nvidia-cublas-cu11

import numpy as np from numba import cuda import math @cuda.jit def matmul(A, B, C): # Perform matrix multiplication of C = A * B row, col = cuda.grid(2) if row < C.shape[0] and col < C.shape[1]: tmp = 0. for k in range(A.shape[1]): tmp += A[row, k] * B[k, col] C[row, col] = tmp # Example usage N = 256 A_host = np.random.rand(N, N).astype(np.float32) B_host = np.random.rand(N, N).astype(np.float32) C_host = np.zeros((N, N), dtype=np.float32) # Allocate device memory A_device = cuda.to_device(A_host) B_device = cuda.to_device(B_host) C_device = cuda.to_device(C_host) # Configure the blocks and threads threads_per_block = (16, 16) blocks_per_grid_x = int(math.ceil(A_host.shape[0] / threads_per_block[0])) blocks_per_grid_y = int(math.ceil(B_host.shape[1] / threads_per_block[1])) blocks_per_grid = (blocks_per_grid_x, blocks_per_grid_y) # Launch the kernel matmul[blocks_per_grid, threads_per_block](A_device, B_device, C_device) # Copy the result back to the host C_result = C_device.copy_to_host() print('Matrix multiplication completed on GPU (via Numba wrapping CUBLAS).') # For verification (optional, requires higher-level libraries to implicitly use CUBLAS or direct numpy CPU op) # C_numpy = np.dot(A_host, B_host) # print(f"Max absolute difference: {np.max(np.abs(C_result - C_numpy))}") # Should be very small