最好的方法来计算最大掩码的sse var

(我只对前3个组件感兴趣)

例如

:
[ 1 2 3 ? ]应该产生[ 0 0 -1 ? ]

同样，重要的是只设置一个"位"，以便:
[ 1 2 2 ? ]不应生成[ 0 -1 -1 ? ]
而是
[ 0 -1 0 ? ]或[ 0 0 -1 ? ](无论哪个)

后一种(坏的)解决方案是可能的，例如通过提取水平最大值并与原始值进行比较:

__m128 abcd; // input
__m128 ccac           = _mm_shuffle_ps(abcd, abcd, 0x8A);
__m128 abcd_ccac      = _mm_max_ps(abcd, ccac);
__m128 babb           = _mm_shuffle_ps(abcd, abcd, 0x51);
__m128 abcd_ccac_babb = _mm_max_ps(abcd_ccac, babb);
__m128 mask           = _mm_cmpeq_ps(abcd, abcd_ccac_babb);

也许一些按位操作来消除重复的集合位?

更新:

我又想出了一个(糟糕的)解决办法。
关键是将每个组件与另一个组件进行比较，避免等式(不将a >= b和b >= a放在另一个地方)。

a > b & a >= c
b > c & b >= a
c > a & c >= b

产量:

([ a b c ? ] > [ b c a ? ]) & ([ a b c ? ] >= [ c a b ? ])

和代码中的

__m128 abcd; // input
__m128 bcad = _mm_shuffle_ps(abcd, abcd, 0xC9);
__m128 gt   = _mm_cmpgt_ps(abcd, bcad);
__m128 cabd = _mm_shuffle_ps(abcd, abcd, 0xD2);
__m128 ge   = _mm_cmpge_ps(abcd, cabd);
__m128 mask = _mm_and_ps(gt, ge);

在[ x x x ? ]的情况下失败(生成[ 0 0 0 ? ])。

接近:-)

任何想法?

更新:

我现在使用以下解决方案:

__m128  abcd; // input
__m128  bcad = _mm_shuffle_ps(abcd, abcd, 0xC9);
__m128  gt   = _mm_cmpgt_ps(abcd, bcad);
__m128  cabd = _mm_shuffle_ps(abcd, abcd, 0xD2);
__m128  ge   = _mm_cmpge_ps(abcd, cabd);
__m128  and  = _mm_and_ps(gt, ge);
__m128i bits = _mm_setr_epi32(_mm_movemask_ps(and), -1, -1, -1);
__m128i dirt = _mm_cmpeq_epi32(bits, _mm_setzero_si128());
__m128i mask = _mm_or_si128(dirt, _mm_castps_si128(and));

__m128 abcd; // input
__m128 ccac = _mm_shuffle_ps( abcd,abcd,0x8A );
__m128 abcd_ccac = _mm_max_ps( abcd,ccac );
__m128 babb = _mm_shuffle_ps( abcd,abcd,0x51 );
__m128 abcd_ccac_babb = _mm_max_ps( abcd_ccac,babb );
__m128 mask = _mm_cmpeq_ps( abcd,abcd_ccac_babb );
// set the '?' position in mask to zero
mask = _mm_blend_ps( mask,_mm_setzero_ps(),0x08 );
// shift mask left 32 bits shifting in zeros
__m128 maskSrl32 = _mm_shuffle_ps( mask,mask,_MM_SHUFFLE( 3,1,0,3 ) );
// shift mask left 64 bits shifting in zeros
__m128 maskSrl64 = _mm_shuffle_ps( mask,mask,_MM_SHUFFLE( 3,0,3,3 ) );
// andnot the shifted masks with mask
// in doing so, the higher order set bits will suppress any set bits which follow
mask = _mm_andnot_ps( maskSrl32,mask );
mask = _mm_andnot_ps( maskSrl64,mask );
// select -1 using the final mask
__m128 result = _mm_and_ps( mask,_mm_set1_ps( -1.0f ) );