Increasing the SIMD size improves the vectorization possibilities

Change the simd-wide-sum.rs to pass the LLVM main branching test.
This commit is contained in:
DianQK 2023-09-21 12:29:20 +08:00
parent cbce15c617
commit d30f210e5d
No known key found for this signature in database
GPG Key ID: 46BDB1AC96C48912

View File

@ -11,14 +11,14 @@
#![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()
}
@ -26,9 +26,9 @@ pub fn wider_reduce_simd(x: Simd<u8, N>) -> u16 {
#[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]);
@ -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()
}
@ -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()
}