利用NVIDIA的cuSolver库分割Pycuda故障

Question

我正在尝试制作一个受科学资料袋-库达库启发的pycuda包装器，对于新的cuSolver库中提供的一些操作，首先我需要通过cusolverDnSgetrf() op进行LU分解。但在此之前，我需要'Workspace‘参数，这是cuSolver为获取它提供的工具，名为cusolverDnSgetrf_bufferSize()；但是当我使用它时，只需要崩溃并返回分段错误。我做错什么了？

注意:我已经使用了这个运行程序，但是cuSolver库使用了很多这样的论点，并且我想比较一下scikits cuda和我的实现与新库之间的用法。

import numpy as np
import pycuda.gpuarray
import ctypes
import ctypes.util

libcusolver = ctypes.cdll.LoadLibrary('libcusolver.so')

class _types:
  handle = ctypes.c_void_p

libcusolver.cusolverDnCreate.restype = int
libcusolver.cusolverDnCreate.argtypes = [_types.handle]

def cusolverCreate():
    handle = _types.handle()
    libcusolver.cusolverDnCreate(ctypes.byref(handle))
    return handle.value

libcusolver.cusolverDnDestroy.restype = int
libcusolver.cusolverDnDestroy.argtypes = [_types.handle]

def cusolverDestroy(handle):
    libcusolver.cusolverDnDestroy(handle)


libcusolver.cusolverDnSgetrf_bufferSize.restype = int
libcusolver.cusolverDnSgetrf_bufferSize.argtypes =[_types.handle,
                                       ctypes.c_int,
                                       ctypes.c_int,
                                       ctypes.c_void_p,
                                       ctypes.c_int,
                                       ctypes.c_void_p]

def cusolverLUFactorization(handle, matrix):
    m,n=matrix.shape
    mtx_gpu = gpuarray.to_gpu(matrix.astype('float32'))
    work=gpuarray.zeros(1, np.float32)
    status=libcusolver.cusolverDnSgetrf_bufferSize(
                          handle, m, n,
                          int(mtx_gpu.gpudata),
                          n, int(work.gpudata))
    print status


x = np.asarray(np.random.rand(3, 3), np.float32)
handle_solver=cusolverCreate()
cusolverLUFactorization(handle_solver,x)
cusolverDestroy(handle_solver)

Answer 1

cusolverDnSgetrf_bufferSize的最后一个参数应该是一个常规指针，而不是GPU内存指针。尝试按以下方式修改cusolverLUFactorization()函数：

​

def cusolverLUFactorization(handle, matrix):
    m,n=matrix.shape
    mtx_gpu = gpuarray.to_gpu(matrix.astype('float32'))

    work = ctypes.c_int()
    status = libcusolver.cusolverDnSgetrf_bufferSize(
                         handle, m, n,
                         int(mtx_gpu.gpudata),
                         n, ctypes.pointer(work))
    print status
    print work.value

​