[Bug target/114428] New: [x86] psrad xmm, xmm, 16 and pand xmm, const_vector (0xffff x4) can be optimized to psrld

[Bug target/114428] New: [x86] psrad xmm, xmm, 16 and pand xmm, const_vector (0xffff x4) can be optimized to psrld

[liuhongt at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=114428

            Bug ID: 114428
           Summary: [x86] psrad xmm, xmm, 16 and pand xmm, const_vector
                    (0xffff x4) can be optimized to psrld
           Product: gcc
           Version: 14.0
            Status: UNCONFIRMED
          Severity: normal
          Priority: P3
         Component: target
          Assignee: unassigned at gcc dot gnu.org
          Reporter: liuhongt at gcc dot gnu.org
  Target Milestone: ---

typedef unsigned short uint16_t;
typedef short int16_t;

#define QUANT_ONE( coef, mf, f )                \
{ \
    if( (coef) > 0 ) \
        (coef) = (f + (coef)) * (mf) >> 16; \
    else \
        (coef) = - ((f - (coef)) * (mf) >> 16); \
    nz |= (coef); \
}

int quant_4x4( int16_t dct[16], uint16_t mf[16], uint16_t bias[16] )
{
    int nz = 0;
    for( int i = 0; i < 16; i++ )
        QUANT_ONE( dct[i], mf[i], bias[i] );
    return !!nz;
}


gcc -O2 -march=x86-64-v3 -S

        mov     edx, 65535
        vmovd   xmm4, edx
        vpbroadcastd    ymm4, xmm4
        ...
        vpsrad  ymm2, ymm2, 16
        vpsrad  ymm6, ymm6, 16
        vpsrad  ymm0, ymm0, 16
        vpand   ymm2, ymm4, ymm2
        vpsrad  ymm1, ymm1, 16
        vpand   ymm6, ymm4, ymm6
        vpand   ymm0, ymm4, ymm0
        vpand   ymm4, ymm4, ymm1
        vpackusdw       ymm2, ymm2, ymm6
        vpackusdw       ymm0, ymm0, ymm4
        vpermq  ymm2, ymm2, 216
        vpermq  ymm0, ymm0, 216
        ...

it can be optimized to below.

        vpsrld  ymm2, ymm2, 16
        vpsrld  ymm6, ymm6, 16
        vpsrld  ymm0, ymm0, 16
        vpsrld  ymm1, ymm1, 16
        vpackusdw       ymm2, ymm2, ymm6
        vpackusdw       ymm0, ymm0, ymm4
        vpermq  ymm2, ymm2, 216
        vpermq  ymm0, ymm0, 216

The optimization opportunity is exposed after vec_pack_trunk_expr is expanded
to vpand + vpackusdw.