diff options
Diffstat (limited to 'libswscale/aarch64/swscale.c')
-rw-r--r-- | libswscale/aarch64/swscale.c | 39 |
1 files changed, 30 insertions, 9 deletions
diff --git a/libswscale/aarch64/swscale.c b/libswscale/aarch64/swscale.c index 09d0a7130e..ab28be4da6 100644 --- a/libswscale/aarch64/swscale.c +++ b/libswscale/aarch64/swscale.c @@ -22,25 +22,46 @@ #include "libswscale/swscale_internal.h" #include "libavutil/aarch64/cpu.h" -void ff_hscale_8_to_15_neon(SwsContext *c, int16_t *dst, int dstW, - const uint8_t *src, const int16_t *filter, - const int32_t *filterPos, int 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, \ + int dstW, const uint8_t *src, \ + const int16_t *filter, \ + const int32_t *filterPos, int filterSize) +#define SCALE_FUNCS(filter_n, opt) \ + SCALE_FUNC(filter_n, 8, 15, opt); +#define ALL_SCALE_FUNCS(opt) \ + SCALE_FUNCS(4, opt); \ + SCALE_FUNCS(X8, opt) + +ALL_SCALE_FUNCS(neon); 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); +#define ASSIGN_SCALE_FUNC2(hscalefn, filtersize, opt) do { \ + if (c->srcBpc == 8 && c->dstBpc <= 14) { \ + hscalefn = \ + ff_hscale8to15_ ## filtersize ## _ ## opt; \ + } \ +} while (0) + +#define ASSIGN_SCALE_FUNC(hscalefn, filtersize, opt) \ + switch (filtersize) { \ + case 4: ASSIGN_SCALE_FUNC2(hscalefn, 4, opt); break; \ + default: if (filtersize % 8 == 0) \ + ASSIGN_SCALE_FUNC2(hscalefn, X8, opt); \ + break; \ + } + av_cold void ff_sws_init_swscale_aarch64(SwsContext *c) { int cpu_flags = av_get_cpu_flags(); if (have_neon(cpu_flags)) { - if (c->srcBpc == 8 && c->dstBpc <= 14 && - (c->hLumFilterSize % 8) == 0 && - (c->hChrFilterSize % 8) == 0) - { - c->hyScale = c->hcScale = ff_hscale_8_to_15_neon; - } + ASSIGN_SCALE_FUNC(c->hyScale, c->hLumFilterSize, neon); + ASSIGN_SCALE_FUNC(c->hcScale, c->hChrFilterSize, neon); if (c->dstBpc == 8) { c->yuv2planeX = ff_yuv2planeX_8_neon; } |