skcuda.linalg.norm¶
-
skcuda.linalg.
norm
(x_gpu, handle=None)[source]¶ Euclidean norm (2-norm) of real vector.
Computes the Euclidean norm of an array.
Parameters: - x_gpu (pycuda.gpuarray.GPUArray) – Input array.
- handle (int) – CUBLAS context. If no context is specified, the default handle from skcuda.misc._global_cublas_handle is used.
Returns: nrm – Euclidean norm of x.
Return type: real
Examples
>>> import pycuda.autoinit >>> import pycuda.gpuarray as gpuarray >>> import numpy as np >>> import skcuda.linalg as linalg >>> linalg.init() >>> x = np.asarray(np.random.rand(4, 4), np.float32) >>> x_gpu = gpuarray.to_gpu(x) >>> nrm = linalg.norm(x_gpu) >>> np.allclose(nrm, np.linalg.norm(x)) True >>> x_gpu = gpuarray.to_gpu(np.array([3+4j, 12-84j])) >>> linalg.norm(x_gpu) 85.0