#include <xmmintrin.h>
#define Ki(x) _mm_set_epi32((x),(x),(x),(x))
// Convert n floats at src to half-floats at dst. n is a multiple of 4
static void qhalf(unsigned short *dst, const float *src, size_t n)
{
while (n) {
__m128i full = _mm_loadu_si128((__m128i*)src);
__m128i sign = full & Ki(1UL << 31); // extract sign
__m128i mantissa = full & Ki((1 << 23) - 1); // extract mantissa
__m128i exp8 = _mm_srli_epi32(full, 23) & Ki(0xff); // extract exponent
__m128i is_huge = _mm_cmpgt_epi32(exp8, Ki(0x8f)); // means flush to INF
__m128i is_tiny = _mm_cmplt_epi32(exp8, Ki(0x70)); // means flush to zero
__m128i exp5 = _mm_add_epi32(exp8, Ki(-0x7f + 0xf)); // rebias exponent
// INF is represented by exponent=0x1f and mantissa=0
exp5 = _mm_and_si128(_mm_or_si128(exp5, is_huge), Ki(0x1f));
mantissa = _mm_andnot_si128(is_huge, mantissa);
__m128i half = _mm_slli_epi32(exp5, 10) | _mm_srli_epi32(mantissa, 13);
// Underflow: force to zero
half = _mm_andnot_si128(is_tiny, half);
// apply sign
half = _mm_or_si128(half, _mm_srai_epi32(sign, 16));
_mm_storel_pi((__m64*)dst, (__m128)_mm_packs_epi32((__m128i)half, (__m128i)half));
dst += 4;
src += 4;
n -= 4;
}
}
On Tue, Jul 19, 2011 at 11:19 AM, Florian Kainz
<address@hidden> wrote:
Have any of you tried to convert vectors of 32-bit floating-point
numbers to vectors of 16-bit floating-point numbers in a way that
is faster than calling OpenEXR's half-from-float constructor for
each vector element? Maybe using MMX, SSE or AVX instructions?
_______________________________________________
Openexr-devel mailing list
address@hidden
https://lists.nongnu.org/mailman/listinfo/openexr-devel
--
James Bowman
http://www.excamera.com/sphinx/articles-openexr.html