http://stackoverflow.com/a/12287839/1404992

results.txt

$ /usr/bin/time --verbose python test.py py uint32 
9.54168200493
	Command being timed: "python test.py py uint32"
	User time (seconds): 11.04
	System time (seconds): 1.46
	Percent of CPU this job got: 98%
	Elapsed (wall clock) time (h:mm:ss or m:ss): 0:12.73
	Average shared text size (kbytes): 0
	Average unshared data size (kbytes): 0
	Average stack size (kbytes): 0
	Average total size (kbytes): 0
	Maximum resident set size (kbytes): 1581780
	Average resident set size (kbytes): 0
	Major (requiring I/O) page faults: 0
	Minor (reclaiming a frame) page faults: 642581
	Voluntary context switches: 1
	Involuntary context switches: 1319
	Swaps: 0
	File system inputs: 0
	File system outputs: 0
	Socket messages sent: 0
	Socket messages received: 0
	Signals delivered: 0
	Page size (bytes): 4096
	Exit status: 0


$ /usr/bin/time --verbose python test.py numpy uint32
2.85147213936
	Command being timed: "python test.py numpy uint32"
	User time (seconds): 4.55
	System time (seconds): 1.29
	Percent of CPU this job got: 97%
	Elapsed (wall clock) time (h:mm:ss or m:ss): 0:05.97
	Average shared text size (kbytes): 0
	Average unshared data size (kbytes): 0
	Average stack size (kbytes): 0
	Average total size (kbytes): 0
	Maximum resident set size (kbytes): 1580980
	Average resident set size (kbytes): 0
	Major (requiring I/O) page faults: 0
	Minor (reclaiming a frame) page faults: 229431
	Voluntary context switches: 1
	Involuntary context switches: 627
	Swaps: 0
	File system inputs: 0
	File system outputs: 0
	Socket messages sent: 0
	Socket messages received: 0
	Signals delivered: 0
	Page size (bytes): 4096
	Exit status: 0


$ /usr/bin/time --verbose python test.py numpy uint64
8.09631299973
	Command being timed: "python test.py numpy uint64"
	User time (seconds): 8.94
	System time (seconds): 2.18
	Percent of CPU this job got: 98%
	Elapsed (wall clock) time (h:mm:ss or m:ss): 0:11.29
	Average shared text size (kbytes): 0
	Average unshared data size (kbytes): 0
	Average stack size (kbytes): 0
	Average total size (kbytes): 0
	Maximum resident set size (kbytes): 2002840
	Average resident set size (kbytes): 0
	Major (requiring I/O) page faults: 0
	Minor (reclaiming a frame) page faults: 232937
	Voluntary context switches: 1
	Involuntary context switches: 1153
	Swaps: 0
	File system inputs: 0
	File system outputs: 0
	Socket messages sent: 0
	Socket messages received: 0
	Signals delivered: 0
	Page size (bytes): 4096
	Exit status: 0


# after removing all reference to numpy from test.py 
/usr/bin/time --verbose pypy test.py
0.00810503959656
	Command being timed: "pypy test.py"
	User time (seconds): 0.21
	System time (seconds): 0.03
	Percent of CPU this job got: 97%
	Elapsed (wall clock) time (h:mm:ss or m:ss): 0:00.25
	Average shared text size (kbytes): 0
	Average unshared data size (kbytes): 0
	Average stack size (kbytes): 0
	Average total size (kbytes): 0
	Maximum resident set size (kbytes): 57072
	Average resident set size (kbytes): 0
	Major (requiring I/O) page faults: 0
	Minor (reclaiming a frame) page faults: 14117
	Voluntary context switches: 1
	Involuntary context switches: 29
	Swaps: 0
	File system inputs: 0
	File system outputs: 0
	Socket messages sent: 0
	Socket messages received: 0
	Signals delivered: 0
	Page size (bytes): 4096
	Exit status: 0

test.py

#!/usr/bin/env python

import timeit, sys
from numpy import arange, roll, column_stack, uint32, uint64

n = 6000
intsize = globals()[sys.argv[2]]

values_array = arange(0, 36000000, dtype=intsize)
values_list  = range(0, 36000000)

def reshape_numpy():
    idx = roll(arange(0, values_array.size, n), -1)
    column_stack( (values_array.reshape(n, -1), values_array[idx]) )

def reshape_py():
    splitlists = [values_list[i:i+n] for i in range(0, len(values_list), n-1)]
    splitlists[-1].append(splitlists[0][0])

if sys.argv[1] == 'numpy':
    t = timeit.Timer(stmt=reshape_numpy)
elif sys.argv[1] == 'py':
    t = timeit.Timer(stmt=reshape_py)

print(t.timeit(10))