def test_cublasDgeam(self):
a = np.random.rand(2, 3).astype(np.float64)
b = np.random.rand(2, 3).astype(np.float64)
a_gpu = gpuarray.to_gpu(a.copy())
b_gpu = gpuarray.to_gpu(b.copy())
c_gpu = gpuarray.zeros_like(a_gpu)
alpha = np.float64(np.random.rand())
beta = np.float64(np.random.rand())
cublas.cublasDgeam(self.cublas_handle, 'n', 'n', 2, 3, alpha,
a_gpu.gpudata, 2, beta, b_gpu.gpudata, 2,
c_gpu.gpudata, 2)
assert np.allclose(c_gpu.get(), alpha * a + beta * b)
def test_cublasDgeam(self):
a = np.random.rand(2, 3).astype(np.float64)
b = np.random.rand(2, 3).astype(np.float64)
a_gpu = gpuarray.to_gpu(a.copy())
b_gpu = gpuarray.to_gpu(b.copy())
c_gpu = gpuarray.zeros_like(a_gpu)
alpha = np.float64(np.random.rand())
beta = np.float64(np.random.rand())
cublas.cublasDgeam(self.cublas_handle, 'n', 'n', 2, 3,
alpha, a_gpu.gpudata, 2,
beta, b_gpu.gpudata, 2,
c_gpu.gpudata, 2)
assert np.allclose(c_gpu.get(), alpha*a+beta*b)