auto merge of #6724 : thestinger/rust/swap_fast, r=thestinger
Passing higher alignment values gives the optimization passes more freedom since it can copy in larger chunks. This change results in rustc outputting the same post-optimization IR as clang for swaps and most copies excluding the lack of information about padding.
Code snippet:
```rust
#[inline(never)]
fn swap<T>(x: &mut T, y: &mut T) {
util::swap(x, y);
}
```
Original IR (for `int`):
```llvm
define internal fastcc void @_ZN9swap_283417_a71830ca3ed2d65d3_00E(i64*, i64*) #1 {
static_allocas:
%2 = icmp eq i64* %0, %1
br i1 %2, label %_ZN4util9swap_283717_a71830ca3ed2d65d3_00E.exit, label %3
; <label>:3 ; preds = %static_allocas
%4 = load i64* %0, align 1
%5 = load i64* %1, align 1
store i64 %5, i64* %0, align 1
store i64 %4, i64* %1, align 1
br label %_ZN4util9swap_283717_a71830ca3ed2d65d3_00E.exit
_ZN4util9swap_283717_a71830ca3ed2d65d3_00E.exit: ; preds = %3, %static_allocas
ret void
}
```
After #6710:
```llvm
define internal fastcc void @_ZN9swap_283017_a71830ca3ed2d65d3_00E(i64* nocapture, i64* nocapture) #1 {
static_allocas:
%2 = load i64* %0, align 1
%3 = load i64* %1, align 1
store i64 %3, i64* %0, align 1
store i64 %2, i64* %1, align 1
ret void
}
```
After this change:
```llvm
define internal fastcc void @_ZN9swap_283017_a71830ca3ed2d65d3_00E(i64* nocapture, i64* nocapture) #1 {
static_allocas:
%2 = load i64* %0, align 8
%3 = load i64* %1, align 8
store i64 %3, i64* %0, align 8
store i64 %2, i64* %1, align 8
ret void
}
```
Another example:
```rust
#[inline(never)]
fn set<T>(x: &mut T, y: T) {
*x = y;
}
```
Before, with `(int, int)` (align 1):
```llvm
define internal fastcc void @_ZN8set_282517_8fa972e3f9e451983_00E({ i64, i64 }* nocapture, { i64, i64 }* nocapture) #1 {
static_allocas:
%2 = bitcast { i64, i64 }* %1 to i8*
%3 = bitcast { i64, i64 }* %0 to i8*
tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %3, i8* %2, i64 16, i32 1, i1 false)
ret void
}
```
After, with `(int, int)` (align 8):
```llvm
define internal fastcc void @_ZN8set_282617_8fa972e3f9e451983_00E({ i64, i64 }* nocapture, { i64, i64 }* nocapture) #1 {
static_allocas:
%2 = bitcast { i64, i64 }* %1 to i8*
%3 = bitcast { i64, i64 }* %0 to i8*
tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %3, i8* %2, i64 16, i32 8, i1 false)
ret void
}
```
dbc57584bd