为什么 Rust 编译器不能优化掉 Box：：downcast 的 Err arm

我有一个Box<dyn Any>，我知道基本类型，所以我想在Box::downcast()(source)中优化测试.

首先，我试着用std::hint::unreachable_unchecked():

pub unsafe fn downcast() -> Box<i32> {
    let value = any();
    if let Ok(value) = value.downcast() {
        value
    } else {
        std::hint::unreachable_unchecked()
    }
}

和

pub unsafe fn downcast() -> Box<i32> {
    any().downcast().map_err(|_| std::hint::unreachable_unchecked()).unwrap()
}

这两个结果都是rustc -C opt-level=3(省略了40行):

example::downcast:
        push    rbx
        sub     rsp, 16
        call    any@PLT
        mov     rbx, rax
        mov     qword ptr [rsp], rax
        mov     qword ptr [rsp + 8], rdx
        mov     rdi, rax
        call    qword ptr [rdx + 24]
        mov     rax, rbx
        add     rsp, 16
        pop     rbx
        ret
        mov     rbx, rax
        mov     rdi, rsp
        call    core::ptr::drop_in_place
        mov     rdi, rbx
        call    _Unwind_Resume@PLT
        ud2

因为这不是我想要的优化，所以我try 了

pub unsafe fn downcast() -> Box<i32> {
    let value = any();
    std::intrinsics::assume(value.is::<i32>());
    value.downcast().unwrap()
}

但情况变得更糟(省略了118行):

example::downcast:
        push    r15
        push    r14
        push    rbx
        sub     rsp, 32
        call    any@PLT
        mov     rbx, rax
        mov     r14, rdx
        mov     qword ptr [rsp], rax
        mov     qword ptr [rsp + 8], rdx
        mov     r15, qword ptr [rdx + 24]
        mov     rdi, rax
        call    r15
        mov     qword ptr [rsp + 16], rbx
        mov     qword ptr [rsp + 24], r14
        mov     rdi, rbx
        call    r15
        movabs  rcx, -5015437470765251660     ;TypeId::of::<i32>()
        cmp     rax, rcx
        jne     .LBB5_7
        mov     rax, rbx
        add     rsp, 32
        pop     rbx
        pop     r14
        pop     r15
        ret
.LBB5_7:
        mov     rdi, rbx
        mov     rsi, r14
        call    core::result::unwrap_failed
        ud2
        mov     rbx, rax
        lea     rdi, [rsp + 16]
        call    core::ptr::drop_in_place
        mov     rdi, rbx
        call    _Unwind_Resume@PLT
        ud2
        mov     rbx, rax
        mov     rdi, rsp
        call    core::ptr::drop_in_place
        mov     rdi, rbx
        call    _Unwind_Resume@PLT
        ud2

我希望生成这样的代码，这是Box::downcast中的Ok个arm:

pub unsafe fn downcast() -> Box<i32> {
    let value = any();
    let raw: *mut dyn Any = Box::into_raw(value);
    Box::from_raw(raw as *mut i32)
}

结果是(省略了zero行):

example::downcast:
        push    rax
        call    any@PLT
        pop     rcx
        ret

为什么编译器不能以这种方式优化代码？

所有组件generated by godbolt.