The branch, master has been updated
via 6f9e8a599dd94911cbc6713b53ae9bf01701c35c (commit)
via ca2a88c1b3f31417cda689bdb9b2ae2c9f607ca6 (commit)
via 49477972b7175284663c9ef4124345c71dc9c7a1 (commit)
from 5929d46f7bd8a19b40dbb266161a2146beed3afb (commit)
- Log -----------------------------------------------------------------
commit 6f9e8a599dd94911cbc6713b53ae9bf01701c35c
Author: Dash Santosh <santda...@gmail.com>
AuthorDate: Mon Aug 11 10:13:19 2025 +0530
Commit: Martin Storsjö <mar...@martin.st>
CommitDate: Tue Aug 12 09:05:00 2025 +0000
checkasm/swscale: fix whitespace issues
diff --git a/tests/checkasm/sw_scale.c b/tests/checkasm/sw_scale.c
index 0306f02695..52e3ebf75c 100644
--- a/tests/checkasm/sw_scale.c
+++ b/tests/checkasm/sw_scale.c
@@ -159,7 +159,7 @@ static void check_yuv2yuv1(int accurate)
(int) dst0[fail_offset],
(int) dst1[fail_offset]);
}
- if(dstW == LARGEST_INPUT_SIZE)
+ if (dstW == LARGEST_INPUT_SIZE)
bench_new(src_pixels, dst1, dstW, dither, offset);
}
}
@@ -266,7 +266,7 @@ static void check_yuv2yuvX(int accurate, int bit_depth, int
dst_pix_format)
show_differences_16(dst0, dst1,
LARGEST_INPUT_SIZE);
}
}
- if(dstW == LARGEST_INPUT_SIZE)
+ if (dstW == LARGEST_INPUT_SIZE)
bench_new(filter, filter_sizes[fsi], src,
(uint8_t*)dst1, dstW - osi, dither, osi);
}
commit ca2a88c1b3f31417cda689bdb9b2ae2c9f607ca6
Author: Dash Santosh <santda...@gmail.com>
AuthorDate: Mon Aug 11 10:10:53 2025 +0530
Commit: Martin Storsjö <mar...@martin.st>
CommitDate: Tue Aug 12 09:05:00 2025 +0000
swscale/output: Implement yuv2nv12cx neon assembly
yuv2nv12cX_2_512_accurate_c: 3540.1 ( 1.00x)
yuv2nv12cX_2_512_accurate_neon: 408.0 ( 8.68x)
yuv2nv12cX_2_512_approximate_c: 3521.4 ( 1.00x)
yuv2nv12cX_2_512_approximate_neon: 409.2 ( 8.61x)
yuv2nv12cX_4_512_accurate_c: 4740.0 ( 1.00x)
yuv2nv12cX_4_512_accurate_neon: 604.4 ( 7.84x)
yuv2nv12cX_4_512_approximate_c: 4681.9 ( 1.00x)
yuv2nv12cX_4_512_approximate_neon: 603.3 ( 7.76x)
yuv2nv12cX_8_512_accurate_c: 7273.1 ( 1.00x)
yuv2nv12cX_8_512_accurate_neon: 1012.2 ( 7.19x)
yuv2nv12cX_8_512_approximate_c: 7223.0 ( 1.00x)
yuv2nv12cX_8_512_approximate_neon: 1015.8 ( 7.11x)
yuv2nv12cX_16_512_accurate_c: 13762.0 ( 1.00x)
yuv2nv12cX_16_512_accurate_neon: 1761.4 ( 7.81x)
yuv2nv12cX_16_512_approximate_c: 13884.0 ( 1.00x)
yuv2nv12cX_16_512_approximate_neon: 1766.8 ( 7.86x)
Benchmarked on:
Snapdragon(R) X Elite - X1E80100 - Qualcomm(R) Oryon(TM) CPU
3417 Mhz, 12 Core(s), 12 Logical Processor(s)
diff --git a/libswscale/aarch64/output.S b/libswscale/aarch64/output.S
index 4945633856..a650d72f54 100644
--- a/libswscale/aarch64/output.S
+++ b/libswscale/aarch64/output.S
@@ -402,3 +402,230 @@ function ff_yuv2plane1_8_neon, export=1
b.gt 2b // loop until width
consumed
ret
endfunc
+
+function ff_yuv2nv12cX_neon_asm, export=1
+// w0 - isSwapped
+// x1 - uint8_t *chrDither
+// x2 - int16_t *chrFilter
+// x3 - int chrFilterSize
+// x4 - int16_t **chrUSrc
+// x5 - int16_t **chrVSrc
+// x6 - uint8_t *dest
+// x7 - int chrDstW
+
+ stp x19, x20, [sp, #-32]!
+ stp x21, x22, [sp, #16]
+
+ ld1 {v0.8b}, [x1] // chrDither[0..7]
+ ext v1.8b, v0.8b, v0.8b, #3 // Rotate for V:
(i+3)&7
+
+ uxtl v0.8h, v0.8b
+ uxtl v1.8h, v1.8b
+
+ ushll v2.4s, v0.4h, #12 // U dither low
+ ushll2 v3.4s, v0.8h, #12 // U dither high
+ ushll v4.4s, v1.4h, #12 // V dither low
+ ushll2 v5.4s, v1.8h, #12 // V dither high
+
+ mov x8, #0 // i = 0
+1:
+ cmp w7, #16
+ blt 5f
+
+ mov v16.16b, v2.16b // U acc low
+ mov v17.16b, v3.16b // U acc high
+ mov v18.16b, v4.16b // V acc low
+ mov v19.16b, v5.16b // V acc high
+
+ mov v20.16b, v2.16b
+ mov v21.16b, v3.16b
+ mov v22.16b, v4.16b
+ mov v23.16b, v5.16b
+
+ mov w9, w3 // chrFilterSize
counter
+ mov x10, x2 // chrFilter pointer
+ mov x11, x4 // chrUSrc base
+ mov x12, x5 // chrVSrc base
+
+2:
+ ldr h6, [x10], #2 // Load filter
coefficient
+
+ ldr x13, [x11], #8 // chrUSrc[j]
+ ldr x14, [x12], #8 // chrVSrc[j]
+ add x13, x13, x8, lsl #1 // &chrUSrc[j][i]
+ add x14, x14, x8, lsl #1 // &chrVSrc[j][i]
+ add x15, x13, #16
+ add x16, x14, #16
+
+ ld1 {v24.8h}, [x13] // U samples 0-7
+ ld1 {v25.8h}, [x14] // V samples 0-7
+
+ ld1 {v26.8h}, [x15] // U samples 8-15
+ ld1 {v27.8h}, [x16] // V samples 8-15
+ subs w9, w9, #1
+
+ smlal v16.4s, v24.4h, v6.h[0]
+ smlal2 v17.4s, v24.8h, v6.h[0]
+ smlal v18.4s, v25.4h, v6.h[0]
+ smlal2 v19.4s, v25.8h, v6.h[0]
+
+ smlal v20.4s, v26.4h, v6.h[0]
+ smlal2 v21.4s, v26.8h, v6.h[0]
+ smlal v22.4s, v27.4h, v6.h[0]
+ smlal2 v23.4s, v27.8h, v6.h[0]
+
+ b.gt 2b
+
+ sqshrun v24.4h, v16.4s, #16 // Process and store
first 8 pixels
+ sqshrun2 v24.8h, v17.4s, #16
+ sqshrun v25.4h, v18.4s, #16
+ sqshrun2 v25.8h, v19.4s, #16
+
+ sqshrun v26.4h, v20.4s, #16 // Process and store
next 8 pixels
+ sqshrun2 v26.8h, v21.4s, #16
+ sqshrun v27.4h, v22.4s, #16
+ sqshrun2 v27.8h, v23.4s, #16
+
+ cbz w0, 3f
+
+ uqshrn v28.8b, v24.8h, #3 // Storing U
+ uqshrn2 v28.16b, v26.8h, #3
+ uqshrn v29.8b, v25.8h, #3 // Storing V
+ uqshrn2 v29.16b, v27.8h, #3
+
+ st2 {v28.16b, v29.16b}, [x6], #32
+ b 4f
+3:
+ uqshrn v28.8b, v25.8h, #3 // Storing V
+ uqshrn2 v28.16b, v27.8h, #3
+ uqshrn v29.8b, v24.8h, #3 // Storing U
+ uqshrn2 v29.16b, v26.8h, #3
+
+ st2 {v28.16b, v29.16b}, [x6], #32
+4:
+ subs w7, w7, #16
+ add x8, x8, #16
+ b.gt 1b
+
+5:
+ cmp w7, #8
+ blt 10f
+6:
+ mov v16.16b, v2.16b // U acc low
+ mov v17.16b, v3.16b // U acc high
+ mov v18.16b, v4.16b // V acc low
+ mov v19.16b, v5.16b // V acc high
+
+ mov w9, w3 // chrFilterSize
counter
+ mov x10, x2 // chrFilter pointer
+ mov x11, x4 // chrUSrc base
+ mov x12, x5 // chrVSrc base
+
+7:
+ ldr h6, [x10], #2 // Load filter
coefficient
+
+ ldr x13, [x11], #8 // chrUSrc[j]
+ ldr x14, [x12], #8 // chrVSrc[j]
+ add x13, x13, x8, lsl #1 // &chrUSrc[j][i]
+ add x14, x14, x8, lsl #1 // &chrVSrc[j][i]
+
+ ld1 {v20.8h}, [x13] // U samples
+ ld1 {v21.8h}, [x14] // V samples
+ subs w9, w9, #1
+
+ smlal v16.4s, v20.4h, v6.h[0]
+ smlal2 v17.4s, v20.8h, v6.h[0]
+ smlal v18.4s, v21.4h, v6.h[0]
+ smlal2 v19.4s, v21.8h, v6.h[0]
+
+ b.gt 7b
+
+ sqshrun v26.4h, v16.4s, #16 // Final processing
and store
+ sqshrun2 v26.8h, v17.4s, #16
+ sqshrun v27.4h, v18.4s, #16
+ sqshrun2 v27.8h, v19.4s, #16
+
+ cbz w0, 8f
+ uqshrn v28.8b, v26.8h, #3 // Storing U
+ uqshrn v29.8b, v27.8h, #3 // Storing V
+ st2 {v28.8b, v29.8b}, [x6], #16
+ b 9f
+8:
+ uqshrn v28.8b, v27.8h, #3 // Storing V
+ uqshrn v29.8b, v26.8h, #3 // Storing U
+ st2 {v28.8b, v29.8b}, [x6], #16
+9:
+ subs w7, w7, #8
+ add x8, x8, #8
+
+10:
+ cbz w7, 15f // Scalar loop
+
+11:
+ and x15, x8, #7
+ ldrb w9, [x1, x15]
+ sxtw x9, w9
+ lsl x9, x9, #12 // u = chrDither[i &
7] << 12;
+
+ add x15, x8, #3
+ and x15, x15, #7
+ ldrb w10, [x1, x15]
+ sxtw x10, w10
+ lsl x10, x10, #12 // v = chrDither[(i +
3) & 7] << 12;
+
+ mov w11, w3 // chrFilterSize
counter
+ mov x12, x2 // chrFilter pointer
+ mov x13, x4 // chrUSrc base
+ mov x14, x5 // chrVSrc base
+
+12:
+ ldrsh x16, [x12], #2
+
+ ldr x17, [x13], #8 // chrUSrc[j]
+ ldr x19, [x14], #8 // chrVSrc[j]
+ add x17, x17, x8, lsl #1 // &chrUSrc[j][i]
+ add x19, x19, x8, lsl #1 // &chrVSrc[j][i]
+
+ ldrsh x20, [x17]
+ ldrsh x21, [x19]
+
+ madd x9, x16, x20, x9
+ madd x10, x16, x21, x10
+
+ subs w11, w11, #1
+ b.gt 12b
+
+ asr x9, x9, #19 // Process and store U
and V
+ asr x10, x10, #19
+
+ cmp x9, #0
+ csel x9, x9, xzr, ge
+ cmp x10, #0
+ csel x10, x10, xzr, ge
+
+ mov x22, #1
+ lsl x22, x22, #8
+ sub x22, x22, #1
+
+ cmp x9, x22
+ csel x9, x22, x9, gt
+ cmp x10, x22
+ csel x10, x22, x10, gt
+
+ cbz w0, 13f
+ strb w9, [x6], #1 // Storing U
+ strb w10, [x6], #1 // Storing V
+ b 14f
+13:
+ strb w10, [x6], #1 // Storing V
+ strb w9, [x6], #1 // Storing U
+
+14:
+ subs w7, w7, #1
+ add x8, x8, #1
+ b.gt 11b
+15:
+ ldp x21, x22, [sp, #16]
+ ldp x19, x20, [sp], #32
+ ret
+endfunc
diff --git a/libswscale/aarch64/swscale.c b/libswscale/aarch64/swscale.c
index 6fd4cc7265..55fff03a5a 100644
--- a/libswscale/aarch64/swscale.c
+++ b/libswscale/aarch64/swscale.c
@@ -191,6 +191,25 @@ void ff_yuv2plane1_8_neon(
const uint8_t *dither,
int offset);
+void ff_yuv2nv12cX_neon_asm(int isSwapped, const uint8_t *chrDither,
+ const int16_t *chrFilter, int chrFilterSize,
+ const int16_t **chrUSrc, const int16_t **chrVSrc,
+ uint8_t *dest, int chrDstW);
+
+static void ff_yuv2nv12cX_neon(enum AVPixelFormat dstFormat, const uint8_t
*chrDither,
+ const int16_t *chrFilter, int chrFilterSize,
+ const int16_t **chrUSrc, const int16_t
**chrVSrc,
+ uint8_t *dest, int chrDstW)
+{
+ if (!isSwappedChroma(dstFormat)) {
+ ff_yuv2nv12cX_neon_asm(1, chrDither, chrFilter, chrFilterSize,
+ chrUSrc, chrVSrc, dest, chrDstW);
+ } else {
+ ff_yuv2nv12cX_neon_asm(0, chrDither, chrFilter, chrFilterSize,
+ chrUSrc, chrVSrc, dest, chrDstW);
+ }
+}
+
#define ASSIGN_SCALE_FUNC2(hscalefn, filtersize, opt) do { \
if (c->srcBpc == 8) { \
if(c->dstBpc <= 14) { \
@@ -300,6 +319,8 @@ av_cold void ff_sws_init_swscale_aarch64(SwsInternal *c)
ASSIGN_VSCALE_FUNC(c->yuv2plane1, neon);
if (c->dstBpc == 8) {
c->yuv2planeX = ff_yuv2planeX_8_neon;
+ if (isSemiPlanarYUV(dstFormat) && !isDataInHighBits(dstFormat))
+ c->yuv2nv12cX = ff_yuv2nv12cX_neon;
}
if (isNBPS(dstFormat) && !isSemiPlanarYUV(dstFormat) &&
!isDataInHighBits(dstFormat)) {
commit 49477972b7175284663c9ef4124345c71dc9c7a1
Author: Logaprakash Ramajayam <logaprakash.ramaja...@multicorewareinc.com>
AuthorDate: Tue Jul 1 23:48:36 2025 -0700
Commit: Martin Storsjö <mar...@martin.st>
CommitDate: Tue Aug 12 09:05:00 2025 +0000
swscale/aarch64/output: Implement neon assembly for
yuv2planeX_10_c_template()
yuv2yuvX_8_2_0_512_accurate_c: 2213.4 ( 1.00x)
yuv2yuvX_8_2_0_512_accurate_neon: 147.5 (15.01x)
yuv2yuvX_8_2_0_512_approximate_c: 2203.9 ( 1.00x)
yuv2yuvX_8_2_0_512_approximate_neon: 154.1 (14.30x)
yuv2yuvX_8_2_16_512_accurate_c: 2147.2 ( 1.00x)
yuv2yuvX_8_2_16_512_accurate_neon: 150.8 (14.24x)
yuv2yuvX_8_2_16_512_approximate_c: 2149.7 ( 1.00x)
yuv2yuvX_8_2_16_512_approximate_neon: 146.8 (14.64x)
yuv2yuvX_8_2_32_512_accurate_c: 2078.9 ( 1.00x)
yuv2yuvX_8_2_32_512_accurate_neon: 139.0 (14.95x)
yuv2yuvX_8_2_32_512_approximate_c: 2083.7 ( 1.00x)
yuv2yuvX_8_2_32_512_approximate_neon: 140.5 (14.84x)
yuv2yuvX_8_2_48_512_accurate_c: 2010.7 ( 1.00x)
yuv2yuvX_8_2_48_512_accurate_neon: 138.2 (14.55x)
yuv2yuvX_8_2_48_512_approximate_c: 2012.6 ( 1.00x)
yuv2yuvX_8_2_48_512_approximate_neon: 141.2 (14.26x)
yuv2yuvX_10LE_16_0_512_accurate_c: 7874.1 ( 1.00x)
yuv2yuvX_10LE_16_0_512_accurate_neon: 831.6 ( 9.47x)
yuv2yuvX_10LE_16_0_512_approximate_c: 7918.1 ( 1.00x)
yuv2yuvX_10LE_16_0_512_approximate_neon: 836.1 ( 9.47x)
yuv2yuvX_10LE_16_16_512_accurate_c: 7630.9 ( 1.00x)
yuv2yuvX_10LE_16_16_512_accurate_neon: 804.5 ( 9.49x)
yuv2yuvX_10LE_16_16_512_approximate_c: 7724.7 ( 1.00x)
yuv2yuvX_10LE_16_16_512_approximate_neon: 808.6 ( 9.55x)
yuv2yuvX_10LE_16_32_512_accurate_c: 7436.4 ( 1.00x)
yuv2yuvX_10LE_16_32_512_accurate_neon: 780.4 ( 9.53x)
yuv2yuvX_10LE_16_32_512_approximate_c: 7366.7 ( 1.00x)
yuv2yuvX_10LE_16_32_512_approximate_neon: 780.5 ( 9.44x)
yuv2yuvX_10LE_16_48_512_accurate_c: 7099.9 ( 1.00x)
yuv2yuvX_10LE_16_48_512_accurate_neon: 761.0 ( 9.33x)
yuv2yuvX_10LE_16_48_512_approximate_c: 7097.6 ( 1.00x)
yuv2yuvX_10LE_16_48_512_approximate_neon: 754.6 ( 9.41x)
Benchmarked on:
Snapdragon(R) X Elite - X1E80100 - Qualcomm(R) Oryon(TM) CPU
3417 Mhz, 12 Core(s), 12 Logical Processor(s)
diff --git a/libswscale/aarch64/output.S b/libswscale/aarch64/output.S
index 190c438870..4945633856 100644
--- a/libswscale/aarch64/output.S
+++ b/libswscale/aarch64/output.S
@@ -20,6 +20,182 @@
#include "libavutil/aarch64/asm.S"
+function ff_yuv2planeX_10_neon, export=1
+// x0 = filter (int16_t*)
+// w1 = filterSize
+// x2 = src (int16_t**)
+// x3 = dest (uint16_t*)
+// w4 = dstW
+// w5 = big_endian
+// w6 = output_bits
+
+ mov w8, #27
+ sub w8, w8, w6 // shift = 11 + 16 -
output_bits
+
+ sub w9, w8, #1
+ mov w10, #1
+ lsl w9, w10, w9 // val = 1 << (shift -
1)
+
+ dup v1.4s, w9
+ dup v2.4s, w9 // Create vectors with
val
+
+ neg w16, w8
+ dup v20.4s, w16 // Create (-shift)
vector for right shift
+
+ mov w10, #1
+ lsl w10, w10, w6
+ sub w10, w10, #1 // (1U << output_bits)
- 1
+ dup v21.4s, w10 // Create Clip vector
for upper bound
+ dup v27.8h, w10
+
+ mov x7, #0 // i = 0
+
+1:
+ cmp w4, #16 // Process 16-pixels
if available
+ blt 4f
+
+ mov v3.16b, v1.16b
+ mov v4.16b, v2.16b
+ mov v5.16b, v1.16b
+ mov v6.16b, v2.16b
+
+ mov w11, w1 // tmpfilterSize =
filterSize
+ mov x12, x2 // srcp = src
+ mov x13, x0 // filterp = filter
+
+2: // Filter loop
+ ldp x14, x15, [x12], #16 // get 2 pointers:
src[j] and src[j+1]
+ ldr s7, [x13], #4 // load filter
coefficients
+ add x14, x14, x7, lsl #1
+ add x15, x15, x7, lsl #1
+ ld1 {v16.8h, v17.8h}, [x14]
+ ld1 {v18.8h, v19.8h}, [x15]
+
+ subs w11, w11, #2 // tmpfilterSize -= 2
+
+ smlal v3.4s, v16.4h, v7.h[0] // Multiply-accumulate
+ smlal2 v4.4s, v16.8h, v7.h[0]
+ smlal v5.4s, v17.4h, v7.h[0]
+ smlal2 v6.4s, v17.8h, v7.h[0]
+
+ smlal v3.4s, v18.4h, v7.h[1]
+ smlal2 v4.4s, v18.8h, v7.h[1]
+ smlal v5.4s, v19.4h, v7.h[1]
+ smlal2 v6.4s, v19.8h, v7.h[1]
+
+ b.gt 2b // continue filter loop
+
+ sshl v3.4s, v3.4s, v20.4s // Shift results
+ sshl v4.4s, v4.4s, v20.4s
+ sshl v5.4s, v5.4s, v20.4s
+ sshl v6.4s, v6.4s, v20.4s
+
+ sqxtun v23.4h, v3.4s // Narrow and clamp to 0
+ sqxtun2 v23.8h, v4.4s
+ sqxtun v24.4h, v5.4s
+ sqxtun2 v24.8h, v6.4s
+
+ umin v23.8h, v23.8h, v27.8h
+ umin v24.8h, v24.8h, v27.8h
+
+ cbz w5, 3f // Check if big endian
+ rev16 v23.16b, v23.16b
+ rev16 v24.16b, v24.16b // Swap bits for big
endian
+3:
+ st1 {v23.8h, v24.8h}, [x3], #32
+
+ subs w4, w4, #16 // dstW = dstW - 16
+ add x7, x7, #16 // i = i + 16
+ b 1b // Continue loop
+
+4:
+ cmp w4, #8 // Process 8-pixels if
available
+ blt 8f
+5:
+ mov v3.16b, v1.16b
+ mov v4.16b, v2.16b
+
+ mov w11, w1 // tmpfilterSize =
filterSize
+ mov x12, x2 // srcp = src
+ mov x13, x0 // filterp = filter
+
+6: // Filter loop
+ ldp x14, x15, [x12], #16
+ ldr s7, [x13], #4
+ add x14, x14, x7, lsl #1
+ add x15, x15, x7, lsl #1
+ ld1 {v5.8h}, [x14]
+ ld1 {v6.8h}, [x15]
+
+ subs w11, w11, #2 // tmpfilterSize -= 2
+
+ smlal v3.4s, v5.4h, v7.h[0] // Multiply-accumulate
+ smlal2 v4.4s, v5.8h, v7.h[0]
+ smlal v3.4s, v6.4h, v7.h[1]
+ smlal2 v4.4s, v6.8h, v7.h[1]
+
+ b.gt 6b // loop until
filterSize consumed
+
+ sshl v3.4s, v3.4s, v20.4s // Shift results
+ sshl v4.4s, v4.4s, v20.4s
+
+ sqxtun v25.4h, v3.4s // Narrow and clamp to 0
+ sqxtun2 v25.8h, v4.4s
+
+ umin v25.8h, v25.8h, v27.8h
+
+ cbz w5, 7f // Check if big endian
+ rev16 v25.16b, v25.16b
+
+7:
+ st1 {v25.8h}, [x3], #16 // Store 8 pixels
+
+ subs w4, w4, #8 // dstW = dstW - 8
+ add x7, x7, #8 // i = i + 8
+8:
+ cbz w4, 12f // Scalar loop for
remaining pixels
+9:
+ mov w11, w1 // tmpfilterSize =
filterSize
+ mov x12, x2 // srcp = src
+ mov x13, x0 // filterp = filter
+ sxtw x9, w9
+ mov x17, x9
+
+10: // Filter loop
+ ldr x14, [x12], #8 // Load src pointer
+ ldrsh w15, [x13], #2 // Load filter
coefficient
+ add x14, x14, x7, lsl #1 // Add pixel offset
+ ldrh w16, [x14]
+
+ sxtw x16, w16
+ sxtw x15, w15
+ madd x17, x16, x15, x17
+
+ subs w11, w11, #1 // tmpfilterSize -= 1
+ b.gt 10b // loop until
filterSize consumed
+
+ sxtw x8, w8
+ asr x17, x17, x8
+ cmp x17, #0
+ csel x17, x17, xzr, ge // Clamp to 0 if
negative
+
+ sxtw x10, w10
+ cmp x17, x10
+ csel x17, x10, x17, gt // Clamp to max if
greater than max
+
+ cbz w5, 11f // Check if big endian
+ rev16 x17, x17 // Swap bits for big
endian
+11:
+ strh w17, [x3], #2
+
+ subs w4, w4, #1 // dstW = dstW - 1
+ add x7, x7, #1 // i = i + 1
+ b.gt 9b // Loop if more pixels
+
+12:
+ ret
+endfunc
+
function ff_yuv2planeX_8_neon, export=1
// x0 - const int16_t *filter,
// x1 - int filterSize,
diff --git a/libswscale/aarch64/swscale.c b/libswscale/aarch64/swscale.c
index 6e5a721c1f..6fd4cc7265 100644
--- a/libswscale/aarch64/swscale.c
+++ b/libswscale/aarch64/swscale.c
@@ -158,6 +158,29 @@ void ff_hscale ## from_bpc ## to ## to_bpc ## _ ##
filter_n ## _ ## opt( \
ALL_SCALE_FUNCS(neon);
+void ff_yuv2planeX_10_neon(const int16_t *filter, int filterSize,
+ const int16_t **src, uint16_t *dest, int dstW,
+ int big_endian, int output_bits);
+
+#define yuv2NBPS(bits, BE_LE, is_be, template_size, typeX_t)
\
+static void yuv2planeX_ ## bits ## BE_LE ## _neon(const int16_t *filter, int
filterSize, \
+ const int16_t **src, uint8_t
*dest, int dstW, \
+ const uint8_t *dither, int
offset) \
+{
\
+ ff_yuv2planeX_## template_size ## _neon(filter,
\
+ filterSize, (const typeX_t **)
src, \
+ (uint16_t *) dest, dstW, is_be,
bits); \
+}
+
+yuv2NBPS( 9, BE, 1, 10, int16_t)
+yuv2NBPS( 9, LE, 0, 10, int16_t)
+yuv2NBPS(10, BE, 1, 10, int16_t)
+yuv2NBPS(10, LE, 0, 10, int16_t)
+yuv2NBPS(12, BE, 1, 10, int16_t)
+yuv2NBPS(12, LE, 0, 10, int16_t)
+yuv2NBPS(14, BE, 1, 10, int16_t)
+yuv2NBPS(14, LE, 0, 10, int16_t)
+
void ff_yuv2planeX_8_neon(const int16_t *filter, int filterSize,
const int16_t **src, uint8_t *dest, int dstW,
const uint8_t *dither, int offset);
@@ -268,6 +291,8 @@ av_cold void ff_sws_init_range_convert_aarch64(SwsInternal
*c)
av_cold void ff_sws_init_swscale_aarch64(SwsInternal *c)
{
int cpu_flags = av_get_cpu_flags();
+ enum AVPixelFormat dstFormat = c->opts.dst_format;
+ const AVPixFmtDescriptor *desc = av_pix_fmt_desc_get(dstFormat);
if (have_neon(cpu_flags)) {
ASSIGN_SCALE_FUNC(c->hyScale, c->hLumFilterSize, neon);
@@ -276,6 +301,19 @@ av_cold void ff_sws_init_swscale_aarch64(SwsInternal *c)
if (c->dstBpc == 8) {
c->yuv2planeX = ff_yuv2planeX_8_neon;
}
+
+ if (isNBPS(dstFormat) && !isSemiPlanarYUV(dstFormat) &&
!isDataInHighBits(dstFormat)) {
+ if (desc->comp[0].depth == 9) {
+ c->yuv2planeX = isBE(dstFormat) ? yuv2planeX_9BE_neon :
yuv2planeX_9LE_neon;
+ } else if (desc->comp[0].depth == 10) {
+ c->yuv2planeX = isBE(dstFormat) ? yuv2planeX_10BE_neon :
yuv2planeX_10LE_neon;
+ } else if (desc->comp[0].depth == 12) {
+ c->yuv2planeX = isBE(dstFormat) ? yuv2planeX_12BE_neon :
yuv2planeX_12LE_neon;
+ } else if (desc->comp[0].depth == 14) {
+ c->yuv2planeX = isBE(dstFormat) ? yuv2planeX_14BE_neon :
yuv2planeX_14LE_neon;
+ } else
+ av_assert0(0);
+ }
switch (c->opts.src_format) {
case AV_PIX_FMT_ABGR:
c->lumToYV12 = ff_abgr32ToY_neon;
diff --git a/tests/checkasm/sw_scale.c b/tests/checkasm/sw_scale.c
index 051b2bb4bf..0306f02695 100644
--- a/tests/checkasm/sw_scale.c
+++ b/tests/checkasm/sw_scale.c
@@ -52,50 +52,59 @@ static void yuv2planeX_8_ref(const int16_t *filter, int
filterSize,
}
}
-static int cmp_off_by_n(const uint8_t *ref, const uint8_t *test, size_t n, int
accuracy)
-{
- for (size_t i = 0; i < n; i++) {
- if (abs(ref[i] - test[i]) > accuracy)
- return 1;
- }
- return 0;
+#define CMP_FUNC(bits)
\
+static int cmp_off_by_n_##bits(const uint##bits##_t *ref, const uint##bits##_t
*test, \
+ size_t n, int accuracy)
\
+{
\
+ for (size_t i = 0; i < n; i++) {
\
+ if (abs((int)ref[i] - (int)test[i]) > accuracy)
\
+ return 1;
\
+ }
\
+ return 0;
\
}
-static void print_data(uint8_t *p, size_t len, size_t offset)
-{
- size_t i = 0;
- for (; i < len; i++) {
- if (i % 8 == 0) {
- printf("0x%04zx: ", i+offset);
- }
- printf("0x%02x ", (uint32_t) p[i]);
- if (i % 8 == 7) {
- printf("\n");
- }
- }
- if (i % 8 != 0) {
- printf("\n");
- }
+CMP_FUNC(8)
+CMP_FUNC(16)
+
+#define SHOW_DIFF_FUNC(bits)
\
+static void print_data_##bits(const uint##bits##_t *p, size_t len, size_t
offset) \
+{
\
+ size_t i = 0;
\
+ for (; i < len; i++) {
\
+ if (i % 8 == 0) {
\
+ printf("0x%04zx: ", i+offset);
\
+ }
\
+ printf("0x%02x ", (uint32_t) p[i]);
\
+ if (i % 8 == 7) {
\
+ printf("\n");
\
+ }
\
+ }
\
+ if (i % 8 != 0) {
\
+ printf("\n");
\
+ }
\
+}
\
+static size_t show_differences_##bits(const uint##bits##_t *a, const
uint##bits##_t *b, \
+ size_t len)
\
+{
\
+ for (size_t i = 0; i < len; i++) {
\
+ if (a[i] != b[i]) {
\
+ size_t offset_of_mismatch = i;
\
+ size_t offset;
\
+ if (i >= 8) i-=8;
\
+ offset = i & (~7);
\
+ printf("test a:\n");
\
+ print_data_##bits(&a[offset], 32, offset);
\
+ printf("\ntest b:\n");
\
+ print_data_##bits(&b[offset], 32, offset);
\
+ printf("\n");
\
+ return offset_of_mismatch;
\
+ }
\
+ }
\
+ return len;
\
}
-static size_t show_differences(uint8_t *a, uint8_t *b, size_t len)
-{
- for (size_t i = 0; i < len; i++) {
- if (a[i] != b[i]) {
- size_t offset_of_mismatch = i;
- size_t offset;
- if (i >= 8) i-=8;
- offset = i & (~7);
- printf("test a:\n");
- print_data(&a[offset], 32, offset);
- printf("\ntest b:\n");
- print_data(&b[offset], 32, offset);
- printf("\n");
- return offset_of_mismatch;
- }
- }
- return len;
-}
+SHOW_DIFF_FUNC(8)
+SHOW_DIFF_FUNC(16)
static void check_yuv2yuv1(int accurate)
{
@@ -140,10 +149,10 @@ static void check_yuv2yuv1(int accurate)
call_ref(src_pixels, dst0, dstW, dither, offset);
call_new(src_pixels, dst1, dstW, dither, offset);
- if (cmp_off_by_n(dst0, dst1, dstW * sizeof(dst0[0]), accurate
? 0 : 2)) {
+ if (cmp_off_by_n_8(dst0, dst1, dstW * sizeof(dst0[0]),
accurate ? 0 : 2)) {
fail();
printf("failed: yuv2yuv1_%d_%di_%s\n", offset, dstW,
accurate_str);
- fail_offset = show_differences(dst0, dst1,
LARGEST_INPUT_SIZE * sizeof(dst0[0]));
+ fail_offset = show_differences_8(dst0, dst1,
LARGEST_INPUT_SIZE * sizeof(dst0[0]));
printf("failing values: src: 0x%04x dither: 0x%02x dst-c:
%02x dst-asm: %02x\n",
(int) src_pixels[fail_offset],
(int) dither[(fail_offset + fail_offset) & 7],
@@ -158,7 +167,7 @@ static void check_yuv2yuv1(int accurate)
sws_freeContext(sws);
}
-static void check_yuv2yuvX(int accurate)
+static void check_yuv2yuvX(int accurate, int bit_depth, int dst_pix_format)
{
SwsContext *sws;
SwsInternal *c;
@@ -179,8 +188,8 @@ static void check_yuv2yuvX(int accurate)
const int16_t **src;
LOCAL_ALIGNED_16(int16_t, src_pixels, [LARGEST_FILTER *
LARGEST_INPUT_SIZE]);
LOCAL_ALIGNED_16(int16_t, filter_coeff, [LARGEST_FILTER]);
- LOCAL_ALIGNED_16(uint8_t, dst0, [LARGEST_INPUT_SIZE]);
- LOCAL_ALIGNED_16(uint8_t, dst1, [LARGEST_INPUT_SIZE]);
+ LOCAL_ALIGNED_16(uint16_t, dst0, [LARGEST_INPUT_SIZE]);
+ LOCAL_ALIGNED_16(uint16_t, dst1, [LARGEST_INPUT_SIZE]);
LOCAL_ALIGNED_16(uint8_t, dither, [LARGEST_INPUT_SIZE]);
union VFilterData{
const int16_t *src;
@@ -190,12 +199,14 @@ static void check_yuv2yuvX(int accurate)
memset(dither, d_val, LARGEST_INPUT_SIZE);
randomize_buffers((uint8_t*)src_pixels, LARGEST_FILTER *
LARGEST_INPUT_SIZE * sizeof(int16_t));
sws = sws_alloc_context();
+ sws->dst_format = dst_pix_format;
if (accurate)
sws->flags |= SWS_ACCURATE_RND;
if (sws_init_context(sws, NULL, NULL) < 0)
fail();
c = sws_internal(sws);
+ c->dstBpc = bit_depth;
ff_sws_init_scale(c);
for(isi = 0; isi < FF_ARRAY_ELEMS(input_sizes); ++isi){
dstW = input_sizes[isi];
@@ -227,24 +238,36 @@ static void check_yuv2yuvX(int accurate)
for(j = 0; j < 4; ++j)
vFilterData[i].coeff[j + 4] = filter_coeff[i];
}
- if (check_func(c->yuv2planeX, "yuv2yuvX_%d_%d_%d_%s",
filter_sizes[fsi], osi, dstW, accurate_str)){
+ if (check_func(c->yuv2planeX, "yuv2yuvX_%d%s_%d_%d_%d_%s",
bit_depth, (bit_depth == 8) ? "" : (isBE(dst_pix_format) ? "BE" : "LE"),
filter_sizes[fsi], osi, dstW, accurate_str)) {
// use vFilterData for the mmx function
const int16_t *filter = c->use_mmx_vfilter ? (const
int16_t*)vFilterData : &filter_coeff[0];
memset(dst0, 0, LARGEST_INPUT_SIZE * sizeof(dst0[0]));
memset(dst1, 0, LARGEST_INPUT_SIZE * sizeof(dst1[0]));
- // We can't use call_ref here, because we don't know if
use_mmx_vfilter was set for that
- // function or not, so we can't pass it the parameters
correctly.
- yuv2planeX_8_ref(&filter_coeff[0], filter_sizes[fsi], src,
dst0, dstW - osi, dither, osi);
-
- call_new(filter, filter_sizes[fsi], src, dst1, dstW - osi,
dither, osi);
- if (cmp_off_by_n(dst0, dst1, LARGEST_INPUT_SIZE *
sizeof(dst0[0]), accurate ? 0 : 2)) {
- fail();
- printf("failed: yuv2yuvX_%d_%d_%d_%s\n",
filter_sizes[fsi], osi, dstW, accurate_str);
- show_differences(dst0, dst1, LARGEST_INPUT_SIZE *
sizeof(dst0[0]));
+ if (c->dstBpc == 8) {
+ // We can't use call_ref here, because we don't know
if use_mmx_vfilter was set for that
+ // function or not, so we can't pass it the parameters
correctly.
+
+ yuv2planeX_8_ref(&filter_coeff[0], filter_sizes[fsi],
src, (uint8_t*)dst0, dstW - osi, dither, osi);
+ call_new(filter, filter_sizes[fsi], src,
(uint8_t*)dst1, dstW - osi, dither, osi);
+
+ if (cmp_off_by_n_8((uint8_t*)dst0, (uint8_t*)dst1,
LARGEST_INPUT_SIZE, accurate ? 0 : 2)) {
+ fail();
+ printf("failed: yuv2yuvX_%d_%d_%d_%d_%s\n",
bit_depth, filter_sizes[fsi], osi, dstW, accurate_str);
+ show_differences_8((uint8_t*)dst0, (uint8_t*)dst1,
LARGEST_INPUT_SIZE);
+ }
+ } else {
+ call_ref(&filter_coeff[0], filter_sizes[fsi], src,
(uint8_t*)dst0, dstW - osi, dither, osi);
+ call_new(&filter_coeff[0], filter_sizes[fsi], src,
(uint8_t*)dst1, dstW - osi, dither, osi);
+
+ if (cmp_off_by_n_16(dst0, dst1, LARGEST_INPUT_SIZE,
accurate ? 0 : 2)) {
+ fail();
+ printf("failed: yuv2yuvX_%d%s_%d_%d_%d_%s\n",
bit_depth, isBE(dst_pix_format) ? "BE" : "LE", filter_sizes[fsi], osi, dstW,
accurate_str);
+ show_differences_16(dst0, dst1,
LARGEST_INPUT_SIZE);
+ }
}
if(dstW == LARGEST_INPUT_SIZE)
- bench_new((const int16_t*)vFilterData,
filter_sizes[fsi], src, dst1, dstW - osi, dither, osi);
+ bench_new(filter, filter_sizes[fsi], src,
(uint8_t*)dst1, dstW - osi, dither, osi);
}
av_freep(&src);
@@ -311,10 +334,10 @@ static void check_yuv2nv12cX(int accurate)
call_ref(sws->dst_format, dither, &filter_coeff[0],
filter_size, srcU, srcV, dst0, dstW);
call_new(sws->dst_format, dither, &filter_coeff[0],
filter_size, srcU, srcV, dst1, dstW);
- if (cmp_off_by_n(dst0, dst1, dstW * 2 * sizeof(dst0[0]),
accurate ? 0 : 2)) {
+ if (cmp_off_by_n_8(dst0, dst1, dstW * 2 * sizeof(dst0[0]),
accurate ? 0 : 2)) {
fail();
printf("failed: yuv2nv12wX_%d_%d_%s\n", filter_size, dstW,
accurate_str);
- show_differences(dst0, dst1, dstW * 2 * sizeof(dst0[0]));
+ show_differences_8(dst0, dst1, dstW * 2 * sizeof(dst0[0]));
}
if (dstW == LARGEST_INPUT_SIZE)
bench_new(sws->dst_format, dither, &filter_coeff[0],
filter_size, srcU, srcV, dst1, dstW);
@@ -441,9 +464,33 @@ void checkasm_check_sw_scale(void)
check_yuv2yuv1(0);
check_yuv2yuv1(1);
report("yuv2yuv1");
- check_yuv2yuvX(0);
- check_yuv2yuvX(1);
- report("yuv2yuvX");
+ check_yuv2yuvX(0, 8, AV_PIX_FMT_YUV420P);
+ check_yuv2yuvX(1, 8, AV_PIX_FMT_YUV420P);
+ report("yuv2yuvX_8");
+ check_yuv2yuvX(0, 9, AV_PIX_FMT_YUV420P9LE);
+ check_yuv2yuvX(1, 9, AV_PIX_FMT_YUV420P9LE);
+ report("yuv2yuvX_9LE");
+ check_yuv2yuvX(0, 9, AV_PIX_FMT_YUV420P9BE);
+ check_yuv2yuvX(1, 9, AV_PIX_FMT_YUV420P9BE);
+ report("yuv2yuvX_9BE");
+ check_yuv2yuvX(0, 10, AV_PIX_FMT_YUV420P10LE);
+ check_yuv2yuvX(1, 10, AV_PIX_FMT_YUV420P10LE);
+ report("yuv2yuvX_10LE");
+ check_yuv2yuvX(0, 10, AV_PIX_FMT_YUV420P10BE);
+ check_yuv2yuvX(1, 10, AV_PIX_FMT_YUV420P10BE);
+ report("yuv2yuvX_10BE");
+ check_yuv2yuvX(0, 12, AV_PIX_FMT_YUV420P12LE);
+ check_yuv2yuvX(1, 12, AV_PIX_FMT_YUV420P12LE);
+ report("yuv2yuvX_12LE");
+ check_yuv2yuvX(0, 12, AV_PIX_FMT_YUV420P12BE);
+ check_yuv2yuvX(1, 12, AV_PIX_FMT_YUV420P12BE);
+ report("yuv2yuvX_12BE");
+ check_yuv2yuvX(0, 14, AV_PIX_FMT_YUV420P14LE);
+ check_yuv2yuvX(1, 14, AV_PIX_FMT_YUV420P14LE);
+ report("yuv2yuvX_14LE");
+ check_yuv2yuvX(0, 14, AV_PIX_FMT_YUV420P14BE);
+ check_yuv2yuvX(1, 14, AV_PIX_FMT_YUV420P14BE);
+ report("yuv2yuvX_14BE");
check_yuv2nv12cX(0);
check_yuv2nv12cX(1);
report("yuv2nv12cX");
-----------------------------------------------------------------------
Summary of changes:
libswscale/aarch64/output.S | 403 +++++++++++++++++++++++++++++++++++++++++++
libswscale/aarch64/swscale.c | 59 +++++++
tests/checkasm/sw_scale.c | 173 ++++++++++++-------
3 files changed, 572 insertions(+), 63 deletions(-)
hooks/post-receive
--
_______________________________________________
ffmpeg-cvslog mailing list
ffmpeg-cvslog@ffmpeg.org
https://ffmpeg.org/mailman/listinfo/ffmpeg-cvslog
To unsubscribe, visit link above, or email
ffmpeg-cvslog-requ...@ffmpeg.org with subject "unsubscribe".
