[Bug target/51509] New: Inefficient neon intrinsic code sequence

["carrot at google dot com" <gcc-bugzilla at gcc dot gnu dot org>]

http://gcc.gnu.org/bugzilla/show_bug.cgi?id=51509

             Bug #: 51509
           Summary: Inefficient neon intrinsic code sequence
    Classification: Unclassified
           Product: gcc
           Version: 4.7.0
            Status: UNCONFIRMED
          Severity: normal
          Priority: P3
         Component: target
        AssignedTo: unassigned@gcc.gnu.org
        ReportedBy: carrot@google.com
            Target: arm-linux-androideabi


Compile the following code with options -march=armv7-a -mfloat-abi=softfp
-mfpu=neon -mthumb -O2 -Wall -fpic

#include <arm_neon.h>
void simple_vld_intrin(uint8_t *src, uint8_t *dst)
{
  uint8x8x4_t x;
  uint8x8x2_t y;

  x = vld4_lane_u8(src, x, 0);

  y.val[0][0] = x.val[1][0];
 y.val[1][0] = x.val[2][0];

 vst2_lane_u8(dst, y, 0);
}

gcc 4.7 generates:


.LC0:
    .word    0
    .word    0
    .word    0
    .word    0
    .word    0
    .word    0
    .word    0
    .word    0
    .text
    .align    2
    .global    simple_vld_intrin
    .thumb
    .thumb_func
    .type    simple_vld_intrin, %function
simple_vld_intrin:
    @ args = 0, pretend = 0, frame = 32
    @ frame_needed = 0, uses_anonymous_args = 0
    @ link register save eliminated.
    ldr    r2, .L2
    sub    sp, sp, #32
.LPIC0:
    add    r2, pc
    vldmia    r2, {d18-d21}
    vmov.i32    d19, #0  @ v8qi
    vmov    d20, d19  @ v8qi
    vmov    q11, q9  @ ti
    vmov    q12, q10  @ ti
    vmov    d16, d19  @ v8qi
    vmov    d17, d19  @ v8qi
    vld4.8    {d22[0], d23[0], d24[0], d25[0]}, [r0]
    vstmia    sp, {d22-d25}
    ldrb    r2, [sp, #8]    @ zero_extendqisi2
    vmov.8    d16[0], r2
    vmov.u8    r3, d24[0]
    vmov.8    d17[0], r3
    vst2.8    {d16[0], d17[0]}, [r1]
    add    sp, sp, #32
    bx    lr
.L3:
    .align    2
.L2:
    .word    .LC0-(.LPIC0+4)


An ideal result should be:

    vld4.8    {d16[0], d17[0], d18[0], d19[0]}, [r0]
    vmov    d20, d17  @ v8qi
    vmov    d21, d18  @ v8qi
    vst2.8    {d20[0], d21[0]}, [r1]
    bx    lr