Missed optimization: comparing array to zero is not vectorized

[theemathas]

I compiled this code with -Copt-level=3 -Ctarget-cpu=raptorlake:

pub fn a0(x: [u8; 64]) -> bool {
    x == [0; 64]
}
pub fn b0(x: [u8; 64]) -> bool {
    x.iter().all(|&y| y == 0)
}

pub fn a1(x: [u8; 64]) -> bool {
    x == [255; 64]
}
pub fn b1(x: [u8; 64]) -> bool {
    x.iter().all(|&y| y == 255)
}

I expected all four functions to be vectorized. Instead, b0, a1, and b1 are vectorized, but a0 is not vectorized.

Generated assembly

example::a0::h0c5a938daa1dd8cf:
        mov     rax, qword ptr [rdi + 24]
        mov     rcx, qword ptr [rdi]
        mov     rdx, qword ptr [rdi + 16]
        or      rdx, qword ptr [rdi + 48]
        mov     rsi, qword ptr [rdi + 8]
        or      rcx, qword ptr [rdi + 32]
        or      rcx, rdx
        or      rax, qword ptr [rdi + 56]
        or      rsi, qword ptr [rdi + 40]
        or      rsi, rax
        or      rsi, rcx
        sete    al
        ret

example::b0::he89db7fcb6c0c0f1:
        vmovdqu ymm0, ymmword ptr [rdi + 32]
        vpor    ymm0, ymm0, ymmword ptr [rdi]
        vptest  ymm0, ymm0
        sete    al
        vzeroupper
        ret

example::a1::h00de82c55f406ff7:
        vmovdqu ymm0, ymmword ptr [rdi]
        vpand   ymm0, ymm0, ymmword ptr [rdi + 32]
        vpcmpeqd        ymm1, ymm1, ymm1
        vptest  ymm0, ymm1
        setb    al
        vzeroupper
        ret

example::b1::h06b133df359bb172:
        vmovdqu ymm0, ymmword ptr [rdi + 32]
        vpand   ymm0, ymm0, ymmword ptr [rdi]
        vpcmpeqd        ymm1, ymm1, ymm1
        vptest  ymm0, ymm1
        setb    al
        vzeroupper
        ret

Godbolt link

Meta

Rust 1.87.0 on Godbolt.

@rustbot labels +C-optimization

[nikic]

Upstream issue: llvm/llvm-project#144861