From 263eb76bdf5c5486c9eed0ac2e3416ce13db9821 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Cl=C3=A9ment=20B=C5=93sch?= Date: Fri, 18 Mar 2016 16:39:34 +0100 Subject: sws/aarch64: add ff_hscale_8_to_15_neon ./ffmpeg -nostats -f lavfi -i testsrc2=4k:d=2 -vf bench=start,scale=1024x1024,bench=stop -f null - before: t:0.489726 avg:0.489883 max:0.491852 min:0.489482 after: t:0.256515 avg:0.256458 max:0.256999 min:0.253755 --- libswscale/utils.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'libswscale/utils.c') diff --git a/libswscale/utils.c b/libswscale/utils.c index ba409d6..24ddd13 100644 --- a/libswscale/utils.c +++ b/libswscale/utils.c @@ -49,6 +49,7 @@ #include "libavutil/mathematics.h" #include "libavutil/opt.h" #include "libavutil/pixdesc.h" +#include "libavutil/aarch64/cpu.h" #include "libavutil/ppc/cpu.h" #include "libavutil/x86/asm.h" #include "libavutil/x86/cpu.h" @@ -1614,7 +1615,8 @@ av_cold int sws_init_context(SwsContext *c, SwsFilter *srcFilter, #endif /* HAVE_MMXEXT_INLINE */ { const int filterAlign = X86_MMX(cpu_flags) ? 4 : - PPC_ALTIVEC(cpu_flags) ? 8 : 1; + PPC_ALTIVEC(cpu_flags) ? 8 : + have_neon(cpu_flags) ? 4 : 1; if ((ret = initFilter(&c->hLumFilter, &c->hLumFilterPos, &c->hLumFilterSize, c->lumXInc, -- cgit v1.1