diff options
Diffstat (limited to 'libavcodec/aarch64/me_cmp_neon.S')
| -rw-r--r-- | libavcodec/aarch64/me_cmp_neon.S | 64 |
1 files changed, 64 insertions, 0 deletions
diff --git a/libavcodec/aarch64/me_cmp_neon.S b/libavcodec/aarch64/me_cmp_neon.S index 26490e189f..c0647c49e9 100644 --- a/libavcodec/aarch64/me_cmp_neon.S +++ b/libavcodec/aarch64/me_cmp_neon.S @@ -420,6 +420,70 @@ function sse16_neon, export=1 ret endfunc +function sse8_neon, export=1 + // x0 - unused + // x1 - pix1 + // x2 - pix2 + // x3 - stride + // w4 - h + + movi v21.4s, #0 + movi v20.4s, #0 + cmp w4, #4 + b.le 2f + +// make 4 iterations at once +1: + + // res = abs(pix1[0] - pix2[0]) + // res * res + + ld1 {v0.8b}, [x1], x3 // Load pix1 for first iteration + ld1 {v1.8b}, [x2], x3 // Load pix2 for second iteration + ld1 {v2.8b}, [x1], x3 // Load pix1 for second iteration + ld1 {v3.8b}, [x2], x3 // Load pix2 for second iteration + uabdl v30.8h, v0.8b, v1.8b // Absolute difference, first iteration + ld1 {v4.8b}, [x1], x3 // Load pix1 for third iteration + ld1 {v5.8b}, [x2], x3 // Load pix2 for third iteration + uabdl v29.8h, v2.8b, v3.8b // Absolute difference, second iteration + umlal v21.4s, v30.4h, v30.4h // Multiply lower half, first iteration + ld1 {v6.8b}, [x1], x3 // Load pix1 for fourth iteration + ld1 {v7.8b}, [x2], x3 // Load pix2 for fourth iteration + uabdl v28.8h, v4.8b, v5.8b // Absolute difference, third iteration + umlal v21.4s, v29.4h, v29.4h // Multiply lower half, second iteration + umlal2 v20.4s, v30.8h, v30.8h // Multiply upper half, first iteration + uabdl v27.8h, v6.8b, v7.8b // Absolute difference, fourth iteration + umlal v21.4s, v28.4h, v28.4h // Multiply lower half, third iteration + umlal2 v20.4s, v29.8h, v29.8h // Multiply upper half, second iteration + sub w4, w4, #4 // h -= 4 + umlal2 v20.4s, v28.8h, v28.8h // Multiply upper half, third iteration + umlal v21.4s, v27.4h, v27.4h // Multiply lower half, fourth iteration + cmp w4, #4 + umlal2 v20.4s, v27.8h, v27.8h // Multiply upper half, fourth iteration + b.ge 1b + + cbz w4, 3f + +// iterate by one +2: + ld1 {v0.8b}, [x1], x3 // Load pix1 + ld1 {v1.8b}, [x2], x3 // Load pix2 + subs w4, w4, #1 + uabdl v30.8h, v0.8b, v1.8b + umlal v21.4s, v30.4h, v30.4h + umlal2 v20.4s, v30.8h, v30.8h + + b.ne 2b + +3: + add v21.4s, v21.4s, v20.4s // Add accumulator vectors together + uaddlv d17, v21.4s // Add up vector + + fmov w0, s17 + ret + +endfunc + function sse4_neon, export=1 // x0 - unused // x1 - pix1 |