Skip to content

AArch64: Use simpler sign expressions in Neon intrinsics code #918

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
kirithika7 merged 2 commits into from
Jul 21, 2026
Merged

AArch64: Use simpler sign expressions in Neon intrinsics code #918

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
db17d20
AArch64: Use simpler expression in sign_diff_neon
georges-arm Jul 16, 2026
48056e6
AArch64: Use simpler sign expression in signOf_neon
georges-arm Jul 17, 2026
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
5 changes: 3 additions & 2 deletions source/common/aarch64/loopfilter-prim.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,9 +15,10 @@ namespace

static inline int8x8_t sign_diff_neon(const uint8x8_t in0, const uint8x8_t in1)
{
int16x8_t in = vreinterpretq_s16_u16(vsubl_u8(in0, in1));
uint8x8_t lt = vclt_u8(in0, in1);
uint8x8_t gt = vcgt_u8(in0, in1);

return vmovn_s16(vmaxq_s16(vminq_s16(in, vdupq_n_s16(1)), vdupq_n_s16(-1)));
return vreinterpret_s8_u8(vsub_u8(lt, gt));
}

static void calSign_neon(int8_t *dst, const pixel *src1, const pixel *src2, const int endX)
Expand Down
6 changes: 3 additions & 3 deletions source/common/aarch64/sao-prim.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ static inline int8x16_t signOf_neon(const pixel *a, const pixel *b)
uint16x8_t s1_lo = vld1q_u16(b);
uint16x8_t s1_hi = vld1q_u16(b + 8);

// signOf(a - b) = -(a > b ? -1 : 0) | (a < b ? -1 : 0)
// signOf(a - b) = (a < b ? -1 : 0) - (a > b ? -1 : 0)
int16x8_t cmp0_lo = vreinterpretq_s16_u16(vcgtq_u16(s0_lo, s1_lo));
int16x8_t cmp0_hi = vreinterpretq_s16_u16(vcgtq_u16(s0_hi, s1_hi));
int16x8_t cmp1_lo = vreinterpretq_s16_u16(vcgtq_u16(s1_lo, s0_lo));
Expand All @@ -47,11 +47,11 @@ static inline int8x16_t signOf_neon(const pixel *a, const pixel *b)
uint8x16_t s0 = vld1q_u8(a);
uint8x16_t s1 = vld1q_u8(b);

// signOf(a - b) = -(a > b ? -1 : 0) | (a < b ? -1 : 0)
// signOf(a - b) = (a < b ? -1 : 0) - (a > b ? -1 : 0)
int8x16_t cmp0 = vreinterpretq_s8_u8(vcgtq_u8(s0, s1));
int8x16_t cmp1 = vreinterpretq_s8_u8(vcgtq_u8(s1, s0));
#endif // HIGH_BIT_DEPTH
return vorrq_s8(vnegq_s8(cmp0), cmp1);
return vsubq_s8(cmp1, cmp0);
}

namespace X265_NS {
Expand Down