mirror of
https://github.com/rust-lang/rust.git
synced 2024-11-26 00:34:06 +00:00
e91f937779
The tests show that the code generation currently uses the least significant bits of <iX x N> vector masks when converting to <i1 xN>. This leads to an additional left shift operation in the assembly for x86, since mask operations on x86 operate based on the most significant bit. On aarch64 the left shift is followed by a comparison against zero, which repeats the sign bit across the whole lane. The exception, which does not introduce an unneeded shift, is simd_bitmask, because the code generation already shifts before truncating. By using the "C" calling convention the tests should be stable regarding changes in register allocation, but it is possible that future llvm updates will require updating some of the checks. This additional instruction would be removed by the fix in #104693, which uses the most significant bit for all mask operations.
41 lines
1.1 KiB
Rust
41 lines
1.1 KiB
Rust
//@ revisions: x86-avx512
|
|
//@ [x86-avx512] compile-flags: --target=x86_64-unknown-linux-gnu -C llvm-args=-x86-asm-syntax=intel
|
|
//@ [x86-avx512] compile-flags: -C target-feature=+avx512f,+avx512vl,+avx512bw,+avx512dq
|
|
//@ [x86-avx512] needs-llvm-components: x86
|
|
//@ [x86-avx512] min-llvm-version: 18.0
|
|
//@ assembly-output: emit-asm
|
|
//@ compile-flags: --crate-type=lib -O
|
|
|
|
#![feature(no_core, lang_items, repr_simd, intrinsics)]
|
|
#![no_core]
|
|
#![allow(non_camel_case_types)]
|
|
|
|
// Because we don't have core yet.
|
|
#[lang = "sized"]
|
|
pub trait Sized {}
|
|
|
|
#[lang = "copy"]
|
|
trait Copy {}
|
|
|
|
#[repr(simd)]
|
|
pub struct f64x4([f64; 4]);
|
|
|
|
#[repr(simd)]
|
|
pub struct m64x4([i64; 4]);
|
|
|
|
#[repr(simd)]
|
|
pub struct pf64x4([*mut f64; 4]);
|
|
|
|
extern "rust-intrinsic" {
|
|
fn simd_scatter<V, P, M>(values: V, pointer: P, mask: M);
|
|
}
|
|
|
|
// CHECK-LABEL: scatter_f64x4
|
|
#[no_mangle]
|
|
pub unsafe extern "C" fn scatter_f64x4(values: f64x4, ptrs: pf64x4, mask: m64x4) {
|
|
// x86-avx512: vpsllq ymm2, ymm2, 63
|
|
// x86-avx512-NEXT: vpmovq2m k1, ymm2
|
|
// x86-avx512-NEXT: vscatterqpd ymmword ptr [1*ymm1] {k1}, ymm0
|
|
simd_scatter(values, ptrs, mask)
|
|
}
|