使用PyCUDA连接cuSOLVER稀疏

我正在尝试使用PyCUDA来连接稀疏cuSOLVER例程cusolverSpDcsrlsvqr（）（> = CUDA 7.0），并且遇到了一些困难：我试图以将密集cuSolver例程包裹在scikits-cuda（https：/中的方式）包装这些方法/github.com/lebedov/scikits.cuda/blob/master/scikits/cuda/cusolver.py）。

但是，在调用cusolverSpDcsrlsvqr（）函数时，代码因分段错误而崩溃。使用cuda-gdb（cuda-gdb --args python -m pycuda.debug test.py; run;bt）进行调试会产生以下堆栈跟踪，

来自/usr/local/cuda/lib64/libcusolver.so中的cusolverSpXcsrissymHost（）中的＃0 0x00007fffd9e3b71a（1
）来自/ usr / local / cudar_xr_x_rx_x0_x（0 * 0764）的0x00007fffd9e3b71a来自/ usr / local / cuda / lib64 / libcus_analys0（764） / usr
/ local /
lib / lib中的/local/cuda/lib64/libcusolver.so＃3 0x00007fffd9f160a0在cusolverXcsrqr_analysis（）中/usr/local/cuda/lib64/libcusolver.so＃4 0x00007fffd9f28d78在cusolverSpScsrlsvqr（）中。

这很奇怪，因为我既不调用cusolverSp S csrlsvqr（），也不认为它应该调用宿主函数（cusolverSpXcsrissym Host）。

这是我正在谈论的代码-感谢您的帮助：

# ### Interface cuSOLVER PyCUDA


import pycuda.gpuarray as gpuarray
import pycuda.driver as cuda
import pycuda.autoinit
import numpy as np
import scipy.sparse as sp
import ctypes


# #### wrap the cuSOLVER cusolverSpDcsrlsvqr() using ctypes

# cuSparse
_libcusparse = ctypes.cdll.LoadLibrary('libcusparse.so')

class cusparseMatDescr_t(ctypes.Structure):
    _fields_ = [
        ('MatrixType', ctypes.c_int),
        ('FillMode', ctypes.c_int),
        ('DiagType', ctypes.c_int),
        ('IndexBase', ctypes.c_int)
        ]
_libcusparse.cusparseCreate.restype = int
_libcusparse.cusparseCreate.argtypes = [ctypes.c_void_p]

_libcusparse.cusparseDestroy.restype = int
_libcusparse.cusparseDestroy.argtypes = [ctypes.c_void_p]

_libcusparse.cusparseCreateMatDescr.restype = int
_libcusparse.cusparseCreateMatDescr.argtypes = [ctypes.c_void_p]


# cuSOLVER
_libcusolver = ctypes.cdll.LoadLibrary('libcusolver.so')



_libcusolver.cusolverSpCreate.restype = int
_libcusolver.cusolverSpCreate.argtypes = [ctypes.c_void_p]

_libcusolver.cusolverSpDestroy.restype = int
_libcusolver.cusolverSpDestroy.argtypes = [ctypes.c_void_p]



_libcusolver.cusolverSpDcsrlsvqr.restype = int
_libcusolver.cusolverSpDcsrlsvqr.argtypes= [ctypes.c_void_p,
                                            ctypes.c_int,
                                            ctypes.c_int,
                                            cusparseMatDescr_t,
                                            ctypes.c_void_p,
                                            ctypes.c_void_p,
                                            ctypes.c_void_p,
                                            ctypes.c_void_p,
                                            ctypes.c_double,
                                            ctypes.c_int,
                                            ctypes.c_void_p,
                                            ctypes.c_void_p]


#### Prepare the matrix and parameters, copy to Device via gpuarray

# coo to csr
val = np.arange(1,5,dtype=np.float64)
col = np.arange(0,4,dtype=np.int32)
row = np.arange(0,4,dtype=np.int32)
A = sp.coo_matrix((val,(row,col))).todense()
Acsr = sp.csr_matrix(A)
b = np.ones(4)
x = np.empty(4)
print('A:' + str(A))
print('b: ' + str(b))


dcsrVal = gpuarray.to_gpu(Acsr.data)
dcsrColInd = gpuarray.to_gpu(Acsr.indices)
dcsrIndPtr = gpuarray.to_gpu(Acsr.indptr)
dx = gpuarray.to_gpu(x)
db = gpuarray.to_gpu(b)
m = ctypes.c_int(4)
nnz = ctypes.c_int(4)
descrA = cusparseMatDescr_t()
reorder = ctypes.c_int(0)
tol = ctypes.c_double(1e-10)
singularity = ctypes.c_int(99)


#create cusparse handle
_cusp_handle = ctypes.c_void_p()
status = _libcusparse.cusparseCreate(ctypes.byref(_cusp_handle))
print('status: ' + str(status))
cusp_handle = _cusp_handle.value

#create MatDescriptor
status = _libcusparse.cusparseCreateMatDescr(ctypes.byref(descrA))
print('status: ' + str(status))

#create cusolver handle
_cuso_handle = ctypes.c_void_p()
status = _libcusolver.cusolverSpCreate(ctypes.byref(_cuso_handle))
print('status: ' + str(status))
cuso_handle = _cuso_handle.value



print('cusp handle: ' + str(cusp_handle))
print('cuso handle: ' + str(cuso_handle))


### Call solver
_libcusolver.cusolverSpDcsrlsvqr(cuso_handle,
                                 m,
                                 nnz,
                                 descrA,
                                 int(dcsrVal.gpudata),
                                 int(dcsrIndPtr.gpudata),
                                 int(dcsrColInd.gpudata),
                                 int(db.gpudata),
                                 tol,
                                 reorder,
                                 int(dx.gpudata),
                                 ctypes.byref(singularity))

# destroy handles
status = _libcusolver.cusolverSpDestroy(cuso_handle)
print('status: ' + str(status))
status = _libcusparse.cusparseDestroy(cusp_handle)
print('status: ' + str(status))