[Bug tree-optimization/31667] New: Integer externsions aren't vectorized

[Bug tree-optimization/31667] New: Integer externsions aren't vectorized

[hjl at lucon dot org]

SSE4.1 has pmovzx and pmovsx. For code like:

[hjl@gnu-2 vect]$ cat pmovzxbw.c
typedef unsigned char vec_t;
typedef unsigned short vecx_t;

extern __attribute__((aligned(16))) vec_t x [64];
extern __attribute__((aligned(16))) vecx_t y [64];

void
foo ()
{
  int i;

  for (i = 0; i < 64; i++)
    y [i]  = x [i];
}

Icc generates

        pmovzxbw  x(%rip), %xmm0                                #13.14
        pmovzxbw  8+x(%rip), %xmm1                              #13.14
        pmovzxbw  16+x(%rip), %xmm2                             #13.14
        pmovzxbw  24+x(%rip), %xmm3                             #13.14
        pmovzxbw  32+x(%rip), %xmm4                             #13.14
        pmovzxbw  40+x(%rip), %xmm5                             #13.14
        pmovzxbw  48+x(%rip), %xmm6                             #13.14
        pmovzxbw  56+x(%rip), %xmm7                             #13.14
        movdqa    %xmm0, y(%rip)                                #13.5
        movdqa    %xmm1, 16+y(%rip)                             #13.5
        movdqa    %xmm2, 32+y(%rip)                             #13.5
        movdqa    %xmm3, 48+y(%rip)                             #13.5
        movdqa    %xmm4, 64+y(%rip)                             #13.5
        movdqa    %xmm5, 80+y(%rip)                             #13.5
        movdqa    %xmm6, 96+y(%rip)                             #13.5
        movdqa    %xmm7, 112+y(%rip)                            #13.5
        ret                                                     #14.1


-- 
           Summary: Integer externsions aren't vectorized
           Product: gcc
           Version: 4.3.0
            Status: UNCONFIRMED
          Severity: enhancement
          Priority: P3
         Component: tree-optimization
        AssignedTo: unassigned at gcc dot gnu dot org
        ReportedBy: hjl at lucon dot org


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=31667

[Bug target/31667] Integer externsions vectorization could be improved

[pinskia at gcc dot gnu dot org]

------- Comment #1 from pinskia at gcc dot gnu dot org  2010-03-13 01:35 -------
GCC 4.5 is able to produce pmovzxbw via sse4_1_zero_extendv8qiv8hi2 but it does
not accept a memory operand for operand 1.
        movdqa  x(%rip), %xmm0
        pmovzxbw        %xmm0, %xmm1
        psrldq  $8, %xmm0
        pmovzxbw        %xmm0, %xmm0
        movdqa  %xmm1, y(%rip)
        movdqa  %xmm0, y+16(%rip)
...
Is what GCC currently produces.


-- 

pinskia at gcc dot gnu dot org changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
             Status|UNCONFIRMED                 |NEW
          Component|tree-optimization           |target
     Ever Confirmed|0                           |1
 GCC target triplet|                            |i?86-*-* x86_64-*-*
           Keywords|                            |missed-optimization
   Last reconfirmed|0000-00-00 00:00:00         |2010-03-13 01:35:56
               date|                            |
            Summary|Integer externsions aren't  |Integer externsions
                   |vectorized                  |vectorization could be
                   |                            |improved


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=31667