[Bug c/112776] New: RISC-V Regression: Missed optimization of VSETVL PASS

["juzhe.zhong at rivai dot ai" <gcc-bugzilla@gcc.gnu.org>]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=112776

            Bug ID: 112776
           Summary: RISC-V Regression: Missed optimization of VSETVL PASS
           Product: gcc
           Version: 14.0
            Status: UNCONFIRMED
          Severity: normal
          Priority: P3
         Component: c
          Assignee: unassigned at gcc dot gnu.org
          Reporter: juzhe.zhong at rivai dot ai
  Target Milestone: ---

#include "riscv_vector.h"

void
foo_vec(float *r, const float *x)
{
int i, k;

vfloat32m4_t x_vec;
vfloat32m4_t x_forward_vec;
vfloat32m4_t temp_vec;

/**
 * I have to use m1 to complicat intrisic
 */
vfloat32m1_t dst_vec;
vfloat32m1_t src_vec;

float result = 0.0f;
float shift_prev = 0.0f;

size_t n = 64;
for(size_t vl; n>0; n -=vl){
    vl = __riscv_vsetvl_e32m4(n); //LMUL=4
    x_vec = __riscv_vle32_v_f32m4(&x[0], vl);
    x_forward_vec = __riscv_vle32_v_f32m4(&x[0], vl);
    temp_vec = __riscv_vfmul_vv_f32m4(x_vec, x_forward_vec, vl);

    /**
     * I have to use m1 to complicat intrisic
     */
    //vfloat32m1_t __riscv_vfmv_s_tu(vfloat32m1_t vd, float rs1, size_t vl);
    src_vec = __riscv_vfmv_s_tu(src_vec, 0.0f, vl);                 //initial
src_vec
    //dst_vec = __riscv_vfmv_s_f_f32m1_tu(dst_vec, 0.0f, vl);         //clean
for vfredosum
    dst_vec = __riscv_vfmv_s_tu(dst_vec, 0.0f, vl);         //clean for
vfredosum
    dst_vec = __riscv_vfredosum_tu(dst_vec, temp_vec, src_vec, vl);

    r[0] = __riscv_vfmv_f_s_f32m1_f32(dst_vec);

   }
}

ASM:

GCC-14 foo_vec:
        li      a4,64
.L2:
        vsetvli a5,a4,e8,m1,ta,ma   ---> 
        vsetvli zero,a5,e32,m1,tu,ma
        vmv.s.x v2,zero
        vmv.s.x v1,zero
        vsetvli zero,a5,e32,m4,tu,ma
        vle32.v v4,0(a1)
        vfmul.vv        v4,v4,v4
        vfredosum.vs    v1,v4,v2
        vfmv.f.s        fa5,v1
        fsw     fa5,0(a0)
        sub     a4,a4,a5
        bne     a4,zero,.L2
        ret

GCC-13:

foo_vec(float*, float const*):
        fmv.s.x fa5,zero
        li      a4,64
.L2:
        vsetvli a5,a4,e32,m4,ta,ma
        vle32.v v28,0(a1)
        vfmv.s.f        v25,fa5
        vfmul.vv        v28,v28,v28
        vfmv.s.f        v24,fa5
        sub     a4,a4,a5
        vfredosum.vs    v24,v28,v25
        vfmv.f.s        fa4,v24
        fsw     fa4,0(a0)
        bne     a4,zero,.L2
        ret