SSE2内在函数 - 比较无符号整数 [英] SSE2 intrinsics - comparing unsigned integers
问题描述
我有兴趣在添加无符号8位整数时识别溢出值，并将结果饱和到0xFF：
__m128i m1 = _mm_loadu_si128（/ * 16 8位无符号整数* /）;
__m128i m2 = _mm_loadu_si128（/ * 16 8位无符号整数* /）;
__m128i m3 = _mm_adds_epu8（m1，m2）;
我有兴趣对这些无符号整数执行比较，类似于 _mm_cmplt_epi8 for signed：
__ m128i mask = _mm_cmplt_epi8（m3，m1）;
m1 = _mm_or_si128（m3，mask）;
如果epu8等效项可用， mask 将具有 0xFF 其中 m3 [i] m1 [i] （overflow！）， 0x00否则，我们将能够饱和 m1 使用or，因此 m1 将保存有效的加法结果，以及 0xFF 。
问题是， _mm_cmplt_epi8 执行签名比较，因此例如 m1 [ i] = 0x70 和 m2 [i] = 0x10 ，则 m3 [i] = 0x80 和 mask [i] = 0xFF ，这显然不是我需要的。
使用VS2012。 / p>
我会感谢另一种方法来执行此操作。谢谢！
无符号8位向量比较的一种方法是利用 _mm_max_epu8 ，它返回无符号8位int元素的最大值。您可以比较两个元素的（无符号）最大值与其中一个源元素的相等性，然后返回相应的结果。这转换为> = 或 <= 的两条指令，以及 > 或< 。
示例代码：
#include< stdio.h>
#include< emmintrin.h> // SSE2
#define _mm_cmpge_epu8（a，b）\
_mm_cmpeq_epi8（_mm_max_epu8（a，b），a）
#define _mm_cmple_epu8 b）_mm_cmpge_epu8（b，a）
#define _mm_cmpgt_epu8（a，b）\
_mm_xor_si128（_mm_cmple_epu8（a，b），_mm_set1_epi8（-1））
#define _mm_cmplt_epu8（a，b）_mm_cmpgt_epu8（b，a）
int main（void）
{
__m128i va = _mm_setr_epi8（0，0，1， 1，1，127，127，127，128，128，128，254，254，254，255，255）;
__m128i vb = _mm_setr_epi8（0，255，0，1，255，0，127，255，0，128，255，0，254，255，0，255）;
__m128i v_ge = _mm_cmpge_epu8（va，vb）;
__m128i v_le = _mm_cmple_epu8（va，vb）;
__m128i v_gt = _mm_cmpgt_epu8（va，vb）;
__m128i v_lt = _mm_cmplt_epu8（va，vb）;
printf（va =％4vhhu \\\
，va）;
printf（vb =％4vhhu \\\
，vb）;
printf（v_ge =％4vhhu \\\
，v_ge）;
printf（v_le =％4vhhu \\\
，v_le）;
printf（v_gt =％4vhhu \\\
，v_gt）;
printf（v_lt =％4vhhu \\\
，v_lt）;
return 0;
}
编译并运行：
$ gcc -Wall _mm_cmplt_epu8.c&& ./a.out
va = 0 0 1 1 1 127 127 127 128 128 128 254 254 254 255 255
vb = 0 255 0 1 255 0 127 255 0 128 255 0 254 255 0 255 b $ b v_ge = 255 0 255 255 0 255 255 0 255 255 0 255 255 0 255 255
v_le = 255 255 0 255 255 0 255 255 0 255 255 0 255 255 0 255
v_gt = 0 0 255 0 0 255 0 0 255 0 0 255 0 0 255 0
v_lt = 0 255 0 0 255 0 0 255 0 0 255 0 0 255 0 0
I'm interested in identifying overflowing values when adding unsigned 8-bit integers, and saturating the result to 0xFF:
__m128i m1 = _mm_loadu_si128(/* 16 8-bit unsigned integers */);
__m128i m2 = _mm_loadu_si128(/* 16 8-bit unsigned integers */);
__m128i m3 = _mm_adds_epu8(m1, m2);
I would be interested in performing comparison for less than on these unsigned integers, similar to _mm_cmplt_epi8 for signed:
__m128i mask = _mm_cmplt_epi8 (m3, m1);
m1 = _mm_or_si128(m3, mask);
If an "epu8" equivalent was available, mask would have 0xFF where m3[i] < m1[i] (overflow!), 0x00 otherwise, and we would be able to saturate m1 using the "or", so m1 will hold the addition result where valid, and 0xFF where it overflowed.
Problem is, _mm_cmplt_epi8 performs a signed comparison, so for instance if m1[i] = 0x70 and m2[i] = 0x10, then m3[i] = 0x80 and mask[i] = 0xFF, which is obviously not what I require.
Using VS2012.
I would appreciate another approach for performing this. Thanks!
One way of implementing compares for unsigned 8 bit vectors is to exploit _mm_max_epu8, which returns the maximum of unsigned 8 bit int elements. You can compare for equality the (unsigned) maximum value of two elements with one of the source elements and then return the appropriate result. This translates to 2 instructions for >= or <=, and 3 instructions for > or <.
Example code:
#include <stdio.h>
#include <emmintrin.h> // SSE2
#define _mm_cmpge_epu8(a, b) \
_mm_cmpeq_epi8(_mm_max_epu8(a, b), a)
#define _mm_cmple_epu8(a, b) _mm_cmpge_epu8(b, a)
#define _mm_cmpgt_epu8(a, b) \
_mm_xor_si128(_mm_cmple_epu8(a, b), _mm_set1_epi8(-1))
#define _mm_cmplt_epu8(a, b) _mm_cmpgt_epu8(b, a)
int main(void)
{
__m128i va = _mm_setr_epi8(0, 0, 1, 1, 1, 127, 127, 127, 128, 128, 128, 254, 254, 254, 255, 255);
__m128i vb = _mm_setr_epi8(0, 255, 0, 1, 255, 0, 127, 255, 0, 128, 255, 0, 254, 255, 0, 255);
__m128i v_ge = _mm_cmpge_epu8(va, vb);
__m128i v_le = _mm_cmple_epu8(va, vb);
__m128i v_gt = _mm_cmpgt_epu8(va, vb);
__m128i v_lt = _mm_cmplt_epu8(va, vb);
printf("va = %4vhhu\n", va);
printf("vb = %4vhhu\n", vb);
printf("v_ge = %4vhhu\n", v_ge);
printf("v_le = %4vhhu\n", v_le);
printf("v_gt = %4vhhu\n", v_gt);
printf("v_lt = %4vhhu\n", v_lt);
return 0;
}
Compile and run:
$ gcc -Wall _mm_cmplt_epu8.c && ./a.out
va = 0 0 1 1 1 127 127 127 128 128 128 254 254 254 255 255
vb = 0 255 0 1 255 0 127 255 0 128 255 0 254 255 0 255
v_ge = 255 0 255 255 0 255 255 0 255 255 0 255 255 0 255 255
v_le = 255 255 0 255 255 0 255 255 0 255 255 0 255 255 0 255
v_gt = 0 0 255 0 0 255 0 0 255 0 0 255 0 0 255 0
v_lt = 0 255 0 0 255 0 0 255 0 0 255 0 0 255 0 0
这篇关于SSE2内在函数 - 比较无符号整数的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！
