Logically equivalent code produces larger assembly and slower performance when Arc and Pin wrapped in a struct #146630
Description
I tried this code:
https://www.godbolt.org/z/Pd5aa9r86
#![feature(arbitrary_self_types)] #![feature(rustc_attrs)] use std::{sync::Arc,pin::Pin,}; trait Trait { fn by_arc(self: Arc<Self>) -> i64; fn by_pin_box(self: Pin<Box<Self>>) -> i64; } impl Trait for i64 { fn by_arc(self: Arc<Self>) -> i64 { *self } fn by_pin_box(self: Pin<Box<Self>>) -> i64 { *self } } pub fn main() { let arc = Arc::new(2i64) as Arc<dyn Trait>; assert_eq!(2, arc.by_arc()); let pin_box = Into::<Pin<Box<i64>>>::into(Box::new(4i64)) as Pin<Box<dyn Trait>>; assert_eq!(4, pin_box.by_pin_box()); }and:
#![feature(arbitrary_self_types)] #![feature(rustc_attrs)] pub struct TempGroup1 { pub field1: Arc<dyn Trait>, pub field2: Pin<Box<dyn Trait>>, } use std::{sync::Arc, pin::Pin}; trait Trait{ fn by_arc(self: Arc<Self>) -> i64; fn by_pin_box(self: Pin<Box<Self>>) -> i64; } impl Trait for i64 { fn by_arc(self: Arc<Self>) -> i64{ *self } fn by_pin_box(self: Pin<Box<Self>>) -> i64{ *self } } pub fn main() { let temp_group_1 = TempGroup1 { field1: Arc::new(2i64) as Arc<dyn Trait>, field2: Into::<Pin<Box<i64>>>::into(Box::new(4i64)) as Pin<Box<dyn Trait>> }; let arc = temp_group_1.field1; assert_eq!(2, arc.by_arc()); let pin_box = temp_group_1.field2; assert_eq!(4, pin_box.by_pin_box()); }I expected to see this happen:
Both code snippets to generate similar optimized assembly and to have similar runtime performance, since they are logically equivalent (both just wrap an i64 in Arc or Pin<Box> and call the same trait methods).
Instead, this happened:
The first version produces about 90 lines of optimized assembly (rustc -C opt-level=3 --emit=asm --crate-type=lib), while the second version produces about 286 lines.
When benchmarked with hyperfine (the main function loop with 10,000,000 iterations), the second version runs about 79.2% slower:
Version A: ≈ 0.1476 s
Version B: ≈ 0.2645 s
This suggests that introducing the TempGroup1 struct changes the generated code in a way that significantly increases overhead, even though the program logic is the same.
Meta
rustc --version --verbose:
rustc 1.89.0-nightly (586ad391f 2025-06-15) binary: rustc commit-hash: 586ad391f5ee4519acc7cae340e34673bae762b1 commit-date: 2025-06-15 host: x86_64-unknown-linux-gnu release: 1.89.0-nightly LLVM version: 20.1.5 Version A hyperfine.json
{ "results": [ { "command": "./target/release/init", "mean": 0.1476577922789474, "stddev": 0.010808251268166473, "median": 0.1482381797, "user": 0.14682449894736843, "system": 0.0010573589473684211, "min": 0.1263320227, "max": 0.1653164557, "times": [ 0.1482381797, 0.1593237487, 0.1408860767, 0.1636745287, 0.1653164557, 0.1612710107, 0.1519671997, 0.1549548597, 0.1503653417, 0.1405962647, 0.1263320227, 0.1509238887, 0.1472579667, 0.1534259367, 0.1366232097, 0.1329117547, 0.1408619007, 0.1355554947, 0.1450122127 ], "exit_codes": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ] } ] } Version B hyperfine.json
{ "results": [ { "command": "./target/release/new", "mean": 0.2645699604018182, "stddev": 0.009253164823394697, "median": 0.26372722522000003, "user": 0.2632035254545454, "system": 0.0014536563636363636, "min": 0.24764987322, "max": 0.28167238222, "times": [ 0.27004933622000005, 0.26448221622000007, 0.25952847222000003, 0.24764987322, 0.26372722522000003, 0.26165526122000005, 0.25714677222000004, 0.28167238222, 0.26352976122000005, 0.27705794322000005, 0.26377032122000005 ], "exit_codes": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ] } ] }