[arm-gnu] vld4 / vst4 NEON intrinsics

[Samuel Rødal <samuel.rodal@xxxxxxxxx>]

The vldX and vstX variation of NEON intrinsics, where X > 1, seem to 
cause the compiler to generate an obscene amount of code.

Example:

void blend1(uint8_t *src, uint8_t *dst)
{
        uint8x8_t temp = vld1_u8(src);
        vst1_u8(dst, temp);
}

generates the sensible

        vld1.8  {d16}, [r0]
        vst1.8  {d16}, [r1]
        bx      lr

Whereas:

void blend4(uint8_t *src, uint8_t *dst)
{
        uint8x8x4_t temp = vld4_u8(src);
        vst4_u8(dst, temp);
}

generates

        stmfd   sp!, {r4, r5, r6}
        .save {r4, r5, r6}
.LCFI4:
        .pad #132
        sub     sp, sp, #132
.LCFI5:
        vld4.8  {d16-d19}, [r0]
        add     r6, sp, #64
        vstmia  r6, {d16-d19}
        mov     r5, r1
        ldmia   r6!, {r0, r1, r2, r3}
        add     ip, sp, #96
        mov     r4, ip
        stmia   r4!, {r0, r1, r2, r3}
        ldmia   r6, {r0, r1, r2, r3}
        stmia   r4, {r0, r1, r2, r3}
        ldmia   ip!, {r0, r1, r2, r3}
        add     ip, sp, #32
        mov     r6, ip
        stmia   r6!, {r0, r1, r2, r3}
        ldmia   r4, {r0, r1, r2, r3}
        stmia   r6, {r0, r1, r2, r3}
        ldmia   ip!, {r0, r1, r2, r3}
        mov     r4, sp
        stmia   r4!, {r0, r1, r2, r3}
        ldmia   r6, {r0, r1, r2, r3}
        stmia   r4, {r0, r1, r2, r3}
        vldmia  sp, {d16-d19}
        vst4.8  {d16-d19}, [r5]
        add     sp, sp, #132
        ldmfd   sp!, {r4, r5, r6}
        bx      lr

Compile flags used were "-mfloat-abi=softfp -mfpu=neon -O3". Any ideas 
or workarounds?

Regards,

Samuel