Enable f16 in assembly on aarch64 platforms that support it
Signed-off-by: rongfu.leng <lenronfu@gmail.com>
This commit is contained in:
rongfu.leng
beetrees
parent
f167efad2f
commit
ec67cdf98a
4 changed files with 55 additions and 7 deletions
|
|
@ -59,11 +59,11 @@ impl AArch64InlineAsmRegClass {
|
|||
_arch: InlineAsmArch,
|
||||
) -> &'static [(InlineAsmType, Option<Symbol>)] {
|
||||
match self {
|
||||
Self::reg => types! { _: I8, I16, I32, I64, F32, F64; },
|
||||
Self::reg => types! { _: I8, I16, I32, I64, F16, F32, F64; },
|
||||
Self::vreg | Self::vreg_low16 => types! {
|
||||
neon: I8, I16, I32, I64, F32, F64,
|
||||
neon: I8, I16, I32, I64, F16, F32, F64,
|
||||
VecI8(8), VecI16(4), VecI32(2), VecI64(1), VecF32(2), VecF64(1),
|
||||
VecI8(16), VecI16(8), VecI32(4), VecI64(2), VecF32(4), VecF64(2);
|
||||
VecI8(16), VecI16(8), VecI32(4), VecI64(2), VecF16(4),VecF16(8), VecF32(4), VecF64(2);
|
||||
},
|
||||
Self::preg => &[],
|
||||
}
|
||||
|
|
|
|||
|
|
@ -5,7 +5,7 @@
|
|||
//@ [arm64ec] compile-flags: --target arm64ec-pc-windows-msvc
|
||||
//@ [arm64ec] needs-llvm-components: aarch64
|
||||
|
||||
#![feature(no_core, lang_items, rustc_attrs, repr_simd, asm_experimental_arch)]
|
||||
#![feature(no_core, lang_items, rustc_attrs, repr_simd, asm_experimental_arch, f16)]
|
||||
#![crate_type = "rlib"]
|
||||
#![no_core]
|
||||
#![allow(asm_sub_register, non_camel_case_types)]
|
||||
|
|
@ -39,6 +39,10 @@ pub struct i32x2(i32, i32);
|
|||
#[repr(simd)]
|
||||
pub struct i64x1(i64);
|
||||
#[repr(simd)]
|
||||
pub struct f16x4(f16, f16, f16, f16);
|
||||
#[repr(simd)]
|
||||
pub struct f16x8(f16, f16, f16, f16, f16, f16, f16, f16);
|
||||
#[repr(simd)]
|
||||
pub struct f32x2(f32, f32);
|
||||
#[repr(simd)]
|
||||
pub struct f64x1(f64);
|
||||
|
|
@ -57,6 +61,7 @@ pub struct f64x2(f64, f64);
|
|||
|
||||
impl Copy for i8 {}
|
||||
impl Copy for i16 {}
|
||||
impl Copy for f16 {}
|
||||
impl Copy for i32 {}
|
||||
impl Copy for f32 {}
|
||||
impl Copy for i64 {}
|
||||
|
|
@ -67,11 +72,13 @@ impl Copy for i16x4 {}
|
|||
impl Copy for i32x2 {}
|
||||
impl Copy for i64x1 {}
|
||||
impl Copy for f32x2 {}
|
||||
impl Copy for f16x4 {}
|
||||
impl Copy for f64x1 {}
|
||||
impl Copy for i8x16 {}
|
||||
impl Copy for i16x8 {}
|
||||
impl Copy for i32x4 {}
|
||||
impl Copy for i64x2 {}
|
||||
impl Copy for f16x8 {}
|
||||
impl Copy for f32x4 {}
|
||||
impl Copy for f64x2 {}
|
||||
|
||||
|
|
@ -165,6 +172,12 @@ check!(reg_i16 i16 reg "mov" "");
|
|||
// CHECK: //NO_APP
|
||||
check!(reg_i32 i32 reg "mov" "");
|
||||
|
||||
// CHECK-LABEL: reg_f16:
|
||||
// CHECK: @APP
|
||||
// CHECK: mov {{[a-z0-9]+}}, {{[a-z0-9]+}}
|
||||
// CHECK: @NO_APP
|
||||
check!(reg_f16 f16 reg "mov");
|
||||
|
||||
// CHECK-LABEL: {{("#)?}}reg_f32{{"?}}
|
||||
// CHECK: //APP
|
||||
// CHECK: mov x{{[0-9]+}}, x{{[0-9]+}}
|
||||
|
|
@ -255,6 +268,20 @@ check!(vreg_i32x2 i32x2 vreg "fmov" "s");
|
|||
// CHECK: //NO_APP
|
||||
check!(vreg_i64x1 i64x1 vreg "fmov" "s");
|
||||
|
||||
// neon-LABEL: vreg_f16x4:
|
||||
// neon: @APP
|
||||
// neon: vmov.f64 d{{[0-9]+}}, d{{[0-9]+}}
|
||||
// neon: @NO_APP
|
||||
#[cfg(neon)]
|
||||
check!(vreg_f16x4 f16x4 vreg "vmov.f64");
|
||||
|
||||
// neon-LABEL: vreg_f16x8:
|
||||
// neon: @APP
|
||||
// neon: vorr q{{[0-9]+}}, q{{[0-9]+}}, q{{[0-9]+}}
|
||||
// neon: @NO_APP
|
||||
#[cfg(neon)]
|
||||
check!(vreg_f16x8 f16x8 vreg "vmov");
|
||||
|
||||
// CHECK-LABEL: {{("#)?}}vreg_f32x2{{"?}}
|
||||
// CHECK: //APP
|
||||
// CHECK: fmov s{{[0-9]+}}, s{{[0-9]+}}
|
||||
|
|
|
|||
|
|
@ -95,7 +95,7 @@ error: type `i128` cannot be used with this register class
|
|||
LL | asm!("{}", in(reg) 0i128);
|
||||
| ^^^^^
|
||||
|
|
||||
= note: register class `reg` supports these types: i8, i16, i32, i64, f32, f64
|
||||
= note: register class `reg` supports these types: i8, i16, i32, i64, f16, f32, f64
|
||||
|
||||
error: type `float64x2_t` cannot be used with this register class
|
||||
--> $DIR/type-check-3.rs:75:28
|
||||
|
|
@ -103,7 +103,7 @@ error: type `float64x2_t` cannot be used with this register class
|
|||
LL | asm!("{}", in(reg) f64x2);
|
||||
| ^^^^^
|
||||
|
|
||||
= note: register class `reg` supports these types: i8, i16, i32, i64, f32, f64
|
||||
= note: register class `reg` supports these types: i8, i16, i32, i64, f16, f32, f64
|
||||
|
||||
error: type `Simd256bit` cannot be used with this register class
|
||||
--> $DIR/type-check-3.rs:77:29
|
||||
|
|
@ -111,7 +111,7 @@ error: type `Simd256bit` cannot be used with this register class
|
|||
LL | asm!("{}", in(vreg) f64x4);
|
||||
| ^^^^^
|
||||
|
|
||||
= note: register class `vreg` supports these types: i8, i16, i32, i64, f32, f64, i8x8, i16x4, i32x2, i64x1, f32x2, f64x1, i8x16, i16x8, i32x4, i64x2, f32x4, f64x2
|
||||
= note: register class `vreg` supports these types: i8, i16, i32, i64, f16, f32, f64, i8x8, i16x4, i32x2, i64x1, f32x2, f64x1, i8x16, i16x8, i32x4, i64x2, f16x4, f16x8, f32x4, f64x2
|
||||
|
||||
error: incompatible types for asm inout argument
|
||||
--> $DIR/type-check-3.rs:88:33
|
||||
|
|
|
|||
21
tests/ui/asm/aarch64/type-f16.rs
Normal file
21
tests/ui/asm/aarch64/type-f16.rs
Normal file
|
|
@ -0,0 +1,21 @@
|
|||
//@ only-aarch64
|
||||
//@ run-pass
|
||||
|
||||
#![feature(f16, f128)]
|
||||
use std::arch::asm;
|
||||
#[inline(never)]
|
||||
pub fn f32_to_f16_asm(a: f32) -> f16 {
|
||||
let ret: f16;
|
||||
unsafe {
|
||||
asm!(
|
||||
"fcvt {ret:h}, {a:s}",
|
||||
a = in(vreg) a,
|
||||
ret = lateout(vreg) ret,
|
||||
options(nomem, nostack),
|
||||
);
|
||||
}
|
||||
ret
|
||||
}
|
||||
fn main() {
|
||||
assert_eq!(f32_to_f16_asm(1.0 as f32), 1.0);
|
||||
}
|
||||
Loading…
Add table
Reference in a new issue