python教程—简单的Python挑战:数据缓冲区上最快的位XOR-Python实用宝典

# python教程—简单的Python挑战:数据缓冲区上最快的位XOR

<强>挑战:< /强>

```from os import urandom
from numpy import frombuffer,bitwise_xor,byte

def slow_xor(aa,bb):
a=frombuffer(aa,dtype=byte)
b=frombuffer(bb,dtype=byte)
c=bitwise_xor(a,b)
r=c.tostring()
return r

aa=urandom(2**20)
bb=urandom(2**20)

def test_it():
for x in xrange(1000):
slow_xor(aa,bb)
```

# 第一次尝试

```import numpy
import time
from os import urandom
from scipy import weave

SIZE = 2**20

def faster_slow_xor(aa,bb):
b = numpy.fromstring(bb, dtype=numpy.uint64)
numpy.bitwise_xor(numpy.frombuffer(aa,dtype=numpy.uint64), b, b)
return b.tostring()

code = """
const __m128i* pa = (__m128i*)a;
const __m128i* pend = (__m128i*)(a + arr_size);
__m128i* pb = (__m128i*)b;
__m128i xmm1, xmm2;
while (pa < pend) {
xmm1 = _mm_loadu_si128(pa); // must use unaligned access
xmm2 = _mm_load_si128(pb); // numpy will align at 16 byte boundaries
_mm_store_si128(pb, _mm_xor_si128(xmm1, xmm2));
++pa;
++pb;
}
"""

def inline_xor(aa, bb):
a = numpy.frombuffer(aa, dtype=numpy.uint64)
b = numpy.fromstring(bb, dtype=numpy.uint64)
arr_size = a.shape[0]
weave.inline(code, ["a", "b", "arr_size"], headers = ['"emmintrin.h"'])
return b.tostring()
```

# 第二次尝试

```support = """
#define ALIGNMENT 16
static void memxor(const char* in1, const char* in2, char* out, ssize_t n) {
const char* end = in1 + n;
while (in1 < end) {
*out = *in1 ^ *in2;
++in1;
++in2;
++out;
}
}
"""

code2 = """
PyObject* res = PyString_FromStringAndSize(NULL, real_size);

const ssize_t tail = (ssize_t)PyString_AS_STRING(res) % ALIGNMENT;
const ssize_t head = (ALIGNMENT - tail) % ALIGNMENT;

memxor((const char*)a, (const char*)b, PyString_AS_STRING(res), head);

const __m128i* pa = (__m128i*)((char*)a + head);
const __m128i* pend = (__m128i*)((char*)a + real_size - tail);
const __m128i* pb = (__m128i*)((char*)b + head);
__m128i xmm1, xmm2;
__m128i* pc = (__m128i*)(PyString_AS_STRING(res) + head);
while (pa < pend) {
_mm_stream_si128(pc, _mm_xor_si128(xmm1, xmm2));
++pa;
++pb;
++pc;
}
memxor((const char*)pa, (const char*)pb, (char*)pc, tail);
return_val = res;
Py_DECREF(res);
"""

def inline_xor_nocopy(aa, bb):
real_size = len(aa)
a = numpy.frombuffer(aa, dtype=numpy.uint64)
b = numpy.frombuffer(bb, dtype=numpy.uint64)
return weave.inline(code2, ["a", "b", "real_size"],
support_code = support)
```

# 计时

• slow_xor: 1.85 s x (1)
• faster_slow_xor: 1.25秒(1.48 x)
• inline_xor: 0.95秒(1.95 x)
• inline_xor_nocopy: 0.32秒(5.78 x)

​Python实用宝典 (pythondict.com)