime API) version (CUDART static linking)
Detected 1 CUDA Capable device(s)
Device 0: “Quadro K3100M”
CUDA Driver Version / Runtime Version 10.1 / 10.1
CUDA Capability Major/Minor version number: 3.0
Total amount of global memory: 4096 MBytes (4294967296 bytes)
( 4) Multiprocessors, (192) CUDA Cores/MP: 768 CUDA Cores
GPU Max Clock rate: 706 MHz (0.71 GHz)
Memory Clock rate: 1600 Mhz
Memory Bus Width: 256-bit
L2 Cache Size: 524288 bytes
Maximum Texture Dimension Size (x,y,z) 1D=(65536), 2D=(65536, 65536), 3D=(4096, 4096, 4096)
Maximum Layered 1D Texture Size, (num) layers 1D=(16384), 2048 layers
Maximum Layered 2D Texture Size, (num) layers 2D=(16384, 16384), 2048 layers
Total amount of constant memory: 65536 bytes
Total amount of shared memory per block: 49152 bytes
Total number of registers available per block: 65536
Warp size: 32
Maximum number of threads per multiprocessor: 2048
Maximum number of threads per block: 1024
Max dimension size of a thread block (x,y,z): (1024, 1024, 64)
Max dimension size of a grid size (x,y,z): (2147483647, 65535, 65535)
Maximum memory pitch: 2147483647 bytes
Texture alignment: 512 bytes
Concurrent copy and kernel execution: Yes with 2 copy engine(s)
Run time limit on kernels: Yes
Integrated GPU sharing Host Memory: No
Support host page-locked memory mapping: Yes
Alignment requirement for Surfaces: Yes
Device has ECC support: Disabled
CUDA Device Driver Mode (TCC or WDDM): WDDM (Windows Display Driver Model)
Device supports Unified Addressing (UVA): Yes
Device supports Compute Preemption: No
Supports Cooperative Kernel Launch: No
Supports MultiDevice Co-op Kernel Launch: No
Device PCI Domain ID / Bus ID / location ID: 0 / 1 / 0
Compute Mode:
< Default (multiple host threads can use ::cudaSetDevice() with device simultaneously) >
deviceQuery, CUDA Driver = CUDART, CUDA Driver Version = 10.1, CUDA Runtime Version = 10.1, NumDevs = 1
Result = PASS
I have followed all the instructions on the Nsight User Guide in the CUDA Debugger Walkthrough : Debugging a CUDA application, and when I launch the Nvidia CUDA Debugger (Legacy) the Nsight Output is:
CUDA context created : 1e9fa5a26e0
CUDA module loaded: 1e9fd0c20d0 matrixMul.cu
CUDA grid launch failed: CUcontext: 2104439219936 CUmodule: 2104484438224 Function: _Z13MatrixMulCUDAILi32EEvPfS0_S0_ii
I have tried to increase the TDR Delay to 10 in the Nsight monitor option, without any success. I give you below my setting:
I am stuck on this, and any help or suggestion would be greatly appreciated.