I'm trying to batch up a bunch of vertices and texture coords in an interleaved array before sending it to pyOpengl's glInterleavedArrays/glDrawArrays. The only problem is that I'm unable to find a suitably fast enough way to append data into a numpy array.

Is there a better way to do this? I would have thought it would be quicker to preallocate the array and then fill it with data but instead, generating a python list and converting it to a numpy array is "faster". Although 15ms for 4096 quads seems slow.

I have included some example code and their timings.

#!/usr/bin/python

import timeit
import numpy
import ctypes
import random

USE_RANDOM=True
USE_STATIC_BUFFER=True

STATIC_BUFFER = numpy.empty(4096*20, dtype=numpy.float32)

def render(i):
    # pretend these are different each time
    if USE_RANDOM:
        tex_left, tex_right, tex_top, tex_bottom = random.random(), random.random(), random.random(), random.random()
        left, right, top, bottom = random.random(), random.random(), random.random(), random.random()
    else:
        tex_left, tex_right, tex_top, tex_bottom = 0.0, 1.0, 1.0, 0.0
        left, right, top, bottom = -1.0, 1.0, 1.0, -1.0

    ibuffer = (
        tex_left, tex_bottom,   left, bottom, 0.0,  # Lower left corner
        tex_right, tex_bottom,  right, bottom, 0.0, # Lower right corner
        tex_right, tex_top,     right, top, 0.0,    # Upper right corner
        tex_left, tex_top,      left, top, 0.0,     # upper left
    )

    return ibuffer



# create python list.. convert to numpy array at end
def create_array_1():
    ibuffer = []
    for x in xrange(4096):
        data = render(x)
        ibuffer += data

    ibuffer = numpy.array(ibuffer, dtype=numpy.float32)
    return ibuffer

# numpy.array, placing individually by index
def create_array_2():
    if USE_STATIC_BUFFER:
        ibuffer = STATIC_BUFFER
    else:
        ibuffer = numpy.empty(4096*20, dtype=numpy.float32)
    index = 0
    for x in xrange(4096):
        data = render(x)
        for v in data:
            ibuffer[index] = v
            index += 1
    return ibuffer

# using slicing
def create_array_3():
    if USE_STATIC_BUFFER:
        ibuffer = STATIC_BUFFER
    else:
        ibuffer = numpy.empty(4096*20, dtype=numpy.float32)
    index = 0
    for x in xrange(4096):
        data = render(x)
        ibuffer[index:index+20] = data
        index += 20
    return ibuffer

# using numpy.concat on a list of ibuffers
def create_array_4():
    ibuffer_concat = []
    for x in xrange(4096):
        data = render(x)
        # converting makes a diff!
        data = numpy.array(data, dtype=numpy.float32)
        ibuffer_concat.append(data)
    return numpy.concatenate(ibuffer_concat)

# using numpy array.put
def create_array_5():
    if USE_STATIC_BUFFER:
        ibuffer = STATIC_BUFFER
    else:
        ibuffer = numpy.empty(4096*20, dtype=numpy.float32)
    index = 0
    for x in xrange(4096):
        data = render(x)
        ibuffer.put( xrange(index, index+20), data)
        index += 20
    return ibuffer

# using ctype array
CTYPES_ARRAY = ctypes.c_float*(4096*20)
def create_array_6():
    ibuffer = []
    for x in xrange(4096):
        data = render(x)
        ibuffer += data
    ibuffer = CTYPES_ARRAY(*ibuffer)
    return ibuffer

def equals(a, b):

    for i,v in enumerate(a):
        if b[i] != v:
            return False
    return True



if __name__ == "__main__":
    number = 100

    # if random, don't try and compare arrays
    if not USE_RANDOM and not USE_STATIC_BUFFER:
        a =  create_array_1()
        assert equals( a, create_array_2() )
        assert equals( a, create_array_3() )
        assert equals( a, create_array_4() )
        assert equals( a, create_array_5() )
        assert equals( a, create_array_6() )

    t = timeit.Timer( "testing2.create_array_1()", "import testing2" )
    print 'from list:', t.timeit(number)/number*1000.0, 'ms'

    t = timeit.Timer( "testing2.create_array_2()", "import testing2" )
    print 'array: indexed:', t.timeit(number)/number*1000.0, 'ms'

    t = timeit.Timer( "testing2.create_array_3()", "import testing2" )
    print 'array: slicing:', t.timeit(number)/number*1000.0, 'ms'

    t = timeit.Timer( "testing2.create_array_4()", "import testing2" )
    print 'array: concat:', t.timeit(number)/number*1000.0, 'ms'

    t = timeit.Timer( "testing2.create_array_5()", "import testing2" )
    print 'array: put:', t.timeit(number)/number*1000.0, 'ms'

    t = timeit.Timer( "testing2.create_array_6()", "import testing2" )
    print 'ctypes float array:', t.timeit(number)/number*1000.0, 'ms'

Timings using random numbers:

$ python testing2.py
from list: 15.0486779213 ms
array: indexed: 24.8184704781 ms
array: slicing: 50.2214789391 ms
array: concat: 44.1691994667 ms
array: put: 73.5879898071 ms
ctypes float array: 20.6674289703 ms

edit note: changed code to produce random numbers for each render to reduce object reuse and to simulate different vertices each time.

edit note2: added static buffer and force all numpy.empty() to use dtype=float32

note 1/Apr/2010: still no progress and I don't really feel that any of the answers have solved the problem yet.