def per_item_cpu(vector_r, matrix_A, matrix_B, matrix_BT, alpha):
vector_r_index = vector_r.nonzero()[0]
vector_r_small = vector_r.data
vector_c_small = alpha * vector_r_small
matrix_B_small = np.take(matrix_B, vector_r_index, axis=0)
matrix_BT_small = np.take(matrix_BT, vector_r_index, axis=1)
denominator = cpu_inv(matrix_A+(matrix_BT_small*vector_c_small).dot(matrix_B_small))
return (denominator.dot(matrix_BT_small)).dot((vector_c_small*vector_r_small+vector_r_small).T).flatten()
def _impl_test_inv(self, dtype):
from scipy.linalg import inv as cpu_inv
x = np.asarray(np.random.rand(4, 4), dtype)
x = np.dot(x.T, x)
x_gpu = gpuarray.to_gpu(x)
xinv = cpu_inv(x)
xinv_gpu = linalg.inv(x_gpu)
assert np.allclose(xinv, xinv_gpu.get(), atol=1e-5)
assert xinv_gpu is not x_gpu
xinv_gpu = linalg.inv(x_gpu, overwrite=True)
assert np.allclose(xinv, xinv_gpu.get(), atol=1e-5)
assert xinv_gpu is x_gpu
def impl_test_inv(self, dtype):
from scipy.linalg import inv as cpu_inv
x = np.asarray(np.random.rand(4, 4), dtype)
x = np.dot(x.T, x)
x_gpu = gpuarray.to_gpu(x)
xinv = cpu_inv(x)
xinv_gpu = linalg.inv(x_gpu)
assert np.allclose(xinv, xinv_gpu.get(), atol=1e-5)
assert xinv_gpu is not x_gpu
xinv_gpu = linalg.inv(x_gpu, overwrite=True)
assert np.allclose(xinv, xinv_gpu.get(), atol=1e-5)
assert xinv_gpu is x_gpu