我正在比较几个 Python 模块/扩展或方法以实现以下目标：
import numpy as np
def fdtd(input_grid, steps):
grid = input_grid.copy()
old_grid = np.zeros_like(input_grid)
previous_grid = np.zeros_like(input_grid)
l_x = grid.shape[0]
l_y = grid.shape[1]
for i in range(steps):
np.copyto(previous_grid, old_grid)
np.copyto(old_grid, grid)
for x in range(l_x):
for y in range(l_y):
grid[x,y] = 0.0
if 0 < x+1 < l_x:
grid[x,y] += old_grid[x+1,y]
if 0 < x-1 < l_x:
grid[x,y] += old_grid[x-1,y]
if 0 < y+1 < l_y:
grid[x,y] += old_grid[x,y+1]
if 0 < y-1 < l_y:
grid[x,y] += old_grid[x,y-1]
grid[x,y] /= 2.0
grid[x,y] -= previous_grid[x,y]
return grid
此函数是有限差分时域 (FDTD) 方法的一个非常基本的实现。我已经通过几种方式实现了这个功能：
- 有更多 NumPy 例程
- 在赛通
- 使用 Numba（自动）jit。
现在我想将性能与 NumbaPro CUDA 进行比较。
这是我第一次为 CUDA 编写代码，我想出了下面的代码。
from numbapro import cuda, float32, int16
import numpy as np
@cuda.jit(argtypes=(float32[:,:], float32[:,:], float32[:,:], int16, int16, int16))
def kernel(grid, old_grid, previous_grid, steps, l_x, l_y):
x,y = cuda.grid(2)
for i in range(steps):
previous_grid[x,y] = old_grid[x,y]
old_grid[x,y] = grid[x,y]
for i in range(steps):
grid[x,y] = 0.0
if 0 < x+1 and x+1 < l_x:
grid[x,y] += old_grid[x+1,y]
if 0 < x-1 and x-1 < l_x:
grid[x,y] += old_grid[x-1,y]
if 0 < y+1 and y+1 < l_x:
grid[x,y] += old_grid[x,y+1]
if 0 < y-1 and y-1 < l_x:
grid[x,y] += old_grid[x,y-1]
grid[x,y] /= 2.0
grid[x,y] -= previous_grid[x,y]
def fdtd(input_grid, steps):
grid = cuda.to_device(input_grid)
old_grid = cuda.to_device(np.zeros_like(input_grid))
previous_grid = cuda.to_device(np.zeros_like(input_grid))
l_x = input_grid.shape[0]
l_y = input_grid.shape[1]
kernel[(16,16),(32,8)](grid, old_grid, previous_grid, steps, l_x, l_y)
return grid.copy_to_host()
不幸的是，我收到以下错误：
File ".../fdtd_numbapro.py", line 98, in fdtd
return grid.copy_to_host()
File "/opt/anaconda1anaconda2anaconda3/lib/python2.7/site-packages/numbapro/cudadrv/devicearray.py", line 142, in copy_to_host
File "/opt/anaconda1anaconda2anaconda3/lib/python2.7/site-packages/numbapro/cudadrv/driver.py", line 1702, in device_to_host
File "/opt/anaconda1anaconda2anaconda3/lib/python2.7/site-packages/numbapro/cudadrv/driver.py", line 772, in check_error
numbapro.cudadrv.error.CudaDriverError: CUDA_ERROR_LAUNCH_FAILED
Failed to copy memory D->H
我也使用了 grid.to_host() ，但这也不起作用。CUDA 肯定在这个系统上使用 NumbaPro。