diff options
| author | xufuji456 <839789740@qq.com> | 2023-11-15 11:53:12 +0800 |
|---|---|---|
| committer | Martin Storsjö <martin@martin.st> | 2023-11-28 15:54:49 +0200 |
| commit | cc86343b960793a822d6c51b58a1a7e3319cb217 (patch) | |
| tree | d37b70fdb4ef8fa8157564e2a5efdd71d39cda87 /libswscale | |
| parent | 67ce690bc6b64623bbe4ec79d4be7cad01cdfbbf (diff) | |
| download | ffmpeg-cc86343b960793a822d6c51b58a1a7e3319cb217.tar.gz | |
lavc/hevcdsp_qpel_neon: using movi.16b instead of movi.2d
Building iOS platform with arm64, the compiler has a warning: "instruction movi.2d with immediate #0 may not function correctly on this CPU, converting to movi.16b"
Signed-off-by: xufuji456 <839789740@qq.com>
Signed-off-by: Martin Storsjö <martin@martin.st>
Diffstat (limited to 'libswscale')
| -rw-r--r-- | libswscale/aarch64/hscale.S | 72 |
1 files changed, 36 insertions, 36 deletions
diff --git a/libswscale/aarch64/hscale.S b/libswscale/aarch64/hscale.S index b49443c964..b3873fc4b7 100644 --- a/libswscale/aarch64/hscale.S +++ b/libswscale/aarch64/hscale.S @@ -50,10 +50,10 @@ function ff_hscale8to15_X8_neon, export=1 add x12, x16, x7 // filter1 = filter0 + filterSize*2 add x13, x12, x7 // filter2 = filter1 + filterSize*2 add x4, x13, x7 // filter3 = filter2 + filterSize*2 - movi v0.2d, #0 // val sum part 1 (for dst[0]) - movi v1.2d, #0 // val sum part 2 (for dst[1]) - movi v2.2d, #0 // val sum part 3 (for dst[2]) - movi v3.2d, #0 // val sum part 4 (for dst[3]) + movi v0.16b, #0 // val sum part 1 (for dst[0]) + movi v1.16b, #0 // val sum part 2 (for dst[1]) + movi v2.16b, #0 // val sum part 3 (for dst[2]) + movi v3.16b, #0 // val sum part 4 (for dst[3]) add x17, x3, w8, uxtw // srcp + filterPos[0] add x8, x3, w0, uxtw // srcp + filterPos[1] add x0, x3, w11, uxtw // srcp + filterPos[2] @@ -108,10 +108,10 @@ function ff_hscale8to15_X4_neon, export=1 ldp w8, w9, [x5] // filterPos[idx + 0], [idx + 1] ldp w10, w11, [x5, #8] // filterPos[idx + 2], [idx + 3] - movi v16.2d, #0 // initialize accumulator for idx + 0 - movi v17.2d, #0 // initialize accumulator for idx + 1 - movi v18.2d, #0 // initialize accumulator for idx + 2 - movi v19.2d, #0 // initialize accumulator for idx + 3 + movi v16.16b, #0 // initialize accumulator for idx + 0 + movi v17.16b, #0 // initialize accumulator for idx + 1 + movi v18.16b, #0 // initialize accumulator for idx + 2 + movi v19.16b, #0 // initialize accumulator for idx + 3 mov x12, x4 // filter pointer for idx + 0 add x13, x4, x7 // filter pointer for idx + 1 @@ -253,8 +253,8 @@ function ff_hscale8to15_4_neon, export=1 ldp w12, w13, [x5, #16] // filterPos[idx + 4][0..3], [idx + 5][0..3], next iteration ldp w14, w15, [x5, #24] // filterPos[idx + 6][0..3], [idx + 7][0..3], next iteration - movi v0.2d, #0 // Clear madd accumulator for idx 0..3 - movi v5.2d, #0 // Clear madd accumulator for idx 4..7 + movi v0.16b, #0 // Clear madd accumulator for idx 0..3 + movi v5.16b, #0 // Clear madd accumulator for idx 4..7 ld4 {v1.8h, v2.8h, v3.8h, v4.8h}, [x4], #64 // load filter idx + 0..7 @@ -299,8 +299,8 @@ function ff_hscale8to15_4_neon, export=1 ld4 {v16.8b, v17.8b, v18.8b, v19.8b}, [sp] ld4 {v1.8h, v2.8h, v3.8h, v4.8h}, [x4], #64 // load filter idx + 0..7 - movi v0.2d, #0 // Clear madd accumulator for idx 0..3 - movi v5.2d, #0 // Clear madd accumulator for idx 4..7 + movi v0.16b, #0 // Clear madd accumulator for idx 0..3 + movi v5.16b, #0 // Clear madd accumulator for idx 4..7 uxtl v16.8h, v16.8b // unsigned extend long, covert src data to 16-bit uxtl v17.8h, v17.8b // unsigned extend long, covert src data to 16-bit @@ -499,10 +499,10 @@ function ff_hscale8to19_X8_neon, export=1 ldr w11, [x5], #4 // filterPos[idx + 2] add x4, x13, x7 // filter3 = filter2 + filterSize*2 ldr w9, [x5], #4 // filterPos[idx + 3] - movi v0.2d, #0 // val sum part 1 (for dst[0]) - movi v1.2d, #0 // val sum part 2 (for dst[1]) - movi v2.2d, #0 // val sum part 3 (for dst[2]) - movi v3.2d, #0 // val sum part 4 (for dst[3]) + movi v0.16b, #0 // val sum part 1 (for dst[0]) + movi v1.16b, #0 // val sum part 2 (for dst[1]) + movi v2.16b, #0 // val sum part 3 (for dst[2]) + movi v3.16b, #0 // val sum part 4 (for dst[3]) add x17, x3, w8, uxtw // srcp + filterPos[0] add x8, x3, w0, uxtw // srcp + filterPos[1] add x0, x3, w11, uxtw // srcp + filterPos[2] @@ -560,10 +560,10 @@ function ff_hscale8to19_X4_neon, export=1 ldp w8, w9, [x5] ldp w10, w11, [x5, #8] - movi v16.2d, #0 // initialize accumulator for idx + 0 - movi v17.2d, #0 // initialize accumulator for idx + 1 - movi v18.2d, #0 // initialize accumulator for idx + 2 - movi v19.2d, #0 // initialize accumulator for idx + 3 + movi v16.16b, #0 // initialize accumulator for idx + 0 + movi v17.16b, #0 // initialize accumulator for idx + 1 + movi v18.16b, #0 // initialize accumulator for idx + 2 + movi v19.16b, #0 // initialize accumulator for idx + 3 mov x12, x4 // filter + 0 add x13, x4, x7 // filter + 1 @@ -865,10 +865,10 @@ function ff_hscale16to15_X8_neon_asm, export=1 add x12, x16, x7 // filter1 = filter0 + filterSize*2 add x13, x12, x7 // filter2 = filter1 + filterSize*2 add x4, x13, x7 // filter3 = filter2 + filterSize*2 - movi v0.2d, #0 // val sum part 1 (for dst[0]) - movi v1.2d, #0 // val sum part 2 (for dst[1]) - movi v2.2d, #0 // val sum part 3 (for dst[2]) - movi v3.2d, #0 // val sum part 4 (for dst[3]) + movi v0.16b, #0 // val sum part 1 (for dst[0]) + movi v1.16b, #0 // val sum part 2 (for dst[1]) + movi v2.16b, #0 // val sum part 3 (for dst[2]) + movi v3.16b, #0 // val sum part 4 (for dst[3]) add x17, x3, w8, uxtw // srcp + filterPos[0] add x8, x3, w10, uxtw // srcp + filterPos[1] add x10, x3, w11, uxtw // srcp + filterPos[2] @@ -945,10 +945,10 @@ function ff_hscale16to15_X4_neon_asm, export=1 ldp w8, w9, [x5] ldp w10, w11, [x5, #8] - movi v16.2d, #0 // initialize accumulator for idx + 0 - movi v17.2d, #0 // initialize accumulator for idx + 1 - movi v18.2d, #0 // initialize accumulator for idx + 2 - movi v19.2d, #0 // initialize accumulator for idx + 3 + movi v16.16b, #0 // initialize accumulator for idx + 0 + movi v17.16b, #0 // initialize accumulator for idx + 1 + movi v18.16b, #0 // initialize accumulator for idx + 2 + movi v19.16b, #0 // initialize accumulator for idx + 3 mov x12, x4 // filter + 0 add x13, x4, x7 // filter + 1 @@ -1270,10 +1270,10 @@ function ff_hscale16to19_X8_neon_asm, export=1 add x13, x12, x7 // filter2 = filter1 + filterSize*2 lsl w10, w10, #1 add x4, x13, x7 // filter3 = filter2 + filterSize*2 - movi v0.2d, #0 // val sum part 1 (for dst[0]) - movi v1.2d, #0 // val sum part 2 (for dst[1]) - movi v2.2d, #0 // val sum part 3 (for dst[2]) - movi v3.2d, #0 // val sum part 4 (for dst[3]) + movi v0.16b, #0 // val sum part 1 (for dst[0]) + movi v1.16b, #0 // val sum part 2 (for dst[1]) + movi v2.16b, #0 // val sum part 3 (for dst[2]) + movi v3.16b, #0 // val sum part 4 (for dst[3]) add x17, x3, w8, uxtw // srcp + filterPos[0] add x8, x3, w10, uxtw // srcp + filterPos[1] add x10, x3, w11, uxtw // srcp + filterPos[2] @@ -1348,10 +1348,10 @@ function ff_hscale16to19_X4_neon_asm, export=1 ldp w8, w9, [x5] ldp w10, w11, [x5, #8] - movi v16.2d, #0 // initialize accumulator for idx + 0 - movi v17.2d, #0 // initialize accumulator for idx + 1 - movi v18.2d, #0 // initialize accumulator for idx + 2 - movi v19.2d, #0 // initialize accumulator for idx + 3 + movi v16.16b, #0 // initialize accumulator for idx + 0 + movi v17.16b, #0 // initialize accumulator for idx + 1 + movi v18.16b, #0 // initialize accumulator for idx + 2 + movi v19.16b, #0 // initialize accumulator for idx + 3 mov x12, x4 // filter + 0 add x13, x4, x7 // filter + 1 |