Skip to content

perf: loadu_si512 instead of slower loadu_epi #49

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

Open
jvdd wants to merge 1 commit into
base: main
Choose a base branch
from
Open

perf: loadu_si512 instead of slower loadu_epi #49

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
2 changes: 1 addition & 1 deletion src/simd/simd_f16_ignore_nan.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -423,7 +423,7 @@ mod avx512_ignore_nan {

#[inline(always)]
unsafe fn _mm_loadu(data: *const f16) -> __m512i {
_f16_as_m521i_to_i16ord(_mm512_loadu_epi16(data as *const i16))
_f16_as_m521i_to_i16ord(_mm512_loadu_si512(data as *const i32))
}

#[inline(always)]
Expand Down
2 changes: 1 addition & 1 deletion src/simd/simd_f16_return_nan.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -394,7 +394,7 @@ mod avx512 {

#[inline(always)]
unsafe fn _mm_loadu(data: *const f16) -> __m512i {
_f16_as_m521i_to_i16ord(_mm512_loadu_epi16(data as *const i16))
_f16_as_m521i_to_i16ord(_mm512_loadu_si512(data as *const i32))
}

#[inline(always)]
Expand Down
2 changes: 1 addition & 1 deletion src/simd/simd_i16.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -283,7 +283,7 @@ mod avx512 {

#[inline(always)]
unsafe fn _mm_loadu(data: *const i16) -> __m512i {
_mm512_loadu_epi16(data as *const i16)
_mm512_loadu_si512(data as *const i32)
}

#[inline(always)]
Expand Down
2 changes: 1 addition & 1 deletion src/simd/simd_i8.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -297,7 +297,7 @@ mod avx512 {

#[inline(always)]
unsafe fn _mm_loadu(data: *const i8) -> __m512i {
_mm512_loadu_epi8(data as *const i8)
_mm512_loadu_si512(data as *const i32)
}

#[inline(always)]
Expand Down
2 changes: 1 addition & 1 deletion src/simd/simd_u16.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -353,7 +353,7 @@ mod avx512 {

#[inline(always)]
unsafe fn _mm_loadu(data: *const u16) -> __m512i {
_u16_as_m512i_to_i16ord(_mm512_loadu_epi16(data as *const i16))
_u16_as_m512i_to_i16ord(_mm512_loadu_si512(data as *const i32))
}

#[inline(always)]
Expand Down
2 changes: 1 addition & 1 deletion src/simd/simd_u8.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -368,7 +368,7 @@ mod avx512 {

#[inline(always)]
unsafe fn _mm_loadu(data: *const u8) -> __m512i {
_u8_as_m512i_to_i8ord(_mm512_loadu_epi8(data as *const i8))
_u8_as_m512i_to_i8ord(_mm512_loadu_si512(data as *const i32))
}

#[inline(always)]
Expand Down