import numpy as np
import cudamat as cm

def distance(self, X, useGPU=False):
    if useGPU:
        print("using GPU...")
        W=self.W
        gpu_W = cm.CUDAMatrix(W)
        gpu_X = cm.CUDAMatrix(X)
        gpu_D = cm.empty ((W.shape[0] , X.shape[0]) )
        gpu_X2 = cm.empty (X.shape)
        gpu_W2 = cm.empty (W.shape)

        cm.pow(gpu_X, 2, target=gpu_X2)
        gpu_X2 = gpu_X2.sum(axis=1)
        cm.pow(gpu_W, 2, target=gpu_W2)
        gpu_W2 = gpu_W2.sum(axis=1)

        gpu_D = cm.dot(gpu_W, gpu_X.T)
        gpu_D = gpu_D.mult((-2))
        gpu_D = gpu_D.add_col_vec(gpu_W2)
        gpu_D = gpu_D.add_row_vec(gpu_X2.transpose())

        D_T=gpu_D.transpose().asarray()

        return D_T
    else:
        W = self.W
        X2 = (X**2).sum(1)[:, None]
        D = -2*np.dot(W, X.T) + (W**2).sum(1)[:, None] + X2.T
        return D.T