1
Fork 0

add inline attribute and codegen test

This commit is contained in:
edwloef 2025-01-28 12:26:32 +01:00
parent 311c3b71f0
commit fb3d1d0c4b
No known key found for this signature in database
2 changed files with 34 additions and 0 deletions

View file

@ -10,6 +10,7 @@ type BufType = [usize; 32];
/// # Safety
///
/// The specified range must be valid for reading and writing.
#[inline]
pub(super) unsafe fn ptr_rotate<T>(left: usize, mid: *mut T, right: usize) {
if T::IS_ZST {
return;
@ -43,6 +44,7 @@ pub(super) unsafe fn ptr_rotate<T>(left: usize, mid: *mut T, right: usize) {
/// # Safety
///
/// The specified range must be valid for reading and writing.
#[inline]
unsafe fn ptr_rotate_memmove<T>(left: usize, mid: *mut T, right: usize) {
// The `[T; 0]` here is to ensure this is appropriately aligned for T
let mut rawarray = MaybeUninit::<(BufType, [T; 0])>::uninit();
@ -114,6 +116,7 @@ unsafe fn ptr_rotate_memmove<T>(left: usize, mid: *mut T, right: usize) {
/// # Safety
///
/// The specified range must be valid for reading and writing.
#[inline]
unsafe fn ptr_rotate_gcd<T>(left: usize, mid: *mut T, right: usize) {
// Algorithm 2
// Microbenchmarks indicate that the average performance for random shifts is better all
@ -218,6 +221,7 @@ unsafe fn ptr_rotate_gcd<T>(left: usize, mid: *mut T, right: usize) {
/// # Safety
///
/// The specified range must be valid for reading and writing.
#[inline]
unsafe fn ptr_rotate_swap<T>(mut left: usize, mut mid: *mut T, mut right: usize) {
loop {
if left >= right {

View file

@ -0,0 +1,30 @@
//@ compile-flags: -O
#![crate_type = "lib"]
// Ensure that the simple case of rotating by a constant 1 optimizes to the obvious thing
// CHECK-LABEL: @rotate_left_by_one
#[no_mangle]
pub fn rotate_left_by_one(slice: &mut [i32]) {
// CHECK-NOT: phi
// CHECK-NOT: call
// CHECK-NOT: load
// CHECK-NOT: store
// CHECK-NOT: getelementptr
// CHECK: %[[END:.+]] = getelementptr
// CHECK-NEXT: %[[DIM:.+]] = getelementptr
// CHECK-NEXT: %[[LAST:.+]] = load
// CHECK-NEXT: %[[FIRST:.+]] = shl
// CHECK-NEXT: call void @llvm.memmove
// CHECK-NEXT: store i32 %[[LAST]], ptr %[[DIM:.+]]
// CHECK-NOT: phi
// CHECK-NOT: call
// CHECK-NOT: load
// CHECK-NOT: store
// CHECK-NOT: getelementptr
// CHECK: ret void
if !slice.is_empty() {
slice.rotate_left(1);
}
}