我正在尝试将scikit-cuda的包装器用于cuSOLVER函数,特别是我想执行cusolverDnSgesvd来计算实数矩阵上的全矩阵单精度SVD。
import pycuda.autoinit
import pycuda.driver as drv
import pycuda.gpuarray as gpuarray
import numpy as np
from skcuda import cusolver
handle = cusolver.cusolverDnCreate()
m = 50
n = 25
a = np.asarray(np.random.random((m, n)))
a_gpu = gpuarray.to_gpu(a)
ldu = m
ldvt = n
s_gpu = gpuarray.empty(min(m, n), np.float32)
u_gpu = gpuarray.empty((ldu, m), np.float32)
vh_gpu = gpuarray.empty((n, n), np.float32)
work_size = cusolver.cusolverDnSgesvd_bufferSize(handle, m, n)
work = gpuarray.empty((m,n), np.float32)
u_gpu, s_gpu, vh_gpu = cusolver.cusolverDnSgesvd(
handle=handle,
jobu='A',
jobvt='A',
m=m,
n=n,
A=a,
lda=m,
S=s_gpu,
U=u_gpu,
ldu=ldu,
VT=vh_gpu,
ldvt=ldvt,
Work=work,
Lwork=work_size,
rwork=None,
devInfo=0
)
但代码不起作用,可能是因为我弄乱了类型。
Traceback (most recent call last):
File "/home/vektor/PycharmProjects/yancut/test_svd.py", line 44, in <module>
devInfo=0
File "/home/vektor/anaconda3/lib/python3.4/site-packages/skcuda/cusolver.py", line 577, in cusolverDnSgesvd
int(A), lda, int(S), int(U),
TypeError: only length-1 arrays can be converted to Python scalars
我应该如何提供所有参数,以便以正确的方式执行SVD?
UPDATE1: 在使用this问题作为参考后,我编辑了代码并收到了新错误。
import pycuda.autoinit
import pycuda.driver as drv
import pycuda.gpuarray as gpuarray
import numpy as np
import ctypes
from skcuda import cusolver
rows = 20
cols = 10
a = np.asarray(np.random.random((rows, cols)))
a_gpu = gpuarray.to_gpu(a.copy())
lda = rows
u_gpu = gpuarray.empty((rows, rows), np.float32)
v_gpu = gpuarray.empty((cols, cols), np.float32)
s_gpu = gpuarray.empty(cols, np.float32)
devInfo = gpuarray.zeros(1, np.int32)
handle = cusolver.cusolverDnCreate()
worksize = cusolver.cusolverDnSgesvd_bufferSize(handle, rows, cols)
print("SIZE", worksize)
Workspace = gpuarray.empty(worksize, np.float32)
svd_status = cusolver.cusolverDnSgesvd(
handle=handle,
jobu='A',
jobvt='A',
m=rows,
n=cols,
A=a_gpu.ptr,
lda=rows,
S=s_gpu.ptr,
U=u_gpu.ptr,
ldu=rows,
VT=v_gpu.ptr,
ldvt=cols,
Work=Workspace.ptr,
Lwork=worksize,
rwork=Workspace.ptr,
devInfo=devInfo.ptr
)
status = cusolver.cusolverDnDestroy(handle)
我收到了新错误
Traceback (most recent call last):
File "/home/vektor/PycharmProjects/yancut/test_svd.py", line 53, in <module>
devInfo=devInfo.ptr
File "/home/vektor/anaconda3/lib/python3.4/site-packages/skcuda/cusolver.py", line 579, in cusolverDnSgesvd
Lwork, int(rwork), int(devInfo))
ctypes.ArgumentError: argument 2: <class 'TypeError'>: wrong type
现在看来,我对devInfo
做错了答案 0 :(得分:2)
从documentation看起来每个矩阵(所以A
,S
,U
,VT
)都需要作为设备指针传递。因此对于PyCUDA gpuarrays,传递A.ptr
而不是A
。它应该工作。