Mercurial > libavcodec.hg
view ppc/Makefile @ 12492:58a960d6e34c libavcodec
Rename h264_idct_sse2.asm to h264_idct.asm; move inline IDCT asm from
h264dsp_mmx.c to h264_idct.asm (as yasm code). Because the loops are now
coded in asm instead of C, this is (depending on the function) up to 50%
faster for cases where gcc didn't do a great job at looping.
Since h264_idct_add8() is now faster than the manual loop setup in h264.c,
in-asm idct calling can now be enabled for chroma as well (see r16207). For
MMX, this is 5% faster. For SSE2 (which isn't done for chroma if h264.c does
the looping), this makes it up to 50% faster. Speed gain overall is ~0.5-1.0%.
author | rbultje |
---|---|
date | Tue, 14 Sep 2010 13:36:26 +0000 |
parents | 9fef0a8ddd63 |
children |
line wrap: on
line source
OBJS += ppc/dsputil_ppc.o \ ALTIVEC-OBJS-$(CONFIG_H264DSP) += ppc/h264_altivec.o ALTIVEC-OBJS-$(CONFIG_VC1_DECODER) += ppc/vc1dsp_altivec.o ALTIVEC-OBJS-$(CONFIG_VP3_DECODER) += ppc/vp3dsp_altivec.o ALTIVEC-OBJS-$(CONFIG_VP5_DECODER) += ppc/vp3dsp_altivec.o ALTIVEC-OBJS-$(CONFIG_VP6_DECODER) += ppc/vp3dsp_altivec.o ALTIVEC-OBJS-$(CONFIG_VP8_DECODER) += ppc/vp8dsp_altivec.o ALTIVEC-OBJS-$(CONFIG_MP1FLOAT_DECODER) += ppc/mpegaudiodec_altivec.o ALTIVEC-OBJS-$(CONFIG_MP2FLOAT_DECODER) += ppc/mpegaudiodec_altivec.o ALTIVEC-OBJS-$(CONFIG_MP3FLOAT_DECODER) += ppc/mpegaudiodec_altivec.o ALTIVEC-OBJS-$(CONFIG_MP3ON4FLOAT_DECODER) += ppc/mpegaudiodec_altivec.o ALTIVEC-OBJS-$(CONFIG_MP3ADUFLOAT_DECODER) += ppc/mpegaudiodec_altivec.o FFT-OBJS-$(HAVE_GNU_AS) += ppc/fft_altivec_s.o \ ALTIVEC-OBJS-$(CONFIG_FFT) += ppc/fft_altivec.o \ $(FFT-OBJS-yes) OBJS-$(HAVE_ALTIVEC) += ppc/dsputil_altivec.o \ ppc/fdct_altivec.o \ ppc/float_altivec.o \ ppc/gmc_altivec.o \ ppc/idct_altivec.o \ ppc/int_altivec.o \ ppc/mpegvideo_altivec.o \ $(ALTIVEC-OBJS-yes)