AES-NI 256位块加密

我正试图使用这段代码，这是从英特尔白皮书中提取的，如下所示。我的目标是使用AES-NI执行256位块加密。我已经使用该方法成功地导出了密钥调度，该方法是在Intel AES-NI库中提供的，用于扩展密钥:iEncExpandKey256(key,expandedKey);扩展密钥在我的非AES- ni AES实现中工作良好。

然而，当我将这些值传递给Rijndael256_encrypt(testVector,testResult,expandedKey,32,1) ;时我得到一个错误的"试图访问受保护的内存，这通常表明内存是损坏的"，并导致这一行的代码是data1 = _mm_xor_si128(data1, KS[0]); /* round 0 (initial xor) */如下所示。

那么我的问题是，对于这样一个错误，可能的错误是什么?我目前的假设是data1和KS[0]的大小可能不同，目前我还在验证中。除此之外，我不确定我还能去哪里看。如果有人能指出我在正确的方向来解决这个错误，我将不胜感激。

#include <wmmintrin.h>
#include <emmintrin.h>
#include <smmintrin.h>
void Rijndael256_encrypt (unsigned char *in,
unsigned char *out,
unsigned char *Key_Schedule,
unsigned long long length,
int number_of_rounds)
{
__m128i tmp1, tmp2, data1 ,data2;
__m128i RIJNDAEL256_MASK =
_mm_set_epi32(0x03020d0c, 0x0f0e0908, 0x0b0a0504, 0x07060100);
__m128i BLEND_MASK=
_mm_set_epi32(0x80000000, 0x80800000, 0x80800000, 0x80808000);
__m128i *KS = (__m128i*)Key_Schedule;
int i,j;
for(i=0; i < length/32; i++) { /* loop over the data blocks */
data1 = _mm_loadu_si128(&((__m128i*)in)[i*2+0]); /* load data block */
data2 = _mm_loadu_si128(&((__m128i*)in)[i*2+1]);
data1 = _mm_xor_si128(data1, KS[0]); /* round 0 (initial xor) */
data2 = _mm_xor_si128(data2, KS[1]);
/* Do number_of_rounds-1 AES rounds */
for(j=1; j < number_of_rounds; j++) {
/*Blend to compensate for the shift rows shifts bytes between two
128 bit blocks*/
tmp1 = _mm_blendv_epi8(data1, data2, BLEND_MASK);
tmp2 = _mm_blendv_epi8(data2, data1, BLEND_MASK);
/*Shuffle that compensates for the additional shift in rows 3 and 4
as opposed to rijndael128 (AES)*/
tmp1 = _mm_shuffle_epi8(tmp1, RIJNDAEL256_MASK);
tmp2 = _mm_shuffle_epi8(tmp2, RIJNDAEL256_MASK);
/*This is the encryption step that includes sub bytes, shift rows,
mix columns, xor with round key*/
data1 = _mm_aesenc_si128(tmp1, KS[j*2]);
data2 = _mm_aesenc_si128(tmp2, KS[j*2+1]);
}
tmp1 = _mm_blendv_epi8(data1, data2, BLEND_MASK);
tmp2 = _mm_blendv_epi8(data2, data1, BLEND_MASK);
tmp1 = _mm_shuffle_epi8(tmp1, RIJNDAEL256_MASK);
tmp2 = _mm_shuffle_epi8(tmp2, RIJNDAEL256_MASK);
tmp1 = _mm_aesenclast_si128(tmp1, KS[j*2+0]); /*last AES round */
tmp2 = _mm_aesenclast_si128(tmp2, KS[j*2+1]);
_mm_storeu_si128(&((__m128i*)out)[i*2+0],tmp1);
_mm_storeu_si128(&((__m128i*)out)[i*2+1],tmp2);
}
}