LogicError: create_buffer failed: invalid buffer size

[robintw]

I've been testing convolve and comparing it to the ndimage implementation. Running the following code:

import gputools import numpy as np img = np.random.rand(10000, 10000) kernel = np.ones((3, 3)) res = gputools.convolve(img, kernel)

Gives the error below. I assume this is due to my GPU not having enough space to store this array - is that correct? The array is around 762Mb, so I guess that might be too large?

---------------------------------------------------------------------------
LogicError                                Traceback (most recent call last)
<ipython-input-10-867ee5568ea6> in <module>()
----> 1 get_ipython().magic(u'timeit res = gputools.convolve(img, kernel)')

/Users/robin/.conda/envs/python2/lib/python2.7/site-packages/IPython/core/interactiveshell.pyc in magic(self, arg_s)
   2305         magic_name, _, magic_arg_s = arg_s.partition(' ')
   2306         magic_name = magic_name.lstrip(prefilter.ESC_MAGIC)
-> 2307         return self.run_line_magic(magic_name, magic_arg_s)
   2308
   2309     #-------------------------------------------------------------------------

/Users/robin/.conda/envs/python2/lib/python2.7/site-packages/IPython/core/interactiveshell.pyc in run_line_magic(self, magic_name, line)
   2226                 kwargs['local_ns'] = sys._getframe(stack_depth).f_locals
   2227             with self.builtin_trap:
-> 2228                 result = fn(*args,**kwargs)
   2229             return result
   2230

/Users/robin/.conda/envs/python2/lib/python2.7/site-packages/IPython/core/magics/execution.pyc in timeit(self, line, cell)

/Users/robin/.conda/envs/python2/lib/python2.7/site-packages/IPython/core/magic.pyc in <lambda>(f, *a, **k)
    191     # but it's overkill for just that one bit of state.
    192     def magic_deco(arg):
--> 193         call = lambda f, *a, **k: f(*a, **k)
    194
    195         if callable(arg):

/Users/robin/.conda/envs/python2/lib/python2.7/site-packages/IPython/core/magics/execution.pyc in timeit(self, line, cell)
   1034             number = 1
   1035             for _ in range(1, 10):
-> 1036                 time_number = timer.timeit(number)
   1037                 worst_tuning = max(worst_tuning, time_number / number)
   1038                 if time_number >= 0.2:

/Users/robin/.conda/envs/python2/lib/python2.7/site-packages/IPython/core/magics/execution.pyc in timeit(self, number)
    130         gc.disable()
    131         try:
--> 132             timing = self.inner(it, self.timer)
    133         finally:
    134             if gcold:

<magic-timeit> in inner(_it, _timer)

/Users/robin/.conda/envs/python2/lib/python2.7/site-packages/gputools-0.1.1-py2.7.egg/gputools/convolve/convolve.pyc in convolve(data, h, res_g)
     35         return _convolve_buf(data,h, res_g)
     36     elif isinstance(data,np.ndarray) and  isinstance(h,np.ndarray):
---> 37         return _convolve_np(data,h)
     38
     39     else:

/Users/robin/.conda/envs/python2/lib/python2.7/site-packages/gputools-0.1.1-py2.7.egg/gputools/convolve/convolve.pyc in _convolve_np(data, h)
     50
     51
---> 52     data_g = OCLArray.from_array(data.astype(np.float32, copy = False))
     53     h_g = OCLArray.from_array(h.astype(np.float32, copy = False))
     54

/Users/robin/.conda/envs/python2/lib/python2.7/site-packages/gputools-0.1.1-py2.7.egg/gputools/core/ocltypes.pyc in from_array(cls, arr, *args, **kwargs)
     27     def from_array(cls,arr,*args, **kwargs):
     28         queue = get_device().queue
---> 29         return cl_array.to_device(queue, arr,*args, **kwargs)
     30     @classmethod
     31     def empty(cls, shape, dtype = np.float32):

/Users/robin/.local/lib/python2.7/site-packages/pyopencl/array.pyc in to_device(queue, ary, allocator, async)
   1676
   1677     result = Array(queue, ary.shape, ary.dtype,
-> 1678                     allocator=allocator, strides=ary.strides)
   1679     result.set(ary, async=async)
   1680     return result

/Users/robin/.local/lib/python2.7/site-packages/pyopencl/array.pyc in __init__(self, cqa, shape, dtype, order, allocator, data, offset, queue, strides, events)
    564
    565                 self.base_data = cl.Buffer(
--> 566                         context, cl.mem_flags.READ_WRITE, alloc_nbytes)
    567             else:
    568                 self.base_data = self.allocator(alloc_nbytes)

LogicError: create_buffer failed: invalid buffer size

[robintw]

Just for reference, this works fine with smaller array sizes, so I suspect it is due to my rubbish graphics card (I know very little about GPUs, but apparently a GeForce 320M is not good!)

[maweigert]

Yes, that is essentially an out of memory error. You can find out about the maximal allocatable memory of the used by printing the device info like so

gputools.get_device().print_info()