我试图在pyopencl中学习字符串操作。我找到了一个示例程序，在这里将字符串复制到空字符串中 - How to pass a list of strings to an opencl kernel using pyopencl?代码本身有一些错误，我不确定我是否能够修复。这是我使用的修改后的代码 -
import numpy as np
import pyopencl as cl
ctx = cl.create_some_context()
queue = cl.CommandQueue(ctx)
#The kernel uses one workitem per char transfert
prog_str = """__kernel void foo(__global char *in, __global char *out, const int size){
int idx = get_global_id(0);
if (idx < size){
out[idx] = in[idx];
}
}"""
#Note that the type of the array of strings is '|S40' for the length
#of third element is 40, the shape is 3 and the nbytes is 120 (3 * 40)
original_str = np.array(("this is an average string",
"and another one",
"let's push even more with a third string"))
str_size = len(original_str)
copied_str = np.empty_like(original_str)
mf = cl.mem_flags
#length = (str_size+1) * 200
in_buf = cl.Buffer(ctx, mf.READ_ONLY | mf.COPY_HOST_PTR, hostbuf=original_str)
out_buf = cl.Buffer(ctx, mf.WRITE_ONLY, size=copied_str.nbytes)
#here launch the kernel with str_size number of workitems in this case 120
#this mean that some of the workitems won't process any meaningful char
#(not all string have a lenght of 40) but it's no biggiea
prog = cl.Program(ctx, prog_str).build()
event = prog.foo(queue, original_str.shape , None, in_buf, out_buf, np.int32(120))
event.wait()
cl.enqueue_copy(queue, copied_str, out_buf)
print(original_str)
print(copied_str)
但是，现在我得到一个unicode解码错误，我无法解决这个问题。如果我谷歌它我只能得到问题与转义字符的主题。
这是错误 -
Traceback (most recent call last):
File "clStringTest.py", line 34, in <module>
print(copied_str)
File "/home/user/miniconda3/envs/pyopencl-env/lib/python3.7/site-packages/numpy/core/arrayprint.py", line 1504, in array_str
return array2string(a, max_line_width, precision, suppress_small, ' ', "")
File "/home/user/miniconda3/envs/pyopencl-env/lib/python3.7/site-packages/numpy/core/arrayprint.py", line 668, in array2string
return _array2string(a, options, separator, prefix)
File "/home/user/miniconda3/envs/pyopencl-env/lib/python3.7/site-packages/numpy/core/arrayprint.py", line 460, in wrapper
return f(self, *args, **kwargs)
File "/home/user/miniconda3/envs/pyopencl-env/lib/python3.7/site-packages/numpy/core/arrayprint.py", line 495, in _array2string
summary_insert, options['legacy'])
File "/home/user/miniconda3/envs/pyopencl-env/lib/python3.7/site-packages/numpy/core/arrayprint.py", line 796, in _formatArray
curr_width=line_width)
File "/home/user/miniconda3/envs/pyopencl-env/lib/python3.7/site-packages/numpy/core/arrayprint.py", line 750, in recurser
word = recurser(index + (-i,), next_hanging_indent, next_width)
File "/home/user/miniconda3/envs/pyopencl-env/lib/python3.7/site-packages/numpy/core/arrayprint.py", line 704, in recurser
return format_function(a[index])
UnicodeDecodeError: 'utf-32-le' codec can't decode bytes in position 8-11: code point not in range(0x110000)
我已经设法找到整数/浮点运算的示例程序，这些程序工作。但我无法找到字符串操作的工作示例。
如果有人能帮助我，我将不胜感激。
更新1：在我的桌面上，我得到了unicode错误，起初至少 -
In [1]: %run clStringTest.py
Choose platform:
[0] <pyopencl.Platform 'NVIDIA CUDA' at 0x5597858ab040>
[1] <pyopencl.Platform 'Portable Computing Language' at 0x7fb273e39020>
Choice [0]:0
Set the environment variable PYOPENCL_CTX='0' to avoid being asked again.
['t' 'h' 'i' 's' ' ' 'i' 's' ' ' 'a' 'n' ' ' 'a' 'v' 'e' 'r' 'a' 'g' 'e'
' ' 's' 't' 'r' 'i' 'n' 'g' ',' ' ' 'a' 'n' 'd' ' ' 'a' 'n' 'o' 't' 'h'
'e' 'r' ' ' 'o' 'n' 'e' ',' ' ' 'l' 'e' 't' "'" 's' ' ' 'p' 'u' 's' 'h'
' ' 'e' 'v' 'e' 'n' ' ' 'm' 'o' 'r' 'e' ' ' 'w' 'i' 't' 'h' ' ' 'a' ' '
't' 'h' 'i' 'r' 'd' ' ' 's' 't' 'r' 'i' 'n' 'g']
84
---------------------------------------------------------------------------
UnicodeDecodeError Traceback (most recent call last)
~/Documents/clStringTest.py in <module>
30 print(original_str)
31 print(len(original_str))
---> 32 print(copied_str)
~/miniconda3/envs/pyopencl-env/lib/python3.7/site-packages/numpy/core/arrayprint.py in array_str(a, max_line_width, precision, suppress_small)
1502 return _guarded_str(np.ndarray.__getitem__(a, ()))
1503
-> 1504 return array2string(a, max_line_width, precision, suppress_small, ' ', "")
1505
1506 def set_string_function(f, repr=True):
~/miniconda3/envs/pyopencl-env/lib/python3.7/site-packages/numpy/core/arrayprint.py in array2string(a, max_line_width, precision, suppress_small, separator, prefix, style, formatter, threshold, edgeitems, sign, floatmode, suffix, **kwarg)
666 return "[]"
667
--> 668 return _array2string(a, options, separator, prefix)
669
670
~/miniconda3/envs/pyopencl-env/lib/python3.7/site-packages/numpy/core/arrayprint.py in wrapper(self, *args, **kwargs)
458 repr_running.add(key)
459 try:
--> 460 return f(self, *args, **kwargs)
461 finally:
462 repr_running.discard(key)
~/miniconda3/envs/pyopencl-env/lib/python3.7/site-packages/numpy/core/arrayprint.py in _array2string(a, options, separator, prefix)
493 lst = _formatArray(a, format_function, options['linewidth'],
494 next_line_prefix, separator, options['edgeitems'],
--> 495 summary_insert, options['legacy'])
496 return lst
497
~/miniconda3/envs/pyopencl-env/lib/python3.7/site-packages/numpy/core/arrayprint.py in _formatArray(a, format_function, line_width, next_line_prefix, separator, edge_items, summary_insert, legacy)
794 return recurser(index=(),
795 hanging_indent=next_line_prefix,
--> 796 curr_width=line_width)
797 finally:
798 # recursive closures have a cyclic reference to themselves, which
~/miniconda3/envs/pyopencl-env/lib/python3.7/site-packages/numpy/core/arrayprint.py in recurser(index, hanging_indent, curr_width)
748
749 for i in range(trailing_items, 1, -1):
--> 750 word = recurser(index + (-i,), next_hanging_indent, next_width)
751 s, line = _extendLine(
752 s, line, word, elem_width, hanging_indent, legacy)
~/miniconda3/envs/pyopencl-env/lib/python3.7/site-packages/numpy/core/arrayprint.py in recurser(index, hanging_indent, curr_width)
702
703 if axes_left == 0:
--> 704 return format_function(a[index])
705
706 # when recursing, add a space to align with the [ added, and reduce the
UnicodeDecodeError: 'utf-32-le' codec can't decode bytes in position 0-3: code point not in range(0x110000)
然而，然后我通过miniconda安装了POCL。突然间，如果我通过GPU执行程序，程序就可以正常工作......至少我不再得到unicode错误了。
$ python3 clStringTest.py
Choose platform:
[0] <pyopencl.Platform 'NVIDIA CUDA' at 0x5561780b9f20>
[1] <pyopencl.Platform 'Portable Computing Language' at 0x7f30edb41020>
Choice [0]:0
Set the environment variable PYOPENCL_CTX='0' to avoid being asked again.
(84,)
['t' 'h' 'i' 's' ' ' 'i' 's' ' ' 'a' 'n' ' ' 'a' 'v' 'e' 'r' 'a' 'g' 'e'
' ' 's' 't' 'r' 'i' 'n' 'g' ',' ' ' 'a' 'n' 'd' ' ' 'a' 'n' 'o' 't' 'h'
'e' 'r' ' ' 'o' 'n' 'e' ',' ' ' 'l' 'e' 't' "'" 's' ' ' 'p' 'u' 's' 'h'
' ' 'e' 'v' 'e' 'n' ' ' 'm' 'o' 'r' 'e' ' ' 'w' 'i' 't' 'h' ' ' 'a' ' '
't' 'h' 'i' 'r' 'd' ' ' 's' 't' 'r' 'i' 'n' 'g']
84
['t' 'h' 'i' 's' ' ' 'i' 's' ' ' 'a' 'n' ' ' 'a' 'v' 'e' 'r' 'a' 'g' 'e'
' ' 's' 't' '' '' '' '' '' '' '' '' '' '' '' '' '' '' '' '' '' '' '' ''
'' '' '' '' '' '' '' '' '' '' '' '' '' '' '' '' '' '' '' '' '' '' '' ''
'' '' '' '' '' '' '' '' '' '' '' '' '' '' '' '' '' '' '']
奇怪的是，在CPU上执行仍然给我同样的错误。
在这一点上，我不知所措，不得不相信这是一个错误。 @doqtor你怎么看？
更新2：我试图看看如果增加工作项的数量和内核的大小参数会发生什么。经过一些试验和错误后，我终于得到了@doqtor所示的输出，使用了（400，）工作项和400大小。我不知道为什么会这样。
$ python3 clStringTest.py
Choose platform:
[0] <pyopencl.Platform 'NVIDIA CUDA' at 0x55f0f357ef20>
[1] <pyopencl.Platform 'Portable Computing Language' at 0x7fb8c82f6020>
Choice [0]:
Set the environment variable PYOPENCL_CTX='' to avoid being asked again.
['t' 'h' 'i' 's' ' ' 'i' 's' ' ' 'a' 'n' ' ' 'a' 'v' 'e' 'r' 'a' 'g' 'e'
' ' 's' 't' 'r' 'i' 'n' 'g' ',' ' ' 'a' 'n' 'd' ' ' 'a' 'n' 'o' 't' 'h'
'e' 'r' ' ' 'o' 'n' 'e' ',' ' ' 'l' 'e' 't' "'" 's' ' ' 'p' 'u' 's' 'h'
' ' 'e' 'v' 'e' 'n' ' ' 'm' 'o' 'r' 'e' ' ' 'w' 'i' 't' 'h' ' ' 'a' ' '
't' 'h' 'i' 'r' 'd' ' ' 's' 't' 'r' 'i' 'n' 'g']
84
['t' 'h' 'i' 's' ' ' 'i' 's' ' ' 'a' 'n' ' ' 'a' 'v' 'e' 'r' 'a' 'g' 'e'
' ' 's' 't' 'r' 'i' 'n' 'g' ',' ' ' 'a' 'n' 'd' ' ' 'a' 'n' 'o' 't' 'h'
'e' 'r' ' ' 'o' 'n' 'e' ',' ' ' 'l' 'e' 't' "'" 's' ' ' 'p' 'u' 's' 'h'
' ' 'e' 'v' 'e' 'n' ' ' 'm' 'o' 'r' 'e' ' ' 'w' 'i' 't' 'h' ' ' 'a' ' '
't' 'h' 'i' 'r' 'd' ' ' 's' 't' 'r' 'i' 'n' 'g']
现在它也适用于CPU，但是在打印输出数组后我得到了 -
corrupted size vs. prev_size
Aborted (core dumped)
如果我减少工件数量（300及以下）或大小，我会再次在CPU上获得可怕的unicode错误。在GPU上，我得到了如上所示的缺少字符。
运行代码会在我的环境中出现以下问题（我没有遇到Unicode错误问题）：
输入字符串（original_str）：
['this is an average string' 'and another one'
"let's push even more with a third string"]
输出字符串（copied_str）：
[ 'thiM\x1b\x7f\x00\x00 c\x0fM\x1b\x7f\x00\x00\xd0i\x0fM\x1b\x7f\x00\x00\xe0b\x0fM\x1b\x7f\x00\x00ph\x0fM\x1b\x7f'
'pa\x0fM\x1b\x7f\x00\x00\xf0f\x0fM\x1b\x7f\x00\x00\x90\xce\x0eM\x1b\x7f\x00\x00\x80l\x0fM\x1b\x7f\x00\x00\x80k\x0fM\x1b\x7f'
'\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x80\xb8\x0eM\x1b\x7f\x00\x00\xc0\xbd\x0eM\x1b\x7f']
输出中的前3个字符只是正确的，其余字符是垃圾 - 这是因为global_size由于将original_str定义为（3，）而设置为3。应该将original_str定义为1维numpy数组，如下所示，以解决上述问题：
original_str = np.array(list("this is an average string, and another one, let's push even more with a third string"))
然后全局大小是（84，），一切都应该按预期工作：
输入字符串（original_str）：
['t' 'h' 'i' 's' ' ' 'i' 's' ' ' 'a' 'n' ' ' 'a' 'v' 'e' 'r' 'a' 'g' 'e'
' ' 's' 't' 'r' 'i' 'n' 'g' ',' ' ' 'a' 'n' 'd' ' ' 'a' 'n' 'o' 't' 'h'
'e' 'r' ' ' 'o' 'n' 'e' ',' ' ' 'l' 'e' 't' "'" 's' ' ' 'p' 'u' 's' 'h'
' ' 'e' 'v' 'e' 'n' ' ' 'm' 'o' 'r' 'e' ' ' 'w' 'i' 't' 'h' ' ' 'a' ' '
't' 'h' 'i' 'r' 'd' ' ' 's' 't' 'r' 'i' 'n' 'g']
输出字符串（copied_str）：
['t' 'h' 'i' 's' ' ' 'i' 's' ' ' 'a' 'n' ' ' 'a' 'v' 'e' 'r' 'a' 'g' 'e'
' ' 's' 't' 'r' 'i' 'n' 'g' ',' ' ' 'a' 'n' 'd' ' ' 'a' 'n' 'o' 't' 'h'
'e' 'r' ' ' 'o' 'n' 'e' ',' ' ' 'l' 'e' 't' "'" 's' ' ' 'p' 'u' 's' 'h'
' ' 'e' 'v' 'e' 'n' ' ' 'm' 'o' 'r' 'e' ' ' 'w' 'i' 't' 'h' ' ' 'a' ' '
't' 'h' 'i' 'r' 'd' ' ' 's' 't' 'r' 'i' 'n' 'g']
正如前面评论中所述，将多维数组传递给OpenCL内核是行不通的。内核只能正确处理单维C风格的数组。
正如@nova发现的那样，如果numpy数组有标志C_CONTIGUOUS : True，可以通过print(original_str.flags)验证，那么numpy数组的字符串也会起作用。然后它就足以将(original_str.nbytes,)作为global_size传递而不对原始源代码进行任何其他修改。