Skip to content

Commit

Permalink
Increasing the SIMD size improves the vectorization possibilities
Browse files Browse the repository at this point in the history
Change the simd-wide-sum.rs to pass the LLVM main branching test.
  • Loading branch information
DianQK committed Sep 21, 2023
1 parent cbce15c commit d30f210
Showing 1 changed file with 13 additions and 13 deletions.
26 changes: 13 additions & 13 deletions tests/codegen/simd/simd-wide-sum.rs
Original file line number Diff line number Diff line change
Expand Up @@ -11,24 +11,24 @@
#![feature(portable_simd)]

use std::simd::{Simd, SimdUint};
const N: usize = 8;
const N: usize = 16;

#[no_mangle]
// CHECK-LABEL: @wider_reduce_simd
pub fn wider_reduce_simd(x: Simd<u8, N>) -> u16 {
// CHECK: zext <8 x i8>
// CHECK-SAME: to <8 x i16>
// CHECK: call i16 @llvm.vector.reduce.add.v8i16(<8 x i16>
// CHECK: zext <16 x i8>
// CHECK-SAME: to <16 x i16>
// CHECK: call i16 @llvm.vector.reduce.add.v16i16(<16 x i16>
let x: Simd<u16, N> = x.cast();
x.reduce_sum()
}

#[no_mangle]
// CHECK-LABEL: @wider_reduce_loop
pub fn wider_reduce_loop(x: Simd<u8, N>) -> u16 {
// CHECK: zext <8 x i8>
// CHECK-SAME: to <8 x i16>
// CHECK: call i16 @llvm.vector.reduce.add.v8i16(<8 x i16>
// CHECK: zext <16 x i8>
// CHECK-SAME: to <16 x i16>
// CHECK: call i16 @llvm.vector.reduce.add.v16i16(<16 x i16>
let mut sum = 0_u16;
for i in 0..N {
sum += u16::from(x[i]);
Expand All @@ -39,9 +39,9 @@ pub fn wider_reduce_loop(x: Simd<u8, N>) -> u16 {
#[no_mangle]
// CHECK-LABEL: @wider_reduce_iter
pub fn wider_reduce_iter(x: Simd<u8, N>) -> u16 {
// CHECK: zext <8 x i8>
// CHECK-SAME: to <8 x i16>
// CHECK: call i16 @llvm.vector.reduce.add.v8i16(<8 x i16>
// CHECK: zext <16 x i8>
// CHECK-SAME: to <16 x i16>
// CHECK: call i16 @llvm.vector.reduce.add.v16i16(<16 x i16>
x.as_array().iter().copied().map(u16::from).sum()
}

Expand All @@ -52,8 +52,8 @@ pub fn wider_reduce_iter(x: Simd<u8, N>) -> u16 {
#[no_mangle]
// CHECK-LABEL: @wider_reduce_into_iter
pub fn wider_reduce_into_iter(x: Simd<u8, N>) -> u16 {
// CHECK: zext <8 x i8>
// CHECK-SAME: to <8 x i16>
// CHECK: call i16 @llvm.vector.reduce.add.v8i16(<8 x i16>
// CHECK: zext <16 x i8>
// CHECK-SAME: to <16 x i16>
// CHECK: call i16 @llvm.vector.reduce.add.v16i16(<16 x i16>
x.to_array().into_iter().map(u16::from).sum()
}

0 comments on commit d30f210

Please sign in to comment.