Dear Experts,
I have just started exploring CUDA. From the book “CUDA by Example (Sanders & Kandrot)” - I tried to compile and run the Julia set example. However, could not do so.
Please help resolving errors.
I am using 3.2 kit on Windows 7 (64 bit). Visual studio 2008. Have two GTX460 cards connected with SLI.
As you probably know, the julia set example code is:
========================================
- Copyright 1993-2010 NVIDIA Corporation. All rights reserved.
- NVIDIA Corporation and its licensors retain all intellectual property and
- proprietary rights in and to this software and related documentation.
- Any use, reproduction, disclosure, or distribution of this software
- and related documentation without an express license agreement from
- NVIDIA Corporation is strictly prohibited.
- Please refer to the applicable NVIDIA end user license agreement (EULA)
- associated with this source code for terms and conditions that govern
- your use of this NVIDIA software.
*/
#include “book.h”
#include “cpu_bitmap.h”
#define DIM 1000
struct cuComplex {
float r;
float i;
cuComplex( float a, float b ) : r(a), i(b) {}
device float magnitude2( void ) {
return r * r + i * i;
}
device cuComplex operator*(const cuComplex& a) {
return cuComplex(ra.r - ia.i, ia.r + ra.i);
}
device cuComplex operator+(const cuComplex& a) {
return cuComplex(r+a.r, i+a.i);
}
};
device int julia( int x, int y ) {
const float scale = 1.5;
float jx = scale * (float)(DIM/2 - x)/(DIM/2);
float jy = scale * (float)(DIM/2 - y)/(DIM/2);
cuComplex c(-0.8, 0.156);
cuComplex a(jx, jy);
int i = 0;
for (i=0; i<200; i++) {
a = a * a + c;
if (a.magnitude2() > 1000)
return 0;
}
return 1;
}
global void kernel( unsigned char *ptr ) {
// map from blockIdx to pixel position
int x = blockIdx.x;
int y = blockIdx.y;
int offset = x + y * gridDim.x;
// now calculate the value at that position
int juliaValue = julia( x, y );
ptr[offset*4 + 0] = 255 * juliaValue;
ptr[offset*4 + 1] = 0;
ptr[offset*4 + 2] = 0;
ptr[offset*4 + 3] = 255;
}
// globals needed by the update routine
struct DataBlock {
unsigned char *dev_bitmap;
};
int main( void ) {
DataBlock data;
CPUBitmap bitmap( DIM, DIM, &data );
unsigned char *dev_bitmap;
HANDLE_ERROR( cudaMalloc( (void**)&dev_bitmap, bitmap.image_size() ) );
data.dev_bitmap = dev_bitmap;
dim3 grid(DIM,DIM);
kernel<<<grid,1>>>( dev_bitmap );
HANDLE_ERROR( cudaMemcpy( bitmap.get_ptr(), dev_bitmap,
bitmap.image_size(),
cudaMemcpyDeviceToHost ) );
HANDLE_ERROR( cudaFree( dev_bitmap ) );
bitmap.display_and_exit();
}
========================================
Press F5 (Debug mode), and following lines are displayed in the output window.
‘firstCuda.exe’: Loaded ‘C:\Suresh_Cuda\firstCuda\x64\Debug\firstCuda.exe’, Symbols loaded.
‘firstCuda.exe’: Loaded ‘C:\Windows\System32\ntdll.dll’
‘firstCuda.exe’: Loaded ‘C:\Windows\System32\kernel32.dll’
‘firstCuda.exe’: Loaded ‘C:\Windows\System32\KernelBase.dll’
‘firstCuda.exe’: Loaded ‘C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v3.2\bin\cudart64_32_16.dll’, Binary was not built with debug information.
‘firstCuda.exe’: Loaded ‘C:\Windows\System32\opengl32.dll’
‘firstCuda.exe’: Loaded ‘C:\Windows\System32\msvcrt.dll’
‘firstCuda.exe’: Loaded ‘C:\Windows\System32\advapi32.dll’
‘firstCuda.exe’: Loaded ‘C:\Windows\System32\sechost.dll’
‘firstCuda.exe’: Loaded ‘C:\Windows\System32\rpcrt4.dll’
‘firstCuda.exe’: Loaded ‘C:\Windows\System32\gdi32.dll’
‘firstCuda.exe’: Loaded ‘C:\Windows\System32\user32.dll’
‘firstCuda.exe’: Loaded ‘C:\Windows\System32\lpk.dll’
‘firstCuda.exe’: Loaded ‘C:\Windows\System32\usp10.dll’
‘firstCuda.exe’: Loaded ‘C:\Windows\System32\glu32.dll’
‘firstCuda.exe’: Loaded ‘C:\Windows\System32\ddraw.dll’
‘firstCuda.exe’: Loaded ‘C:\Windows\System32\dciman32.dll’
‘firstCuda.exe’: Loaded ‘C:\Windows\System32\setupapi.dll’
‘firstCuda.exe’: Loaded ‘C:\Windows\System32\cfgmgr32.dll’
‘firstCuda.exe’: Loaded ‘C:\Windows\System32\oleaut32.dll’
‘firstCuda.exe’: Loaded ‘C:\Windows\System32\ole32.dll’
‘firstCuda.exe’: Loaded ‘C:\Windows\System32\devobj.dll’
‘firstCuda.exe’: Loaded ‘C:\Windows\System32\dwmapi.dll’
The program ‘[4624] firstCuda.exe: Native’ has exited with code -1073741701 (0xc000007b).
Press F5 (Release mode), and following lines are displayed in the output window.
1>------ Build started: Project: firstCuda, Configuration: Release x64 ------
1>Compiling with CUDA Build Rule…
1>“C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v3.2\bin\nvcc.exe” -arch sm_10 -ccbin “C:\Program Files (x86)\Microsoft Visual Studio 9.0\VC\bin” -Xcompiler "/EHsc /W3 /nologo /O2 /Zi /MT " -maxrregcount=32 --compile -o “x64\Release\sample.cu.obj” “c:\Suresh_Cuda\firstCuda\firstCuda\sample.cu”
1>sample.cu
1>tmpxft_00000678_00000000-3_sample.cudafe1.gpu
1>tmpxft_00000678_00000000-8_sample.cudafe2.gpu
1>sample.cu
1>tmpxft_00000678_00000000-3_sample.cudafe1.cpp
1>tmpxft_00000678_00000000-14_sample.ii
1>Linking…
1>sample.cu.obj : error LNK2001: unresolved external symbol cudaGetErrorString
1>sample.cu.obj : error LNK2001: unresolved external symbol __cudaUnregisterFatBinary
1>sample.cu.obj : error LNK2001: unresolved external symbol cudaLaunch
1>sample.cu.obj : error LNK2001: unresolved external symbol cudaSetupArgument
1>sample.cu.obj : error LNK2001: unresolved external symbol __cudaRegisterFunction
1>sample.cu.obj : error LNK2001: unresolved external symbol __cudaRegisterFatBinary
1>sample.cu.obj : error LNK2001: unresolved external symbol cudaFree
1>sample.cu.obj : error LNK2001: unresolved external symbol cudaMemcpy
1>sample.cu.obj : error LNK2001: unresolved external symbol cudaConfigureCall
1>sample.cu.obj : error LNK2001: unresolved external symbol cudaMalloc
1>C:\Suresh_Cuda\firstCuda\x64\Release\firstCuda.exe : fatal error LNK1120: 10 unresolved externals
1>Build log was saved at “file://c:\Suresh_Cuda\firstCuda\firstCuda\x64\Release\BuildLog.htm”
1>firstCuda - 11 error(s), 0 warning(s)
========== Build: 0 succeeded, 1 failed, 0 up-to-date, 0 skipped ==========
Suggestions towards resolving the issue in debug mode would be appreciated.
Thank you.