From 705f5e5e155f6f280a360af220fc5b30cfcee702 Mon Sep 17 00:00:00 2001 From: Janne Grunau Date: Tue, 1 Dec 2015 13:37:41 +0100 Subject: arm64: port synth_filter_float_neon from arm ~25% faster dts decoding overall. The checkasm CPU cycles numbers are not that useful since synth_filter_float() calls FFTContext.imdct_half(). cortex-a57 cortex-a53 synth_filter_float_c: 1866.2 3490.9 synth_filter_float_neon: 915.0 1531.5 With fftc.imdct_half forced to imdct_half_neon: cortex-a57 cortex-a53 synth_filter_float_c: 1718.4 3025.3 synth_filter_float_neon: 926.2 1530.1 --- libavcodec/aarch64/Makefile | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'libavcodec/aarch64/Makefile') diff --git a/libavcodec/aarch64/Makefile b/libavcodec/aarch64/Makefile index 0b614a3ac2..2175578f8e 100644 --- a/libavcodec/aarch64/Makefile +++ b/libavcodec/aarch64/Makefile @@ -16,7 +16,8 @@ OBJS-$(CONFIG_VORBIS_DECODER) += aarch64/vorbisdsp_init.o ARMV8-OBJS-$(CONFIG_VIDEODSP) += aarch64/videodsp.o -NEON-OBJS-$(CONFIG_DCA_DECODER) += aarch64/dcadsp_neon.o +NEON-OBJS-$(CONFIG_DCA_DECODER) += aarch64/dcadsp_neon.o \ + aarch64/synth_filter_neon.o NEON-OBJS-$(CONFIG_FFT) += aarch64/fft_neon.o NEON-OBJS-$(CONFIG_H264CHROMA) += aarch64/h264cmc_neon.o NEON-OBJS-$(CONFIG_H264DSP) += aarch64/h264dsp_neon.o \ -- cgit v1.2.3