[Bug rtl-optimization/111096] New: Frame pointer is not used even when -fomit-frame-pointer is specified

["tkoenig at gcc dot gnu.org" <gcc-bugzilla@gcc.gnu.org>]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=111096

            Bug ID: 111096
           Summary: Frame pointer is not used even when
                    -fomit-frame-pointer is specified
           Product: gcc
           Version: 14.0
            Status: UNCONFIRMED
          Severity: enhancement
          Priority: P3
         Component: rtl-optimization
          Assignee: unassigned at gcc dot gnu.org
          Reporter: tkoenig at gcc dot gnu.org
  Target Milestone: ---

The code, by Kent Dickey posted to comp.arch

typedef unsigned int u32;
typedef unsigned long long u64;

u64 do_op(u64 out0, u64 in0, u64 in1, u32 opcode, int size);

void
calc_loop(u64 *optr, u64 *iptr0, u64 *iptr1, u32 opcode, int size, int len)
{
        u64     o0, i0, i1, val, result;
        int     num, shift, pos;
        int     i, j;

        // size is 0,1,2,3 representing 8,16,32,64 bytes
        num = 8 >> size;                // 8,4,2,1
        shift = 8 << size;              // 8,16,32,64
        for(i = 0; i < len; i++) {
                o0 = optr[i];
                i0 = iptr0[i];
                i1 = iptr1[i];
                result = 0;
                pos = 0;
                for(j = 0; j < num; j++) {
                        val = do_op(o0, i0, i1, opcode, size);
                        result = result | (val << pos);
                        pos += shift;
                        if(shift < 64) {
                                o0 = o0 >> shift;
                                i0 = i0 >> shift;
                                i1 = i1 >> shift;
                        }
                }
                optr[i] = result;
        }
}

compiled for aarch64 on godbolt with recent trunk and -O3 -fomit-frame-pointer
(see https://godbolt.org/z/5bKPeGWrK ) does not set up the frame pointer,
but it also does not use it for aoviding spill/restore pairs:

calc_loop:
        stp     x19, x20, [sp, -144]!
        mov     w6, 8
        asr     w19, w6, w4
        stp     x27, x28, [sp, 64]
        lsl     w27, w6, w4
        str     x30, [sp, 80]
        stp     x0, x1, [sp, 112]
        str     x2, [sp, 128]
        cmp     w5, 0
        ble     .L1
        sbfiz   x0, x5, 3, 32
        stp     x21, x22, [sp, 16]
        mov     w20, w4
        stp     x23, x24, [sp, 32]
        mov     w21, w3
        stp     x25, x26, [sp, 48]
        str     x0, [sp, 136]
        cmp     w27, 63
        ble     .L3
        mov     x25, 0
.L6:
        ldr     x0, [sp, 112]
        ldr     x23, [x0, x25]
        ldr     x0, [sp, 120]
        ldr     x0, [x0, x25]
        str     x0, [sp, 104]
        ldr     x0, [sp, 128]
        ldr     x24, [x0, x25]
        cbz     w19, .L10
        mov     w22, 0
        mov     w28, 0
        mov     x26, 0
.L5:
        ldr     x1, [sp, 104]
        mov     w4, w20
        mov     w3, w21
        mov     x2, x24
        mov     x0, x23
        add     w22, w22, 1
        bl      do_op
        lsl     x0, x0, x28
        add     w28, w28, w27
        orr     x26, x26, x0
        cmp     w19, w22
        bne     .L5
        ldr     x0, [sp, 112]
        str     x26, [x0, x25]
        add     x25, x25, 8
        ldr     x0, [sp, 136]
        cmp     x0, x25
        bne     .L6
.L17:
        ldp     x21, x22, [sp, 16]
        ldp     x23, x24, [sp, 32]
        ldp     x25, x26, [sp, 48]
.L1:
        ldp     x27, x28, [sp, 64]
        ldr     x30, [sp, 80]
        ldp     x19, x20, [sp], 144
        ret
.L3:
        str     xzr, [sp, 104]
        ldp     x0, x1, [sp, 104]
        ldr     x24, [x1, x0]
        ldr     x1, [sp, 120]
        ldr     x25, [x1, x0]
        ldr     x1, [sp, 128]
        ldr     x22, [x1, x0]
        cbz     w19, .L11
.L20:
        mov     w26, 0
        mov     w28, 0
        mov     x23, 0
.L8:
        mov     x2, x22
        mov     x1, x25
        mov     x0, x24
        mov     w4, w20
        mov     w3, w21
        add     w26, w26, 1
        bl      do_op
        lsr     x24, x24, x27
        lsl     x0, x0, x28
        add     w28, w28, w27
        orr     x23, x23, x0
        lsr     x25, x25, x27
        lsr     x22, x22, x27
        cmp     w19, w26
        bne     .L8
        ldp     x0, x1, [sp, 104]
        str     x23, [x1, x0]
        add     x0, x0, 8
        ldr     x1, [sp, 136]
        str     x0, [sp, 104]
        cmp     x1, x0
        beq     .L17
.L19:
        ldp     x0, x1, [sp, 104]
        ldr     x24, [x1, x0]
        ldr     x1, [sp, 120]
        ldr     x25, [x1, x0]
        ldr     x1, [sp, 128]
        ldr     x22, [x1, x0]
        cbnz    w19, .L20
.L11:
        ldp     x0, x1, [sp, 104]
        mov     x23, 0
        str     x23, [x1, x0]
        add     x0, x0, 8
        ldr     x1, [sp, 136]
        str     x0, [sp, 104]
        cmp     x1, x0
        bne     .L19
        b       .L17
.L10:
        ldr     x0, [sp, 112]
        mov     x26, 0
        str     x26, [x0, x25]
        add     x25, x25, 8
        ldr     x0, [sp, 136]
        cmp     x0, x25
        bne     .L6
        b       .L17