diff options
author | Hubert Mazur <hum@semihalf.com> | 2022-10-28 11:34:38 +0000 |
---|---|---|
committer | Martin Storsjö <martin@martin.st> | 2022-11-01 15:24:53 +0200 |
commit | 9ccf8c5bfc3939762e421f4addb6fb71600e2026 (patch) | |
tree | 00cd72a12243a2c67eec34173cfc25eda28305e6 /libswscale/aarch64/swscale.c | |
parent | 1e9cfa5bb0253784798029bda377823ab5d1a529 (diff) | |
download | ffmpeg-9ccf8c5bfc3939762e421f4addb6fb71600e2026.tar.gz |
sw_scale: Add specializations for hscale 16 to 15
Add arm64 neon implementations for hscale 16 to 15 with filter
sizes 4, 8 and X4.
The tests and benchmarks run on AWS Graviton 2 instances.
The results from a checkasm tool are shown below.
hscale_16_to_15__fs_4_dstW_512_c: 6703.5
hscale_16_to_15__fs_4_dstW_512_neon: 2298.0
hscale_16_to_15__fs_8_dstW_512_c: 10983.0
hscale_16_to_15__fs_8_dstW_512_neon: 3216.5
hscale_16_to_15__fs_12_dstW_512_c: 15526.0
hscale_16_to_15__fs_12_dstW_512_neon: 3993.0
hscale_16_to_15__fs_16_dstW_512_c: 20183.5
hscale_16_to_15__fs_16_dstW_512_neon: 5369.7
hscale_16_to_15__fs_32_dstW_512_c: 39315.2
hscale_16_to_15__fs_32_dstW_512_neon: 9511.2
hscale_16_to_15__fs_40_dstW_512_c: 48995.7
hscale_16_to_15__fs_40_dstW_512_neon: 11570.0
(Note, the checkasm tests for these functions haven't been
merged since they fail on x86.)
Signed-off-by: Hubert Mazur <hum@semihalf.com>
Signed-off-by: Martin Storsjö <martin@martin.st>
Diffstat (limited to 'libswscale/aarch64/swscale.c')
-rw-r--r-- | libswscale/aarch64/swscale.c | 61 |
1 files changed, 61 insertions, 0 deletions
diff --git a/libswscale/aarch64/swscale.c b/libswscale/aarch64/swscale.c index 171fb51329..5d0887cfe5 100644 --- a/libswscale/aarch64/swscale.c +++ b/libswscale/aarch64/swscale.c @@ -22,6 +22,63 @@ #include "libswscale/swscale_internal.h" #include "libavutil/aarch64/cpu.h" +void ff_hscale16to15_4_neon_asm(int shift, int16_t *_dst, int dstW, + const uint8_t *_src, const int16_t *filter, + const int32_t *filterPos, int filterSize); +void ff_hscale16to15_X8_neon_asm(int shift, int16_t *_dst, int dstW, + const uint8_t *_src, const int16_t *filter, + const int32_t *filterPos, int filterSize); +void ff_hscale16to15_X4_neon_asm(int shift, int16_t *_dst, int dstW, + const uint8_t *_src, const int16_t *filter, + const int32_t *filterPos, int filterSize); + +static void ff_hscale16to15_4_neon(SwsContext *c, int16_t *_dst, int dstW, + const uint8_t *_src, const int16_t *filter, + const int32_t *filterPos, int filterSize) +{ + const AVPixFmtDescriptor *desc = av_pix_fmt_desc_get(c->srcFormat); + int sh = desc->comp[0].depth - 1; + + if (sh<15) { + sh = isAnyRGB(c->srcFormat) || c->srcFormat==AV_PIX_FMT_PAL8 ? 13 : (desc->comp[0].depth - 1); + } else if (desc->flags & AV_PIX_FMT_FLAG_FLOAT) { /* float input are process like uint 16bpc */ + sh = 16 - 1; + } + ff_hscale16to15_4_neon_asm(sh, _dst, dstW, _src, filter, filterPos, filterSize); + +} + +static void ff_hscale16to15_X8_neon(SwsContext *c, int16_t *_dst, int dstW, + const uint8_t *_src, const int16_t *filter, + const int32_t *filterPos, int filterSize) +{ + const AVPixFmtDescriptor *desc = av_pix_fmt_desc_get(c->srcFormat); + int sh = desc->comp[0].depth - 1; + + if (sh<15) { + sh = isAnyRGB(c->srcFormat) || c->srcFormat==AV_PIX_FMT_PAL8 ? 13 : (desc->comp[0].depth - 1); + } else if (desc->flags & AV_PIX_FMT_FLAG_FLOAT) { /* float input are process like uint 16bpc */ + sh = 16 - 1; + } + ff_hscale16to15_X8_neon_asm(sh, _dst, dstW, _src, filter, filterPos, filterSize); + +} + +static void ff_hscale16to15_X4_neon(SwsContext *c, int16_t *_dst, int dstW, + const uint8_t *_src, const int16_t *filter, + const int32_t *filterPos, int filterSize) +{ + const AVPixFmtDescriptor *desc = av_pix_fmt_desc_get(c->srcFormat); + int sh = desc->comp[0].depth - 1; + + if (sh<15) { + sh = isAnyRGB(c->srcFormat) || c->srcFormat==AV_PIX_FMT_PAL8 ? 13 : (desc->comp[0].depth - 1); + } else if (desc->flags & AV_PIX_FMT_FLAG_FLOAT) { /* float input are process like uint 16bpc */ + sh = 16 - 1; + } + ff_hscale16to15_X4_neon_asm(sh, _dst, dstW, _src, filter, filterPos, filterSize); +} + #define SCALE_FUNC(filter_n, from_bpc, to_bpc, opt) \ void ff_hscale ## from_bpc ## to ## to_bpc ## _ ## filter_n ## _ ## opt( \ SwsContext *c, int16_t *data, \ @@ -56,6 +113,10 @@ void ff_yuv2plane1_8_neon( } else \ hscalefn = \ ff_hscale8to19_ ## filtersize ## _ ## opt; \ + } else { \ + if (c->dstBpc <= 14) \ + hscalefn = \ + ff_hscale16to15_ ## filtersize ## _ ## opt; \ } \ } while (0) |