Skip to content

Convert x86/sse41.rs intrinsics to const generics #1026

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Mar 1, 2021
Merged

Convert x86/sse41.rs intrinsics to const generics #1026

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
cfc519a
add macros to validate imm2, imm3, and imm4
lqd Feb 28, 2021
c934f5f
convert `x86::sse41` intrinsics to const generics
lqd Feb 28, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
33 changes: 27 additions & 6 deletions crates/core_arch/src/macros.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,18 +1,39 @@
//! Utility macros.

// Helper struct used to trigger const eval errors when a const generic immediate value is
// out of range.
pub(crate) struct ValidateConstImm8<const imm8: i32>();
impl<const imm8: i32> ValidateConstImm8<imm8> {
// Helper struct used to trigger const eval errors when the const generic immediate value `imm` is
// out of `bits`-bit range.
pub(crate) struct ValidateConstImm<const imm: i32, const bits: i32>;
impl<const imm: i32, const bits: i32> ValidateConstImm<imm, bits> {
pub(crate) const VALID: () = {
let _ = 1 / ((imm8 >= 0 && imm8 <= 255) as usize);
let _ = 1 / ((imm >= 0 && imm < (1 << bits)) as usize);
};
}

#[allow(unused)]
macro_rules! static_assert_imm2 {
($imm:ident) => {
let _ = $crate::core_arch::macros::ValidateConstImm::<$imm, 2>::VALID;
};
}

#[allow(unused)]
macro_rules! static_assert_imm3 {
($imm:ident) => {
let _ = $crate::core_arch::macros::ValidateConstImm::<$imm, 3>::VALID;
};
}

#[allow(unused)]
macro_rules! static_assert_imm4 {
($imm:ident) => {
let _ = $crate::core_arch::macros::ValidateConstImm::<$imm, 4>::VALID;
};
}

#[allow(unused)]
macro_rules! static_assert_imm8 {
($imm:ident) => {
let _ = $crate::core_arch::macros::ValidateConstImm8::<$imm>::VALID;
let _ = $crate::core_arch::macros::ValidateConstImm::<$imm, 8>::VALID;
};
}

Expand Down
10 changes: 5 additions & 5 deletions crates/core_arch/src/x86/avx2.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4415,14 +4415,14 @@ mod tests {

#[simd_test(enable = "avx2")]
unsafe fn test_mm_broadcastb_epi8() {
let a = _mm_insert_epi8(_mm_set1_epi8(0x00), 0x2a, 0);
let a = _mm_insert_epi8::<0>(_mm_set1_epi8(0x00), 0x2a);
let res = _mm_broadcastb_epi8(a);
assert_eq_m128i(res, _mm_set1_epi8(0x2a));
}

#[simd_test(enable = "avx2")]
unsafe fn test_mm256_broadcastb_epi8() {
let a = _mm_insert_epi8(_mm_set1_epi8(0x00), 0x2a, 0);
let a = _mm_insert_epi8::<0>(_mm_set1_epi8(0x00), 0x2a);
let res = _mm256_broadcastb_epi8(a);
assert_eq_m256i(res, _mm256_set1_epi8(0x2a));
}
Expand Down Expand Up @@ -5204,7 +5204,7 @@ mod tests {
#[simd_test(enable = "avx2")]
unsafe fn test_mm256_sll_epi32() {
let a = _mm256_set1_epi32(0xFFFF);
let b = _mm_insert_epi32(_mm_set1_epi32(0), 4, 0);
let b = _mm_insert_epi32::<0>(_mm_set1_epi32(0), 4);
let r = _mm256_sll_epi32(a, b);
assert_eq_m256i(r, _mm256_set1_epi32(0xFFFF0));
}
Expand Down Expand Up @@ -5295,7 +5295,7 @@ mod tests {
#[simd_test(enable = "avx2")]
unsafe fn test_mm256_sra_epi32() {
let a = _mm256_set1_epi32(-1);
let b = _mm_insert_epi32(_mm_set1_epi32(0), 1, 0);
let b = _mm_insert_epi32::<0>(_mm_set1_epi32(0), 1);
let r = _mm256_sra_epi32(a, b);
assert_eq_m256i(r, _mm256_set1_epi32(-1));
}
Expand Down Expand Up @@ -5365,7 +5365,7 @@ mod tests {
#[simd_test(enable = "avx2")]
unsafe fn test_mm256_srl_epi32() {
let a = _mm256_set1_epi32(0xFFFF);
let b = _mm_insert_epi32(_mm_set1_epi32(0), 4, 0);
let b = _mm_insert_epi32::<0>(_mm_set1_epi32(0), 4);
let r = _mm256_srl_epi32(a, b);
assert_eq_m256i(r, _mm256_set1_epi32(0xFFF));
}
Expand Down
Loading