sse2 mm_floor_ps

sse2_floor.h

/*
MIT License

Copyright(c) 2022 James Edward Anhalt III - https://github.com/jeaiii

Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:

The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.
*/

#include <xmmintrin.h>

// truncate float to int
// go back to float -> 'f'
// compare original 'n' to  'f'
// if 'n' < 'f' then we need to subtract one
// mm_cmplt_ps creates a mask of 0xffffffff (true) and 0x00000000 (false) in each lane
// this is -1 as a 32bit integer
// covert the integer -1s and 0s to floats
// and add it to 'f' (so we subtract 1 or do nothing)
// https://godbolt.org/z/YzjPqPda1

__m128 mm_floor_ps(__m128 n)
{
    auto f = _mm_cvtepi32_ps(_mm_cvttps_epi32(n));
    return _mm_add_ps(f, _mm_cvtepi32_ps(_mm_castps_si128(_mm_cmplt_ps(n, f))));
}

float sse2_floor(float n)
{
    return _mm_cvtss_f32(mm_floor_ps(_mm_set_ss(n)));
}