这是this one的后续问题。现在我想以相反的方向转换float - > 无符号 int。 以下标量运算的最佳和精确矢量序列是什么?
float x = ...
unsigned int res = (unsigned int)x;
答案 0 :(得分:2)
这是基于旧的但有用的Apple AltiVec-SSE迁移文档中的示例,遗憾的是,http://developer.apple.com现已不再提供此文档:
inline __m128i _mm_ctu_ps(const __m128 f)
{
const __m128 two31 = _mm_set1_ps(0x1.0p31f);
const __m128 two32 = _mm_add_ps(two31, two31);
const __m128 zero = _mm_xor_ps(f,f);
// check for overflow before conversion to int
const __m128 overflow = _mm_cmpge_ps(f, two31);
const __m128 overflow2 = _mm_cmpge_ps(f, two32);
const __m128 subval = _mm_and_ps(overflow, two31);
const __m128i addval = _mm_slli_epi32((__m128i)overflow, 31);
__m128i result;
// bias the value to signed space if it is >= 2**31
f = _mm_sub_ps(f, subval);
// clip at zero
f = _mm_max_ps(f, zero);
// convert to int with saturation
result = _mm_cvtps_epi32(f); // rounding mode should be round to nearest
// unbias
result = _mm_add_epi32(result, addval);
// patch up the overflow case
result = _mm_or_si128(result, (__m128i)overflow2);
return result;
}