rust/tests/assembly/simd-intrinsic-mask-reduce.rs
Josh Stone 706f06c39a Use an explicit x86-64 cpu in tests that are sensitive to it
There are a few tests that depend on some target features **not** being
enabled by default, and usually they are correct with the default x86-64
target CPU. However, in downstream builds we have modified the default
to fit our distros -- `x86-64-v2` in RHEL 9 and `x86-64-v3` in RHEL 10
-- and the latter especially trips tests that expect not to have AVX.

These cases are few enough that we can just set them back explicitly.
2024-05-01 15:25:26 -07:00

62 lines
1.8 KiB
Rust

// verify that simd mask reductions do not introduce additional bit shift operations
//@ revisions: x86 aarch64
//@ [x86] compile-flags: --target=x86_64-unknown-linux-gnu -C llvm-args=-x86-asm-syntax=intel
//@ [x86] compile-flags: -C target-cpu=x86-64
//@ [x86] needs-llvm-components: x86
//@ [aarch64] compile-flags: --target=aarch64-unknown-linux-gnu
//@ [aarch64] needs-llvm-components: aarch64
//@ [aarch64] 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 mask8x16([i8; 16]);
extern "rust-intrinsic" {
fn simd_reduce_all<T>(x: T) -> bool;
fn simd_reduce_any<T>(x: T) -> bool;
}
// CHECK-LABEL: mask_reduce_all:
#[no_mangle]
pub unsafe extern "C" fn mask_reduce_all(m: mask8x16) -> bool {
// x86: psllw xmm0, 7
// x86-NEXT: pmovmskb eax, xmm0
// x86-NEXT: {{cmp ax, -1|xor eax, 65535}}
// x86-NEXT: sete al
//
// aarch64: shl v0.16b, v0.16b, #7
// aarch64-NEXT: cmlt v0.16b, v0.16b, #0
// aarch64-NEXT: uminv b0, v0.16b
// aarch64-NEXT: fmov [[REG:[a-z0-9]+]], s0
// aarch64-NEXT: and w0, [[REG]], #0x1
simd_reduce_all(m)
}
// CHECK-LABEL: mask_reduce_any:
#[no_mangle]
pub unsafe extern "C" fn mask_reduce_any(m: mask8x16) -> bool {
// x86: psllw xmm0, 7
// x86-NEXT: pmovmskb
// x86-NEXT: test eax, eax
// x86-NEXT: setne al
//
// aarch64: shl v0.16b, v0.16b, #7
// aarch64-NEXT: cmlt v0.16b, v0.16b, #0
// aarch64-NEXT: umaxv b0, v0.16b
// aarch64-NEXT: fmov [[REG:[a-z0-9]+]], s0
// aarch64-NEXT: and w0, [[REG]], #0x1
simd_reduce_any(m)
}