scikits.cuda.linalg.mdot

scikits.cuda.linalg.mdot(*args, **kwargs)[source]

Product of several matrices.

Computes the matrix product of several arrays of shapes.

Parameters:

a_gpu, b_gpu, ... : pycuda.gpuarray.GPUArray

Arrays to multiply.

handle : int

CUBLAS context. If no context is specified, the default handle from scikits.cuda.misc._global_cublas_handle is used.

Returns:

c_gpu : pycuda.gpuarray.GPUArray

Matrix product of a_gpu, b_gpu, etc.

Notes

The input matrices must all contain elements of the same data type.

Examples

>>> import pycuda.gpuarray as gpuarray
>>> import pycuda.autoinit
>>> import numpy as np
>>> import linalg
>>> linalg.init()
>>> a = np.asarray(np.random.rand(4, 2), np.float32)
>>> b = np.asarray(np.random.rand(2, 2), np.float32)
>>> c = np.asarray(np.random.rand(2, 2), np.float32)
>>> a_gpu = gpuarray.to_gpu(a)
>>> b_gpu = gpuarray.to_gpu(b)
>>> c_gpu = gpuarray.to_gpu(c)
>>> d_gpu = linalg.mdot(a_gpu, b_gpu, c_gpu)
>>> np.allclose(np.dot(a, np.dot(b, c)), d_gpu.get())
True