https://gcc.gnu.org/bugzilla/show_bug.cgi?id=83479
--- Comment #4 from Daniel Fruzynski <bugzi...@poradnik-webmastera.com> ---
Rule No.1: never log bugs before morning coffee ;)
This does not produce warnings, compiled with "-O3 -march=haswell -mavx512f
-mavx512vl -mavx512bw -mavx512dq -mavx512cd -Wall -Werror".
[code]
#include "immintrin.h"
double test(const double data[9][8])
{
__m512d vLastRow, vLastCol, vSqrtRow, vSqrtCol;
__m512d v1 = _mm512_load_pd (&data[0][0]);
__m512d v2 = _mm512_load_pd (&data[1][0]);
__m512d v3 = _mm512_load_pd (&data[2][0]);
__m512d v4 = _mm512_load_pd (&data[3][0]);
__m512d v5 = _mm512_load_pd (&data[4][0]);
__m512d v6 = _mm512_load_pd (&data[5][0]);
__m512d v7 = _mm512_load_pd (&data[6][0]);
__m512d v8 = _mm512_load_pd (&data[7][0]);
// 8
vLastRow = _mm512_load_pd (&data[9][0]);
vSqrtRow = _mm512_sqrt_pd(vLastRow);
vLastCol = _mm512_set1_pd(vLastRow[0]);
vSqrtCol = _mm512_sqrt_pd(vLastCol);
v1 = (v1 - vLastRow * vLastCol) * vSqrtRow * vSqrtCol;
vLastCol = _mm512_set1_pd(vLastRow[1]);
vSqrtCol = _mm512_sqrt_pd(vLastCol);
v2 = (v2 - vLastRow * vLastCol) * vSqrtRow * vSqrtCol;
vLastCol = _mm512_set1_pd(vLastRow[2]);
vSqrtCol = _mm512_sqrt_pd(vLastCol);
v3 = (v3 - vLastRow * vLastCol) * vSqrtRow * vSqrtCol;
vLastCol = _mm512_set1_pd(vLastRow[3]);
vSqrtCol = _mm512_sqrt_pd(vLastCol);
v4 = (v4 - vLastRow * vLastCol) * vSqrtRow * vSqrtCol;
vLastCol = _mm512_set1_pd(vLastRow[4]);
vSqrtCol = _mm512_sqrt_pd(vLastCol);
v5 = (v5 - vLastRow * vLastCol) * vSqrtRow * vSqrtCol;
vLastCol = _mm512_set1_pd(vLastRow[5]);
vSqrtCol = _mm512_sqrt_pd(vLastCol);
v6 = (v6 - vLastRow * vLastCol) * vSqrtRow * vSqrtCol;
vLastCol = _mm512_set1_pd(vLastRow[6]);
vSqrtCol = _mm512_sqrt_pd(vLastCol);
v7 = (v7 - vLastRow * vLastCol) * vSqrtRow * vSqrtCol;
vLastCol = _mm512_set1_pd(vLastRow[7]);
vSqrtCol = _mm512_sqrt_pd(vLastCol);
v8 = (v8 - vLastRow * vLastCol) * vSqrtRow * vSqrtCol;
// 7
vLastRow = v8;
vSqrtRow = _mm512_sqrt_pd(vLastRow);
vLastCol = _mm512_set1_pd(vLastRow[0]);
vSqrtCol = _mm512_sqrt_pd(vLastCol);
v1 = (v1 - vLastRow * vLastCol) * vSqrtRow * vSqrtCol;
vLastCol = _mm512_set1_pd(vLastRow[1]);
vSqrtCol = _mm512_sqrt_pd(vLastCol);
v2 = (v2 - vLastRow * vLastCol) * vSqrtRow * vSqrtCol;
vLastCol = _mm512_set1_pd(vLastRow[2]);
vSqrtCol = _mm512_sqrt_pd(vLastCol);
v3 = (v3 - vLastRow * vLastCol) * vSqrtRow * vSqrtCol;
vLastCol = _mm512_set1_pd(vLastRow[3]);
vSqrtCol = _mm512_sqrt_pd(vLastCol);
v4 = (v4 - vLastRow * vLastCol) * vSqrtRow * vSqrtCol;
vLastCol = _mm512_set1_pd(vLastRow[4]);
vSqrtCol = _mm512_sqrt_pd(vLastCol);
v5 = (v5 - vLastRow * vLastCol) * vSqrtRow * vSqrtCol;
vLastCol = _mm512_set1_pd(vLastRow[5]);
vSqrtCol = _mm512_sqrt_pd(vLastCol);
v6 = (v6 - vLastRow * vLastCol) * vSqrtRow * vSqrtCol;
vLastCol = _mm512_set1_pd(vLastRow[6]);
vSqrtCol = _mm512_sqrt_pd(vLastCol);
v7 = (v7 - vLastRow * vLastCol) * vSqrtRow * vSqrtCol;
// 6
vLastRow = v7;
vSqrtRow = _mm512_sqrt_pd(vLastRow);
vLastCol = _mm512_set1_pd(vLastRow[0]);
vSqrtCol = _mm512_sqrt_pd(vLastCol);
v1 = (v1 - vLastRow * vLastCol) * vSqrtRow * vSqrtCol;
vLastCol = _mm512_set1_pd(vLastRow[1]);
vSqrtCol = _mm512_sqrt_pd(vLastCol);
v2 = (v2 - vLastRow * vLastCol) * vSqrtRow * vSqrtCol;
vLastCol = _mm512_set1_pd(vLastRow[2]);
vSqrtCol = _mm512_sqrt_pd(vLastCol);
v3 = (v3 - vLastRow * vLastCol) * vSqrtRow * vSqrtCol;
vLastCol = _mm512_set1_pd(vLastRow[3]);
vSqrtCol = _mm512_sqrt_pd(vLastCol);
v4 = (v4 - vLastRow * vLastCol) * vSqrtRow * vSqrtCol;
vLastCol = _mm512_set1_pd(vLastRow[4]);
vSqrtCol = _mm512_sqrt_pd(vLastCol);
v5 = (v5 - vLastRow * vLastCol) * vSqrtRow * vSqrtCol;
vLastCol = _mm512_set1_pd(vLastRow[5]);
vSqrtCol = _mm512_sqrt_pd(vLastCol);
v6 = (v6 - vLastRow * vLastCol) * vSqrtRow * vSqrtCol;
// 5
vLastRow = v6;
vSqrtRow = _mm512_sqrt_pd(vLastRow);
vLastCol = _mm512_set1_pd(vLastRow[0]);
vSqrtCol = _mm512_sqrt_pd(vLastCol);
v1 = (v1 - vLastRow * vLastCol) * vSqrtRow * vSqrtCol;
vLastCol = _mm512_set1_pd(vLastRow[1]);
vSqrtCol = _mm512_sqrt_pd(vLastCol);
v2 = (v2 - vLastRow * vLastCol) * vSqrtRow * vSqrtCol;
vLastCol = _mm512_set1_pd(vLastRow[2]);
vSqrtCol = _mm512_sqrt_pd(vLastCol);
v3 = (v3 - vLastRow * vLastCol) * vSqrtRow * vSqrtCol;
vLastCol = _mm512_set1_pd(vLastRow[3]);
vSqrtCol = _mm512_sqrt_pd(vLastCol);
v4 = (v4 - vLastRow * vLastCol) * vSqrtRow * vSqrtCol;
vLastCol = _mm512_set1_pd(vLastRow[4]);
vSqrtCol = _mm512_sqrt_pd(vLastCol);
v5 = (v5 - vLastRow * vLastCol) * vSqrtRow * vSqrtCol;
// 4
vLastRow = v5;
vSqrtRow = _mm512_sqrt_pd(vLastRow);
vLastCol = _mm512_set1_pd(vLastRow[0]);
vSqrtCol = _mm512_sqrt_pd(vLastCol);
v1 = (v1 - vLastRow * vLastCol) * vSqrtRow * vSqrtCol;
vLastCol = _mm512_set1_pd(vLastRow[1]);
vSqrtCol = _mm512_sqrt_pd(vLastCol);
v2 = (v2 - vLastRow * vLastCol) * vSqrtRow * vSqrtCol;
vLastCol = _mm512_set1_pd(vLastRow[2]);
vSqrtCol = _mm512_sqrt_pd(vLastCol);
v3 = (v3 - vLastRow * vLastCol) * vSqrtRow * vSqrtCol;
vLastCol = _mm512_set1_pd(vLastRow[3]);
vSqrtCol = _mm512_sqrt_pd(vLastCol);
v4 = (v4 - vLastRow * vLastCol) * vSqrtRow * vSqrtCol;
// 3
vLastRow = v4;
vSqrtRow = _mm512_sqrt_pd(vLastRow);
vLastCol = _mm512_set1_pd(vLastRow[0]);
vSqrtCol = _mm512_sqrt_pd(vLastCol);
v1 = (v1 - vLastRow * vLastCol) * vSqrtRow * vSqrtCol;
vLastCol = _mm512_set1_pd(vLastRow[1]);
vSqrtCol = _mm512_sqrt_pd(vLastCol);
v2 = (v2 - vLastRow * vLastCol) * vSqrtRow * vSqrtCol;
vLastCol = _mm512_set1_pd(vLastRow[2]);
vSqrtCol = _mm512_sqrt_pd(vLastCol);
v3 = (v3 - vLastRow * vLastCol) * vSqrtRow * vSqrtCol;
// 2
vLastRow = v3;
vSqrtRow = _mm512_sqrt_pd(vLastRow);
vLastCol = _mm512_set1_pd(vLastRow[0]);
vSqrtCol = _mm512_sqrt_pd(vLastCol);
v1 = (v1 - vLastRow * vLastCol) * vSqrtRow * vSqrtCol;
vLastCol = _mm512_set1_pd(vLastRow[1]);
vSqrtCol = _mm512_sqrt_pd(vLastCol);
v2 = (v2 - vLastRow * vLastCol) * vSqrtRow * vSqrtCol;
// 1
vLastRow = v2;
vSqrtRow = _mm512_sqrt_pd(vLastRow);
vLastCol = _mm512_set1_pd(vLastRow[0]);
vSqrtCol = _mm512_sqrt_pd(vLastCol);
v1 = (v1 - vLastRow * vLastCol) * vSqrtRow * vSqrtCol;
return v1[0];
}
[/code]
