Skip to content

WIP: Use NEON intrinsics for lrint on arm64 processors #232

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

Draft
janblaesi wants to merge 1 commit into
base: master
Choose a base branch
from
Draft

WIP: Use NEON intrinsics for lrint on arm64 processors #232

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
20 changes: 20 additions & 0 deletions src/common.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,6 +36,10 @@
# endif
#endif

#if defined(__aarch64__) || defined(_M_ARM64)
# define HAVE_NEON_INTRINSICS
#endif

#ifdef HAVE_SSE2_INTRINSICS
#ifdef HAVE_IMMINTRIN_H
#include <immintrin.h>
Expand All @@ -44,6 +48,10 @@
#endif
#endif /* HAVE_SSE2_INTRINSICS */

#if defined(HAVE_NEON_INTRINSICS)
#include <arm_neon.h>
#endif /* HAVE_NEON_INTRINSICS */

#include <math.h>

#ifdef HAVE_VISIBILITY
Expand Down Expand Up @@ -214,6 +222,18 @@ psf_lrint (double x)
return _mm_cvtsd_si32 (_mm_load_sd (&x)) ;
}

#elif defined(HAVE_NEON_INTRINSICS)

static inline int psf_lrintf (float x)
{
return vcvts_s32_f32(x);
} /* psf_lrintf */

static inline int psf_lrint (double x)
{
return (int) vcvtd_s64_f64(x);
} /* psf_lrint */

#else

static inline int psf_lrintf (float x)
Expand Down