NASP/cuda-samples
60
0
Fork 0
mirror of https://github.com/NVIDIA/cuda-samples.git synced 2026-04-02 15:45:41 +08:00
Code Issues Packages Projects Releases Wiki Activity

Bug 5952280: Add cuModuleUnload(Module) to release resource for 6 samples

Browse Source
This commit is contained in:
Shawn Zeng 2026-03-10 16:05:27 +08:00
parent 5cf83b5a98
commit e32d17e67e
6 changed files with 11 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
Samples/0_Introduction/matrixMulDrv/matrixMulDrv.cpp
View File

@ -255,6 +255,7 @@ void runTest(int argc, char **argv)
checkCudaErrors(cuMemFree(d_A));
checkCudaErrors(cuMemFree(d_B));
checkCudaErrors(cuMemFree(d_C));
checkCudaErrors(cuModuleUnload(cuModule));
checkCudaErrors(cuCtxDestroy(cuContext));
}

10
Samples/0_Introduction/matrixMulDynlinkJIT/matrixMulDynlinkJIT.cpp
View File

@ -68,6 +68,7 @@ extern "C" void computeGold(float *, const float *, const float *, unsigned int,
// Globals
////////////////////////////////////////////////////////////////////////////////
CUcontext g_cuContext;
CUmodule g_cuModule;
bool noprompt = false;
static const char *sSDKsample = "matrixMulDynlinkJIT (CUDA dynamic linking)";
@ -90,7 +91,6 @@ CUresult initCUDA(int argc, char **argv, CUfunction *pMatrixMul, int *block_size
{
CUresult status;
CUdevice cuDevice;
CUmodule cuModule;
CUfunction cuFunction;
int major, minor, block_size, devID = 0;
char deviceName[256];
@ -185,10 +185,10 @@ CUresult initCUDA(int argc, char **argv, CUfunction *pMatrixMul, int *block_size
#if defined(_WIN64) || defined(__LP64__)
status =
cuModuleLoadDataEx(&cuModule, matrixMul_kernel_64_ptxdump, jitNumOptions, jitOptions, (void **)jitOptVals);
cuModuleLoadDataEx(&g_cuModule, matrixMul_kernel_64_ptxdump, jitNumOptions, jitOptions, (void **)jitOptVals);
#else
status =
cuModuleLoadDataEx(&cuModule, matrixMul_kernel_32_ptxdump, jitNumOptions, jitOptions, (void **)jitOptVals);
cuModuleLoadDataEx(&g_cuModule, matrixMul_kernel_32_ptxdump, jitNumOptions, jitOptions, (void **)jitOptVals);
#endif
printf("> PTX JIT log:\n%s\n", jitLogBuffer);
@ -206,9 +206,10 @@ CUresult initCUDA(int argc, char **argv, CUfunction *pMatrixMul, int *block_size
// retrieve CUDA function from the compiled module
status = cuModuleGetFunction(
&cuFunction, cuModule, (block_size == 16) ? "matrixMul_bs16_32bit" : "matrixMul_bs32_32bit");
&cuFunction, g_cuModule, (block_size == 16) ? "matrixMul_bs16_32bit" : "matrixMul_bs32_32bit");
if (CUDA_SUCCESS != status) {
cuModuleUnload(g_cuModule);
cuCtxDestroy(g_cuContext);
exit(EXIT_FAILURE);
}
@ -337,6 +338,7 @@ int main(int argc, char **argv)
checkCudaErrors(cuMemFree(d_A));
checkCudaErrors(cuMemFree(d_B));
checkCudaErrors(cuMemFree(d_C));
checkCudaErrors(cuModuleUnload(g_cuModule));
checkCudaErrors(cuCtxDestroy(g_cuContext));
printf("Test run %s\n", (1 == res) ? "success!" : "failed!");

1
Samples/0_Introduction/simpleTextureDrv/simpleTextureDrv.cpp
View File

@ -297,6 +297,7 @@ void runTest(int argc, char **argv)
free(image_path);
free(ref_path);
checkCudaErrors(cuModuleUnload(cuModule));
checkCudaErrors(cuCtxDestroy(cuContext));
exit(bTestResults ? EXIT_SUCCESS : EXIT_FAILURE);

1
Samples/0_Introduction/vectorAddDrv/vectorAddDrv.cpp
View File

@ -211,6 +211,7 @@ int CleanupNoFailure()
free(h_C);
}
checkCudaErrors(cuModuleUnload(cuModule));
checkCudaErrors(cuCtxDestroy(cuContext));
return EXIT_SUCCESS;

1
Samples/0_Introduction/vectorAddMMAP/vectorAddMMAP.cpp
View File

@ -247,6 +247,7 @@ int CleanupNoFailure()
free(h_C);
}
checkCudaErrors(cuModuleUnload(cuModule));
checkCudaErrors(cuCtxDestroy(cuContext));
return EXIT_SUCCESS;

1
Samples/3_CUDA_Features/memMapIPCDrv/memMapIpc.cpp
View File

@ -419,6 +419,7 @@ static void childProcess(int devId, int id, char **argv)
// Clean up!
checkCudaErrors(cuStreamDestroy(stream));
checkCudaErrors(cuModuleUnload(cuModule));
checkCudaErrors(cuCtxDestroy(ctx));
// Unmap the allocations from our address space. Unmapping will also free the