CuPy

>>> import cupy as cp >>> x = cp.array ([ 1 , 2 , 3 ] ) >>> x array ([ 1 , 2 , 3 ] ) >>> y = cp.arange ( 10 ) >>> y array ( [ 0 , 1 , 2 , 3 , 4 , 5 , 6 , 7 , 8 , 9 ] )

>>> import cupy as cp >>> x = cp.arange ( 12 ) .reshape ( 3 , 4 ) .astype ( cp.float32 ) >>> x array ( [ [ 0 , 1 , 2 , 3 ] , [ 4 , 5 , 6 , 7 ] , [ 8 , 9 , 10 , 11 ] ] , dtype = float32 ) >>> x.sum ( axis = 1 ) array ( [ 6 , 22 , 38 ] , dtype = float32 )

>>> import cupy as cp >>> kern = cp.RawKernel ( r ' '' ... extern "C" __global__ ... void multiply_elemwise(const float* in1, const float* in2, float* out) { ... int tid = blockDim.x * blockIdx.x + threadIdx.x; ... out[tid] = in1[tid] * in2[tid] ; ... } ... ' ' ' , ' multiply_elemwise ' ) >>> in1 = cp.arange ( 16 , dtype = cp.float32 ) .reshape ( 4 , 4 ) >>> in2 = cp.arange ( 16 , dtype = cp.float32 ) .reshape ( 4 , 4 ) >>> out = cp . zeros (( 4 , 4 ), dtype = cp.float32 ) >>> kern (( 4 , ) , ( 4 ,), ( in1 , in2 , out )) # الشبكة، والكتلة، والوسائط >>> out array ([[ 0 , 1 , 4 , 9 ], [ 16 , 25 , 36 , 49 ], [ 64 , 81 , 100 , 121 ], [ 144 , 169 , 196 , 225 ]], dtype = float32 )