Question

我对SSE编码非常新 - 我希望将带有int32类型的_m128i [4]的结果存储到一个带有int8类型的_m128i。（_m128i [j] ._ i32 [k]的值都在（-127和+ 127）之间

我认为在伪代码中这是以下内容：

 result._i8 = { 
           vec1._i8[0], vec1._i8[4], vec1._i8[8], vec1._i8[12],
           vec2._i8[0], vec2._i8[4], vec2._i8[8], vec2._i8[12],
           vec3._i8[0], vec3._i8[4], vec3._i8[8], vec3._i8[12],          
           vec4._i8[0], vec4._i8[4], vec4._i8[8], vec4._i8[12]};

我发现的唯一方法是这种混乱的洗牌。

    __m128i mmResult, mmResult0_3, mmResult4_7, mmResult8_11, mmResult12_15;
    //some calculation ...

    __m128i mmShuffler0_3 = _mm_set_epi8(-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,-1,12, 8, 4, 0);
    __m128i mmShuffler4_7 = _mm_set_epi8(-1, -1, -1, -1, -1, -1, -1, -1, 12, 8, 4, 0, -1, -1, -1, -1);
    __m128i mmShuffler8_11 = _mm_set_epi8(-1, -1, -1, -1, 12, 8, 4, 0, -1, -1, -1, -1, -1, -1, -1, -1);
    __m128i mmShuffler12_15 = _mm_set_epi8(12, 8, 4, 0, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1);

    mmResult0_3 = _mm_shuffle_epi8(mmResult0_3, mmShuffler0_3);
    mmResult4_7 = _mm_shuffle_epi8(mmResult4_7, mmShuffler4_7);
    mmResult8_11 = _mm_shuffle_epi8(mmResult8_11, mmShuffler8_11);
    mmResult12_15 = _mm_shuffle_epi8(mmResult12_15, mmShuffler12_15);

    mmResult = _mm_or_si128(_mm_or_si128(mmResult0_3, mmResult4_7), _mm_or_si128(mmResult8_11, mmResult12_15));

有没有这样做更漂亮？有没有办法更快地做到这一点？

Answer 1

您可以使用打包操作将32位值减少到8位，例如假设您有4个32位int元素的向量，v0 ... v3：

__m128i v01 = _mm_packs_epi32(v0, v1);        // pack v0, v1 to 16 bits
__m128i v23 = _mm_packs_epi32(v2, v3);        // pack v2, v3 to 16 bits
__m128i v0123 = _mm_packs_epi16(v01, v23);    // pack v0...v3 to 8 bits

示例：

#include <xmmintrin.h>
#include <stdio.h>

int main(void)
{
    __m128i v0 = _mm_setr_epi32(-8, -7, -6, -5);
    __m128i v1 = _mm_setr_epi32(-4, -3, -2, -1);
    __m128i v2 = _mm_setr_epi32( 0,  1,  2,  3);
    __m128i v3 = _mm_setr_epi32( 4,  5,  6,  7);

    printf("v0 = %vld\n", v0);
    printf("v1 = %vld\n", v1);
    printf("v2 = %vld\n", v2);
    printf("v3 = %vld\n", v3);

    __m128i v01 = _mm_packs_epi32(v0, v1);        // pack v0, v1 to 16 bits
    __m128i v23 = _mm_packs_epi32(v2, v3);        // pack v2, v3 to 16 bits
    __m128i v0123 = _mm_packs_epi16(v01, v23);    // pack v0...v3 to 8 bits

    printf("v0123 = %vd\n", v01234);

    return 0;
}

编译和测试：

$ gcc -Wall pack_32_8.c && ./a.out
v0 = -8 -7 -6 -5
v1 = -4 -3 -2 -1
v2 = 0 1 2 3
v3 = 4 5 6 7
v0123 = -8 -7 -6 -5 -4 -3 -2 -1 0 1 2 3 4 5 6 7

SSE：如何将_m128i._i32 [4]减少为_m128i._i8

1 个答案: