runtime error with cuda 9.1

Hello Cuda Dev Team,

I updated project cuda 4.2 to Cuda 9.1 and its compiling fine with latest cusp and Thrust file.
While i am running my application and loading an obj file getting run time error-
Status: Using GLEW 2.1.0

I am using VS2015, cuda 9.1, quadro M1200 with windows 10.

CUDA error 9 [C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v9.1\include\thrust/system/cuda/detail/parallel_for.h, 143]: invalid configuration argument
Thurst Runtime Error: parallel_for failed: invalid configuration argument
Press any key to continue . . .

Please help me to resolve this issue, my project is stuck because these issue.

please help me to make my project working.

Thanks
santosh

I’d run this binary with the cuda-memcheck utility, as this may give you more details about whether it’s a CUDA API call that failed, and from which code line the failure was triggered (provided the executable has debug info).

It’s part of the CUDA toolkit, however on Windows I could not tell you exactly where to look for it. It may be in the PATH already, if you are lucky.

Thanks cbuchner1,

i am not clear, Please explain the above cuda-memcheck process and your steps.
If you want my code for testing at your side.
please let me know.

It is a command line tool, documented here:

When using a Windows Command shell (cmd.exe or Powershell) you can run cuda-memcheck with arguments specifying which binary to test/debug.

This is why I recommend cuda-memcheck for tracking down the source of your error

3.6. CUDA API Error Checking

The memcheck tool supports reporting an error if a CUDA API call made by the user program returned
an error. The tool supports this detection for both CUDA run time and CUDA driver API calls. In all
 cases, if the API function call has a nonzero return value, CUDA-MEMCHECK will print an error 
message containing the name of the API call that failed and the return value of the API call.

Read more at: http://docs.nvidia.com/cuda/cuda-memcheck/index.html#ixzz5Bso3GOU7

Christian

Thanks cbuchner1 for quick reply.

I will follow the toolkit document for the cuda-memcheck process then i will update to you soon.

Hello chuchner1,

i run the cuda-memcheck and got the details on the command window

[b]C:\Windows\system32>cuda-memcheck C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe
========= CUDA-MEMCHECK
---- General Information for device 0----
Name: Quadro M1200
Compute capability: 5.0
Clock rate: 1148000
Device copy overlap: Enabled
Kernel execition timeout : Enabled

---- Memory Information for device 0----
Total global mem: 4294967296
Total constant mem: 65536
Max mem pitch: 2147483647
Texture Alignment: 512

---- MP Information for device 0----
Multiprocessor count: 5
Shared mem per mp: 49152
Registers per mp: 65536
Threads in warp: 32
Max threads per block: 1024
Max thread dimensions: (1024 1024 64)
Max grid dimensions: (2147483647 65535 65535)

Status: Using GLEW 2.1.0
CUDA error 9 [C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v9.1\include\thrust/system/cuda/detail/parallel_for.h, 143]: invalid configuration argument
Thurst Runtime Error: parallel_for failed: invalid configuration argument
========= Internal Memcheck Error: Memcheck failed initialization as some other tools is currently attached. Please make sure that nvprof and Nsight Visual Studio Edition are not being run simultaneously
========= Saved host backtrace up to driver entry point at error
========= Host Frame:C:\Windows\system32\nvcuda.dll (cuGraphicsResourceGetMappedPointer + 0x1a9d38) [0x1b7407]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\cudart64_91.dll (_cudaInitManagedRuntime + 0x3485) [0x10945]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\cudart64_91.dll (_cudaInitManagedRuntime + 0x51b1) [0x12671]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\cudart64_91.dll (cudaD3D11SetDirect3DDevice + 0x4c6) [0x332e6]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\cudart64_91.dll (_cudaInitManagedRuntime + 0x51eb) [0x126ab]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\cudart64_91.dll (_cudaInitManagedRuntime + 0x53b7) [0x12877]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\cudart64_91.dll (cudaSetDevice + 0x35) [0x1dac5]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (main + 0x47) [0x7ef57]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (invoke_main + 0x34) [0x228394]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (__scrt_common_main_seh + 0x127) [0x2282c7]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (__scrt_common_main + 0xe) [0x22818e]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (mainCRTStartup + 0x9) [0x2283a9]
========= Host Frame:C:\Windows\System32\KERNEL32.DLL (BaseThreadInitThunk + 0x14) [0x11fe4]
========= Host Frame:C:\Windows\SYSTEM32\ntdll.dll (RtlUserThreadStart + 0x21) [0x6efc1]

========= ERROR SUMMARY: 1 error

C:\Windows\system32>[/b]

Please have a look of errors and help me.

Using cuda-memcheck on Windows is outside my area of expertise, but Google finds possible solution to your problem

https://stackoverflow.com/questions/19323560/internal-memcheck-error-memcheck-failed-initialization-as-profiler-is-attached

make sure these two environment variables are not set.
CUDA_INJECTION32_PATH
CUDA_INJECTION64_PATH

e.g. by emptying them explicitly

set CUDA_INJECTION32_PATH=
set CUDA_INJECTION64_PATH=

also you want to set the COMPUTE_PROFILE variable to 0

set COMPUTE_PROFILE=0

thanks cbuchner1,

I checked in environment variable setting and got this
CUDA_INJECTION32_PATH = C:\Program Files (x86)\NVIDIA Corporation\Nsight Visual Studio Edition 5.5\Monitor\Common\Injection32\Nvda.Cuda.Injection.dll

CUDA_INJECTION64_PATH = C:\Program Files (x86)\NVIDIA Corporation\Nsight Visual Studio Edition 5.5\Monitor\Common\Injection64\Nvda.Cuda.Injection.dll

Please check this.

it’s the cause of the observed error, so please execute the commands before running your binary in cuda-memcheck

set CUDA_INJECTION32_PATH=
set CUDA_INJECTION64_PATH=
cuda-memcheck C:\Users\ivasa\Desktop015\bin\Clothsim.exe

Hello cbuchner1,

I tried with and without CUDA_INJECTION32_PATH and CUDA_INJECTION64_PATH environment variable setting with the
COMPUTE_PROFILE=0 but i was getting the same run time issue my side.

Please help me to make it working.

Sorry, now I am out of ideas concerning this “Memcheck failed initialization as some other tools is currently attached” error.

Hello cbuchner1,

After using your suggestion
set CUDA_INJECTION32_PATH=
set CUDA_INJECTION64_PATH=
cuda-memcheck C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe

[b]Microsoft Windows [Version 10.0.16299.309]
(c) 2017 Microsoft Corporation. All rights reserved.

C:\Windows\system32>set CUDA_INJECTION32_PATH=

C:\Windows\system32>set CUDA_INJECTION64_PATH=

C:\Windows\system32>cuda-memcheck C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe
========= CUDA-MEMCHECK
---- General Information for device 0----
Name: Quadro M1200
Compute capability: 5.0
Clock rate: 1148000
Device copy overlap: Enabled
Kernel execition timeout : Enabled

---- Memory Information for device 0----
Total global mem: 4294967296
Total constant mem: 65536
Max mem pitch: 2147483647
Texture Alignment: 512

---- MP Information for device 0----
Multiprocessor count: 5
Shared mem per mp: 49152
Registers per mp: 65536
Threads in warp: 32
Max threads per block: 1024
Max thread dimensions: (1024 1024 64)
Max grid dimensions: (2147483647 65535 65535)

Status: Using GLEW 2.1.0
========= ERROR SUMMARY: 0 errors

C:\Windows\system32>cuda-memcheck C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe
========= CUDA-MEMCHECK
---- General Information for device 0----
Name: Quadro M1200
Compute capability: 5.0
Clock rate: 1148000
Device copy overlap: Enabled
Kernel execition timeout : Enabled

---- Memory Information for device 0----
Total global mem: 4294967296
Total constant mem: 65536
Max mem pitch: 2147483647
Texture Alignment: 512

---- MP Information for device 0----
Multiprocessor count: 5
Shared mem per mp: 49152
Registers per mp: 65536
Threads in warp: 32
Max threads per block: 1024
Max thread dimensions: (1024 1024 64)
Max grid dimensions: (2147483647 65535 65535)

Status: Using GLEW 2.1.0
CUDA error 9 [C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v9.1\include\thrust/system/cuda/detail/parallel_for.h, 143]: invalid configuration argument
Thurst Runtime Error: parallel_for failed: invalid configuration argument
========= Program hit cudaErrorInvalidConfiguration (error 9) due to “invalid configuration argument” on CUDA API call to cudaLaunch.
========= Saved host backtrace up to driver entry point at error
========= Host Frame:C:\Windows\system32\nvcuda.dll (cuGraphicsResourceGetMappedPointer + 0x2cbecc) [0x2d959b]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\cudart64_91.dll (cudaLaunch + 0x14f) [0x2d4df]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (cudaLaunch + 0x28) [0x1d39c8]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (__device_stub__Z17_gl_init_rest_lenPfPyS0_S_S0_y + 0xec) [0x1d259c]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (_gl_init_rest_len + 0x5a) [0x1d1d7a]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (gpu_cloth_solver::init_edge_rest_len + 0x191) [0xa6de1]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (gpu_cloth_solver::pre_sim + 0x6d) [0xa629d]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (gpu_cloth_solver::gpu_cloth_solver + 0x9bb) [0xa37ab]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (gpu_cloth_solver_block::gpu_cloth_solver_block + 0x3b) [0x104dab]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (plugin_IO::internel_setup + 0x1bf) [0x15ceaf]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (plugin_IO::init_main + 0x190) [0x15cce0]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (plugin_IO::init_from_file + 0x2a6) [0x15cae6]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (mainFrame::mainFrame + 0x217) [0x68ed7]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (UI::GLWnd::MainFrameWindow + 0x6f8) [0x593c8]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (UI::GLWnd::WndProc + 0x33d) [0x5a1ad]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (UI::WindowProc + 0x48) [0x59e48]
========= Host Frame:C:\Windows\System32\USER32.dll (CallWindowProcW + 0x4dd) [0xb85d]
========= Host Frame:C:\Windows\System32\USER32.dll (CallWindowProcW + 0x8b) [0xb40b]
========= Host Frame:C:\Windows\SYSTEM32\OPENGL32.dll (glDebugEntry + 0xf16d) [0x38e5d]
========= Host Frame:C:\Windows\System32\USER32.dll (CallWindowProcW + 0x4dd) [0xb85d]
========= Host Frame:C:\Windows\System32\USER32.dll (DispatchMessageW + 0x1af) [0xb1ef]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (main + 0x22e) [0x7f13e]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (invoke_main + 0x34) [0x228394]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (__scrt_common_main_seh + 0x127) [0x2282c7]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (__scrt_common_main + 0xe) [0x22818e]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (mainCRTStartup + 0x9) [0x2283a9]
========= Host Frame:C:\Windows\System32\KERNEL32.DLL (BaseThreadInitThunk + 0x14) [0x11fe4]
========= Host Frame:C:\Windows\SYSTEM32\ntdll.dll (RtlUserThreadStart + 0x21) [0x6efc1]

========= Program hit cudaErrorInvalidConfiguration (error 9) due to “invalid configuration argument” on CUDA API call to cudaPeekAtLastError.
========= Saved host backtrace up to driver entry point at error
========= Host Frame:C:\Windows\system32\nvcuda.dll (cuGraphicsResourceGetMappedPointer + 0x2cbecc) [0x2d959b]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\cudart64_91.dll (cudaPeekAtLastError + 0x107) [0x1d117]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::cuda_cub::launcher::triple_chevron::doit_host<void (__cdecl*)(thrust::cuda_cub::__transform::unary_transform_f<unsigned __int64 * __ptr64,thrust::device_ptr,thrust::cuda_cub::__transform::no_stencil_tag,thrust::identity,thrust::cuda_cub::__transform::always_true_predicate>,__int64),thrust::cuda_cub::__transform::unary_transform_f<unsigned __int64 * __ptr64,thrust::device_ptr,thrust::cuda_cub::__transform::no_stencil_tag,thrust::identity,thrust::cuda_cub::__transform::always_true_predicate>,__int64> + 0xc0) [0xd1dd0]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::cuda_cub::launcher::triple_chevron::doit<void (__cdecl*)(thrust::cuda_cub::__transform::unary_transform_f<unsigned __int64 * __ptr64,thrust::device_ptr,thrust::cuda_cub::__transform::no_stencil_tag,thrust::identity,thrust::cuda_cub::__transform::always_true_predicate>,__int64),thrust::cuda_cub::__transform::unary_transform_f<unsigned __int64 * __ptr64,thrust::device_ptr,thrust::cuda_cub::__transform::no_stencil_tag,thrust::identity,thrust::cuda_cub::__transform::always_true_predicate>,__int64> + 0x5b) [0xd0d7b]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::cuda_cub::core::AgentLauncher<thrust::cuda_cub::__parallel_for::ParallelForAgent<thrust::cuda_cub::__transform::unary_transform_f<unsigned __int64 * __ptr64,thrust::device_ptr,thrust::cuda_cub::__transform::no_stencil_tag,thrust::identity,thrust::cuda_cub::__transform::always_true_predicate>,__int64> >::launch_impl<thrust::cuda_cub::__transform::unary_transform_f<unsigned __int64 * __ptr64,thrust::device_ptr,thrust::cuda_cub::__transform::no_stencil_tag,thrust::identity,thrust::cuda_cub::__transform::always_true_predicate>,__int64> + 0x192) [0xd7df2]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::cuda_cub::core::AgentLauncher<thrust::cuda_cub::__parallel_for::ParallelForAgent<thrust::cuda_cub::__transform::unary_transform_f<unsigned __int64 * __ptr64,thrust::device_ptr,thrust::cuda_cub::__transform::no_stencil_tag,thrust::identity,thrust::cuda_cub::__transform::always_true_predicate>,__int64> >::launch<thrust::cuda_cub::__transform::unary_transform_f<unsigned __int64 * __ptr64,thrust::device_ptr,thrust::cuda_cub::__transform::no_stencil_tag,thrust::identity,thrust::cuda_cub::__transform::always_true_predicate>,__int64> + 0x59) [0xd6359]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::cuda_cub::__parallel_for::parallel_for<thrust::cuda_cub::__transform::unary_transform_f<unsigned __int64 * __ptr64,thrust::device_ptr,thrust::cuda_cub::__transform::no_stencil_tag,thrust::identity,thrust::cuda_cub::__transform::always_true_predicate>,__int64> + 0xec) [0xdd61c]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::cuda_cub::parallel_for<thrust::cuda_cub::tag,thrust::cuda_cub::__transform::unary_transform_f<unsigned __int64 * __ptr64,thrust::device_ptr,thrust::cuda_cub::__transform::no_stencil_tag,thrust::identity,thrust::cuda_cub::__transform::always_true_predicate>,__int64> + 0x77) [0xdee47]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::cuda_cub::__transform::unary<thrust::cuda_cub::execution_policythrust::cuda_cub::tag,unsigned __int64 * __ptr64,__int64,thrust::device_ptr,thrust::cuda_cub::__transform::no_stencil_tag,thrust::identity,thrust::cuda_cub::__transform::always_true_predicate> + 0xc3) [0xeb553]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::cuda_cub::transform_if<thrust::cuda_cub::tag,unsigned __int64 * __ptr64,thrust::device_ptr,thrust::cuda_cub::__transform::no_stencil_tag,thrust::identity,thrust::cuda_cub::__transform::always_true_predicate> + 0x8b) [0xe90bb]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::cuda_cub::transform_if<thrust::cuda_cub::tag,unsigned __int64 * __ptr64,thrust::device_ptr,thrust::identity,thrust::cuda_cub::__transform::always_true_predicate> + 0x74) [0xe9024]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::cuda_cub::transform<thrust::cuda_cub::tag,unsigned __int64 * __ptr64,thrust::device_ptr,thrust::identity > + 0x68) [0xe83d8]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::cuda_cub::__copy::device_to_device<thrust::cuda_cub::tag,unsigned __int64 * __ptr64,thrust::device_ptr > + 0x59) [0xcd949]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::cuda_cub::copy_n<thrust::cuda_cub::tag,unsigned __int64 * __ptr64,__int64,thrust::device_ptr > + 0x73) [0xca4f3]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::cuda_cub::__copy::cross_system_copy_n<thrust::system::cpp::detail::tag,thrust::cuda_cub::tag,std::_Vector_const_iterator<std::_Vector_val<std::_Simple_types > >,__int64,thrust::device_ptr > + 0x1e4) [0xcba44]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::cuda_cub::__copy::cross_system_copy_n<thrust::system::cpp::detail::tag,thrust::cuda_cub::tag,std::_Vector_const_iterator<std::_Vector_val<std::_Simple_types > >,__int64,thrust::device_ptr > + 0xd4) [0xcbb94]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::cuda_cub::__copy::cross_system_copy<thrust::system::cpp::detail::tag,thrust::cuda_cub::tag,std::_Vector_const_iterator<std::_Vector_val<std::_Simple_types > >,thrust::device_ptr > + 0x12b) [0xcab9b]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::cuda_cub::copy<thrust::system::cpp::detail::tag,thrust::cuda_cub::tag,std::_Vector_const_iterator<std::_Vector_val<std::_Simple_types > >,thrust::device_ptr > + 0xde) [0xc8fbe]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::copy<thrust::cuda_cub::cross_systemthrust::system::cpp::detail::tag,thrust::cuda_cub::tag,std::_Vector_const_iterator<std::_Vector_val<std::_Simple_types > >,thrust::device_ptr > + 0xfe) [0xc7e9e]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::detail::two_system_copy<thrust::system::cpp::detail::tag,thrust::cuda_cub::tag,std::_Vector_const_iterator<std::_Vector_val<std::_Simple_types > >,thrust::device_ptr > + 0x11f) [0xeb06f]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::detail::allocator_traits_detail::copy_construct_range<thrust::system::cpp::detail::tag,thrust::device_malloc_allocator,std::_Vector_const_iterator<std::_Vector_val<std::_Simple_types > >,thrust::device_ptr > + 0xf1) [0xc9f31]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::detail::copy_construct_range<thrust::system::cpp::detail::tag,thrust::device_malloc_allocator,std::_Vector_const_iterator<std::_Vector_val<std::_Simple_types > >,thrust::device_ptr > + 0xcd) [0xca02d]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::detail::contiguous_storage<unsigned __int64,thrust::device_malloc_allocator >::uninitialized_copy<std::_Vector_const_iterator<std::_Vector_val<std::_Simple_types > > > + 0xf4) [0xec8c4]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::detail::vector_base<unsigned __int64,thrust::device_malloc_allocator >::allocate_and_copy<std::_Vector_const_iterator<std::_Vector_val<std::_Simple_types > > > + 0x1cd) [0xc674d]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::detail::vector_base<unsigned __int64,thrust::device_malloc_allocator >::range_init<std::_Vector_const_iterator<std::_Vector_val<std::_Simple_types > > > + 0x157) [0xe53f7]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::detail::vector_base<unsigned __int64,thrust::device_malloc_allocator >::range_init<std::_Vector_const_iterator<std::_Vector_val<std::_Simple_types > > > + 0xa6) [0xe5276]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::detail::vector_base<unsigned __int64,thrust::device_malloc_allocator >::vector_base<unsigned __int64,thrust::device_malloc_allocator ><unsigned __int64,std::allocator > + 0xe0) [0xb2c10]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::device_vector<unsigned __int64,thrust::device_malloc_allocator >::device_vector<unsigned __int64,thrust::device_malloc_allocator ><unsigned __int64,std::allocator > + 0x32) [0xb2b22]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (gpu_cloth_solver_block::init_independant_sets + 0x175) [0x1072d5]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (gpu_cloth_solver_block::gpu_cloth_solver_block + 0x159) [0x104ec9]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (plugin_IO::internel_setup + 0x1bf) [0x15ceaf]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (plugin_IO::init_main + 0x190) [0x15cce0]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (plugin_IO::init_from_file + 0x2a6) [0x15cae6]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (mainFrame::mainFrame + 0x217) [0x68ed7]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (UI::GLWnd::MainFrameWindow + 0x6f8) [0x593c8]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (UI::GLWnd::WndProc + 0x33d) [0x5a1ad]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (UI::WindowProc + 0x48) [0x59e48]
========= Host Frame:C:\Windows\System32\USER32.dll (CallWindowProcW + 0x4dd) [0xb85d]
========= Host Frame:C:\Windows\System32\USER32.dll (CallWindowProcW + 0x8b) [0xb40b]
========= Host Frame:C:\Windows\SYSTEM32\OPENGL32.dll (glDebugEntry + 0xf16d) [0x38e5d]
========= Host Frame:C:\Windows\System32\USER32.dll (CallWindowProcW + 0x4dd) [0xb85d]
========= Host Frame:C:\Windows\System32\USER32.dll (DispatchMessageW + 0x1af) [0xb1ef]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (main + 0x22e) [0x7f13e]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (invoke_main + 0x34) [0x228394]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (__scrt_common_main_seh + 0x127) [0x2282c7]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (__scrt_common_main + 0xe) [0x22818e]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (mainCRTStartup + 0x9) [0x2283a9]
========= Host Frame:C:\Windows\System32\KERNEL32.DLL (BaseThreadInitThunk + 0x14) [0x11fe4]
========= Host Frame:C:\Windows\SYSTEM32\ntdll.dll (RtlUserThreadStart + 0x21) [0x6efc1]

========= Program hit cudaErrorInvalidConfiguration (error 9) due to “invalid configuration argument” on CUDA API call to cudaPeekAtLastError.
========= Saved host backtrace up to driver entry point at error
========= Host Frame:C:\Windows\system32\nvcuda.dll (cuGraphicsResourceGetMappedPointer + 0x2cbecc) [0x2d959b]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\cudart64_91.dll (cudaPeekAtLastError + 0x107) [0x1d117]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::cuda_cub::__parallel_for::parallel_for<thrust::cuda_cub::__transform::unary_transform_f<unsigned __int64 * __ptr64,thrust::device_ptr,thrust::cuda_cub::__transform::no_stencil_tag,thrust::identity,thrust::cuda_cub::__transform::always_true_predicate>,__int64> + 0xf1) [0xdd621]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::cuda_cub::parallel_for<thrust::cuda_cub::tag,thrust::cuda_cub::__transform::unary_transform_f<unsigned __int64 * __ptr64,thrust::device_ptr,thrust::cuda_cub::__transform::no_stencil_tag,thrust::identity,thrust::cuda_cub::__transform::always_true_predicate>,__int64> + 0x77) [0xdee47]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::cuda_cub::__transform::unary<thrust::cuda_cub::execution_policythrust::cuda_cub::tag,unsigned __int64 * __ptr64,__int64,thrust::device_ptr,thrust::cuda_cub::__transform::no_stencil_tag,thrust::identity,thrust::cuda_cub::__transform::always_true_predicate> + 0xc3) [0xeb553]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::cuda_cub::transform_if<thrust::cuda_cub::tag,unsigned __int64 * __ptr64,thrust::device_ptr,thrust::cuda_cub::__transform::no_stencil_tag,thrust::identity,thrust::cuda_cub::__transform::always_true_predicate> + 0x8b) [0xe90bb]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::cuda_cub::transform_if<thrust::cuda_cub::tag,unsigned __int64 * __ptr64,thrust::device_ptr,thrust::identity,thrust::cuda_cub::__transform::always_true_predicate> + 0x74) [0xe9024]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::cuda_cub::transform<thrust::cuda_cub::tag,unsigned __int64 * __ptr64,thrust::device_ptr,thrust::identity > + 0x68) [0xe83d8]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::cuda_cub::__copy::device_to_device<thrust::cuda_cub::tag,unsigned __int64 * __ptr64,thrust::device_ptr > + 0x59) [0xcd949]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::cuda_cub::copy_n<thrust::cuda_cub::tag,unsigned __int64 * __ptr64,__int64,thrust::device_ptr > + 0x73) [0xca4f3]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::cuda_cub::__copy::cross_system_copy_n<thrust::system::cpp::detail::tag,thrust::cuda_cub::tag,std::_Vector_const_iterator<std::_Vector_val<std::_Simple_types > >,__int64,thrust::device_ptr > + 0x1e4) [0xcba44]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::cuda_cub::__copy::cross_system_copy_n<thrust::system::cpp::detail::tag,thrust::cuda_cub::tag,std::_Vector_const_iterator<std::_Vector_val<std::_Simple_types > >,__int64,thrust::device_ptr > + 0xd4) [0xcbb94]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::cuda_cub::__copy::cross_system_copy<thrust::system::cpp::detail::tag,thrust::cuda_cub::tag,std::_Vector_const_iterator<std::_Vector_val<std::_Simple_types > >,thrust::device_ptr > + 0x12b) [0xcab9b]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::cuda_cub::copy<thrust::system::cpp::detail::tag,thrust::cuda_cub::tag,std::_Vector_const_iterator<std::_Vector_val<std::_Simple_types > >,thrust::device_ptr > + 0xde) [0xc8fbe]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::copy<thrust::cuda_cub::cross_systemthrust::system::cpp::detail::tag,thrust::cuda_cub::tag,std::_Vector_const_iterator<std::_Vector_val<std::_Simple_types > >,thrust::device_ptr > + 0xfe) [0xc7e9e]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::detail::two_system_copy<thrust::system::cpp::detail::tag,thrust::cuda_cub::tag,std::_Vector_const_iterator<std::_Vector_val<std::_Simple_types > >,thrust::device_ptr > + 0x11f) [0xeb06f]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::detail::allocator_traits_detail::copy_construct_range<thrust::system::cpp::detail::tag,thrust::device_malloc_allocator,std::_Vector_const_iterator<std::_Vector_val<std::_Simple_types > >,thrust::device_ptr > + 0xf1) [0xc9f31]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::detail::copy_construct_range<thrust::system::cpp::detail::tag,thrust::device_malloc_allocator,std::_Vector_const_iterator<std::_Vector_val<std::_Simple_types > >,thrust::device_ptr > + 0xcd) [0xca02d]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::detail::contiguous_storage<unsigned __int64,thrust::device_malloc_allocator >::uninitialized_copy<std::_Vector_const_iterator<std::_Vector_val<std::_Simple_types > > > + 0xf4) [0xec8c4]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::detail::vector_base<unsigned __int64,thrust::device_malloc_allocator >::allocate_and_copy<std::_Vector_const_iterator<std::_Vector_val<std::_Simple_types > > > + 0x1cd) [0xc674d]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::detail::vector_base<unsigned __int64,thrust::device_malloc_allocator >::range_init<std::_Vector_const_iterator<std::_Vector_val<std::_Simple_types > > > + 0x157) [0xe53f7]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::detail::vector_base<unsigned __int64,thrust::device_malloc_allocator >::range_init<std::_Vector_const_iterator<std::_Vector_val<std::_Simple_types > > > + 0xa6) [0xe5276]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::detail::vector_base<unsigned __int64,thrust::device_malloc_allocator >::vector_base<unsigned __int64,thrust::device_malloc_allocator ><unsigned __int64,std::allocator > + 0xe0) [0xb2c10]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::device_vector<unsigned __int64,thrust::device_malloc_allocator >::device_vector<unsigned __int64,thrust::device_malloc_allocator ><unsigned __int64,std::allocator > + 0x32) [0xb2b22]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (gpu_cloth_solver_block::init_independant_sets + 0x175) [0x1072d5]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (gpu_cloth_solver_block::gpu_cloth_solver_block + 0x159) [0x104ec9]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (plugin_IO::internel_setup + 0x1bf) [0x15ceaf]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (plugin_IO::init_main + 0x190) [0x15cce0]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (plugin_IO::init_from_file + 0x2a6) [0x15cae6]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (mainFrame::mainFrame + 0x217) [0x68ed7]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (UI::GLWnd::MainFrameWindow + 0x6f8) [0x593c8]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (UI::GLWnd::WndProc + 0x33d) [0x5a1ad]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (UI::WindowProc + 0x48) [0x59e48]
========= Host Frame:C:\Windows\System32\USER32.dll (CallWindowProcW + 0x4dd) [0xb85d]
========= Host Frame:C:\Windows\System32\USER32.dll (CallWindowProcW + 0x8b) [0xb40b]
========= Host Frame:C:\Windows\SYSTEM32\OPENGL32.dll (glDebugEntry + 0xf16d) [0x38e5d]
========= Host Frame:C:\Windows\System32\USER32.dll (CallWindowProcW + 0x4dd) [0xb85d]
========= Host Frame:C:\Windows\System32\USER32.dll (DispatchMessageW + 0x1af) [0xb1ef]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (main + 0x22e) [0x7f13e]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (invoke_main + 0x34) [0x228394]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (__scrt_common_main_seh + 0x127) [0x2282c7]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (__scrt_common_main + 0xe) [0x22818e]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (mainCRTStartup + 0x9) [0x2283a9]
========= Host Frame:C:\Windows\System32\KERNEL32.DLL (BaseThreadInitThunk + 0x14) [0x11fe4]
========= Host Frame:C:\Windows\SYSTEM32\ntdll.dll (RtlUserThreadStart + 0x21) [0x6efc1]

========= Program hit cudaErrorInvalidConfiguration (error 9) due to “invalid configuration argument” on CUDA API call to cudaPeekAtLastError.
========= Saved host backtrace up to driver entry point at error
========= Host Frame:C:\Windows\system32\nvcuda.dll (cuGraphicsResourceGetMappedPointer + 0x2cbecc) [0x2d959b]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\cudart64_91.dll (cudaPeekAtLastError + 0x107) [0x1d117]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::cuda_cub::__parallel_for::parallel_for<thrust::cuda_cub::__transform::unary_transform_f<unsigned __int64 * __ptr64,thrust::device_ptr,thrust::cuda_cub::__transform::no_stencil_tag,thrust::identity,thrust::cuda_cub::__transform::always_true_predicate>,__int64> + 0x10e) [0xdd63e]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::cuda_cub::parallel_for<thrust::cuda_cub::tag,thrust::cuda_cub::__transform::unary_transform_f<unsigned __int64 * __ptr64,thrust::device_ptr,thrust::cuda_cub::__transform::no_stencil_tag,thrust::identity,thrust::cuda_cub::__transform::always_true_predicate>,__int64> + 0x77) [0xdee47]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::cuda_cub::__transform::unary<thrust::cuda_cub::execution_policythrust::cuda_cub::tag,unsigned __int64 * __ptr64,__int64,thrust::device_ptr,thrust::cuda_cub::__transform::no_stencil_tag,thrust::identity,thrust::cuda_cub::__transform::always_true_predicate> + 0xc3) [0xeb553]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::cuda_cub::transform_if<thrust::cuda_cub::tag,unsigned __int64 * __ptr64,thrust::device_ptr,thrust::cuda_cub::__transform::no_stencil_tag,thrust::identity,thrust::cuda_cub::__transform::always_true_predicate> + 0x8b) [0xe90bb]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::cuda_cub::transform_if<thrust::cuda_cub::tag,unsigned __int64 * __ptr64,thrust::device_ptr,thrust::identity,thrust::cuda_cub::__transform::always_true_predicate> + 0x74) [0xe9024]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::cuda_cub::transform<thrust::cuda_cub::tag,unsigned __int64 * __ptr64,thrust::device_ptr,thrust::identity > + 0x68) [0xe83d8]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::cuda_cub::__copy::device_to_device<thrust::cuda_cub::tag,unsigned __int64 * __ptr64,thrust::device_ptr > + 0x59) [0xcd949]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::cuda_cub::copy_n<thrust::cuda_cub::tag,unsigned __int64 * __ptr64,__int64,thrust::device_ptr > + 0x73) [0xca4f3]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::cuda_cub::__copy::cross_system_copy_n<thrust::system::cpp::detail::tag,thrust::cuda_cub::tag,std::_Vector_const_iterator<std::_Vector_val<std::_Simple_types > >,__int64,thrust::device_ptr > + 0x1e4) [0xcba44]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::cuda_cub::__copy::cross_system_copy_n<thrust::system::cpp::detail::tag,thrust::cuda_cub::tag,std::_Vector_const_iterator<std::_Vector_val<std::_Simple_types > >,__int64,thrust::device_ptr > + 0xd4) [0xcbb94]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::cuda_cub::__copy::cross_system_copy<thrust::system::cpp::detail::tag,thrust::cuda_cub::tag,std::_Vector_const_iterator<std::_Vector_val<std::_Simple_types > >,thrust::device_ptr > + 0x12b) [0xcab9b]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::cuda_cub::copy<thrust::system::cpp::detail::tag,thrust::cuda_cub::tag,std::_Vector_const_iterator<std::_Vector_val<std::_Simple_types > >,thrust::device_ptr > + 0xde) [0xc8fbe]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::copy<thrust::cuda_cub::cross_systemthrust::system::cpp::detail::tag,thrust::cuda_cub::tag,std::_Vector_const_iterator<std::_Vector_val<std::_Simple_types > >,thrust::device_ptr > + 0xfe) [0xc7e9e]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::detail::two_system_copy<thrust::system::cpp::detail::tag,thrust::cuda_cub::tag,std::_Vector_const_iterator<std::_Vector_val<std::_Simple_types > >,thrust::device_ptr > + 0x11f) [0xeb06f]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::detail::allocator_traits_detail::copy_construct_range<thrust::system::cpp::detail::tag,thrust::device_malloc_allocator,std::_Vector_const_iterator<std::_Vector_val<std::_Simple_types > >,thrust::device_ptr > + 0xf1) [0xc9f31]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::detail::copy_construct_range<thrust::system::cpp::detail::tag,thrust::device_malloc_allocator,std::_Vector_const_iterator<std::_Vector_val<std::_Simple_types > >,thrust::device_ptr > + 0xcd) [0xca02d]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::detail::contiguous_storage<unsigned __int64,thrust::device_malloc_allocator >::uninitialized_copy<std::_Vector_const_iterator<std::_Vector_val<std::_Simple_types > > > + 0xf4) [0xec8c4]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::detail::vector_base<unsigned __int64,thrust::device_malloc_allocator >::allocate_and_copy<std::_Vector_const_iterator<std::_Vector_val<std::_Simple_types > > > + 0x1cd) [0xc674d]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::detail::vector_base<unsigned __int64,thrust::device_malloc_allocator >::range_init<std::_Vector_const_iterator<std::_Vector_val<std::_Simple_types > > > + 0x157) [0xe53f7]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::detail::vector_base<unsigned __int64,thrust::device_malloc_allocator >::range_init<std::_Vector_const_iterator<std::_Vector_val<std::_Simple_types > > > + 0xa6) [0xe5276]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::detail::vector_base<unsigned __int64,thrust::device_malloc_allocator >::vector_base<unsigned __int64,thrust::device_malloc_allocator ><unsigned __int64,std::allocator > + 0xe0) [0xb2c10]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (thrust::device_vector<unsigned __int64,thrust::device_malloc_allocator >::device_vector<unsigned __int64,thrust::device_malloc_allocator ><unsigned __int64,std::allocator > + 0x32) [0xb2b22]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (gpu_cloth_solver_block::init_independant_sets + 0x175) [0x1072d5]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (gpu_cloth_solver_block::gpu_cloth_solver_block + 0x159) [0x104ec9]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (plugin_IO::internel_setup + 0x1bf) [0x15ceaf]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (plugin_IO::init_main + 0x190) [0x15cce0]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (plugin_IO::init_from_file + 0x2a6) [0x15cae6]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (mainFrame::mainFrame + 0x217) [0x68ed7]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (UI::GLWnd::MainFrameWindow + 0x6f8) [0x593c8]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (UI::GLWnd::WndProc + 0x33d) [0x5a1ad]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (UI::WindowProc + 0x48) [0x59e48]
========= Host Frame:C:\Windows\System32\USER32.dll (CallWindowProcW + 0x4dd) [0xb85d]
========= Host Frame:C:\Windows\System32\USER32.dll (CallWindowProcW + 0x8b) [0xb40b]
========= Host Frame:C:\Windows\SYSTEM32\OPENGL32.dll (glDebugEntry + 0xf16d) [0x38e5d]
========= Host Frame:C:\Windows\System32\USER32.dll (CallWindowProcW + 0x4dd) [0xb85d]
========= Host Frame:C:\Windows\System32\USER32.dll (DispatchMessageW + 0x1af) [0xb1ef]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (main + 0x22e) [0x7f13e]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (invoke_main + 0x34) [0x228394]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (__scrt_common_main_seh + 0x127) [0x2282c7]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (__scrt_common_main + 0xe) [0x22818e]
========= Host Frame:C:\Users\ivasa\Desktop\2015\bin\Clothsim.exe (mainCRTStartup + 0x9) [0x2283a9]
========= Host Frame:C:\Windows\System32\KERNEL32.DLL (BaseThreadInitThunk + 0x14) [0x11fe4]
========= Host Frame:C:\Windows\SYSTEM32\ntdll.dll (RtlUserThreadStart + 0x21) [0x6efc1]

========= ERROR SUMMARY: 4 errors

C:\Windows\system32>[/b]

Please check this.

Three options come to my mind

a) thrust has a newly introduced bug in the 9.1 CUDA release
b) thrust used to tolerate incorrect (e.g. zero) input data sizes in a previous release, but no longer does in release 9.1
c) your application only passes incorrect data to thrust only when running with CUDA 9.1

You may want to inspect what data you pass to the thrust libraries in these two functions to determine which of the above might apply.

gpu_cloth_solver::init_edge_rest_len()
gpu_cloth_solver_block::init_independant_sets()

If your use of the thrust API looks correct, then try modifying line 143 in “C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v9.1\include\thrust\system\cuda\detail\parallel_for.h” to print out the exact block and grid and shared memory size passed to the kernel launch. See if they are out of bounds (e.g. zero block or grid dimension, or too large shared memory requests).

If you find out of bounds, maybe you will be able to backtrack how the incorrect kernel launch arguments are getting computed inside thrust.

Christian

removed duplicate

After looking at your code again, it appears this CUDA API function also reports a failure

CUresult cuGraphicsResourceGetMappedPointer ( CUdeviceptr* pDevPtr, size_t* pSize, CUgraphicsResource resource )

http://docs.nvidia.com/cuda/cuda-driver-api/group__CUDA__GRAPHICS.html

Are you doing any mapping of OpenGL or DirectX graphics resources into the CUDA address space?

The CUDA error code 9 (invalid configuration argument) is unexpected for this function. It is expected to return one of these errors:

CUDA_SUCCESS, CUDA_ERROR_DEINITIALIZED, CUDA_ERROR_NOT_INITIALIZED, CUDA_ERROR_INVALID_CONTEXT, CUDA_ERROR_INVALID_VALUE, CUDA_ERROR_INVALID_HANDLE, CUDA_ERROR_NOT_MAPPED, CUDA_ERROR_NOT_MAPPED_AS_POINTER

It might be that this error code simply carried over from a previous kernel launch attempt in thrust’s parallel_for where there wasn’t a proper error check.

Thanks Christian,

I followed your above suggestion and in the parallel_for i print the data at the line 143:

[b]parallel_for_plan = {block_threads=256 items_per_thread=2 items_per_tile=512 …}

{block_threads=256 items_per_thread=2 items_per_tile=512 …}

block_threads = 256
items_per_thread = 2
items_per_tile = 512
shared_memory_size = 0
grid_size = 0
stream = 0x0000000000000001 {…}

debug_sync = false
num_items = 72
cudaSuccess = cudaSuccess (0)
count = 72[/b]

The problem is coming while the gpu_cloth_solver_block::init_independant_sets() running.

I am storing the vector data in the thrust::device_vector.
vector host_face_indepSet_ends[7]= {3,8,13,18,21,25,27}

[b]gmt.init_coloring_system();

///////// face
//// host end temporary containers for independant sets & combined array
std::vector<size_t> host_face_indepSet_ends;
std::vector<size_t> host_face_indepSet_combined_array;

size_t numFaceColors = gmt.getNumFaceColors();
const std::vector<size_t>& face_colors = gmt.getFaceColorArray();

for(size_t color = 0; color < numFaceColors; color++)	// for each color
{
	// scan the whole array for specific color
	for(size_t f = 0; f < face_colors.size(); f++)
	{
		if(face_colors[f] == color)
			host_face_indepSet_combined_array.push_back(f);
	}

	// update independant set end
	host_face_indepSet_ends.push_back (host_face_indepSet_combined_array.size() - 1);
}

//// update the device end arrays
face_indepSet_ends = thrust::device_vector< size_t > (host_face_indepSet_ends);
face_indepSet_combined_array = thrust::device_vector< size_t > (host_face_indepSet_combined_array);[/b]

this is the function data and the problem is coming with face_indepSet_ends = thrust::device_vector< size_t > (host_face_indepSet_ends); and getting the problem.

I am using the opengl with this project.

Please check the above and help me.

Thanks.

Hello Christian,

Please suggest me what to do with this thrust.

Hello Dev Team,

Please help me with the above issue, invalid configuration argument of Thrust with cuda 9.1.

Hello Team,

I solved the Nsight debugger issue with the Cuda project.

I Identify the Cuda version that you are using, Installed the Cuda toolkit with custom install and choose the driver that comes with the Toolkit, this removes the pre-installed drivers.

Now go to the Nsight site [url]NVIDIA GameWorks Documentation
and choose that version of the Nsight which support the installed graphics driver , This works for me in my both the projects:
one with Cuda 7.5 in which i used the driver 353.90 and Nsight 4.7,
second project with the Cuda 8 and the driver version 377.55 and Nsight 5.2.

Thanks.