GNAT can't vectorize Real_Matrix multiplication from Ada.Numerics.Real_Arrays. What a surprise!

[Bojan Bozovic <bozovic.bojan@gmail.com>]

-- code

with Ada.Calendar;
with Ada.Text_IO;
with Ada.Numerics.Real_Arrays;
use Ada.Calendar;
use Ada.Text_IO;
use Ada.Numerics.Real_Arrays;

procedure Matrix_Mul is

   package F_IO is new Ada.Text_IO.Fixed_IO (Day_Duration);
   use F_IO;

   Start_Time, End_Time : Time;

   procedure Put (X : Real_Matrix) is
   begin
      for I in X'Range (1) loop
         for J in X'Range (2) loop
            Put (Float'Image (Float (X (I, J))));
         end loop;
         New_Line;
      end loop;
   end Put;

   Matrix_A, Matrix_B, Result : Real_Matrix (1 .. 4, 1 .. 4);
   Elapsed_Time               : Duration;
   Sum                        : Float;
begin
   Matrix_A :=
     ((1.0, 1.0, 1.0, 1.0),
      (2.0, 2.0, 2.0, 2.0),
      (3.0, 3.0, 3.0, 3.0),
      (4.0, 4.0, 4.0, 4.0));
   Matrix_B :=
     ((16.0, 15.0, 14.0, 13.0),
      (12.0, 11.0, 10.0, 9.0),
      (8.0, 7.0, 6.0, 5.0),
      (4.0, 3.0, 2.0, 1.0));

   Start_Time := Clock;
   for Iteration in 1 .. 10_000_000 loop
      Result := Matrix_A * Matrix_B;
   end loop;
   End_Time     := Clock;
   Elapsed_Time := End_Time - Start_Time;
   Put (Result);
   New_Line;
   Put ("Elapsed Time is ");
   Put (Elapsed_Time);
   New_Line;
   Start_Time := Clock;
   for Iteration in 1 .. 10_000_000 loop
      for I in Matrix_A'Range (1) loop
         for J in Matrix_A'Range (2) loop
            Sum := 0.0;
            for K in Matrix_A'Range (2) loop
               Sum := Sum + Matrix_A (I, K) * Matrix_B (K, J);
            end loop;
            Result (I, J) := Sum;
         end loop;
      end loop;
   end loop;
   End_Time     := Clock;
   Elapsed_Time := End_Time - Start_Time;
   Put (Result);
   New_Line;
   Put ("Elapsed time is ");
   Put (Elapsed_Time);
   New_Line;
end Matrix_Mul;
-- end code

Results: FSF GNAT 7.2.0 x64
C:\Users\Bojan\Documents>gnatmake -O3 -fopt-info -march=skylake matrix_mul.adb -largs -s
gcc -c -O3 -fopt-info -march=skylake matrix_mul.adb
matrix_mul.adb:56:41: note: loop turned into non-loop; it never loops.
matrix_mul.adb:56:41: note: loop with 4 iterations completely unrolled
matrix_mul.adb:54:38: note: loop turned into non-loop; it never loops.
matrix_mul.adb:54:38: note: loop with 4 iterations completely unrolled
matrix_mul.adb:53:35: note: loop turned into non-loop; it never loops.
matrix_mul.adb:53:35: note: loop with 4 iterations completely unrolled
matrix_mul.adb:40:15: note: basic block vectorized
matrix_mul.adb:42:26: note: basic block vectorized
matrix_mul.adb:18:31: note: basic block vectorized
matrix_mul.adb:49:9: note: basic block vectorized
C:/MSYS64/MINGW64/lib/gcc/x86_64-w64-mingw32/7.2.0/adainclude/a-tifiio.adb:706:10: note: basic block vectorized
matrix_mul.adb:64:17: note: basic block vectorized
matrix_mul.adb:18:31: note: basic block vectorized
matrix_mul.adb:68:9: note: basic block vectorized
C:/MSYS64/MINGW64/lib/gcc/x86_64-w64-mingw32/7.2.0/adainclude/a-tifiio.adb:706:10: note: basic block vectorized
gnatbind -x matrix_mul.ali
gnatlink matrix_mul.ali -O3 -fopt-info -march=skylake -s

C:\Users\Bojan\Documents>matrix_mul
 4.00000E+01 3.60000E+01 3.20000E+01 2.80000E+01
 8.00000E+01 7.20000E+01 6.40000E+01 5.60000E+01
 1.20000E+02 1.08000E+02 9.60000E+01 8.40000E+01
 1.60000E+02 1.44000E+02 1.28000E+02 1.12000E+02

Elapsed Time is      1.338206667
 4.00000E+01 3.60000E+01 3.20000E+01 2.80000E+01
 8.00000E+01 7.20000E+01 6.40000E+01 5.60000E+01
 1.20000E+02 1.08000E+02 9.60000E+01 8.40000E+01
 1.60000E+02 1.44000E+02 1.28000E+02 1.12000E+02

Elapsed time is      0.000000445

C:\Users\Bojan\Documents>set path=C:\GNAT\2017\BIN;%path%

Results GPL GNAT/2017 from AdaCore.

C:\Users\Bojan\Documents>gnatmake -O3 -fopt-info -mavx2 matrix_mul.adb -largs -s
gcc -c -O3 -fopt-info -mavx2 matrix_mul.adb
matrix_mul.adb:56:41: note: loop turned into non-loop; it never loops.
matrix_mul.adb:56:41: note: loop with 4 iterations completely unrolled
matrix_mul.adb:54:38: note: loop turned into non-loop; it never loops.
matrix_mul.adb:54:38: note: loop with 4 iterations completely unrolled
matrix_mul.adb:53:35: note: loop turned into non-loop; it never loops.
matrix_mul.adb:53:35: note: loop with 4 iterations completely unrolled
matrix_mul.adb:40:15: note: basic block vectorized
matrix_mul.adb:68:9: note: basic block vectorized
gnatbind -x matrix_mul.ali
gnatlink matrix_mul.ali -O3 -fopt-info -mavx2 -s

C:\Users\Bojan\Documents>matrix_mul
 4.00000E+01 3.60000E+01 3.20000E+01 2.80000E+01
 8.00000E+01 7.20000E+01 6.40000E+01 5.60000E+01
 1.20000E+02 1.08000E+02 9.60000E+01 8.40000E+01
 1.60000E+02 1.44000E+02 1.28000E+02 1.12000E+02

Elapsed Time is      2.145337334
 4.00000E+01 3.60000E+01 3.20000E+01 2.80000E+01
 8.00000E+01 7.20000E+01 6.40000E+01 5.60000E+01
 1.20000E+02 1.08000E+02 9.60000E+01 8.40000E+01
 1.60000E+02 1.44000E+02 1.28000E+02 1.12000E+02

Elapsed time is      0.000000444

C:\Users\Bojan\Documents>gcc --version
gcc (GCC) 6.3.1 20170510 (for GNAT GPL 2017 20170515)
Copyright (C) 2016 Free Software Foundation, Inc.
This is free software; see the source for copying conditions.
See your AdaCore support agreement for details of warranty and support.
If you do not have a current support agreement, then there is absolutely
no warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR
PURPOSE.

Should I submit this as bug to AdaCore? My computer is Intel Core i3-6100U (Skylake AVX2). Please try to reproduce.